Detection of lesions and classification of diabetic retinopathy using fundus images
01 Dec 2016-pp 1-5
TL;DR: This paper automatically detect as well as to classify the severity of diabetic retinopathy by applying artificial neural network (ANN) and found that the system can give the classification accuracy of 96% and it supports a great help to ophthalmologists.
Abstract: Diabetes retinopathy is a retinal disease that is affected by diabetes on the eyes. The main risk of the disease can lead to blindness. Detection the disease at early stage can rescue the patients from loss of vision. The major purpose of this paper is to automatically detect as well as to classify the severity of diabetic retinopathy. At first, the lesions on the retina especially blood vessels, exudates and microaneurysms are extracted. Features such as area, perimeter and count from these lesions are used to classify the stages of the disease by applying artificial neural network (ANN). We used 214 fundus images from DIARECTDB1 and local databases. We found that the system can give the classification accuracy of 96% and it supports a great help to ophthalmologists.
Citations
More filters
TL;DR: This work presents a novel CNN model to extract features from retinal fundus images for better classification performance and results indicate that the proposed feature extraction technique along with the J48 classifier outperforms all the other classifiers for MESSIDOR, IDRiD, and KAGGLE datasets.
99 citations
TL;DR: There is still a need for accurate development of CAD systems to assist in the clinical diagnosis of diabetic retinopathy, and all those CAD systems that have been developed by various computational intelligence and image processing techniques are described.
Abstract: Diabetic retinopathy (DR) is a complication of diabetes that exists throughout the world. DR occurs due to a high ratio of glucose in the blood, which causes alterations in the retinal microvasculature. Without preemptive symptoms of DR, it leads to complete vision loss. However, early screening through computer-assisted diagnosis (CAD) tools and proper treatment have the ability to control the prevalence of DR. Manual inspection of morphological changes in retinal anatomic parts are tedious and challenging tasks. Therefore, many CAD systems were developed in the past to assist ophthalmologists for observing inter- and intra-variations. In this paper, a recent review of state-of-the-art CAD systems for diagnosis of DR is presented. We describe all those CAD systems that have been developed by various computational intelligence and image processing techniques. The limitations and future trends of current CAD systems are also described in detail to help researchers. Moreover, potential CAD systems are also compared in terms of statistical parameters to quantitatively evaluate them. The comparison results indicate that there is still a need for accurate development of CAD systems to assist in the clinical diagnosis of diabetic retinopathy.
73 citations
TL;DR: A detailed review of the detection of diabetic retinopathy with three major aspects; retinal datasets, DR detection methods, and performance evaluation metrics is presented.
Abstract: Diabetic retinopathy (DR) is a fast-spreading disease across the globe, which is caused by diabetes. The DR may lead the diabetic patients to complete vision loss. In this scenario, early identification of DR is more essential to recover the eyesight and provide help for timely treatment. The detection of DR can be manually performed by ophthalmologists and can also be done by an automated system. In the manual system, analysis and explanation of retinal fundus images need ophthalmologists, which is a time-consuming and very expensive task, but in the automated system, artificial intelligence is used to perform an imperative role in the area of ophthalmology and specifically in the early detection of diabetic retinopathy over the traditional detection approaches. Recently, numerous advanced studies related to the identification of DR have been reported. This paper presents a detailed review of the detection of DR with three major aspects; retinal datasets, DR detection methods, and performance evaluation metrics. Furthermore, this study also covers the author’s observations and provides future directions in the field of diabetic retinopathy to overcome the research challenges for the research community.
49 citations
Cites methods from "Detection of lesions and classifica..."
...[19] introduced an approach for the classification of lesions including micro aneurysms, exudates, and blood vessels....
[...]
TL;DR: A deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically and works well even if the eye image is captured under low lighting condition with pupil position is not at the center location.
Abstract: Automatic pterygium detection is an essential screening tool for health community service groups. It allows non-expert to perform screening process without the needs of big and expensive equipment, especially for the application in rural areas. Thence, patients who have been screened as positive pterygium will be referred to the certified medical personnel for further diagnosis and treatment. Current state-of-the-art algorithms for pterygium detection rely on basic machine learning approach such as artificial neural network and support vector machine, which have not yet achieved high detection sensitivity and specificity as required in standard medical practice. Hence, a deep learning approach based on fully convolutional neural networks is proposed to detect and localize the pterygium infected tissues automatically. The input image requirement for the developed system is low as any commercial mobile phone camera is sufficient. Moreover, the developed algorithm, which we refer as Pterygium-Net works well even if the eye image is captured under low lighting condition with pupil position is not at the center location. Pterygium-Net utilizes three layers of convolutional neural networks (CNN) and three layers of fully connected networks. Two steps are implemented to overcome lacks of training data by generating synthetic images and pre-training the CNN weights and biases in a different public dataset. As for pterygium localization, an additional step of box proposal based on edges information is used to generate possible regions of the pterygium infected tissues. Hanning window is also applied to the generated regions to give more weightage to the center area. Experimental results show that Pterygium-Net produces high average detection sensitivity and specificity of 0.95 and 0.983, respectively. As for pterygium tissues localization, the algorithm achieves 0.811 accuracy with a very low failure rate of 0.053. In the future, deeper networks can be implemented to further improve pterygium localization.
33 citations
TL;DR: This review presents a comprehensive summary of DR detection techniques from five different aspects namely, datasets, image preprocessing techniques, machine learning-based approaches, deep learning- based approaches, and performance measures.
Abstract: Diabetic Retinopathy (DR) is the disease caused by uncontrolled diabetes that may lead to blindness among the patients. Due to the advancements in artificial intelligence, early detection of DR through an automated system is more beneficial over the manual detection. At present, there are several published studies on automated DR detection systems through machine learning or deep learning approaches. This study presents a review on DR detection techniques from five different aspects namely, datasets, image preprocessing techniques, machine learning-based approaches, deep learning-based approaches, and performance measures. Moreover, it also presents the authors’ observation and significance of the review findings. Furthermore, we also discuss nine new research challenges in DR detection. After a rigorous selection process, 74 primary publications were selected from eight academic databases for this review. From the selected studies, it was observed that many public datasets are available in the field of DR detection. In image preprocessing techniques, contrast enhancement combined with green channel extraction contributed the most in classification accuracy. In features, shape-based, texture-based and statistical features were reported as the most discriminative in DR detection. The Artificial Neural Network was proven eminent classifier compared to other machine learning classifiers. In deep learning, Convolutional Neural Network outperformed compared to other deep learning networks. Finally, to measure the classification performance, accuracy, sensitivity, and specificity metrics were mostly employed. This review presents a comprehensive summary of DR detection techniques and will be proven useful for the community of scientists working in the field of automated DR detection techniques.
32 citations
References
More filters
30 Sep 2015
TL;DR: Major trends in the prevalence, incidence, progression and regression of DR and DME are explored, and gaps in literature identified, and established and novel risk factors are extensively reviewed.
Abstract: Diabetic retinopathy (DR) is a leading cause of vision-loss globally. Of an estimated 285 million people with diabetes mellitus worldwide, approximately one third have signs of DR and of these, a further one third of DR is vision-threatening DR, including diabetic macular edema (DME). The identification of established modifiable risk factors for DR such as hyperglycemia and hypertension has provided the basis for risk factor control in preventing onset and progression of DR. Additional research investigating novel risk factors has improved our understanding of multiple biological pathways involved in the pathogenesis of DR and DME, especially those involved in inflammation and oxidative stress. Variations in DR prevalence between populations have also sparked interest in genetic studies to identify loci associated with disease susceptibility. In this review, major trends in the prevalence, incidence, progression and regression of DR and DME are explored, and gaps in literature identified. Established and novel risk factors are also extensively reviewed with a focus on landmark studies and updates from the recent literature.
1,022 citations
01 Jan 2007
TL;DR: With the proposed database and protocol, it is possible to compare different algorithms, and correspondingly, analyse their maturity for technology transfer from the research laboratories to the medical practice.
Abstract: Automatic diagnosis of diabetic retinopathy from digital fundus images has been an active research topic in the medical image processing community. The research interest is justified by the excellent potential for new products in the medical industry and significant reductions in health care costs. However, the maturity of proposed algorithms cannot be judged due to the lack of commonly accepted and representative image database with a verified ground truth and strict evaluation protocol. In this study, an evaluation methodology is proposed and an image database with ground truth is described. The database is publicly available for benchmarking diagnosis algorithms. With the proposed database and protocol, it is possible to compare different algorithms, and correspondingly, analyse their maturity for technology transfer from the research laboratories to the medical practice.
776 citations
TL;DR: This work has proposed a computer-based approach for the detection of diabetic retinopathy stage using fundus images and demonstrated a classification accuracy of 93%, sensitivity of 90% and specificity of 100%.
Abstract: Diabetic retinopathy (DR) is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). The retinal fundus photographs are widely used in the diagnosis and treatment of various eye diseases in clinics. It is also one of the main resources for mass screening of diabetic retinopathy. In this work, we have proposed a computer-based approach for the detection of diabetic retinopathy stage using fundus images. Image preprocessing, morphological processing techniques and texture analysis methods are applied on the fundus images to detect the features such as area of hard exudates, area of the blood vessels and the contrast. Our protocol uses total of 140 subjects consisting of two stages of DR and normal. Our extracted features are statistically significant (p?
252 citations
TL;DR: An extension of the m-Mediods based modeling approach is presented, and combines it with a Gaussian Mixture Model in an ensemble to form a hybrid classifier to improve the accuracy of the classification.
239 citations
"Detection of lesions and classifica..." refers background in this paper
...MAs and HMs are dark lesions and EXs are bright [3]....
[...]
TL;DR: This study demonstrates a sensitivity of more than 90% for the classifier with the specificity of 100% and classification of the four eye diseases was achieved using a three-layer feedforward neural network.
226 citations
"Detection of lesions and classifica..." refers background in this paper
...It can be occurred because enough rate of insulin in the body is not secreted properly by the pancreas [1]....
[...]