Article

Plasmodium Species Aware based Quantification of Malaria Parasitaemia in Light Microscopy Thin Blood Smear

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Malaria is a serious worldwide disease, caused by a bite of a female Anopheles mosquito. The parasite transferred into complex life round in which it is grown and reproduces into the human body. The detection and recognition of Plasmodium species are possible and efficient through a process called staining (Giemsa). The staining process slightly colorizes the red blood cells (RBCs) but highlights Plasmodium parasites, white blood cells and artifacts. Giemsa stains nuclei, chromatin in blue tone and RBCs in pink color. It has been reported in numerous studies that manual microscopy is not a trustworthy screening technique when performed by nonexperts. Malaria parasites host in RBCs when it enters the bloodstream. This paper presents segmentation of Plasmodium parasite from the thin blood smear points on region growing and dynamic convolution based filtering algorithm. After segmentation, malaria parasite classified into four Plasmodium species: Plasmodium falciparum, Plasmodium ovale, Plasmodium vivax, and Plasmodium malaria. The random forest and K‐nearest neighbor are used for classification base on local binary pattern and hue saturation value features. The sensitivity for malaria parasitemia (MP) is 96.75% on training and testing of the proposed approach while specificity is 94.59%. Beside these, the comparisons of the two features are added to the proposed work for classification having sensitivity is 83.60% while having specificity is 94.90% through random forest classifier based on local binary pattern feature. Plasmodium parasite from the thin blood smear is segmented through region growing and dynamic convolution based filtering algorithms. To classify, local binary pattern and hue saturation value features are extracted from Plasmodium parasite and fed to random forest and K‐nearest neighbor classifiers.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Medical imaging analysis plays a significant role to detect abnormality in different organs of the body such as blood cancer [1][2][3][4][5][6][7], skin cancer [10,[22][23][24][25][26], breast cancer [11,16,17,19], brain tumor [8,9,[13][14][15]18,20,77], lung cancer [12,21], retina [27][28][29]50] etc. The organ abnormality mostly results in tumor growth quickly which is the main death cause worldwide [30]. ...
... Acute leukemia produces blasts in the bone marrow to over 20%. It will develop rapidly and take life in a couple of months if it is not treated and managed in time [2]. ...
... Acute lymphocytic leukemia (ALL) is a type of cancer of the blood and bone marrow. Literature reveals different machine-assisted Acute Lymphoblastic Leukemia (ALL) classification techniques in health applications [1,2]. ...
Article
Full-text available
Cancer is a fatal illness often caused by genetic disorder aggregation and a variety of pathological changes. Cancerous cells are abnormal areas often growing in any part of human body that are life-threatening. Cancer also known as tumor must be quickly and correctly detected in the initial stage to identify what might be beneficial for its cure. Even though modality has different considerations, such as complicated history, improper diagnostics and treatement that are main causes of deaths. The aim of the research is to analyze, review, categorize and address the current developments of human body cancer detection using machine learning techniques for breast, brain, lung, liver, skin cancer leukemia. The study highlights how cancer diagnosis, cure process is assisted using machine learning with supervised, unsupervised and deep learning techniques. Several state of art techniques are categorized under the same cluster and results are compared on benchmark datasets from accuracy, sensitivity, specificity, false-positive metrics. Finally, challenges are also highlighted for possible future work.
... At present, malaria case management and routine surveillance rely on traditional diagnostic methods based on microscopy and rapid diagnostic tests (RDTs). These methods are widely deployed by the National Malaria Control Programmes (NMCPs) in most malaria endemic countries in Africa (Tawe et al., 2018;Abbas et al., 2019;Tessema et al., 2019b;Morgan et al., 2020). Despite their short turnaround time, these methods have major limitations (Apinjoh et al., 2019 (Table 1). ...
Article
Full-text available
Recent developments in molecular biology and genomics have revolutionized biology and medicine mainly in the developed world. The application of next generation sequencing (NGS) and CRISPR-Cas tools is now poised to support endemic countries in the detection, monitoring and control of endemic diseases and future epidemics, as well as with emerging and re-emerging pathogens. Most low and middle income countries (LMICs) with the highest burden of infectious diseases still largely lack the capacity to generate and perform bioinformatic analysis of genomic data. These countries have also not deployed tools based on CRISPR-Cas technologies. For LMICs including Tanzania, it is critical to focus not only on the process of generation and analysis of data generated using such tools, but also on the utilization of the findings for policy and decision making. Here we discuss the promise and challenges of NGS and CRISPR-Cas in the context of malaria as Africa moves towards malaria elimination. These innovative tools are urgently needed to strengthen the current diagnostic and surveillance systems. We discuss ongoing efforts to deploy these tools for malaria detection and molecular surveillance highlighting potential opportunities presented by these innovative technologies as well as challenges in adopting them. Their deployment will also offer an opportunity to broadly build in-country capacity in pathogen genomics and bioinformatics, and to effectively engage with multiple stakeholders as well as policy makers, overcoming current workforce and infrastructure challenges. Overall, these ongoing initiatives will build the malaria molecular surveillance capacity of African researchers and their institutions, and allow them to generate genomics data and perform bioinformatics analysis in-country in order to provide critical information that will be used for real-time policy and decision-making to support malaria elimination on the continent.
... Malaria is an infectious disease caused by a Plasmodium parasite transmitted through female Anopheles mosquito bites [1]. ere are five types of Plasmodium species that cause malaria in humans: Plasmodium falciparum, Plasmodium vivax, Plasmodium ovale, Plasmodium malariae, and Plasmodium knowlesi. ...
Article
Full-text available
The previous study showed that xanthone had antiplasmodial activity. Xanthone, with additional hydroxyl groups, was synthesized to increase its antiplasmodial activity. One of the strategies to evaluate a compound that can be developed into an antimalarial drug is by testing its mechanism in inhibiting heme polymerization. In acidic condition, hematin can be polymerized to β-hematin in vitro, which is analog with hemozoin in Plasmodium. This study was conducted to evaluate the antiplasmodial activity of hydroxyxanthone derivative compounds on two strains of Plasmodium falciparum 3D-7 and FCR-3, to assess inhibition of heme polymerization activity and determine the selectivity of hydroxyxanthone derivative compounds. The antiplasmodial activity of each compound was tested on Plasmodium falciparum 3D-7 and FCR-3 with 72 hours incubation period, triplicated in three replications with the microscopic method. The compound that showed the best antiplasmodial activity underwent flow cytometry assay. Heme polymerization inhibition test was performed using the in vitro heme polymerization inhibition activity (HPIA) assay. The antiplasmodial activity and heme polymerization inhibition activity were expressed as the 50% inhibitory concentration (IC50). In vitro cytotoxicity was tested using the MTT assay method on Vero cell lines to determine its selectivity index. The results showed that among 5-hydroxyxanthone derivative compounds, the 1,6,8-trihydroxyxanthone had the best in vitro antiplasmodial activity on both 3D-7 and FCR-3 Plasmodium falciparum strains with IC50 values of 6.10 ± 2.01 and 6.76 ± 2.38 μM, respectively. The 1,6,8-trihydroxyxanthone showed inhibition activity of heme polymerization with IC50 value of 2.854 mM and showed the high selectivity with selectivity index of 502.2–556.54. In conclusion, among 5-hydroxyxanthone derivatives tested, the 1,6,8-trihydroxyxantone showed the best antiplasmodial activity and has heme polymerization inhibition activity and high selectivity. 1. Introduction Malaria is an infectious disease caused by a Plasmodium parasite transmitted through female Anopheles mosquito bites [1]. There are five types of Plasmodium species that cause malaria in humans: Plasmodium falciparum, Plasmodium vivax, Plasmodium ovale, Plasmodium malariae, and Plasmodium knowlesi. Plasmodium falciparum (P. falciparum) is a cause of malaria with severe symptoms which can lead to death [2]. One of the mechanisms of antimalarials is inhibiting the polymerization of heme. The polymerization of the heme is the process of changing free heme to hemozoin. One of the drugs that have a mechanism of action inhibiting the polymerization of heme is chloroquine [3, 4]. The formation of chloroquine and heme complexes can inhibit hemozoin formation [5]. The chloroquine target is to bind the heme. Free heme in Plasmodium’s digestive vacuoles is toxic to cell membranes and Plasmodium proteolytic enzymes. The free heme is then polymerized by the Plasmodium into nontoxic hemozoin to protect the Plasmodium life. Hemozoin formation occurs only in the Plasmodium infection of the erythrocytic cycle. Hemozoin has a similar structure to β-hematin, while heme is similar to hematin. Therefore, by assessing this process, a compound can be developed into an antimalarial drug using the mechanism of action of heme polymerization. In vitro hematin can be polymerized into β-hematin in the acidic conditions, which has the same properties as existing hemozoin in the Plasmodium [6]. Plasmodium falciparum resistance to antimalarials is one of the factors of malaria treatment failure [7–9]. More advanced research is required to find new antimalarials. One of the strategies is to synthesize new compounds from the guiding compounds that have been known to have antiplasmodial activity. The determination of a compound to be used as a guide compound can be based on the resemblance of its chemical structure with other compounds that have been known to have high antiplasmodial activity [10]. One of the compounds that are promising to be developed as an antiplasmodial alternative is the xanthone derivative compound. Xanthone is a natural phenolic compound known to have antiplasmodial activity. Various studies have shown that the xanthone compounds of natural materials are proven to have the inhibition of Plasmodium growth [11, 12]. While encouraging as candidates, these potential antiplasmodials, derived from natural compounds, have a limited amount, so that their availability cannot be guaranteed. Therefore, to ensure the availability and sustainability of its production, it is necessary to develop a synthetic compound that can be remanufactured in large quantities. One study conducted by Amanatie et al. reported that the xanthone derived 2-hydroxyxanthone compound had an antiplasmodial activity with inhibitory concentration of 50% (IC50) of 4.385 μg/mL. The study stated that the hydroxyl group influenced the high antiplasmodial activity of hydroxyxanthone in the xanthone framework. The addition of a hydroxyl group to the xanthone derivatives causes the antiplasmodial activity of the compound to be higher than the xanthone compound before it is tied to the hydroxyl group [13]. Some hydroxyxanthone derivative compounds have been synthesized by Fatmasari [14], however, their antiplasmodial activity is not known. Previous studies showed that an interaction occurs between the phenol compounds with the hematin electronic system. The phenol compound with a hydroxyl group can bind the heme iron [6]. The hydroxyl clusters that bind to hematin can form complexes that it will inhibit the formation of β-hematin in vitro. The inhibitory test of the polymerization of heme can be used to identify the mechanisms of action of antiplasmodials. Testing cytotoxicity on Vero cells can be conducted to evaluate the safety of hydroxyxanthone derivative compounds. To develop the hydroxyxanthone derivative compounds as malaria treatment, it is necessary to test their antiplasmodial activity, heme polymerization inhibitory activity, and cytotoxic effect on the Vero cells. 2. Materials and Methods 2.1. Testing Compounds and Plasmodium Five hydroxyxanthone derivatives have been synthesized by Fatmasari [14], i.e., 1,6,8-trihydroxyxanthone (HX1); 1,6-dihydroxyxanthone (HX2); 1,5,6-trihydroxyxanthone (HX3); 1-hydroxy-5-chloroxanthone (HX4); and 1,6-dihydroxy-5-methylxanthone (HX5). The Plasmodium falciparum 3D-7 (chloroquine-sensitive strain) and FCR-3 (chloroquine-resistant strain) were obtained from laboratory collection of Department of Pharmacology and Therapy, Faculty of Medicine Public Health and Nursing, Universitas Gadjah Mada, Yogyakarta, Indonesia. 2.2. Plasmodium Culture The test of antiplasmodial activity began with the culture of P. falciparum 3D-7 and FCR-3 using the modified Trager and Jensen method [15]. The plasmodium was cultured in human O red blood cells diluted to 3% haematocrit in RPMI 1640 medium complemented with 10% human O serum. The medium was made by adding 10.43 g of powder RPMI 1640, 6 g HEPES, 2 g NaHCO3, 25 mg gentamycin, and sterile distilled water up to 1 L. The medium pH was adjusted so that it reached ±7.2. It was sterilized using a 0.22 μm filter and stored at 4°C. The complete plasmodium culture medium was made by adding human serum with a concentration of 10% in the medium. The plasmodium culture was incubated in candle jar in an incubator with a temperature of 37°C and was observed every 24 hours. 2.3. In Vitro Antiplasmodial Activity Assay The plasmodium was synchronized to obtain the ring stage by adding 5% of D-sorbitol. The plasmodium was transferred from culture flask to a conical tube, and then it was centrifuged with a speed of 1000 rpm for 10 minutes. After the supernatant was disposed, the sterile 5% sorbitol was added and incubated for 10 minutes at a temperature of 37°C. The plasmodium suspension was centrifuged again; the supernatant was disposed and the plasmodium was washed by adding culture medium. Then, the plasmodium suspension was centrifuged again, and the supernatant was discarded, resulting in a plasmodium in ring stage only. The parasitemia was calculated from a thin blood preparation. The test used 1% parasitemia at 2% haematocrit in RPMI medium which complemented with 10% human O serum. Each testing compound was dissolved in RPMI medium. The testing compound in various concentrations with volume of 100 μL was incorporated into the 96-well microplate, and then 100 μL of Plasmodium suspension was added. Each series of concentrations was replicated three times. The microplate was incubated at a temperature of 37°C for 72 hours. At the end of the incubation, a thin blood smear was made using 10% Giemsa stain and observed under a light microscope at 1000x magnification. The percentage of parasitemia (counting a minimum of 1,000 erythrocytes) was calculated from the preparation of thin blood and then used to calculate the percentage of plasmodium growth inhibition. As a control, plasmodium culture without any testing compounds was considered to have a growth of 100%. Antiplasmodial activity is expressed as IC50, which is the concentration of a compound that is required for 50% inhibition of plasmodium growth. The IC50 value was calculated by probit analysis using SPSS software (IBM Corp., Chicago). The lower the IC50 value obtained, the greater the antiplasmodial activity. The antiplasmodial activity was classified into 5 categories, i.e., excellent (IC50 < 1 μM), good (IC50 1–20 μM), moderate (IC50 20–100 μM), low (IC50 100–200 μM), and inactive (IC50 > 200 μM) [16, 17]. 2.4. Flow Cytometry Method The Plasmodium falciparum strains of 3D-7 were used in this method. The plasmodium synchronized to obtain the ring stage by adding 5% of D-sorbitol. Plasmodium with 1% parasitemia was cultured in a 96-well microplate. The testing compounds were added in duplicate and incubated at 37°C for 72 hours. The samples were centrifuged with a speed of 1000 rpm for 10 minutes and washed twice in 100 μL of phosphate-buffered saline (PBS). Samples were incubated with 50 μL of 1 : 1000 SYBR green I and 20μL of CD235A-PE for 15 minutes at room temperature. Cells were washed and resuspended in PBS. Data were obtained using a FACSCalibur with the acquisition of 1,00,000 events per sample. Initial gating was done with uninfected and unstained erythrocytes to account for erythrocyte autofluorescence. The control plasmodium-infected erythrocyte was referred as 100% growth to calculate the percentage of growth inhibition after treated with testing compound. 2.5. In Vitro Heme Polymerization Inhibitory Activity Assay The heme polymerization inhibitory activity (HPIA) was conducted according to Basilico et al.’s modified method [6]. The 100 μL of 1 mM hematin in 0.2 M NaOH was added into a microtube. Then, 50 μL of testing compound at various concentrations (20.475; 10.238; 5.119; 2.580; 1.269 mM) was added in triplicates. Distilled water was used as a negative control. The 50 μL solution of glacial acetic acid (pH 2.6) was added into the microtube to initiate the polymerization reaction and incubated at a temperature of 37°C for 24 hours. Microtubes were centrifuged at 8000 rpm for 10 minutes and the supernatant was discarded and then washed three times using the 200 μL dimethyl sulfoxide (DMSO).Then, the deposition of the hematin crystal was dissolved with 200 μL of 0.1 M NaOH and 100 μL of solution was added into the 96-well microplate. Absorbance was read using ELISA reader at λ 405 nm. A standard curve was made to illustrate the relationship between the concentration of hematin and its absorbance. The various concentrations of hematin (250; 125; 62.5; 31.25; 15.6; 7.8; and 3.9 mM) were used to make the standard curve. The heme polymerization inhibition was expressed as IC50, which is the concentration of testing compounds that can inhibit 50% of the formation of β-hematin. The IC50 value was calculated by probit analysis using SPSS software (IBM Corp., Chicago). A compound shows to have heme polymerization inhibition activity in if it has an IC50 value lower than the IC50 value of chloroquine as in reference (37.5 mM) [17]. 2.6. In vitro Cytotoxicity Test on Vero Cell The in vitro cytotoxicity test was conducted using the 3-(4,5-dimethylthiazol-2-yl)2,5-diphenyltetrazolium bromide (MTT) assay method on Vero cell line culture using the Anderson et al.’s modified method [18]. 2.7. Vero Cell Line Culture The cell was removed from the cryo medium. Then, the cell was thawed at 37°C. The liquid cell was subsequently transferred to the tube and a culture medium was added to a volume of 10 mL. Then, the suspension was centrifuged for 15 minutes so that it would form cell pellets. The supernatant was removed and 1 mL of culture medium was added to the cell pellets. Finally, the suspension was transferred to the Petri dish and incubated in the incubator with 5% of CO2 at 37°C. 2.8. Cell Harvesting The medium of Vero cell culture was removed, and then the cell was washed using a PBS solution with a volume of PBS ± 1/2 of the initial medium volume. This step was done twice and 1 mL of trypsin 0.25% was added. Subsequently, the cell was incubated in the CO2 incubator at 37°C for 3 minutes. Then, the cell was resuspended using 2 mL of culture medium and PBS solution was added up to 10 mL. The suspension was centrifuged for 15 minutes so that it formed pellets. Pellets were added with 1 mL of culture medium and resuspended. Take 10 μL of the cell suspension and density of cells was calculated. Then, the cell was added with culture medium to 10 mL. A total of 100 μL of such suspensions was transferred into each well of the 96-well microplate, but three of the wells were emptied as medium controls. Subsequently, the microplate was incubated in a 5% CO2 incubator at 37°C. 2.9. Preparation of Testing Compounds Each hydroxyxanthone derivative compound was dissolved in DMSO, and a variety of concentrations were prepared in the medium. Each concentration of the testing compound was added into the 96-well microplate triplicately. Cell control and medium control were not given a testing compound solution. The medium control remained blank, while the cell control contained culture medium only. Chloroquine was used as a positive control. Then, the cell was incubated in a 5% CO2 incubator at 37°C for 24 hours. 2.10. MTT and SDS Addition After the cell was incubated for 24 hours, the medium was discarded and washed with PBS. Then, each well was added with 100 μL of 5 mg/mL of MTT solution. The 96-well microplate was incubated again in the incubator of CO2 at 37°C for 4 hours. Then, 100 μL of 10% of SDS in 0.01 MHCl was added. The cells were placed in a dark room at room temperature for 24 hours. 2.11. Measurement of the Absorbance and IC50 Value The absorbance was measured using the enzyme-linked immunosorbent assay (ELISA) reader at 595 nm wavelength. The cytotoxicity test on the Vero cells was done by calculating the percentage of Vero cell inhibition of the absorption value of the test compound, cell control, and medium control. The cytotoxic effect was expressed as IC50. The IC50 value was obtained from the probit analysis by using SPSS software (IBM Corp., Chicago). The degree of selectivity was expressed as a selectivity index. The selectivity index was obtained from the ratio between the IC50 cytotoxic effect on Vero cells and IC50 antiplasmodial activity on Plasmodium [19]. A compound is said to be safe if the value of the selectivity index is >10 [20]. 3. Results 3.1. In Vitro Antiplasmodial Activity Assay The increasing concentrations of testing compounds showed increasing the percentage of Plasmodium growth inhibition. The percentages of Plasmodium growth inhibition of hydroxyxanthone derivatives and chloroquine on P. falciparum 3D-7 and FCR-3 are presented in Table 1. The IC50 values of hydroxyxanthone derivatives on P. falciparum 3D-7 and FCR-3 are presented in Table 2. The lowest IC50 value of the hydroxyxanthone derivative compound on P. falciparum 3D-7 6.10 ± 2.01 μM was found in HX1. In contrast, the highest IC50 value of hydroxyxanthone derivative compounds on P. falciparum strain 3D7 85.30 ± 4.87 μM was found in HX4. The lowest IC50 value of the hydroxyxanthone derivative compound with the microscopic method on P. falciparum FCR-3 was also found in HX1 (6.76 ± 2.38 μM) while the highest IC50 value of hydroxyxanthone derivatives on P. falciparum FCR-3 was 89.85 ± 17.69 μM found in HX4. These results showed that the HX1 showed good antiplasmodial activity, whereas HX2, HX3, HX4, and HX5 had moderate antiplasmodial activity on P. falciparum 3D-7 and FCR-3. Chloroquine as positive control had IC50 value 0.01 ± 0.001 on P. falciparum strain 3D-7 and 0.11 ± 0.052 on P. falciparum strain FCR-3. Compound Concentration (μM) Growth inhibition of P. falciparum (%) Strain 3D-7 Strain FCR-3 1,6,8-Trihydroxyxanthone (HX1) 102.38 75.864 ± 0.471 73.671 ± 4.277 51.19 69.033 ± 0.888 64.446 ± 0.671 25.59 64.726 ± 0.861 60.171 ± 2.739 12.8 61.479 ± 0.710 55.160 ± 3.588 6.39 47.405 ± 5.857 50.894 ± 2.308 1,6-Dihidroxyxanthone (HX2) 876.42 90.560 ± 0.665 87.623 ± 2.239 438.21 73.618 ± 0.713 74.226 ± 1.318 219.11 67.164 ± 0.601 67.144 ± 2.757 109.55 54.805 ± 2.433 50.248 ± 2.629 54.78 49.172 ± 1.606 47.192 ± 0.687 1,5,6-Trihydroxyxanthone (HX3) 409.5 87.438 ± 1.154 82.978 ± 1.396 204.75 80.923 ± 0.679 71.858 ± 7.842 102.38 68.886 ± 0.151 51.920 ± 0.466 51.19 63.400 ± 0.421 43.133 ± 0.126 25.59 47.295 ± 0.611 38.265 ± 1.186 1-Hydroxy-5-chloroxanthone (HX4) 810.86 74.002 ± 0.923 72.933 ± 1.345 405.43 64.513 ± 0.418 61.202 ± 3.024 202.71 57.136 ± 1.574 56.371 ± 3.792 101.36 50.963 ± 0.361 49.754 ± 3.361 50.68 46.473 ± 0.800 47.388 ± 0.736 1,6-Dihydroxy-5-methylxanthone (HX5) 330.25 93.288 ± 0.956 84.664 ± 0.902 165.13 75.364 ± 1.287 73.462 ± 1.596 82.56 54.180 ± 1.574 46.519 ± 0.816 41.28 45.041 ± 0.563 41.140 ± 0.396 20.64 37.886 ± 0.441 33.632 ± 0.327 Chloroquine 0.037 97.766 ± 0.690 84.189 ± 2.449 0.029 97.490 ± 0.517 82.599 ± 2.945 0.023 96.581 ± 1.330 79.923 ± 3.863 0.016 96.354 ± 1.131 78.570 ± 4.507 0.008 54.415 ± 12.42 18.748 ± 9.233
... Tumors that are allotted grade I and II (low grade) are safe and nonenhancing whereas those given grade III and IV are known as malignant and enhancing ( Abbas et al., 2019;Yousaf et al., 2019). The development of a cancerous tumor is gradual. ...
Article
Automatic and precise segmentation and classification of tumor area in medical images is still a challenging task in medical research. Most of the conventional neural network based models usefully connected or convolutional neural networks to perform segmentation and classification. In this research, we present deep learning models using long short term memory (LSTM) and convolutional neural networks (ConvNet) for accurate brain tumor delineation from benchmark medical images. The two different models, that is, ConvNet and LSTM networks are trained using the same data set and combined to form an ensemble to improve the results. We used publicly available MICCAI BRATS 2015 brain cancer data set consisting of MRI images of four modalities T1, T2, T1c, and FLAIR. To enhance the quality of input images, multiple combinations of preprocessing methods such as noise removal, histogram equalization, and edge enhancement are formulated and best performer combination is applied. To cope with the class imbalance problem, class weighting is used in proposed models. The trained models are tested on validation data set taken from the same image set and results obtained from each model are reported. The individual score (accuracy) of ConvNet is found 75% whereas for LSTM based network produced 80% and ensemble fusion produced 82.29% accuracy. ConvNet, LSTMNet and their fusion is employed to improve the tumor segmentation of human brain MRI images taken from publically available multimodal MICCAI BRATS 2015 training data set. Ensemble network provided best results.
... The reason behind this could be the prevention and control strategies for disease which were used in past. Recently, Abbas et al. (2019) published on segmentation of Plasmodium on region growing and dynamic convolution based filtering algorithm from thin blood semear points and classified four species viz; P. falciparum, P. ovale, P. vivax and P. malariae. They found 96.75% of sensitivity for malaria parasitemia and 94.59% of specificity. ...
Article
Full-text available
Plasmodium (P), mosquito-borne unicellular parasite, is responsible for "malaria". Pakistan remains at risk of malaria and almost 1.6 million cases of malaria are reported every year. The present study was planned to screen the mosquito vectors for Plasmodium sp. in Faisalabad district, Punjab, Pakistan using nested PCR. For this purpose, convenient sampling of adult mosquitoes was done from different places including: animal populated areas, lavatories, water storage tanks, livestock farms and roadside ditches in 70% ethanol. DNA extraction was done after stereomicroscopic identification of the specimens. Species identification of P. falciparum, P. vivax, P. ovale and P. malariae was done through universal forward and species-specific reverse primers in the nested PCR. Prevalence of Culex mosquitoes was higher as compared to Anopheles. Plasmodium falciparum and P. vivax were found higher as compared to other species of Plasmodium. The overall prevalence of Plasmodium sp. in mosquito vectors was 46% (14 out of 30 pools for Plasmodium sp.). Results were analyzed through chi-square analyses. Present study may explore the vectorial capacity of mosquitoes which can be an indicator of Plasmodium sp. distribution in an area for large scale metagenomics.
... In medical image analysis, various methods are introduced to diagnose and cure chronic diseases Abbas, Saba, Rehman, Mehmood, Javaid, et al. 2019;Abbas, Saba, Rehman, Mehmood, Kolivand, et al. 2019;Amin, Sharif, Yasmin, Saba, & Raza, 2019;Jamal, Hazim Alkawaz, Rehman, & Saba, 2017;Mughal, Muhammad, Sharif, Saba, & Rehman, 2017;Mughal, Muhammad, Sharif, Rehman, & Saba, 2018;Ullah et al., 2019;. Accordingly, several in-depth techniques/ reviews are presented (Javed, Rahim, Saba, & Rehman, 2020;Norouzi et al., 2014;Saba, Bokhari, Sharif, Yasmin, & Raza, 2018;Saba, Rehman, Mehmood, Kolivand, & Sharif, 2018), and automated systems are developed in state of art , Saba, Al-Zahrani, & Rehman, 2012Rehman, Abbas, Saba, Mahmood, & Kolivand, 2018;Rehman, Abbas, Saba, Rahman, et al., 2018;Rahim, Norouzi, Rehman, & Saba, 2017;Rahim, Rehman, Kurniawan, & Saba, 2017;Iftikhar, Fatima, Rehman, Almazyad, & Saba, 2017;Fahad et al, 2018). ...
Article
The numbers of diagnosed patients by melanoma are drastic and contribute more deaths annually among young peoples. An approximately 192,310 new cases of skin cancer are diagnosed in 2019, which shows the importance of automated systems for the diagnosis process. Accordingly, this article presents an automated method for skin lesions detection and recognition using pixel‐based seed segmented images fusion and multilevel features reduction. The proposed method involves four key steps: (a) mean‐based function is implemented and fed input to top‐hat and bottom‐hat filters which later fused for contrast stretching, (b) seed region growing and graph‐cut method‐based lesion segmentation and fused both segmented lesions through pixel‐based fusion, (c) multilevel features such as histogram oriented gradient (HOG), speeded up robust features (SURF), and color are extracted and simple concatenation is performed, and (d) finally variance precise entropy‐based features reduction and classification through SVM via cubic kernel function. Two different experiments are performed for the evaluation of this method. The segmentation performance is evaluated on PH2, ISBI2016, and ISIC2017 with an accuracy of 95.86, 94.79, and 94.92%, respectively. The classification performance is evaluated on PH2 and ISBI2016 dataset with an accuracy of 98.20 and 95.42%, respectively. The results of the proposed automated systems are outstanding as compared to the current techniques reported in state of art, which demonstrate the validity of the proposed method. Current research proposed a new auto system for skin lesions detection, recognition using pixel‐based seed segmented images fusion, and multilevel features reduction. Finally, using a SVM via cubic kernel functions, skin lesions are classified.
... In the past few years, researchers have focused their attention on the development of automated tools and systems in the domain of computer vision that could detect and classify the anomalies in lesions in computed tomography (CT) and other imageries ( Abbas et al., 2019;Abbas, Saba, Mohamad, et al., 2018;M. A. Khan, Akram, Sharif, Awais, et al., 2018;M. ...
Article
The emergence of cloud infrastructure has the potential to provide significant benefits in a variety of areas in the medical imaging field. The driving force behind the extensive use of cloud infrastructure for medical image processing is the exponential increase in the size of computed tomography (CT) and magnetic resonance imaging (MRI) data. The size of a single CT/MRI image has increased manifold since the inception of these imagery techniques. This demand for the introduction of effective and efficient frameworks for extracting relevant and most suitable information (features) from these sizeable images. As early detection of lungs cancer can significantly increase the chances of survival of a lung scanner patient, an effective and efficient nodule detection system can play a vital role. In this article, we have proposed a novel classification framework for lungs nodule classification with less false positive rates (FPRs), high accuracy, sensitivity rate, less computationally expensive and uses a small set of features while preserving edge and texture information. The proposed framework comprises multiple phases that include image contrast enhancement, segmentation, feature extraction, followed by an employment of these features for training and testing of a selected classifier. Image preprocessing and feature selection being the primary steps-playing their vital role in achieving improved classification accuracy. We have empirically tested the efficacy of our technique by utilizing the well-known Lungs Image Consortium Database dataset. The results prove that the technique is highly effective for reducing FPRs with an impressive sensitivity rate of 97.45%. K E Y W O R D S computed tomography, feature selection, lungs segmentation, pulmonary nodules, wavelet features
... Malaria is often detected by employing a thick and thin smear blood microscopic examination of RBCs [7]. The thick smear test is conducted to assess the concentration of the malaria parasites in a body. ...
Article
Full-text available
Malaria is a life-threatening infection that infects the red blood cells (RBCs) that gradually grows throughout the body. The plasmodium parasite is caused by a female anopheles mosquito bite and severely affects numerous individuals within the world every year. Therefore, early detection tests are required to predict infected parasitic cells. The proposed technique exploits deep convolutional neural network (CNN) learning capability to detect the thin-blood smear parasitic patients from healthy individuals. In this regard, the detection is accomplished using a novel STM-SB-RENet block-based CNN that employs the idea of split-transform-merge (STM) and channel Squeezing-Boosting (SB) in a modified fashion. In this connection, a new convolutional block-based STM is developed, which systematically implements region and edge operations to explore the parasitic malaria pattern related to region-homogeneity, structural obstruction, and boundary-defining features. Moreover, the diverse boosted feature maps are achieved by incorporating the new channel SB and Transfer Learning (TL) idea in each STM block at abstract, intermediate, and target levels to capture minor contrast and texture variation between parasitic and normal artifacts. The malaria input images to the proposed models are initially transformed using discrete wavelet transform to generate enhanced and reduced feature space. The proposed architectures are validated using hold-out cross-validation on the National Institute of Health Malaria dataset. The proposed methods outperform the train from scratch, and TL-based fine-tuned existing techniques. The considerable performance (accuracy: 97.98%, sensitivity: 0.988, F-score: 0.980, and AUC: 0.996) of STM-SB-RENet suggests that it can be utilized to screen parasitic malaria patients.
... WBC play a crucial role in for proper functioning of human body and provide defensive system against various chronic diseases. The components of the blood cells can be broadly classified into RBCs, platelets, and WBCs [16]. WBCs are the primary component which is involved in the body's immune response and account for about 1% of the blood. ...
Chapter
Full-text available
In recent development of machine learning (ML)-based medical image analysis that have contributed to the prediction, planning, and early diagnostic process. Different chronic hermitic diseases like blood cancer/leukemia, AIDs, malaria, anemia and even COVID-19, all these are diagnoses via analyzing leucocytes or white blood cells (WBCs). Leucocytes analysis is the process of detection, localization, counting, analyzing WBCs, and it perform an active role in clinical hematology to assist health specialists in early stage disease diagnosing process. An automatic leucocytes analysis provide valuable diagnostics facts to doctors, via they can automatically detect, blood cancer, brain tumor and significantly improve the hematological, pathological activities. Manual Detection, counting and classification of WBCs is very slow, challenging and boring task due to having complex overlapping and morphological uneven structure. In this chapter, we provide a concise analysis of available ML techniques, to use these techniques for leucocytes analysis in microscopic images. The main aim of this chapter is to identify high performer and suitable ML algorithms for WBCs analysis using blood microscopic smear images. In the proposed review study, the recent and most relevant research papers are collected from IEEE, Science Direct, springer, and web of science (WoS) with the following keywords: ‘leucocytes detection’ or ‘leucocytes classification’. This study gives an extensive review of MIA but the research focuses more on the ML-based leucocytes/WBCs analysis in smear images. These techniques include traditional machine learning (TML), deep learning (DL), convolutional neural network (CNN) models, hybrid learning, and attention learning-based techniques to analyze medical image modalities to detect and classify cells in smear images.
Chapter
Breast cancer (BC) is one of the most leading malignancies amongst women globally; consequently, one in eight women is infected during the lifespan. The malignancy growth is reported in the breast glandular epithelium. The breast-cancer-infected individuals' prediction would be enhanced due to the required early detection and diagnosis process. Regardless of vast medical evolution, breast cancer has the second primary cause of mortality yet. Hence, initial diagnosis plays a preeminent role in decreasing the mortality rate. Several breast cancer detection procedures include computed tomography, mammography, X-rays, ultrasound, magnetic resonance imaging, thermography and more. Deep learning techniques were commonly used for medical imaging recognition for the past several years. convolutional neural network (CNN) was developed for accurate image recognition and classification, including breast cancer images due to its automatic detection and disease classification. This chapter aims to provide an extensive analysis of breast cancer, abnormalities, diagnosis, treatments and prevention strategies using image processing and CNN techniques. Additionally, available datasets description and critical statistical analysis based on CNN and different modalities for further study and future challenges are also highlighted.
Chapter
Full-text available
Tuberculosis is a major health threat in many regions of the world. Opportunistic infections in immunocompromised HIV/AIDS patients and multi-drugresistant bacterial strains have exacerbated the problem, while diagnosing tuberculosis remains challenging. Medical images have made a high impact on medicine, diagnosis, and treatment. The most important part of image processing is image segmentation. This chapter presents a novel X-ray of lungs segmentation method using the U-net model. First, we construct the U-net which combine the lungs and mask. Then, we convert to problem of positive and negative TB lungs into the segmentation of lungs, and extract the lungs by subtracting the chest from the radiography. In experiment, the proposed model achieves 97.62% on the public dataset of collection by Shenzhen Hospital, China and Montgomery County X-ray Set.
Article
A brain tumor is an uncontrolled development of brain cells in brain cancer if not detected at an early stage. Early brain tumor diagnosis plays a crucial role in treatment planning and patients' survival rate. There are distinct forms, properties, and therapies of brain tumors. Therefore, manual brain tumor detection is complicated, time‐consuming, and vulnerable to error. Hence, automated computer‐assisted diagnosis at high precision is currently in demand. This article presents segmentation through Unet architecture with ResNet50 as a backbone on the Figshare data set and achieved a level of 0.9504 of the intersection over union (IoU). The preprocessing and data augmentation concept were introduced to enhance the classification rate. The multi‐classification of brain tumors is performed using evolutionary algorithms and reinforcement learning through transfer learning. Other deep learning methods such as ResNet50, DenseNet201, MobileNet V2, and InceptionV3 are also applied. Results thus obtained exhibited that the proposed research framework performed better than reported in state of the art. Different CNN, models applied for tumor classification such as MobileNet V2, Inception V3, ResNet50, DenseNet201, NASNet and attained accuracy 91.8, 92.8, 92.9, 93.1, 99.6%, respectively. However, NASNet exhibited the highest accuracy. Highlights Two processes of transfer learning: freeze and fine‐tune, are performed to extract significant features from MRI slices. Brain tumor multi‐classification is performed using transfer learning, ResNet50‐UNet, and NASNet architecture.
Article
Full-text available
Image processing plays a major role in neurologists' clinical diagnosis in the medical field. Several types of imagery are used for diagnostics, tumor segmentation, and classification. Magnetic resonance imaging (MRI) is favored among all modalities due to its noninvasive nature and better representation of internal tumor information. Indeed, early diagnosis may increase the chances of being lifesaving. However, the manual dissection and classification of brain tumors based on MRI is vulnerable to error, time-consuming, and formidable task. Consequently, this article presents a deep learning approach to classify brain tumors using an MRI data analysis to assist practitioners. The recommended method comprises three main phases: preprocessing, brain tumor segmentation using k-means clustering, and finally, classify tumors into their respective categories (benign/malignant) using MRI data through a finetuned VGG19 (i.e., 19 layered Visual Geometric Group) model. Moreover, for better classification accuracy, the synthetic data augmentation concept i s introduced to increase available data size for classifier training. The proposed approach was evaluated on BraTS 2015 benchmarks data sets through rigorous experiments. The results endorse the effectiveness of the proposed strategy and it achieved better accuracy compared to the previously reported state of the art techniques.
Article
Brain tumor is one of the most dreadful natures of cancer and caused a huge number of deaths among kids and adults from the past few years. According to WHO standard, the 700,000 humans are being with a brain tumor and around 86,000 are diagnosed since 2019. While the total number of deaths due to brain tumors is 16,830 since 2019 and the average survival rate is 35%. Therefore, automated techniques are needed to grade brain tumors precisely from MRI scans. In this work, a new deep learning‐based method is proposed for microscopic brain tumor detection and tumor type classification. A 3D convolutional neural network (CNN) architecture is designed at the first step to extract brain tumor and extracted tumors are passed to a pretrained CNN model for feature extraction. The extracted features are transferred to the correlation‐based selection method and as the output, the best features are selected. These selected features are validated through feed‐forward neural network for final classification. Three BraTS datasets 2015, 2017, and 2018 are utilized for experiments, validation, and accomplished an accuracy of 98.32, 96.97, and 92.67%, respectively. A comparison with existing techniques shows the proposed design yields comparable accuracy.
Article
Full-text available
Artificial intelligence (AI) is the usage of scientific techniques to simulate human intellectual skills and to tackle complex medical issues involving complicated genetic defects such as cancer. The rapid expansion of AI in the past era has paved the way to optimum judgment-making by superior intellect, where the human brain is constrained to manage large information in a limited period. Cancer is a complicated ailment along with several genomic variants. AI-centred systems carry enormous potential in detecting these genomic alterations and abnormal protein communications at a very initial phase. The contemporary biomedical study is also dedicated to bringing AI expertise to hospitals securely and ethically. AI-centred support to diagnosticians and doctors can be the big surge ahead for the forecast of illness threat, identification, diagnosis, and therapies. The applications related to AI and Machine Learning (ML) in the identification of cancer and its therapy possess the potential to provide therapeutic support for quicker planning of a novel therapy for each person. Through the utilization of AI- based methods, scientists can work together in real-time and distribute their expertise digitally to possibly cure billions. In this review, the focus was on the study of linking biology with AI and describe how AI-centred support could assist oncologists in accurate therapy. It is essential to identify new biomarkers that inject drug defiance and discover medicinal goals to improve medication methods. The advent of the “next-generation sequencing” (NGS) programs resolves these challenges and has transformed the prospect of “Precision Oncology” (PO). NGS delivers numerous medical functions which are vital for hazard prediction, initial diagnosis of infection, “Sequence” identification and “Medical Imaging” (MI), precise diagnosis, “biomarker” detection, and recognition of medicinal goals for innovation in medicine. NGS creates a huge repository that requires specific “bioinformatics” sources to examine the information that is pertinent and medically important. The malignancy diagnostics and analytical forecast are improved with NGS and MI that provide superior quality images via AI technology. Irrespective of the advancements in technology, AI faces a few problems and constraints, and the clinical application of NGS continues to be authenticated. Through the steady progress of invention and expertise, the prospects of AI and PO look promising. The purpose of this review was to assess, evaluate, classify, and tackle the present developments in cancer diagnosis utilizing AI methods for breast, lung, liver, skin cancer, and leukaemia. The research emphasizes in what way cancer identification, the treatment procedure is aided by utilizing AI with supervised, unsupervised, and deep learning (DL) methods. Numerous AI methods were assessed on benchmark datasets with respect to “accuracy”, “sensitivity”, “specificity”, and “false-positive” (FP) metrics. Lastly, challenges along with future work were discussed.
Article
Lung cancer is the most common cause of cancer‐related death globally. Currently, lung nodule detection and classification are performed by radiologist‐assisted computer‐aided diagnosis systems. However, emerged artificially intelligent techniques such as neural network, support vector machine, and HMM have improved the detection and classification process of cancer in any part of the human body. Such automated methods and their possible combinations could be used to assist radiologists at early detection of lung nodules that could reduce treatment cost, death rate. Literature reveals that classification based on voting of classifiers exhibited better performance in the detection and classification process. Accordingly, this article presents an automated approach for lung nodule detection and classification that consists of multiple steps including lesion enhancement, segmentation, and features extraction from each candidate's lesion. Moreover, multiple classifiers logistic regression, multilayer perceptron, and voted perceptron are tested for the lung nodule classification using k‐fold cross‐validation process. The proposed approach is evaluated on the publically available Lung Image Database Consortium benchmark data set. Based on the performance evaluation, it is observed that the proposed method performed better in the stateof the art and achieved an overall accuracy rate of 100%. This research presents the lung nodule detection and classification framework. Multiple classifiers logistic regression, multilayer perceptron and voted perceptron using k‐fold cross‐validation process tested on LIDC dataset show promising accuracy results.
Chapter
Full-text available
Melanoma is one of the riskiest diseases that extensively influence the quality of life and can be dangerous or even fatal. Skin lesion classification methods faced challenges in varying scenarios. The available hand-crafted features could not generate better results when the skin lesion images contain low contrast, under and over-segmented images. The hand-crafted features for skin lesions did not discriminate well between the two significantly different densities. The pigmented network feature vector and deep feature vector have been fused using a parallel fusion method to increase classification accuracy. This optimized fused feature vector has been fed to machine learning classifiers that accurately classify the dermoscopic images into two categories as benign and malignant melanoma. The statistical performance measures were used to assess the proposed fused feature vector on three skin lesion datasets (ISBI 2016, ISIC 2017, and PH2). The proposed fused feature vector accurately classified the skin lesion with the highest accuracy of 99.8% for the ISBI 2016.
Article
Skin covers the entire body and is the largest organ. Skin cancer is one of the most dreadful cancers that is primarily triggered by sensitivity to ultraviolet rays from the sun. However, the riskiest is melanoma, although it starts in a few different ways. The patient is extremely unaware of recognizing skin malignant growth at the initial stage. Literature is evident that various handcrafted and automatic deep learning features are employed to diagnose skin cancer using the traditional machine and deep learning techniques. The current research presents a comparison of skin cancer diagnosis techniques using handcrafted and non‐handcrafted features. Additionally, clinical features such as Menzies method, seven‐point detection, asymmetry, border color and diameter, visual textures (GRC), local binary patterns, Gabor filters, random fields of Markov, fractal dimension, and an oriental histography are also explored in the process of skin cancer detection. Several parameters, such as jacquard index, accuracy, dice efficiency, preciseness, sensitivity, and specificity, are compared on benchmark data sets to assess reported techniques. Finally, publicly available skin cancer data sets are described and the remaining issues are highlighted. Computer vision‐based traditional and deep learning techniques for skin cancer diagnosis are explored with handcrafted and non‐handcrafted features, respectively. Results are compared on several benchmark data sets.
Article
Full-text available
Dementia directly influences the quality of life of a person suffering from this chronic illness. The caregivers or carers of dementia people provide critical support to them but are subject to negative health outcomes because of burden and stress. The intervention of mobile health (mHealth) has become a fast-growing assistive technology (AT) in therapeutic treatment of individuals with chronic illness. The purpose of this comprehensive study is to identify, appraise, and synthesize the existing evidence on the use of mHealth applications (apps) as a healthcare resource for people with dementia and their caregivers. A review of both peer-reviewed and full-text literature was undertaken across five (05) electronic databases for checking the articles published during the last five years (between 2014 and 2018). Out of 6195 searches yielded articles, 17 were quantified according to inclusion and exclusion criteria. The included studies distinguish between five categories, viz., (1) cognitive training and daily living, (2) screening, (3) health and safety monitoring, (4) leisure and socialization, and (5) navigation. Furthermore, two most popular commercial app stores, i.e., Google Play Store and Apple App Store, were searched for finding mHealth based dementia apps for PwD and their caregivers. Initial search generated 356 apps with thirty-five (35) meeting the defined inclusion and exclusion criteria. After shortlisting of mobile applications, it is observed that these existing apps generally addressed different dementia specific aspects overlying with the identified categories in research articles. The comprehensive study concluded that mobile health apps appear as feasible AT intervention for PwD and their carers irrespective of limited available research, but these apps have potential to provide different resources and strategies to help this community.
Article
Full-text available
Background: In digital mammography, finding accurate breast profile segmentation of women's mammogram is considered a challenging task. The existence of the pectoral muscle may mislead the diagnosis of cancer due to its high-level similarity to breast body. In addition, some other challenges due to manifestation of the breast body pectoral muscle in the mammogram data include inaccurate estimation of the density level and assessment of the cancer cell. The discrete differentiation operator has been proven to eliminate the pectoral muscle before the analysis processing. Methods: We propose a novel approach to remove the pectoral muscle in terms of the mediolateral-oblique observation of a mammogram using a discrete differentiation operator. This is used to detect the edges boundaries and to approximate the gradient value of the intensity function. Further refinement is achieved using a convex hull technique. This method is implemented on dataset provided by MIAS and 20 contrast enhanced digital mammographic images. Results: To assess the performance of the proposed method, visual inspections by radiologist as well as calculation based on well-known metrics are observed. For calculation of performance metrics, the given pixels in pectoral muscle region of the input scans are calculated as ground truth. Conclusions: Our approach tolerates an extensive variety of the pectoral muscle geometries with minimum risk of bias in breast profile than existing techniques.
Article
Full-text available
Despite broad investigation in content-based image retrieval (CBIR), issue to lessen the semantic gap between high-level semantics and local attributes of the image is still an important issue. The local attributes of an image such as shape, color, and texture are not sufficient for effective CBIR. Visual similarity is a principal step in CBIR and in the baseline approach. In this article, we introduce a novel approach, which relies on the fusion of visual words of scale-invariant feature transform (SIFT) and binary robust invariant scalable keypoints (BRISK) descriptors based on the visual-bag-of-words approach. The two local feature descriptors are chosen as their fusion adds complementary improvement to CBIR. The SIFT descriptor is capable of detecting objects robustly under cluttering due to its invariance to scale, rotation, noise, and illumination variance. However, SIFT descriptor does not perform well at low illumination or poorly localized keypoints within an image. Due to this reason, the discriminative power of the SIFT descriptor is lost during the quantization process, which also reduces the performance of CBIR. However, the BRISK descriptor provides scale and rotation-invariant scale-space, high quality and adaptive performance in classification based applications. It also performs better at poorly localized keypoints along the edges of an object within an image as compared to the SIFT descriptor. The suggested approach based on the fusion of visual words achieves effective results on the Corel-1K, Corel-1.5K, Corel-5K, and Caltech-256 image repositories as equated to the feature fusion of both descriptors and latest CBIR approaches with the surplus assistances of scalability and fast indexing.
Article
Full-text available
The storage size of the image and video repositories are growing day by day due to the extensive use of digital image acquisition devices. The position of an object within an image is obtained by analyzing the content-based properties like shape, texture, and color, while compositional properties present the image layout and include the photographic rule of composition. The high-quality images are captured on the basis of the rule of thirds that divide each image into nine square areas. According to this rule, salient objects of an image are placed on the intersection points or along the imagery lines of the grid to capture the position of the salient objects. To improve image retrieval performance, visual-bag-of-words (VBoW) framework-based image representation is widely used nowadays. According to this framework, the spatial relationship between salient objects of an image is lost due to the formation of a global histogram of the image. This article presents a novel adapted triangular area-based technique, which computes local intensity order pattern (LIOP) features, weighted soft codebooks, and triangular histograms from the four triangular areas of each image. The proposed technique adds the spatial contents from four adapted triangular areas of each image to the inverted index of the VBoW framework, solve overfitting problem of the larger sizes of the codebook, and overwhelmed the problem of the semantic gap. The experimental results and statistical analysis performed on five image collections show an encouraging robustness of the proposed technique that is compared with the recent CBIR techniques.
Article
Full-text available
Peripheral Blood Smear analysis plays a vital role in diagnosis of many diseases such as leukemia, anemia, malaria, lymphoma and infections. Unusual variations in color, shape and size of blood cells indicate abnormal condition. We used a total of 117 images from Leishman stained peripheral blood smears acquired at a magnification of 100X. In this paper we present a robust image processing algorithm for detection of nuclei and classification of white blood cells based on features of the nuclei. We used novel image enhancement method to manage illumination variations and TissueQuant method to manage color variations for the detection of nuclei. Dice similarity coefficient of 0.95 was obtained for nucleus detection. We also compared the proposed method with a state-of-the-art method and the proposed method was found to be better. Shape and texture features of the detected nuclei were used for classifying white blood cells. We considered classification of WBCs using two approaches such as 5-class and cell-by-cell approaches using neural network and hybrid-classifier respectively. We compared the results of both the approaches for classification of white blood cells. Cell-by-cell approach offered 1.4% higher sensitivity in comparison with the 5-class approach. We obtained an accuracy of 100% for lymphocyte and basophil detection. Hence, we conclude that lymphocytes and basophils can be accurately detected even when the analysis is limited to the features of nuclei whereas, accurate detection of other types of WBCs will require analysis of the cytoplasm too.
Article
Full-text available
Content-based image retrieval (CBIR) is a mechanism that is used to retrieve similar images from an image collection. In this paper, an effective novel technique is introduced to improve the performance of CBIR on the basis of visual words fusion of scale-invariant feature transform (SIFT) and local intensity order pattern (LIOP) descriptors. SIFT performs better on scale changes and on invariant rotations. However, SIFT does not perform better in the case of low contrast and illumination changes within an image, while LIOP performs better in such circumstances. SIFT performs better even at large rotation and scale changes, while LIOP does not perform well in such circumstances. Moreover, SIFT features are invariant to slight distortion as compared to LIOP. The proposed technique is based on the visual words fusion of SIFT and LIOP descriptors which overcomes the aforementioned issues and significantly improves the performance of CBIR. The experimental results of the proposed technique are compared with another proposed novel features fusion technique based on SIFT-LIOP descriptors as well as with the state-of-the-art CBIR techniques. The qualitative and quantitative analysis carried out on three image collections, namely, Corel-A, Corel-B, and Caltech-256, demonstrate the robustness of the proposed technique based on visual words fusion as compared to features fusion and the state-of-the-art CBIR techniques.
Article
Full-text available
Auscultation of heart dispenses identification of the cardiac valves. An electronic stethoscope is used for the acquisition of heart murmurs that is further classified into normal or abnormal murmurs. The process of heart sound segmentation involves discrete wavelet transform to obtain individual components of the heart signal and its separation into systole and diastole intervals. This research presents a novel scheme to develop a semi-automatic cardiac valve disorder diagnosis system. Accordingly, features are extracted using wavelet transform and spectral analysis of input signals. The proposed classification scheme is the fusion of adaptive-neuro fuzzy inference system (ANFIS) and HMM. Both classifiers are trained using the extracted features to correctly identify normal and abnormal heart murmurs. Experimental results thus achieved exhibit that proposed system furnishes promising classification accuracy with excellent specificity and sensitivity. However, the proposed system has fewer classification errors, fewer computations, and lower dimensional feature set to build an intelligent system for detection and classification of heart murmurs.
Article
Full-text available
A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research.
Article
Full-text available
Human activity monitoring in the video sequences is an intriguing computer vision domain which incorporates colossal applications, e.g., surveillance systems, human-computer interaction, and traffic control systems. In this research, our primary focus is in proposing a hybrid strategy for efficient classification of human activities from a given video sequence. The proposed method integrates four major steps: (a) segment the moving objects by fusing novel uniform segmentation and expectation maximization, (b) extract a new set of fused features using local binary patterns with histogram oriented gradient and Harlick features, (c) feature selection by novel Euclidean distance and joint entropy-PCA-based method, and (d) feature classification using multi-class support vector machine. The three benchmark datasets (MIT, CAVIAR, and BMW-10) are used for training the classifier for human classification; and for testing, we utilized multi-camera pedestrian videos along with MSR Action dataset, INRIA, and CASIA dataset. Additionally, the results are also validated using dataset recorded by our research group. For action recognition, four publicly available datasets are selected such as Weizmann, KTH, UIUC, and Muhavi to achieve recognition rates of 95.80, 99.30, 99, and 99.40%, respectively, which confirm the authenticity of our proposed work. Promising results are achieved in terms of greater precision compared to existing techniques.
Article
Full-text available
Abstract: In the last few decades, crowd detection has gained much interest from the research community to assist a variety of applications in surveillance systems. While human detection in partially crowded scenarios have achieved many reliable works, a highly dense crowd-like situation still is far from being solved. Densely crowded scenes offer patterns that could be used to tackle these challenges. This problem is challenging due to the crowd volume, occlusions, clutter and distortion. Crowd region classification is a precursor to several types of applications. In this paper, we propose a novel approach for crowd region detection in outdoor densely crowded scenarios based on color variation context and RGB channel dissimilarity. Experimental results are presented to demonstrate the effectiveness of the new color-based features for better crowd region detection. Read More: http://www.worldscientific.com/doi/abs/10.1142/S1793962318500125?src=recsys
Article
Full-text available
Medical imaging plays an integral role in the identification, segmentation, and classification of brain tumors. The invention of MRI has opened new horizons for brain-related research. Recently, researchers have shifted their focus towards applying digital image processing techniques to extract, analyze and categorize brain tumors from MRI. Categorization of brain tumors is defined in a hierarchical way moving from major to minor ones. A plethora of work could be seen in literature related to the classification of brain tumors in categories such as benign and malignant. However, there are only a few works reported on the multiclass classification of brain images where each part of the image containing tumor is tagged with major and minor categories. The precise classification is difficult to achieve due to ambiguities in images and overlapping characteristics of different type of tumors. In the current study, a comprehensive review of recent research on brain tumors multiclass classification using MRI is provided. These multiclass classification studies are categorized into two major groups: XX and YY and each group are further divided into three sub-groups. A set of common parameters from the reviewed works is extracted and compared to highlight the merits and demerits of individual works. Based on our analysis, we provide a set of recommendations for researchers and professionals working in the area of brain tumors classification.
Article
Full-text available
Currently, in the medical imaging, equipment produces 3D results for better visualization and cure. Likewise, need of capable devices for representation of these 3D medicinal images is expanding as it is valuable to view human tissues or organs straightforwardly and is an immense support to medical staff. Consequently, 3D images recreation from 2D images has attracted several researchers. The CT images normally composed of bones soft tissue and background. This paper presents 3D segmentation of leg’s bones in Computed Tomography images (CT scan). The bone section is extracted from each 2D slice and is placed in the 3D space. Surface rendering is applied on 2D bone slices. The data is visualized via multi-planar reformatting, surface rendering, and hardware-accelerated volume rendering. At last, the paper presents an enhanced technique to reproduce 3D bone segmentation in medicinal images that exhibits promising outcomes as compared to the techniques reported in literature. The proposed technique involves contour extraction, image enhancement, segmentation, outlier reduction and 3D modelling.
Article
Full-text available
With the advent of voluminous medical database, healthcare analytics in big data have become a major research area. Healthcare analytics are playing an important role in big data analysis issues by predicting valuable information through data mining and machine learning techniques. This prediction helps physicians in making right decisions for successful diagnosis and prognosis of various diseases. In this paper, an evolution based hybrid methodology is used to develop a healthcare analytic model exploiting data mining and machine learning algorithms Support Vector Machine (SVM), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The proposed model may assist physicians to diagnose various types of heart diseases and to identify the associated risk factors with high accuracy. The developed model is evaluated with the results reported by the literature algorithms in diagnosing heart diseases by taking the case study of Cleveland heart disease database. A great prospective of conducting this research is to diagnose any disease in less time with less number of factors or symptoms. The proposed healthcare analytic model is capable of reducing the search space significantly while analyzing the big data, therefore less number of computing resources will be consumed.
Article
Full-text available
With an increase in the advancement of digital imaging and computing power, computationally intelligent technologies are in high demand to be used in ophthalmology cure and treatment. In current research, Retina Image Analysis (RIA) is developed for optometrist at Eye Care Center in Management and Science University. This research aims to analyze the retina through vessel detection. The RIA assists in the analysis of the retinal images and specialists are served with various options like saving, processing and analyzing retinal images through its advanced interface layout. Additionally, RIA assists in the selection process of vessel segment; processing these vessels by calculating its diameter, standard deviation, length, and displaying detected vessel on the retina. The Agile Unified Process is adopted as the methodology in developing this research. To conclude, Retina Image Analysis might help the optometrist to get better understanding in analyzing the patient's retina. Finally, the Retina Image Analysis procedure is developed using MATLAB (R2011b). Promising results are attained that are comparable in the state of art.
Article
Full-text available
Making deductions and expectations about climate has been a challenge all through mankind’s history. Challenges with exact meteorological directions assist to foresee and handle problems well in time. Different strategies have been investigated using various machine learning techniques in reported forecasting systems. Current research investigates climate as a major challenge for machine information mining and deduction. Accordingly, this paper presents a hybrid neural model (MLP and RBF) to enhance the accuracy of weather forecasting. Proposed hybrid model ensure precise forecasting due to the specialty of climate anticipating frameworks. The study concentrates on the data representing Saudi Arabia weather forecasting. The main input features employed to train individual and hybrid neural networks that include average dew point, minimum temperature, maximum temperature, mean temperature, average relative moistness, precipitation, normal wind speed, high wind speed and average cloudiness. The output layer composed of two neurons to represent rainy and dry weathers. Moreover, trial and error approach is adopted to select an appropriate number of inputs to the hybrid neural network. Correlation coefficient, RMSE and scatter index are the standard yard sticks adopted for forecast accuracy measurement. On individual standing MLP forecasting results are better than RBF, however, the proposed simplified hybrid neural model comes out with better forecasting accuracy as compared to both individual networks. Additionally, results are better than reported in the state of art, using a simple neural structure that reduces training time and complexity.
Article
Full-text available
This paper aims to develop the computer assisted malaria infected erythrocyte classification based on a hybrid classifier. The major issues are feature extraction, optimal feature selection and erythrocytes classification. 54 dimensional features formed by the combination of the proposed features and the existing features have been used to define the feature set. The features such as prediction error, co-occurrence of linear binary pattern, chrominance channel histogram, R-G color channel difference histogram are the newly proposed features in our system. For feature selection, the different techniques have been explored to obtain the optimal feature set. Further, the performance of the different individual classifiers (SVM, k-NN and Naive Bayes) and hybrid classifier, obtained by combining the individual classifiers, is evaluated using the optimal feature set. Using the proposed optimal feature set and hybrid model, better performances (i.e. sensitivity 95.86%, accuracy 98.5%, F-score 93.82%) have been achieved on the collected clinical database. Based on the experimental results it may be concluded that hybrid classifier provides satisfactory results with an improvement in sensitivity (1.09%, 12.04%, 0%), accuracy (0.12%, 1.15%, 1.27%) and F-score (0.7%, 5.77%, 4.61%) as compared to the individual classifiers i.e. SVM, k-NN and Naive Bayes respectively.
Article
Full-text available
Segmentation of objects from a noisy and complex image is still a challenging task that needs to be addressed. This article proposed a new method to detect and segment nuclei to determine whether they are malignant or not (determination of the region of interest, noise removal, enhance the image, candidate detection is employed on the centroid transform to evaluate the centroid of each object, the level set [LS] is applied to segment the nuclei). The proposed method consists of three main stages: preprocessing, seed detection, and segmentation. Preprocessing stage involves the preparation of the image conditions to ensure that they meet the segmentation requirements. Seed detection detects the seed point to be used in the segmentation stage, which refers to the process of segmenting the nuclei using the LS method. In this research work, 58 H&E breast cancer images from the UCSB Bio-Segmentation Benchmark dataset are evaluated. The proposed method reveals the high performance and accuracy in comparison to the techniques reported in literature. The experimental results are also harmonized with the ground truth images.
Article
Full-text available
Malaria parasitemia is the quantitative measurement of the parasites in the blood to grade the degree of infection. Light microscopy is the most well-known method used to examine the blood for parasitemia quantification. The visual quantification of malaria parasitemia is laborious, time-consuming and subjective. Although automating the process is a good solution, the available techniques are unable to evaluate the same cases such as anemia and hemoglobinopathies due to deviation from normal RBCs’ morphology. The main aim of this research is to examine the microscopic images of stained thin blood smears using a variety of computer vision techniques, grading malaria parasitemia on independent factors (RBC’s morphology). The proposed methodology is based on inductive approach, color segmentation of malaria parasites through adaptive algorithm of Gaussian mixture model (GMM). The quantification accuracy of RBCs is improved, splitting the occlusions of RBCs with distance transform and local maxima. Further, the classification of infected and non-infected RBCs has been made to properly grade parasitemia. The training and evaluation have been carried out on image dataset with respect to ground truth data, determining the degree of infection with the sensitivity of 98 % and specificity of 97 %. The accuracy and efficiency of the proposed scheme in the context of being automatic were proved experimentally, surpassing other state-of-the-art schemes. In addition, this research addressed the process with independent factors (RBCs’ morphology). Eventually, this can be considered as low-cost solutions for malaria parasitemia quantification in massive examinations.
Article
Full-text available
Image contrast is an essential visual feature that determines whether an image is of good quality. In computed tomography (CT), captured images tend to be low contrast, which is a prevalent artifact that reduces the image quality and hampers the process of extracting its useful information. A common tactic to process such artifact is by using histogram-based techniques. However, although these techniques may improve the contrast for different grayscale imaging applications, the results are mostly unacceptable for CT images due to the presentation of various faults, noise amplification, excess brightness, and imperfect contrast. Therefore, an ameliorated version of the contrast-limited adaptive histogram equalization (CLAHE) is introduced in this article to provide a good brightness with decent contrast for CT images. The novel modification to the aforesaid technique is done by adding an initial phase of a normalized gamma correction function that helps in adjusting the gamma of the processed image to avoid the common errors of the basic CLAHE of the excess brightness and imperfect contrast it produces. The newly developed technique is tested with synthetic and real-degraded low-contrast CT images, in which it highly contributed in producing better quality results. Moreover, a low intricacy technique for contrast enhancement is proposed, and its performance is also exhibited against various versions of histogram-based enhancement technique using three advanced image quality assessment metrics of Universal Image Quality Index (UIQI), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM). Finally, the proposed technique provided acceptable results with no visible artifacts and outperformed all the comparable techniques.
Article
Currently, rapid growth of digital images on the internet is observed, accordingly, the need for content-based image retrieval systems are in high demand. Content-based image retrieval (CBIR) is an image search technique that does not depend on manually assigned annotations; rather, CBIR uses discriminative features to search an image. By refining features, an efficient retrieval mechanism could be achieved. The aim of this research is to review features extraction and selection that have an impact on content-based image retrieval (CBIR) and information extraction from images using global and local features such as shape, texture and colour. In order to extract most appropriate features for content-based image retrieval (CBIR), several feature extraction and selection techniques are analysed and their efficiency is compared. Additionally, shortcomings of current content-based image retrieval techniques are addressed and possible solutions are suggested to enhance accuracy.
Article
Brain tumor identification using magnetic resonance images (MRI) is an important research domain in the field of medical imaging. Use of computerized techniques helps the doctors for the diagnosis and treatment against brain cancer. In this article, an automated system is developed for tumor extraction and classification from MRI. It is based on marker-based watershed segmentation and features selection. Five primary steps are involved in the proposed system including tumor contrast , tumor extraction, multimodel features extraction, features selection, and classification. A gamma contrast stretching approach is implemented to improve the contrast of a tumor. Then, segmentation is done using marker-based watershed algorithm. Shape, texture, and point features are extracted in the next step and high ranked 70% features are only selected through chi-square max conditional priority features approach. In the later step, selected features are fused using a serial-based concatenation method before classifying using support vector machine. All the experiments are performed on three data sets including Harvard, BRATS 2013, and privately collected MR images data set. Simulation results clearly reveal that the proposed system outperforms existing methods with greater precision and accuracy.
Article
Skin cancer is being a most deadly type of cancers which have grown extensively worldwide from the last decade. For an accurate detection and classification of melanoma, several measures should be considered which include, contrast stretching, irregularity measurement, selection of most optimal features, and so forth. A poor contrast of lesion affects the segmentation accuracy and also increases classification error. To overcome this problem, an efficient model for accurate border detection and classification is presented. The proposed model improves the segmentation accuracy in its preprocessing phase, utilizing contrast enhancement of lesion area compared to the background. The enhanced 2D blue channel is selected for the construction of saliency map, at the end of which threshold function produces the binary image. In addition, particle swarm optimization (PSO) based segmentation is also utilized for accurate border detection and refinement. Few selected features including shape, texture, local, and global are also extracted which are later selected based on genetic algorithm with an advantage of identifying the fittest chromosome. Finally, optimized features are later fed into the support vector machine (SVM) for classification. Comprehensive experiments have been carried out on three datasets named as PH2, ISBI2016, and ISIC (i.e., ISIC MSK-1, ISIC MSK-2, and ISIC UDA). The improved accuracy of 97.9, 99.1, 98.4, and 93.8%, respectively obtained for each dataset. The SVM outperforms on the selected dataset in terms of sensitivity, precision rate, accuracy, and FNR. Furthermore, the selection method outperforms and successfully removed the redundant features.
Article
Automatic medical image analysis is one of the key tasks being used by the medical community for disease diagnosis and treatment planning. Statistical methods are the major algorithms used and consist of few steps including preprocessing, feature extraction, segmentation, and classification. Performance of such statistical methods is an important factor for their successful adaptation. The results of these algorithms depend on the quality of images fed to the processing pipeline: better the images, higher the results. Preprocessing is the pipeline phase that attempts to improve the quality of images before applying the chosen statistical method. In this work, popular preprocessing techniques are investigated from different perspectives where these preprocessing techniques are grouped into three main categories: noise removal, contrast enhancement, and edge detection. All possible combinations of these techniques are formed and applied on different image sets which are then passed to a predefined pipeline of feature extraction, segmentation, and classification. Classification results are calculated using three different measures: accuracy, sensitivity, and specificity while segmentation results are calculated using dice similarity score. Statistics of five high scoring combinations are reported for each data set. Experimental results show that application of proper preprocessing techniques could improve the classification and segmentation results to a greater extent. However, the combinations of these techniques depend on the characteristics and type of data set used. Enhanced Features for Brain Tumar Classification. The current research presents a features enhancement framework for brain tumor segmentation and classification. The impact of noise removal, contrast enhancement and edge detection techniques on medical image analysis, classification is highlighted.
Article
Visual inspection for the quantification of malaria parasitaemiain (MP) and classification of life cycle stage are hard and time taking. Even though, automated techniques for the quantification of MP and their classification are reported in the literature. However, either reported techniques are imperfect or cannot deal with special issues such as anemia and hemoglobinopathies due to clumps of red blood cells (RBCs). The focus of the current work is to examine the thin blood smear microscopic images stained with Giemsa by digital image processing techniques, grading MP on independent factors (RBCs morphology) and classification of its life cycle stage. For the classification of the life cycle of malaria parasite the k‐nearest neighbor, Naïve Bayes and multi‐class support vector machine are employed for classification based on histograms of oriented gradients and local binary pattern features. The proposed methodology is based on inductive technique, segment malaria parasites through the adaptive machine learning techniques. The quantification accuracy of RBCs is enhanced; RBCs clumps are split by analysis of concavity regions for focal points. Further, classification of infected and non‐infected RBCs has been made to grade MP precisely. The training and testing of the proposed approach on benchmark dataset with respect to ground truth data, yield 96.75% MP sensitivity and 94.59% specificity. Additionally, the proposed approach addresses the process with independent factors (RBCs morphology). Finally, it is an economical solution for MP grading in immense testing.
Article
Atomic recognition of the Exudates (EXs), the major symbol of diabetic retinopathy is essential for automated retinal images analysis. In this article, we proposed a novel machine learning technique for early detection and classification of EXs in color fundus images. The major challenge observed in the classification technique is the selection of optimal features to reduce computational time and space complexity and to provide a high degree of classification accuracy. To address these challenges, this article proposed an evolutionary algorithm based solution for optimal feature selection, which accelerates the classification process and reduces computational complexity. Similarly, three well‐known classifiers that is, Naïve Bayes classifier, Support Vector Machine, and Artificial Neural Network are used for the classification of EXs. Moreover, an ensemble‐based classifier is used for the selection of best classifier on the basis of majority voting technique. Experiments are performed on three well‐known benchmark datasets and a real dataset developed at local Hospital. It has been observed that the proposed technique achieved an accuracy of 98% in the detection and classification of EXs in color fundus images. This research presents an evolutionary algorithm to classify EXs in color fundus Images by optimal feature selection and classifiers fusion to accelerate the classification process and reduces computational complexity.
Article
Acute Leukemia is a life‐threatening disease common both in children and adults that can lead to death if left untreated. Acute Lymphoblastic Leukemia (ALL) spreads out in children's bodies rapidly and takes the life within a few weeks. To diagnose ALL, the hematologists perform blood and bone marrow examination. Manual blood testing techniques that have been used since long time are often slow and come out with the less accurate diagnosis. This work improves the diagnosis of ALL with a computer‐aided system, which yields accurate result by using image processing and deep learning techniques. This research proposed a method for the classification of ALL into its subtypes and reactive bone marrow (normal) in stained bone marrow images. A robust segmentation and deep learning techniques with the convolutional neural network are used to train the model on the bone marrow images to achieve accurate classification results. Experimental results thus obtained and compared with the results of other classifiers Naïve Bayesian, KNN, and SVM. Experimental results reveal that the proposed method achieved 97.78% accuracy. The obtained results exhibit that the proposed approach could be used as a tool to diagnose Acute Lymphoblastic Leukemia and its sub‐types that will definitely assist pathologists. This research proposed a method for the classification of Acute Lymphoblastic Leukemia (ALL) into its subtypes and reactive bone marrow (Normal) in stained bone marrow images using deep learning techniques with convolutional neural networks.
Article
This research comes out with an in-depth review of widely used techniques to handwritten signature verification based, feature selection techniques. The focus of this research is to explore best features selection criteria for signature verification to avoid forgery. This paper further present pros and cons of local and global features selection techniques, reported in the state of art. Experiments are conducted on benchmark databases for signature verification systems (GPDS). Results are tested using two standard protocols; GPDS and the program for rate estimation and feature selection. The current precision of the signature verification techniques reported in state of art are compared on benchmark database and possible solutions are suggested to improve the accuracy. As the equal error rate is an important factor for evaluating the signature verification's accuracy, the results show that the feature selection methods have successfully contributed toward efficient signature verification.
Article
Glaucoma is a neurodegenerative illness and is considered as a standout amongst the most widely recognized reasons for visual impairment. Nerve's degeneration is an irretrievable procedure, so the diagnosis of the illness at an early stage is an absolute requirement to stay away from lasting loss of vision. Glaucoma effected mainly because of increased intraocular pressure, if it is not distinguished and looked early, it can result in visual impairment. There are not generally evident side effects of glaucoma; thus, patients attempt to get treatment just when the seriousness of malady is advanced altogether. Determination of glaucoma often comprises of review of the basic crumbling of the nerve in conjunction with the examination of visual function capacity. This article shows the persistent illustration of glaucoma, its side effects, and the potential people inclined to this malady. The essence of this article is on different classification methods being utilized and proposed by various scientists for the identification of glaucoma. This article audits a few division and segmentation methodologies that are exceptionally useful for recognizable proof, identification, and diagnosis of glaucoma. The research related to the findings and the treatment is likewise evaluated in this article.
Article
Identifying abnormality using breast mammography is a challenging task for radiologists due to its nature. A more consistent and precise imaging based CAD system plays a vital role in the classification of doubtful breast masses. In the proposed CAD system, pre-processing is performed to suppress the noise in the mammographic image. Then segmentation locates the tumor in mammograms using the cascading of Fuzzy C-Means (FCM) and region-growing (RG) algorithm called FCMRG. Features extraction step involves identification of important and distinct elements using Local Binary Pattern Gray-Level Co-occurrence Matrix (LBP-GLCM) and Local Phase Quantization (LPQ). The hybrid features are obtained from these techniques. The mRMR algorithm is employed to choose suitable features from individual and hybrid feature sets. The nominated feature sets are analysed through various machine learning procedures to isolate the malignant tumors from the benign ones. The classifiers are probed on 109 and 72 images of MIAS and DDSM databases respectively using k-fold (10-fold) cross-validation method. The enhanced classification accuracy of 98.2% is achieved for MIAS dataset using hybrid features classified by Decision Tree. Whereas 95.8% accuracy is obtained for DDSM dataset using KNN classifier applied on LPQ features.
Article
Background: Knee bone diseases are rare but might be highly destructive. Magnetic Resonance Imaging (MRI) is the main approach to identify knee cancer and its treatment. Normally, the knee cancers are detected with the help of different MRI analysis techniques and later image analysis strategies assess these images. Discussion: Computer-based medical image analysis is getting researcher’s interest due to its advantages of speed and accuracy as compared to traditional techniques. The focus of current research is MRI-based medical image analysis for knee bone disease detection. Accordingly, several approaches for features extraction and segmentation for knee bone cancer are analyzed and compared on benchmark database. Conclusion: Finally, the current state of the art is investigated and future directions are proposed.
Article
Malaria parasitemia diagnosis and grading is hard and still far from perfection. Inaccurate diagnosis and grading has caused tremendous deaths rate particularly in young children worldwide. The current research deeply reviews automated malaria parasitemia diagnosis and grading in thin blood smear digital images through image analysis and computer vision based techniques. Actually, state‐of‐the‐art reveals that current proposed practices present partially or morphology dependent solutions to the problem of computer vision based microscopy diagnosis of malaria parasitemia. Accordingly, a deep appraisal of the current practices is investigated, compared and analyzed on benchmark datasets. The open gaps are highlighted and the future directions are laid down for a complete automated microscopy diagnosis for malaria parasitemia based on those factors that have not been affected by other diseases. Moreover, a general computer vision framework to perform malaria parasitemia estimation/grading is constructed in universal directions. Finally, remaining problems are highlighted and possible directions are suggested. Research Highlights The current research presents a microscopic malaria parasitemia diagnosis and grading of malaria in thin blood smear digital images through image analysis and computer vision based techniques. The open gaps are highlighted and future directions for a complete automated microscopy diagnosis of malaria parasitemia mentioned.
Article
Splitting the rouleaux RBCs from single RBCs and its further subdivision is a challenging area in computer‐assisted diagnosis of blood. This phenomenon is applied in complete blood count, anemia, leukemia, and malaria tests. Several automated techniques are reported in the state of art for this task but face either under or over splitting problems. The current research presents a novel approach to split Rouleaux red blood cells (chains of RBCs) precisely, which are frequently observed in the thin blood smear images. Accordingly, this research address the rouleaux splitting problem in a realistic, efficient and automated way by considering the distance transform and local maxima of the rouleaux RBCs. Rouleaux RBCs are splitted by taking their local maxima as the centres to draw circles by mid‐point circle algorithm. The resulting circles are further mapped with single RBC in Rouleaux to preserve its original shape. The results of the proposed approach on standard data set are presented and analyzed statistically by achieving an average recall of 0.059, an average precision of 0.067 and F‐measure 0.063 are achieved through ground truth with visual inspection. Rouleaux RBCs are splitted by taking their local maxima as the centres to draw circles employing mid‐point circle algorithm. The resulting circles are further mapped with single RBC into Rouleaux at high accuracy, while preserving original shape.
Article
Arabic writer identification and associated tasks are still fresh due to huge variety of Arabic writer's styles. Current research presents a fusion of statistical features, extracted from fragments of Arabic handwriting samples to identify the writer using fuzzy ARTMAP classifier. Fuzzy ARTMP is supervised neural model, especially suited to classification problems. It is faster to train and need less number of training epochs to "learn" from input data for generalization. The extracted features are fed to Fuzzy ARTMP for training and testing. Fuzzy ARTMAP is employed for the first time along with a novel fusion of statistical features for Arabic writer identification. The entire IFN/ENIT database is used in experiments such that 75% handwritten Arabic words from 411 writers are employed in training and 25% for testing the system at random. Several combinations of extracted features are tested using fuzzy ARTMAP classifier and finally one combination exhibited promising accuracy of 94.724% for Arabic writer identification on IFN/ENIT benchmark database.
Article
Early screening of skeptical masses or breast carcinomas in mammograms is supposed to decline the mortality rate among women. This amount can be decreased more on development of the computer-aided diagnosis with reduction of false suppositions in medical informatics. Our aim is to provide a robust tumor detection system for accurate classification of breast masses using normal, abnormal, benign, or malignant classes. The breast carcinomas are classified on the basis of observed classes. This is highly dependent on feature extraction process. In propose work, a novel algorithm for classification based on the combination of top Hat transformation and gray level cooccurrence matrix with back propagation neural network. The aim of this study is to present a robust classification model for automated diagnosis of the breast tumor with reduction of false assumptions in medical informatics. The proposed method is verified on two datasets MIAS and DDSM. It is observed that rate of false positives decreased by the proposed method to improve the performance of classification, efficiently.
Article
Knee bone diseases are rare but might be highly destructive. Magnetic resonance imaging (MRI) is the main approach to identify knee cancer and its treatment. Normally, the knee cancers are pointed out with the help of different MRI analysis techniques and latter image analysis strategies understand these images. Computer-based medical image analysis is getting researcher's interest due to its advantages of speed and accuracy as compared to traditional techniques. The focus of current research is MRI-based medical image analysis for knee bone disease detection. Accordingly, several approaches for features extraction and segmentation for knee bone cancer are analyzed and compared on benchmark database. Finally, the current state of the art is investigated and future directions are proposed.
Article
This paper presents an ear biometric approach to classify humans. Accordingly an improved local features extraction technique based on ear region features is proposed. Accordingly, ear image is segmented in to certain regions to extract eigenvector from all regions. The extracted features are normalized and fed to a trained neural network. To benchmark results, benchmark database from University of Science and Technology Beijing (USTB) is employed that have mutually exclusive sets for training and testing. Promising results are achieved that are comparable in the state of art. However, a few region features exhibited low accuracy that will be addressed in the subsequent research.
Article
Extraction of the breast border and simultaneously exclusion of pectoral muscle are principal steps for diagnosing of breast cancer based on mammogram data. The objective of propose method is to classify the mediolateral oblique fragment of the pectoral muscle. The extraction of breast region is performed using the multilevel wavelet decomposition of mammogram images. Moreover, artifact suppression and pectoral muscle detection is carried out by morphological operator. The efficient extraction with higher accuracy is validated on the set of 322 digital images taken from MIAS dataset.
Article
Extraction of the breast border and simultaneously exclusion of pectoral muscle are principal steps for diagnosing of breast cancer based on mammogram data. The objective of proposed method is to classify the mediolateral oblique fragment of the pectoral muscle. The extraction of breast region is performed using the multilevel wavelet decomposition of mammogram images. Moreover, artifact suppression and pectoral muscle detection are carried out by the morphological operator. The efficient extraction with higher accuracy is validated on the set of 322 digital images taken from MIAS dataset.
Conference Paper
Malaria is a very serious infectious disease caused by a peripheral blood parasite of the genus Plasmodium. Conventional microscopy, which is currently “the gold standard” for malaria diagnosis has occasionally proved inefficient since it is time consuming and results are difficult to reproduce. As it poses a serious global health problem, automation of the evaluation process is of high importance. In this work, an accurate, rapid and affordable model of malaria diagnosis using stained thin blood smear images was developed. The method made use of the intensity features of Plasmodium parasites and erythrocytes. Images of infected and non-infected erythrocytes were acquired, pre-processed, relevant features extracted from them and eventually diagnosis was made based on the features extracted from the images. A set of features based on intensity have been proposed, and the performance of these features on the red blood cell samples from the created database have been evaluated using an artificial neural network (ANN) classifier. The results have shown that these features could be successfully used for malaria detection.
Conference Paper
Blood cell segmentation is a critical innovation for differential blood count, and parasitic disease identification such as malaria, Babesiosis, Chagas etc. In many parasitic diseases parasites infect blood cells. In sickle cell anemia blood cells segmentation is important to know the morphology of Red Blood Cells (RBCs). This paper proposed a method of an automatic blood cells segmentation using K-Mean clustering. Giemsa stained thin blood slides are used for image acquisition by high resolution camera. Processing includes preprocessing, segmentation, separation of overlapped blood cells and evaluation of segmentation results. Proposed algorithm is tested on 60 images. Database images used are of different magnification and surrounding conditions. Correct segmentation accuracy achieved is 98.89%.
Article
Now a days, writer identification is at high demand to identify the original writer of the script at high accuracy. The one of the main challenge in writer identification is how to extract the discriminative features of different authors’ scripts to classify precisely. In this paper, the adaptive division method on the offline Latin script has been implemented using several variant window sizes. Fragments of binarized text a set of features are extracted and classified into clusters in the form of groups or classes. Finally, the proposed approach in this paper has been tested on various parameters in terms of text division and window sizes. It is observed that selection of the right window size yields a well positioned window division. The proposed approach is tested on IAM standard dataset (IAM, Institut für Informatik und angewandte Mathematik, University of Bern, Bern, Switzerland) that is a constraint free script database. Finally, achieved results are compared with several techniques reported in the literature.
Article
Image fusion process consolidates data and information from various images of same sight into a solitary image. Each of the source images might speak to a fractional perspective of the scene, and contains both "pertinent" and "immaterial" information. In this study, a new image fusion method is proposed utilizing the Discrete Cosine Transform (DCT) to join the source image into a solitary minimized image containing more exact depiction of the sight than any of the individual source images. In addition, the fused image comes out with most ideal quality image without bending appearance or loss of data. DCT algorithm is considered efficient in image fusion. The proposed scheme is performed in five steps: (1) RGB colour image (input image) is split into three channels R, G, and B for source images. (2) DCT algorithm is applied to each channel (R, G, and B). (3) The variance values are computed for the corresponding 8 × 8 blocks of each channel. (4) Each block of R of source images is compared with each other based on the variance value and then the block with maximum variance value is selected to be the block in the new image. This process is repeated for all channels of source images. (5) Inverse discrete cosine transform is applied on each fused channel to convert coefficient values to pixel values, and then combined all the channels to generate the fused image. The proposed technique can potentially solve the problem of unwanted side effects such as blurring or blocking artifacts by reducing the quality of the subsequent image in image fusion process. The proposed approach is evaluated using three measurement units: the average of Q(abf) , standard deviation, and peak Signal Noise Rate. The experimental results of this proposed technique have shown good results as compared with older techniques. Microsc. Res. Tech., 2016. © 2016 Wiley Periodicals, Inc.
Article
Offline clinical guidelines are typically designed to integrate a clinical knowledge base, patient data and an inference engine to generate case specific advice. In this regard, offline clinical guidelines are still popular among the healthcare professionals for updating and support of clinical guidelines. Although their current format and development process have several limitations, these could be improved with artificial intelligence approaches such as expert systems/decision support systems. This paper first, presents up to date critical review of existing clinical expert systems namely AAPHelpm, MYCIN, EMYCIN, PIP, GLIF and PROforma. Additionally, an analysis is performed to evaluate all these fundamental clinical expert systems. Finally, this paper presents the proposed research and development of a clinical expert system to help healthcare professionals for treatment.
Article
Arabic script classification is a complex area of research in the field of computer vision. The issue of offline Arabic script classification has been a concern of many researchers interest currently as it is assumed that online Arabic script recognition is comparatively simple and significant achievements have been attained. Numerous researchers deal with these issues evolved in pre-processing and post-processing techniques of Arabic script and presented various approaches to improve its accuracy rate. However, offline Arabic script classification and its related issues are still fresh. In this paper, we focus on pre-processing to post-processing techniques and highlight several issues in each phase in order to highlight need of high classification performance for Arabic script classification (offline and online). Additionally, top experimental results are reported, discussed and compared, and current challenges are also discussed. Finally, online versus offline Arabic script recognition achievements are also compared.
Article
The Leukocytes are differentiated from each other on the basis of their nuclei, demanded in many Medical studies, especially in all types of Leukemia by the Hematologists to note the disorder caused by specific type of Leukocyte. Leukemia is a life threatening disease. The work for diagnosing is manually carried out by the Hematologists involving much labor, time and human errors. The problems mentioned are easily addressed through computer vision techniques, but still accuracy and efficiency are demanded in terms of the basic and challenging step segmentation of Leukocyte's nuclei. The underlying study proposed better method in terms of accuracy and efficiency by designing a dynamic convolution filter for boosting low intensity values in the separated green channel of an RGB image and suppressing the high values in the same channel. The high values in the green channel become 255 (background) while the nuclei always have low values in the green channel and thus clearly appear as foreground. The proposed technique is tested on 365 images achieving an overall accuracy of 95.89%, while improving the efficiency by 10%. The proposed technique achieved its targets in a realistic way by improving the accuracy as well as the efficiency and both are highly required in the area.
Article
The aim of this study is to propose an algorithm that can recognize partially occluded objects under different variations by computing three histograms of colour spaces (RGB, HSV, YCbCr). The dataset used in this research are from kitchen apparatuses. It is created by the researcher and include two parts: referenced objects (18 single objects) and tested objects (occluded objects) made from two single objects to represent the occluded object under different variations (scale, rotation, transformation) with varying percentage of occlusion (30–90 %). Three different colour spaces histogram (RGB, HIS, YCbCr) are used for extracting the features. Histogram intersection distance works for matching objects. Computation histograms and matching process are used to each block of image that given by image division process and finally compared the performance of each colour space by evaluating the accuracy. The experimental results demonstrate that the proposed algorithm is robust for identifying occluded objects and it could work at high occlusion. © 2015, 3D Research Center, Kwangwoon University and Springer-Verlag Berlin Heidelberg.
Article
The overall success of automatic speech recognition (ASR) depends on efficient phoneme recognition performance and quality of speech signal received in ASR. However, dissimilar inputs of speakers affect the overall recognition performance. One of the main problems that affect recognition performance is inter-speaker variability. Vocal tract length normalization (VTLN) is introduced to compensate inter-speaker variation on the speaker signal by applying speaker-specific warping of the frequency scale of a filter bank. Instead of measuring the performance on word level with speaker-specific warping, this research focuses on direct tackling at the phoneme level and applying VTLN on all speakers’ speech signals to analyse the best setting for the highest recognition performance. This research seeks to compare each phoneme recognition results from warping factor between 0.74 and 1.54 with 0.02 increments on nine different ranges of frequency warping boundary. The warp factor and frequency warping range that provides the highest phoneme recognition performance is applied on word recognition. The results show an improved performance in phoneme recognition by 0.7% and spoken word recognition by 0.5% using warp factor of 1.40 on frequency range of 300–5000 Hz in comparison to baseline results.
Article
Face detection plays important roles in many applications such as human-computer interaction, security and surveillance, face recognition, etc. This article presents an intelligent enhanced fused approach for face recognition based on the Voronoi diagram (VD) and wavelet moment invariants. Discrete wavelet transform and moment invariants are used for feature extraction of the facial face. Finally, VD and the dual tessellation (Delaunay triangulation, DT) are used to locate and detect original face images. Face recognition results based on this new fusion are promising in the state of the art.