ArticlePDF Available

A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding

Authors:

Abstract and Figures

Eye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue to detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming a variety of up-to-date systems and demonstrating the capacity to deal with other heterogenous anatomical structures.
Content may be subject to copyright.
A preview of the PDF is not available
... The thresholding approach has received wide attention because of its low complexity, low storage requirements and low processing time [16]. However, it is not effective if the different regions in the image under consideration have not well-defined areas (e.g., different objects with similar gray areas), or the pixel intensity histograms are unimodal [17]. For detailed descriptions of recent thresholding segmentation approaches, readers may refer to [18], [17], [19], [20]. ...
... However, it is not effective if the different regions in the image under consideration have not well-defined areas (e.g., different objects with similar gray areas), or the pixel intensity histograms are unimodal [17]. For detailed descriptions of recent thresholding segmentation approaches, readers may refer to [18], [17], [19], [20]. ...
Article
In this paper, we address the problem of automatic image segmentation methods applied to the partial automation of the production process of a traditional Sardinian flatbread called pane Carasau for assuring quality control. The study focuses on one of the most critical activities for obtaining an efficient degree of automation: the estimation of the size and shape of the bread sheets during the production phase, to study the shape variations undergone by the sheet depending on some environmental and production variables. The knowledge can thus be used to create a system capable of predicting the quality of the shape of the dough produced and empower the production process. We implemented an image acquisition system and created an efficient machine learning algorithm, based on support vector machines, for the segmentation and estimation of image measurements for Carasau bread. Experiments demonstrated that the method can successfully achieve accurate segmentation of bread sheets images, ensuring that the dimensions extracted are representative of the sheets coming from the production process. The algorithm proved to be fast and accurate in estimating the size of the bread sheets in various scenarios that occurred over a year of acquisitions. The maximum error committed by the algorithm is equal to the 2.2% of the pixel size in the worst scenario and to 1.2% elsewhere.
... Almotiri et al. [9] established an algorithm based on a hybrid segmentation procedure for the segmentation of blood vessels. The algorithm consists of adaptive fuzzy thresholding and mathematical Morphology. ...
Article
Full-text available
Segmentation of Blood Vessel is a challenging mission in medical image processing to diagnose the disease. It evaluates vessels crucial in automatic retinal vessel extraction with different methodologies, techniques and algorithms to predict the diseases such as Laryngology, neurosurgery and ophthalmology. Using a computer-aided technique, segmentation of blood vessels is conducted in the retina closer to the clinical application routine. This research aims to provide an overview of numerous retinal vessel segmentation approaches, analyse different categories of segmentation techniques, provide a brief description, and evaluate the performance measures. It also reviews, examines, and classifies the procedures, techniques, and methodologies and highlights the important points. The main intention is to provide the reader with a framework for the existing research, introduce the range of retinal vessel segmentation procedures, deliberate the current trends and future directions and summarize the open problems. First, retinal image photography is introduced from the fundus camera. Pre-processing operations and methods of identifying retinal vessels on computer-aided techniques are introduced and discussed to validate results based on the evaluation of various segmentation techniques. The performance of various segmentation techniques and algorithms is estimated using a publicly present database such as DRIVE, STARE, HRF, CHASE, Infant and MESSIDOR. The performance and comparison of various algorithms are assessed in average accuracy, sensitivity, specificity and ROC curves. A huge volume of techniques is considered based on retinal vessel segmentation published in current years. A systematic review is constructed by considering the publications from 2001 to 2021, focusing on methods based on automatic vessel segmentation and classification using fundus camera images. The advantages and limitations are discussed, and tables are included for summarising results at-a-glance. Then an attempt is made to measure the quantitative merit of segmentation methods in terms of accuracy development compared to other methods. Finally, it represented the recent trends with the future direction and summarized the open challenge issues.
... Almotiri et al. [9] established an algorithm based on a hybrid segmentation procedure for the segmentation of blood vessels. The algorithm consists of adaptive fuzzy thresholding and mathematical Morphology. ...
Article
Full-text available
Segmentation of Blood Vessel is a challenging mission in medical image processing to diagnose the disease. It evaluates vessels crucial in automatic retinal vessel extraction with different methodologies, techniques and algorithms to predict the diseases such as Laryngology, neurosurgery and ophthalmology. Using a computer-aided technique, segmentation of blood vessels is conducted in the retina closer to the clinical application routine. This research aims to provide an overview of numerous retinal vessel segmentation approaches, analyse different categories of segmentation techniques, provide a brief description, and evaluate the performance measures. It also reviews, examines, and classifies the procedures, techniques, and methodologies and highlights the important points. The main intention is to provide the reader with a framework for the existing research, introduce the range of retinal vessel segmentation procedures, deliberate the current trends and future directions and summarize the open problems. First, retinal image photography is introduced from the fundus camera. Pre-processing operations and methods of identifying retinal vessels on computer-aided techniques are introduced and discussed to validate results based on the evaluation of various segmentation techniques. The performance of various segmentation techniques and algorithms is estimated using a publicly present database such as DRIVE, STARE, HRF, CHASE, Infant and MESSIDOR. The performance and comparison of various algorithms are assessed in average accuracy, sensitivity, specificity and ROC curves. A huge volume of techniques is considered based on retinal vessel segmentation published in current years. A systematic review is constructed by considering the publications from 2001 to 2021, focusing on methods based on automatic vessel segmentation and classification using fundus camera images. The advantages and limitations are discussed, and tables are included for summarising results at-a-glance. Then an attempt is made to measure the quantitative merit of segmentation methods in terms of accuracy development compared to other methods. Finally, it represented the recent trends with the future direction and summarized the open challenge issues.
... Edge detection employs the improved Canny edge detection algorithm.(3) Morphological processing[24][25][26][27][28] utilizes linear operators to perform closed operations, so that the detected edge information is connected into a connected region. According to the length of the car number in the image and the experiment, the selected linear operator is [1, to the brushing rules of the passenger train number and the prior knowledge of the length and width of the car number in the actual captured image, combined with the wavelet transform image size transformation relationship, the minimum circumscribed rectangle segmentation is used to extract the region that satisfies the constraint condition and complete the car number positioning. ...
Article
Full-text available
With the continuous increase of the urban population, urban traffic problems have become increasingly prominent. The subway and light rail have the characteristics of large passenger volume and low pollution, which are the preferred solutions to solve the traffic problems in large and medium cities. Due to the high density of rail transit trains, the close distance between stations, and the high safety requirements, the real-time and accurate determination of the train's position on the line is the premise to ensure safety, maximize efficiency, and provide the best service. How to accurately detect the speed and position of the train to control its the operation is the core content of the rail transit system. Therefore, the in-depth study of train positioning methods has great and far-reaching significance for promoting the research of train operation control system and the development of rail transit system. It has become a research hotspot to rely on computer technology and image recognition technology to realize precise positioning of trains. In order to realize the real-time precise positioning of the train, this paper proposes a train positioning method based on Haar wavelet transform. First, the samples are obtained by the method of video acquisition, and the video images are initially processed by binarization. Second, the image is compressed, denoised, and enhanced by Haar wavelet transform, and the train number is determined. Finally, the orbital electronic map and satellite assistance are used to determine the position of the train and realize the train positioning. The simulation experiments show that the image acquired by Haar wavelet transform can accurately identify the train and track. Based on the satellite aid of the orbital electronic map, the train positioning can be accurately realized, and the proposed Haar wavelet transform is proposed and has good positioning accuracy.
... Using fuzzy morphological techniques, DR diagnosis can be achieved with an accuracy of 93.8% [12]. Similarly, Almotiri et al. applied fuzzy c-means (FCM) clustering for image segmentation, and DR detection was achieved with 95.88% accuracy [13]. ...
Article
Full-text available
Diabetic retinopathy (DR) is one of the most important microvascular complications associated with diabetes mellitus. The early signs of DR are microaneurysms, which can lead to complete vision loss. The detection of DR at an early stage can help to avoid non-reversible blindness. To do this, we incorporated fuzzy logic techniques into digital image processing to conduct effective detection. The digital fundus images were segmented using particle swarm optimization to identify microaneurysms. The particle swarm optimization clustering combined the membership functions by grouping the high similarity data into clusters. Model testing was conducted on the publicly available dataset called DIARETDB0, and image segmentation was done by probability-based (PBPSO) clustering algorithms. Different fuzzy models were applied and the outcomes were compared with our probability discrete particle swarm optimization algorithm. The results revealed that the proposed PSO algorithm achieved an accuracy of 99.9% in the early detection of DR.
... --neural network 5 [42] A hybrid segmentation algorithm DIARETDB1 Fuzzy C-means with mathematical morphology -and adaptive fuzzy thresholding 6 [24] An ensemble classifier of bootstrapped DIARETDB1 Ensemble decision trees combines with Gabor E-Ophtha classifier filter and morphological reconstruction. ...
Preprint
Full-text available
Diabetic retinopathy refers to the pathology of the retina induced by diabetes and is one of the leading causes of preventable blindness in the world. Early detection of diabetic retinopathy is critical to avoid vision problem through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of lesion and low contrast of the images. Thus, computer-assisted diagnosis of diabetic retinopathy based on the detection of red lesions is actively being explored recently. In this paper, we present a convolutional neural network with residual skip connection for the segmentation of exudates in retinal images. To improve the performance of network architecture, a suitable image augmentation technique is used. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. Comparative performance analysis of three benchmark databases: HEI-MED, E-ophtha, and DiaretDB1 is presented. It is shown that the proposed method achieves accuracy (0.98, 0.99, 0.98) and sensitivity (0.97, 0.92, and 0.95) on E-ophtha, HEI-MED, and DiaReTDB1, respectively.
... However, due to the lack of a public database for ROP and hence the difficulty in obtaining a large clinical dataset, the development of DL algorithms for diagnosing ROP lags behind other retinal diseases. Some studies have used DL models to process retinal images by vessel segmentation or zone identification and have recommended the application of the feature-based images for further clinical diagnosis or DL model building [10][11][12]. Some studies followed this flow to build an entire DL model for diagnosing ROP. ...
Article
Full-text available
Background: Retinopathy of prematurity (ROP) occurs in preterm infants and may contribute to blindness. Deep learning (DL) models have been used for ophthalmologic diagnoses. We performed a systematic review and meta-analysis of published evidence to summarize and evaluate the diagnostic accuracy of DL algorithms for ROP by fundus images. Methods: We searched PubMed, EMBASE, Web of Science, and Institute of Electrical and Electronics Engineers Xplore Digital Library on June 13, 2021, for studies using a DL algorithm to distinguish individuals with ROP of different grades, which provided accuracy measurements. The pooled sensitivity and specificity values and the area under the curve (AUC) of summary receiver operating characteristics curves (SROC) summarized overall test performance. The performances in validation and test datasets were assessed together and separately. Subgroup analyses were conducted between the definition and grades of ROP. Threshold and nonthreshold effects were tested to assess biases and evaluate accuracy factors associated with DL models. Results: Nine studies with fifteen classifiers were included in our meta-analysis. A total of 521,586 objects were applied to DL models. For combined validation and test datasets in each study, the pooled sensitivity and specificity were 0.953 (95% confidence intervals (CI): 0.946-0.959) and 0.975 (0.973-0.977), respectively, and the AUC was 0.984 (0.978-0.989). For the validation dataset and test dataset, the AUC was 0.977 (0.968-0.986) and 0.987 (0.982-0.992), respectively. In the subgroup analysis of ROP vs. normal and differentiation of two ROP grades, the AUC was 0.990 (0.944-0.994) and 0.982 (0.964-0.999), respectively. Conclusions: Our study shows that DL models can play an essential role in detecting and grading ROP with high sensitivity, specificity, and repeatability. The application of a DL-based automated system may improve ROP screening and diagnosis in the future.
Article
Automated extraction of retinal vasculature is becoming a crucial task during the study of pathological disorders present in the retinal fundus image. In this work, we propose an unsupervised approach for automatically extracting blood vessels from fundus photographs. In this paper, Logarithmic transformation (Log) and contrast limited adaptive histogram equalisation (CLAHE) are being used to boost the contrast level of the fundus photographs. After that, Matched filtering technique is used for further vessel enhancement. Then, different thresholding techniques are evaluated and compared to find out the best thresholding scheme for this segmentation. We have found that Otsu with entropy weighting thresholding is the best threshold method for segmenting the blood vessels. In the post-processing step, the area-based thresholding process is considered, and it gives the final vessel segmented image. Using the following statistical measures, the final vessel segmented image is compared to the ground truth image, such as sensitivity (Sens), precision (Spec), and accuracy (Acc). This work is evaluated by freely accessible DRIVE (Digital Retinal Images for Vessel Extraction), STARE (Structured Analysis of the Retina), and CHASE_DB1 (Child Heart and Health Study in England) datasets. This work achieves an average accuracy of 0.9562, 0.946, and 0.946 on the DRIVE, STARE, and CHASE_DB1 datasets, respectively.
Article
Single-valued point can not effectively describe the gray characteristic of the image region, which makes existing fuzzy clustering algorithms difficult to segment image with uneven illumination, weak edges and strong noise. Hence, fuzzy c-means clustering with quadratic polynomial surface as clustering center has become a new method to solve complex image segmentation. Aiming at the shortcoming of current latest spatial fuzzy c-means clustering algorithm with quadratic surface as clustering center, quadratic polynomial surface is firstly introduced into existing widely used fuzzy local information c-means clustering algorithm, and further modify the membership degree of fuzzy local information c-means clustering by means of local membership of neighborhood pixels, a novel fuzzy dual-local information c-means clustering with quadratic polynomial-center clusters is proposed to solve the segmentation problem of complex image in the presence of high noise. Then the convergence of the proposed algorithm is strictly proved by Zangwill theorem and bordered Hessian matrix. Experimental results show that the proposed algorithm has better segmentation performance and anti-noise robustness than existing quadratic polynomial-related QPFCM, widely used FLICM, and multiple state-of-the-art algorithms, meanwhile, it also promotes the development of robust fuzzy clustering-related image segmentation theory.
Article
The accurate segmentation of the retinal vessel tree has become the prerequisite step for automatic ophthalmological and cardiovascular diagnosis systems. Aside from accuracy, robustness and processing speed are also considered crucial for medical purposes. In order to meet those requirements, this work presents a novel approach to extract blood vessels from the retinal fundus, by using morphology-based global thresholding to draw the retinal venule structure and centerline detection method for capillaries. The proposed system is tested on DRIVE and STARE databases and has an average accuracy of 95.88% for single-database test and 95.27% for the cross-database test. Meanwhile, the system is designed to minimize the computing complexity and processes multiple independent procedures in parallel, thus having an execution time of 1.677 s per image on CPU platform.
Article
Diabetic Retinopathy (DR) is the one among other main reasons of blindness in the adult population. Early discovery of DR through screening programs and successive treatment is critical in order to avoid visual blindness. The early signs of DR as manifested in retinal images include micro-aneurysms, hemorrhages and exudates. In this paper, we have presented an ensemble classifier of bootstrapped decision trees for multiscale localization and segmentation of exudates in retinal fundus images. The candidate exudates are extracted at fine grain and coarse grain levels using morphological reconstruction and Gabor filter respectively. The contextual cues are applied to the candidate exudates, which greatly reduces false positives in exudate segmentation. Several region based features are computed from candidate regions to train the ensemble classifier for classification of pixel as exudate and non-exudate region. The method has been evaluated on four publically available databases; DIARETDB1, e-Ophtha EX, HEI-MED and Messidor. The method has achieved the segmentation accuracy as (0.8772, 0.8925, 0.9577, and 0.9836) and area under ROC as (0.9310, 0.9403, 0.9842, and 0.9961) for each of the dataset respectively. The algorithm appears to be an efficient tool for automated detection of exudates in large population based DR screening programs, due to the attained accuracy, robustness, simplicity and speed.
Conference Paper
Indonesia is one of ten countries with the highest diabetic prevalence. It becomes a concern of the government because aside from personal health, this disease also has social and economic impacts since it causes a decrease in productivity. One complication of this disease to the patient is impaired vision is diabetic retinopathy (DR). In order to prevent further development of DR, early detection needs to be performed with routine check on patient's eyes. Clinical features on eye retina that can be used for detection of DR include microaneurysms, hard and soft exudates, haemorrhages, neovazcularisation and macular edema. Segmentation of optic disc (OD) is a very important step to detect these features. This study used red channel from original image based on dispersive phase stretch transform (PST) to detect OD. Final result of segmented optic disc is validated by measuring positive predictive value (PPV). The result shows that PPV for optic disc detection by comparing detected optic disc in ground truth image is 97.74%. This result indicates that the proposed approach successfully detect optic disc and is able to assist the ophthalmologists in analysing retinal fundus image to diagnose glaucoma and diabetic retinopathy.
Article
Accurate and reliable optic disc (OD) segmentation is important for retinal image analysis and retinal disease screening. This paper presents a novel method to automatically segment OD in fundus images based on variational model with multiple energies. Firstly, a sparse coding based technique is designed to localize the OD center, based on which an initial boundary curve is then estimated by a circular Hough transform. Next, OD segmentation is regarded as an energy minimization problem, and a variational model integrating three energy terms is proposed to evolve the curve to the OD boundary. In the proposed model, the first term, named phase-based boundary energy, is designed to attract the evolution curve to the OD boundary, even the one with low contrast; the second term, named PCA-based shape energy, constraints the evolution curve to a common OD shape, which can suppress the negative effect of bright interferences, e.g., the bright lesions and myelinated nerve fibers, in OD segmentation; the last one is the region energy, which drives the evolution curve to the boundary of the homogeneous regions and hence improve the robustness of the model to the noises boundary and the initial position of evolution curve. The proposed OD segmentation method is evaluated on three public available databases, i.e., the MESSIDOR, ONHSD and DRIONS databases, and the experimental results demonstrate that the proposed method outperforms the state-of-the art techniques.
Conference Paper
Automated segmentation of retinal blood vessels in label-free fundus images entails a pivotal role in computed aided diagnosis of ophthalmic pathologies, viz., diabetic retinopathy, hypertensive disorders and cardiovascular diseases. The challenge remains active in medical image analysis research due to varied distribution of blood vessels, which manifest variations in their dimensions of physical appearance against a noisy background. In this paper we formulate the segmentation challenge as a classification task. Specifically, we employ unsupervised hierarchical feature learning using ensemble of two level of sparsely trained denoised stacked autoencoder. First level training with bootstrap samples ensures decoupling and second level ensemble formed by different network architectures ensures architectural revision. We show that ensemble training of auto-encoders fosters diversity in learning dictionary of visual kernels for vessel segmentation. SoftMax classifier is used for fine tuning each member autoencoder and multiple strategies are explored for 2-level fusion of ensemble members. On DRIVE dataset, we achieve maximum average accuracy of 95.33% with an impressively low standard deviation of 0.003 and Kappa agreement coefficient of 0.708. Comparison with other major algorithms substantiates the high efficacy of our model.
Conference Paper
Glaucoma is one of the leading cause of blindness. The manual examination of optic cup and disc is a standard procedure used for detecting glaucoma. This paper presents a fully automatic regression based method which accurately segments optic cup and disc in retinal colour fundus image. First, we roughly segment optic disc using circular hough transform. The approximated optic disc is then used to compute the initial optic disc and cup shapes. We propose a robust and efficient cascaded shape regression method which iteratively learns the final shape of the optic cup and disc from a given initial shape. Gradient boosted regression trees are employed to learn each regressor in the cascade. A novel data augmentation approach is proposed to improve the regressors performance by generating synthetic training data. The proposed optic cup and disc segmentation method is applied on an image set of 50 patients and demonstrate high segmentation accuracy for optic cup and disc with dice metric of 0.95 and 0.85 respectively. Comparative study shows that our proposed method outperforms state of the art optic cup and disc segmentation methods.
Article
In this paper a new algorithm is presented for automatic segmentation of the optic disk (OD) in human retinal images. In proposed method, an equiripple low pass finite impulse response (FIR) filter is designed to suppress the dominance of blood vessels and to enhance the OD region in retinal image. Desired frequency response with optimized order of the filter is achieved by choosing proper values of filter design parameters. This method computes the appropriate value of threshold to locate the OD in retinal image. Segmentation of the OD region is carried out using grayscale morphological dilation and median filtering operation. The proposed algorithm has been tested on four standard databases (DRIVE, DIRATEDB0, DIRATEDB1 and DRIONS database). The proposed algorithm detects the OD successfully with accuracies 100%, 96.92%, 98.98%, 100% on DRIVE, DIRATEDB0, DIRATEDB1 and DRIONS databases respectively. The OD segmentation sensitivity and specificity are in the range of 74.60–87.07%, 99.39–99.61% on these four databases. The proposed algorithm has low computation complexity as it takes low computation time to segment the OD over existing methods. Also it is robust to differences in image illumination and retinal anomalies. Hence the proposed method can be used for automatic screening system of retinal related diseases like glaucoma and diabetic retinopathy.
Conference Paper
Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large-scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational imaging framework using deep and ensemble learning based hybrid architecture for reliable detection of blood vessels in fundus color images. A deep neural network (DNN) is used for unsupervised learning of vesselness dictionaries using sparse trained denoising auto-encoders (DAE), followed by supervised learning of the DNN response using a random forest for detecting vessels in color fundus images. In experimental evaluation with the DRIVE database, we achieve the objective of vessel detection with max. avg. accuracy of 0.9327 and area under ROC curve of 0.9195.
Article
The automatic exudate segmentation in colour retinal fundus images is an important task in computer aided diagnosis and screening systems for diabetic retinopathy. In this paper, we present a location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images, which includes three stages: anatomic structure removal, exudate location and exudate segmentation. In anatomic structure removal stage, matched filters based main vessels segmentation method and a saliency based optic disk segmentation method are proposed. The main vessel and optic disk are then removed to eliminate the adverse affects that they bring to the second stage. In the location stage, we learn a random forest classifier to classify patches into two classes: exudate patches and exudate-free patches, in which the histograms of completed local binary patterns are extracted to describe the texture structures of the patches. Finally, the local variance, the size prior about the exudate regions and the local contrast prior are used to segment the exudate regions out from patches which are classified as exudate patches in the location stage. We evaluate our method both at exudate-level and image-level. For exudate-level evaluation, we test our method on e-ophtha EX dataset, which provides pixel level annotation from the specialists. The experimental results show that our method achieves 76% in sensitivity and 75% in positive prediction value(PPV), which both outperform the state of the art methods significantly. For image-level evaluation, we test our method on DiaRetDB1, and achieve competitive performance compared to the state of the art methods.