ArticlePDF Available

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

Authors:
Jasem Almotiri at Taif University
Jasem Almotiri
Khaled Elleithy at University of Bridgeport
Khaled Elleithy
Abdelrahman K. Elleithy
Abdelrahman K. Elleithy
Abdelrahman K. Elleithy
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Download full-text PDFDownload full-text PDF
Read full-text
Download citation

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.
Figures - uploaded by Khaled Elleithy
Author content
All figure content in this area was uploaded by Khaled Elleithy
Content may be subject to copyright.
A Multi-Anatomical Retinal Structu
re.pdf
Content uploaded by Khaled Elleithy
Author content
All content in this area was uploaded by Khaled Elleithy on May 25, 2018
Content may be subject to copyright.
A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholdi
ng.pdf
Available via license: CC BY-NC-ND 4.0
Content may be subject to copyright.
A preview of the PDF is not available
... • Optic Disc Pallor Diagnosis using Morphological Adaptive Fuzzy Thresholding based OD segmentation (ODPD_MAFT) [23] • Optic Disc Pallor Diagnosis using Region based Convolutional Neural Network oriented OD segmentation (ODPD_RCNN) [6] • Optic Disc Pallor Diagnosis using Fuzzy Broad Learning System based OD segmentation (ODPD_FBLS) [7]. ...
... ODPD_MAFT [23] ODPD_RCNN [6] ODPD_FBLS [7] Proposed ODPD_ROMF Fig. 8 Average sensitivity analysis on OD segmentation Content courtesy of Springer Nature, terms of use apply. Rights reserved. ...
Optic disc pallor diagnosis using ROMF based optic disc segmentation in fundus images
Article
Full-text available
Disc pallor is a pale yellow discoloration of the optic disc (OD) that causes irreversible damage to the fiber of the retina's anterior visual pathway. Automatic disc pallor diagnosis has obstacles such as increased time consumption and reduced accuracy due to less powerful OD segmentation algorithms. Hence, a new development for pallor diagnosis through the enhanced version of OD segmentation, namely, 'Optic Disc Pallor Diagnosis using ROMF-based OD segmentation in fundus images (ODPD_ROMF)', is proposed. Herein, the essential contribution is a new OD segmentation method, namely 'Optic disc segmentation using Retinex and ONH structure-specific Membership based FCM method (ROMF)’. The ROMF method is constituted based on a new variant of Fuzzy C Means (FCM), namely 'Optic Nerve Head (ONH) structure-influenced Fuzzy C Means (FCM)', where the membership function and the objective function are redefined to calibrate according to the refined or updated ONH structure, which results in fast and accurate OD segmentation. The second-best approach has an average classification accuracy of 93.00, while the proposed ODPD_ROMF method has an average accuracy of 96.17. The suggested ROMF method's average segmentation accuracy in OD segmentation is 97.52, while the second-best method's average segmentation accuracy is 96.66. Because of its great competence, the proposed ODPD_ROMF method can be utilized to identify disc pallor more effectively.
View
... Identifying blood vessels in digital images is important for diagnosis [1][2][3][4][5][6] as well as for obtaining accurate measurements for supporting current studies on the vascular system [7][8][9][10]. Blood vessels can have very different shapes and appearances, and they form a complex interconnected structure that usually spans a whole tissue sample. ...
A New Approach for Evaluating and Improving the Performance of Segmentation Algorithms on Hard-to-Detect Blood Vessels
Preprint
Full-text available
  • Jun 2024
Many studies regarding the vasculature of biological tissues involve the segmentation of the blood vessels in a sample followed by the creation of a graph structure to model the vasculature. The graph is then used to extract relevant vascular properties. Small segmentation errors can lead to largely distinct connectivity patterns and a high degree of variability of the extracted properties. Nevertheless, global metrics such as Dice, precision, and recall are commonly applied for measuring the performance of blood vessel segmentation algorithms. These metrics might conceal important information about the accuracy at specific regions of a sample. To tackle this issue, we propose a local vessel salience (LVS) index to quantify the expected difficulty in segmenting specific blood vessel segments. The LVS index is calculated for each vessel pixel by comparing the local intensity of the vessel with the image background around the pixel. The index is then used for defining a new accuracy metric called low-salience recall (LSRecall), which quantifies the performance of segmentation algorithms on blood vessel segments having low salience. The perspective provided by the LVS index is used to define a data augmentation procedure that can be used to improve the segmentation performance of convolutional neural networks. We show that segmentation algorithms having high Dice and recall values can display very low LSRecall values, which reveals systematic errors of these algorithms for vessels having low salience. The proposed data augmentation procedure is able to improve the LSRecall of some samples by as much as 25%. The developed methodology opens up new possibilities for comparing the performance of segmentation algorithms regarding hard-to-detect blood vessels as well as their capabilities for vascular topology preservation.
View
... This method of filtering makes use of the medical pictures from the CA, lung CT, cerebral DSA, and retinal fundus are used to evaluate the performance. The evaluation, both qualitative and quantitative, demonstrates the effectiveness of the suggested method for improving contrast [16]. ...
An Improved Combined Adaptive Outline for Contrast Enhancement of Blood Vessels
Article
Full-text available
  • Sep 2023
Appropriate vascular segmentation is dependent on effective picture pre-processing techniques that improve the contrast of the blood vessels, reduce noise, eliminate non-uniform illumination, highlight thin vessels, and retain background texture. These techniques are necessary for accurate vessel segmentation. Here, both the edge- and texture-smoothed data from the vessel probability map are used in the derivation of the adaptive optimal q-order in the G-L mask. The smooth information is not affected, the textures are maintained, and the contrast of the blood vessels is enhanced, thanks to the proposed filter. In addition to sharpening the focus on the vessels themselves, a Gaussian curve fitting is used to contrast stretch the entire image. Retinal fundus images processed with cerebral DSA are subjected to both qualitative and quantitative assessments of contrast enhancement. Quantitative performance indicators are tabulated and compared to other approaches to show how well this technique works for improving medical images everywhere. The suggested filter is easy to implement, flexible enough to adapt to different images, and effective at increasing both vessel contrast and overall image contrast.
View
... --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. ...
Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy
Article
  • May 2023
  • MICROSC RES TECHNIQ
Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems 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 the lesion and the low contrast of the images. Thus, computer‐assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E‐ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. Research Highlights The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time‐consuming and requires intense effort. The authors compare qualitative results of the state‐of‐the‐art convolutional neural network (CNN) architectures and propose a computer‐assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.
View
... The image patches were trained using the deep neural network. A segmentation algorithm featured with mathematical morphology and adaptive fuzzy thresholding to analyze segmentation process of retinal fundus images was introduced [27] and extracted the fragile blood vessels using the canny edge detection method and proposed the early stage detection method for diabetic retinopathy by using retinal fundus images. A model [28] for the detection of retinal disease like glaucoma and macular syndrome by locating the fovea and Optical Disc (OD) with the use of erosion and dilation operation on gray scale fundus images was developed. ...
Retinal Blood Vessel Tracking and Diameter Estimation Via Gaussian Process With Rider Optimization Algorithm
Article
Full-text available
  • Jan 2023
Retinal blood vessels structure analysis is an important step in the detection of ocular diseases such as diabetic retinopathy and retinopathy of prematurity. Accurate tracking and estimation of retinal blood vessels in terms of their diameter remains a major challenge in retinal structure analysis. In this research, we develop a rider-based Gaussian approach for accurate tracking and diameter estimation of retinal blood vessels. The diameter and curvature of the blood vessel are assumed as the Gaussian processes. The features are determined for training the Gaussian process using Radon transform. The kernel hyperparameter of Gaussian processes is optimized using Rider Optimization Algorithm for evaluating the direction of the vessel. Multiple Gaussian processes are used for detecting the bifurcations and the difference in the prediction direction is quantified. The performance of the proposed Rider-based Gaussian process is evaluated with mean and standard deviation. Our method achieved high performance with the standard deviation of 0.2499 and mean average of 0.0147, which outperformed the state-of-the-art method by 6.32%. Although the proposed model outperformed the state-of-the-art method in normal blood vessels, in future research, one can include tortuous blood vessels of different retinopathy patients, which would be more challenging due to large angle variations. We used Rider-based Gaussian process for tracking blood vessels to obtain the diameter of retinal blood vessels, and the method performed well on the “STrutred Analysis of the REtina (STARE) Database,” accessed on Oct. 2020 ( https://cecas.clemson.edu/ ahoover/stare/ ). To the best of our knowledge, this experiment is one of the most recent analysis using this type of algorithm.
View
View
H-Detect: an Algorithm for Early Detection of HydrocephalusH-Detect: алгоритм раннего выявления гидроцефалии
Article
Full-text available
  • Mar 2024
Hydrocephalus is a central nervous system disorder which most commonly affects infants and toddlers. It starts as an abnormal build-up of cerebrospinal fluid in the ventricular system of the brain. Hence, early diagnosis becomes vital, which may be performed by Computed Tomography (CT), one of the most effective diagnostic methods for diagnosing Hydrocephalus (CT), where the enlarged ventricular system becomes apparent. However, most disease progression assessments rely on the radiologist's evaluation and physical measures, which are subjective, time-consuming, and inaccurate. This paper develops an automatic prediction utilizing the H-detect framework for enhanced accurate hydrocephalus prediction. This paper uses a pre-processing step to normalize the input image and remove unwanted noises, which can help extract valuable features easily. The feature extraction is done by segmenting the image based on edge detection using triangular fuzzy rules. Thereby, the exact information on the nature of CSF inside the brain is highlighted. These segmented images are saved and again given to the CatBoost algorithm. The Categorical feature processing allows for quicker training. When necessary, the overfitting detector will stop model training and thus efficiently predicts Hydrocephalus. The outcomes demonstrate that the new H-detect strategy outperforms the traditional approaches.
View
TUnet-LBF: Retinal fundus image fine segmentation model based on transformer Unet network and LBF
Article
  • Apr 2023
  • COMPUT BIOL MED
Segmentation of retinal fundus images is a crucial part of medical diagnosis. Automatic extraction of blood vessels in low-quality retinal images remains a challenging problem. In this paper, we propose a novel two-stage model combining Transformer Unet (TUnet) and local binary energy function model (LBF), TUnet-LBF, for coarse to fine segmentation of retinal vessels. In the coarse segmentation stage, the global topological information of blood vessels is obtained by TUnet. The neural network outputs the initial contour and the probability maps, which are input to the fine segmentation stage as the priori information. In the fine segmentation stage, an energy modulated LBF model is proposed to obtain the local detail information of blood vessels. The proposed model reaches accuracy (Acc) of 0.9650, 0.9681 and 0.9708 on the public datasets DRIVE, STARE and CHASE_DB1 respectively. The experimental results demonstrate the effectiveness of each component in the proposed model.
View
A Tremor Suppression and Noise Removal Algorithm for Microscopic Robot-Assisted Cataract Surgery
Article
  • Oct 2023
Ophthalmic surgery consists of a series of precise manipulations performed using a surgical microscope. A surgical robot with a master–slave paradigm is commonly adopted to improve the precision and guidance intelligence for ophthalmic surgery; however, the surgeon's hand tremor, misoperation, inherent characteristics of the robot, and environmental interference may cause tremors of the end-effector of the surgical manipulator, thus increasing the risk of soft tissue damage and poor prognosis for the patient. A symmetrical threshold noise reduction combiner (STIC) is proposed to suppress hand tremors and reduce environmental noise interference. Additionally, the inverse kinematic model of the eight-degrees-of-freedom surgical robot for cataract surgery is developed, with the constraints of continuous circular capsulorhexis manipulation. Simulation results show that the signal-to-noise ratio of the STIC is increased from 35.3907 to 57.0158 dB, whereas the maximum, average, standard deviation, and root mean square of the output of the STIC are decreased by 64.79%, 77.24%, 74.50%, and 75.86%, respectively. Three sets of in vitro experimental results show that these four indicators of the STIC performance are reduced by 59.73%, 76.57%, 57.23%, and 65.02%, respectively. These results validate the feasibility and effectiveness of the proposed method on hand tremor suppression and inherent high-frequency disturbance elimination, thereby enhancing the accuracy of the microsurgical operation.
View
Ensemble Architecture for Prediction of Grading of Diabetic Retinopathy
Article
  • Dec 2022
Diabetic Retinopathy (DR) is a diabetic issue that influences the eyes. It harms the veins of the light-delicate tissue behind the eye (retina). DR is an issue of diabetes and the main source of visual deficiency. Since there are trained doctors to diagnose the disease, but to make their work easier, ensemble architectures were proposed for the prediction of grading of DR using modern technology known as deep learning. Deep neural network results in a better diagnostic system in comparison to machine learning networks. ResNET 101 and Ensemble CNN architectures were proposed using Adam Optimization for the detection of DR. From the results, it has been observed that for any constant size Network architecture, the loss cannot be further reduced after a certain number known as Bayes error. With the help of a learning curve, it can easily understand that the proposed architecture costs are decreasing after every iteration. The Ensemble and ResNET 101 model attain 87.67% and 81.28% accuracy, respectively, and 0.5046 and 0.5328 cross-entropy loss, respectively. The proposed Ensemble model results in an 18.4% improvement over the Inception V3 model and 7.8% over the proposed ResNet 101 model.
View
Fast, accurate and robust retinal vessel segmentation system
Article
  • Apr 2017
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.
View
Multiscale segmentation of exudates in retinal images using contextual cues and ensemble classification
Article
  • May 2017
  • BIOMED SIGNAL PROCES
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.
View
Segmentation of optic disc using dispersive phase stretch transform
Conference Paper
  • Aug 2016
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.
View
Optic Disc Segmentation based on Variational Model with Multiple Energies
Article
  • Apr 2017
  • PATTERN RECOGN
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.
View
Deep neural ensemble for retinal vessel segmentation in fundus images towards achieving label-free angiography
Conference Paper
  • Aug 2016
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.
View
Segmentation of optic disc and optic cup in retinal fundus images using shape regression
Conference Paper
  • Aug 2016
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.
View
Automatic segmentation of optic disk in retinal images
Article
  • Jan 2017
  • BIOMED SIGNAL PROCES
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.
View
Deep neural network and random forest hybrid architecture for learning to detect retinal vessels in fundus images
Conference Paper
  • Aug 2015
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.
View
View
A Location-to-Segmentation Strategy for Automatic Exudate Segmentation in Colour Retinal Fundus Images
Article
  • Sep 2016
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.
View