Automated Detection of Diabetic Retinopathy using Deep Residual Learning
17 Mar 2020-International Journal of Computer Applications (Foundation of Computer Science (FCS), NY, USA)-Vol. 177, Iss: 42, pp 25-32
TL;DR: A residual learning framework has been proposed that overcomes the challenges while efficiently detecting DR and to identify dynamic DR grading using residual networks to facilitate the network training that are significantly intense than previously used networks.
Abstract: Significant amount of people suffer from Diabetic Retinopathy (DR), which is one of the major causes of vision loss. The incidence of this disease is even higher due to not being diagnosed at the right time. On numerous occasions, due to neglect and poor care, diabetic retinopathy can lead to significant damage to the eyes. That is why, early diagnosis of eye diseases, proper treatment and care for the disease can prevent vision loss. Referral of eyes with diabetic retinopathy for advanced assessment and treatment would aid in reducing the chances of vision loss, allowing proper diagnoses. The purpose of this study is to develop resilient and flexible diagnostic techniques for the detection of DR and to identify dynamic DR grading using residual networks to facilitate the network training that are significantly intense than previously used networks. Even though lots of research has been done on DR, its identifications remains challenging due to time and space complexity along with higher accuracy specificity. Here, a residual learning framework has been proposed that overcomes the challenges while efficiently detecting DR. Hence, using a high-end Graphics Processor Unit (GPU) the model has been trained on the publicly available Kaggle dataset and empirical evidence has been provided in order to support the results with a sensitivity of 95.6% and an accuracy of 93.20%.
Citations
More filters
TL;DR: A weighted fusion deep learning network to automatically extract features and classify DR stages from fundus scans is presented to treat the issue of low quality and identify retinopathy symptoms in fundus images and achieves comparable performance.
Abstract: It is a well-known fact that diabetic retinopathy (DR) is one of the most common causes of visual impairment between the ages of 25 and 74 around the globe. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Early diagnosis can minimise the risk of proliferated diabetic retinopathy, which is the advanced level of this disease, and having higher risk of severe impairment. Therefore, it becomes important to classify DR stages. To this effect, this paper presents a weighted fusion deep learning network (WFDLN) to automatically extract features and classify DR stages from fundus scans. The proposed framework aims to treat the issue of low quality and identify retinopathy symptoms in fundus images. Two channels of fundus images, namely, the contrast-limited adaptive histogram equalization (CLAHE) fundus images and the contrast-enhanced canny edge detection (CECED) fundus images are processed by WFDLN. Fundus-related features of CLAHE images are extracted by fine-tuned Inception V3, whereas the features of CECED fundus images are extracted using fine-tuned VGG-16. Both channels’ outputs are merged in a weighted approach, and softmax classification is used to determine the final recognition result. Experimental results show that the proposed network can identify the DR stages with high accuracy. The proposed method tested on the Messidor dataset reports an accuracy level of 98.5%, sensitivity of 98.9%, and specificity of 98.0%, whereas on the Kaggle dataset, the proposed model reports an accuracy level of 98.0%, sensitivity of 98.7%, and specificity of 97.8%. Compared with other models, our proposed network achieves comparable performance.
28 citations
TL;DR: In this article, a multi-stage convolutional neural network (CNN)-based model was proposed to predict whether a person has diabetes or not from a photograph of his/her retina.
Abstract: Diabetes is one of the leading fatal diseases globally, putting a huge burden on the global healthcare system. Early diagnosis of diabetes is hence, of utmost importance and could save many lives. However, current techniques to determine whether a person has diabetes or has the risk of developing diabetes are primarily reliant upon clinical biomarkers. In this article, we propose a novel deep learning architecture to predict if a person has diabetes or not from a photograph of his/her retina. Using a relatively small-sized dataset, we develop a multi-stage convolutional neural network (CNN)-based model DiaNet that can reach an accuracy level of over 84% on this task, and in doing so, successfully identifies the regions on the retina images that contribute to its decision-making process, as corroborated by the medical experts in the field. This is the first study that highlights the distinguishing capability of the retinal images for diabetes patients in the Qatari population to the best of our knowledge. Comparing the performance of DiaNet against the existing clinical data-based machine learning models, we conclude that the retinal images contain sufficient information to distinguish the Qatari diabetes cohort from the control group. In addition, our study reveals that retinal images may contain prognosis markers for diabetes and other comorbidities like hypertension and ischemic heart disease. The results led us to believe that the inclusion of retinal images into the clinical setup for the diagnosis of diabetes is warranted in the near future.
14 citations
TL;DR: In this article, a case-control study was conducted to develop a machine learning (ML) model distinguishing healthy individuals from people having CVD, which could reveal the list of potential risk factors associated to CVD in Qatar.
Abstract: Cardiovascular disease (CVD) is reported to be the leading cause of mortality in the middle eastern countries, including Qatar. But no comprehensive study has been conducted on the Qatar specific CVD risk factors identification. The objective of this case-control study was to develop machine learning (ML) model distinguishing healthy individuals from people having CVD, which could ultimately reveal the list of potential risk factors associated to CVD in Qatar. To the best of our knowledge, this study considered the largest collection of biomedical measurements representing the anthropometric measurements, clinical biomarkers, bioimpedance, spirometry, VICORDER readings, and behavioral factors of the CVD group from Qatar Biobank (QBB). CatBoost model achieved 93% accuracy, thereby outperforming the existing model for the same purpose. Interestingly, combining multimodal datasets into the proposed ML model outperformed the ML model built upon currently known risk factors for CVD, emphasizing the importance of incorporating other clinical biomarkers into consideration for CVD diagnosis plan. The ablation study on the multimodal dataset from QBB revealed that physio-clinical and bioimpedance measurements have the most distinguishing power to classify these two groups irrespective of gender and age of the participants. Multiple feature subset selection techniques confirmed known CVD risk factors (blood pressure, lipid profile, smoking, sedentary life, and diabetes), and identified potential novel risk factors linked to CVD-related comorbidities such as renal disorder (e.g., creatinine, uric acid, homocysteine, albumin), atherosclerosis (intima media thickness), hypercoagulable state (fibrinogen), and liver function (e.g., alkaline phosphate, gamma-glutamyl transferase). Moreover, the inclusion of the proposed novel factors into the ML model provides better performance than the model with traditional known risk factors for CVD. The association of the proposed risk factors and comorbidities are required to be investigated in clinical setup to understand their role in CVD better.
13 citations
01 Feb 2021
TL;DR: In this paper, an automated detection of diabetic retinopathy using deep belief networks has been presented which process the retinal images of patients and provides accurate diagnosis of categories of diabetic Retinopathy.
Abstract: Diabetic retinopathy is a disease that infects the vision of human eyes suffering from diabetes. It affects the blood vessels of soft tissues at retina, which is located at the backside of the eyes. This disease is evaluated by the physicians based on the retinal images of patients. Detection of the disease initiates human-intensive work for medical practitioners with monetary expenses also. Recent research works have identified that the use of deep learning methods for automatic detection of diabetic retinopathy helps the experts to make quick decision about the patient’s health conditions. In this paper, automated detection of diabetic retinopathy using deep belief networks has been presented which process the retinal images of patients and provides accurate diagnosis of categories of diabetic retinopathy. The proposed method has been trained and tested with Convolutional Neural Networks and Deep Belief Networks. The confidence level of diagnosis is computed and 94.69% with 96.01% are achieved in the detection of Proliferative diabetic retinopathy using CNN and DBN based on the features of data.
2 citations
Cites background from "Automated Detection of Diabetic Ret..."
...[2] And, automated detection of DR classification is needed so that the medical practitioners are able to make decisions quickly....
[...]
19 Mar 2021
TL;DR: In this article, the authors have built a mechanism after studying various existing programs which help in identifying the correct stage of diabetic retinopathy, which is the result of the deterioration of blood vessels in the retina.
Abstract: Diabetic Retinopathy is the result of the deterioration of blood vessels in the retina. Diabetic patients are more likely to develop this problem after a prolonged suffering and a lack of recommended control over their blood sugar level. It figures among the significant causes leading to blindness globally. It is majorly classified into four categories: firstly, mild non-proliferative, moderate non-proliferative, severe non-proliferative, proliferative diabetic retinopathy. Since, it is a very tedious task to manually diagnose such diseases, we have built a mechanism after studying various existing programs which help in identifying the correct stage of diabetic retinopathy. This paper identifies various methodologies and architectures such as Convolutional Neural Network which performs detection using colour fundus photographs of the human retina. The dataset used for training and testing was obtained from the open-source platform, Kaggle. The model proposed and implemented in this paper gave an accuracy of 84 percent and this work specifically targeted improvements in specificity and sensitivity, leading to achieving 98.25 percent and 98 percent for both respectively. This research strengthens the notion that such algorithms play a key role in the field of medical and technology. They help in quick processing and deep investigation of medical problem.
1 citations
References
More filters
TL;DR: An algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and diabetic macular edema in retinal fundus photographs from adults with diabetes.
Abstract: Importance Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. Objective To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs. Design and Setting A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency. Exposure Deep learning–trained algorithm. Main Outcomes and Measures The sensitivity and specificity of the algorithm for detecting referable diabetic retinopathy (RDR), defined as moderate and worse diabetic retinopathy, referable diabetic macular edema, or both, were generated based on the reference standard of the majority decision of the ophthalmologist panel. The algorithm was evaluated at 2 operating points selected from the development set, one selected for high specificity and another for high sensitivity. Results The EyePACS-1 data set consisted of 9963 images from 4997 patients (mean age, 54.4 years; 62.2% women; prevalence of RDR, 683/8878 fully gradable images [7.8%]); the Messidor-2 data set had 1748 images from 874 patients (mean age, 57.6 years; 42.6% women; prevalence of RDR, 254/1745 fully gradable images [14.6%]). For detecting RDR, the algorithm had an area under the receiver operating curve of 0.991 (95% CI, 0.988-0.993) for EyePACS-1 and 0.990 (95% CI, 0.986-0.995) for Messidor-2. Using the first operating cut point with high specificity, for EyePACS-1, the sensitivity was 90.3% (95% CI, 87.5%-92.7%) and the specificity was 98.1% (95% CI, 97.8%-98.5%). For Messidor-2, the sensitivity was 87.0% (95% CI, 81.1%-91.0%) and the specificity was 98.5% (95% CI, 97.7%-99.1%). Using a second operating point with high sensitivity in the development set, for EyePACS-1 the sensitivity was 97.5% and specificity was 93.4% and for Messidor-2 the sensitivity was 96.1% and specificity was 93.9%. Conclusions and Relevance In this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy. Further research is necessary to determine the feasibility of applying this algorithm in the clinical setting and to determine whether use of the algorithm could lead to improved care and outcomes compared with current ophthalmologic assessment.
4,810 citations
"Automated Detection of Diabetic Ret..." refers background in this paper
...The results obtained from the paper [15] demonstrates that deep neural networks can be trained using large data sets to identify diabetic retinopathy or diabetic macular edema in retinal fundus images with high sensitivity and high specificity....
[...]
TL;DR: A diagnostic tool based on a deep-learning framework for the screening of patients with common treatable blinding retinal diseases, which demonstrates performance comparable to that of human experts in classifying age-related macular degeneration and diabetic macular edema.
2,750 citations
TL;DR: In this evaluation of retinal images from multiethnic cohorts of patients with diabetes, the DLS had high sensitivity and specificity for identifying diabetic retinopathy and related eye diseases.
Abstract: Importance A deep learning system (DLS) is a machine learning technology with potential for screening diabetic retinopathy and related eye diseases. Objective To evaluate the performance of a DLS in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, possible glaucoma, and age-related macular degeneration (AMD) in community and clinic-based multiethnic populations with diabetes. Design, Setting, and Participants Diagnostic performance of a DLS for diabetic retinopathy and related eye diseases was evaluated using 494 661 retinal images. A DLS was trained for detecting diabetic retinopathy (using 76 370 images), possible glaucoma (125 189 images), and AMD (72 610 images), and performance of DLS was evaluated for detecting diabetic retinopathy (using 112 648 images), possible glaucoma (71 896 images), and AMD (35 948 images). Training of the DLS was completed in May 2016, and validation of the DLS was completed in May 2017 for detection of referable diabetic retinopathy (moderate nonproliferative diabetic retinopathy or worse) and vision-threatening diabetic retinopathy (severe nonproliferative diabetic retinopathy or worse) using a primary validation data set in the Singapore National Diabetic Retinopathy Screening Program and 10 multiethnic cohorts with diabetes. Exposures Use of a deep learning system. Main Outcomes and Measures Area under the receiver operating characteristic curve (AUC) and sensitivity and specificity of the DLS with professional graders (retinal specialists, general ophthalmologists, trained graders, or optometrists) as the reference standard. Results In the primary validation dataset (n = 14 880 patients; 71 896 images; mean [SD] age, 60.2 [2.2] years; 54.6% men), the prevalence of referable diabetic retinopathy was 3.0%; vision-threatening diabetic retinopathy, 0.6%; possible glaucoma, 0.1%; and AMD, 2.5%. The AUC of the DLS for referable diabetic retinopathy was 0.936 (95% CI, 0.925-0.943), sensitivity was 90.5% (95% CI, 87.3%-93.0%), and specificity was 91.6% (95% CI, 91.0%-92.2%). For vision-threatening diabetic retinopathy, AUC was 0.958 (95% CI, 0.956-0.961), sensitivity was 100% (95% CI, 94.1%-100.0%), and specificity was 91.1% (95% CI, 90.7%-91.4%). For possible glaucoma, AUC was 0.942 (95% CI, 0.929-0.954), sensitivity was 96.4% (95% CI, 81.7%-99.9%), and specificity was 87.2% (95% CI, 86.8%-87.5%). For AMD, AUC was 0.931 (95% CI, 0.928-0.935), sensitivity was 93.2% (95% CI, 91.1%-99.8%), and specificity was 88.7% (95% CI, 88.3%-89.0%). For referable diabetic retinopathy in the 10 additional datasets, AUC range was 0.889 to 0.983 (n = 40 752 images). Conclusions and Relevance In this evaluation of retinal images from multiethnic cohorts of patients with diabetes, the DLS had high sensitivity and specificity for identifying diabetic retinopathy and related eye diseases. Further research is necessary to evaluate the applicability of the DLS in health care settings and the utility of the DLS to improve vision outcomes.
1,309 citations
TL;DR: A fully data-driven artificial intelligence-based grading algorithm can be used to screen fundus photographs obtained from diabetic patients and to identify, with high reliability, which cases should be referred to an ophthalmologist for further evaluation and treatment.
864 citations
TL;DR: A deep-learning enhanced algorithm for the automated detection of DR, achieves significantly better performance than a previously reported, otherwise essentially identical, algorithm that does not employ deep learning.
Abstract: Purpose To compare performance of a deep-learning enhanced algorithm for automated detection of diabetic retinopathy (DR), to the previously published performance of that algorithm, the Iowa Detection Program (IDP)-without deep learning components-on the same publicly available set of fundus images and previously reported consensus reference standard set, by three US Board certified retinal specialists. Methods We used the previously reported consensus reference standard of referable DR (rDR), defined as International Clinical Classification of Diabetic Retinopathy moderate, severe nonproliferative (NPDR), proliferative DR, and/or macular edema (ME). Neither Messidor-2 images, nor the three retinal specialists setting the Messidor-2 reference standard were used for training IDx-DR version X2.1. Sensitivity, specificity, negative predictive value, area under the curve (AUC), and their confidence intervals (CIs) were calculated. Results Sensitivity was 96.8% (95% CI: 93.3%-98.8%), specificity was 87.0% (95% CI: 84.2%-89.4%), with 6/874 false negatives, resulting in a negative predictive value of 99.0% (95% CI: 97.8%-99.6%). No cases of severe NPDR, PDR, or ME were missed. The AUC was 0.980 (95% CI: 0.968-0.992). Sensitivity was not statistically different from published IDP sensitivity, which had a CI of 94.4% to 99.3%, but specificity was significantly better than the published IDP specificity CI of 55.7% to 63.0%. Conclusions A deep-learning enhanced algorithm for the automated detection of DR, achieves significantly better performance than a previously reported, otherwise essentially identical, algorithm that does not employ deep learning. Deep learning enhanced algorithms have the potential to improve the efficiency of DR screening, and thereby to prevent visual loss and blindness from this devastating disease.
725 citations
"Automated Detection of Diabetic Ret..." refers background in this paper
...The researchers in [18] developed a deep-learning algorithm for automated detection of Diabetic Retinopathy (DR)....
[...]