Dataset Information

Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading.

ABSTRACT: Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening and diagnosis. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, although we use only a small fraction of images (<1/4) in training but are aided with higher image resolutions. We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification, including state-of-the-art results for accurately classifying images according to clinical five-grade diabetic retinopathy and for the first time for the four-grade diabetic macular edema scales. These results suggest, that a deep learning system could increase the cost-effectiveness of screening and diagnosis, while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading.

SUBMITTER: Sahlsten J

PROVIDER: S-EPMC6656880 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading.

Sahlsten Jaakko J Jaskari Joel J Kivinen Jyri J Turunen Lauri L Jaanio Esa E Hietala Kustaa K Kaski Kimmo K

Scientific reports 20190724 1

Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening and diagnosis. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, althou ...[more]

PMID: 31341220

Similar Datasets

Project description:Summary We described a challenge named “Diabetic Retinopathy (DR)—Grading and Image Quality Estimation Challenge” in conjunction with ISBI 2020 to hold three sub-challenges and develop deep learning models for DR image assessment and grading. The scientific community responded positively to the challenge, with 34 submissions from 574 registrations. In the challenge, we provided the DeepDRiD dataset containing 2,000 regular DR images (500 patients) and 256 ultra-widefield images (128 patients), both having DR quality and grading annotations. We discussed details of the top 3 algorithms in each sub-challenges. The weighted kappa for DR grading ranged from 0.93 to 0.82, and the accuracy for image quality evaluation ranged from 0.70 to 0.65. The results showed that image quality assessment can be used as a further target for exploration. We also have released the DeepDRiD dataset on GitHub to help develop automatic systems and improve human judgment in DR screening and diagnosis. Graphical abstract Highlights • Provides the DeepDRiD dataset, performance evaluation, top methods and results• Presents deep learning approaches in DR image quality assessment and grading• Discusses the future work of DR automatic screening The bigger picture Diabetic retinopathy (DR) is the most common disease caused by diabetes. Challenges are held to address real-world issues encountered in the design of DR automated screening systems to advance the technology in this area. Thus, we described a challenge named "Diabetic Retinopathy (DR)—Grading and Image Quality Estimation Challenge" in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI 2020) for fundus image assessment and DR grading. The scientific community responded positively to the challenge. In the challenge, we provided a deep DR image dataset (DeepDRiD) containing regular DR images and ultra-widefield (UWF) DR images, both having image quality and DR grading diagnosis. We discussed details of the three best algorithms in each sub-challenges. The results by the top algorithms showed that image quality assessment can be used as a target for further exploration. In DeepDRiD challenge, organizers hold a real-world exploration in diabetic retinopathy (DR) auto-screening systems using regular fundus images from 500 participants and ultra-widefield fundus images from 128 participants. Among the 34 participating teams, we summarized the top 3 teams in the three sub-challenges involved in DR grading and image quality assessment. In addition to providing new insights into image quality assessment strategy, these models can enhance the judgment of healthcare workers in DR screening and bring precise screening results.

Project description:ImportanceStudies have shown oxidized low-density lipoprotein to be associated with the incidence of proliferative retinopathy and other complications of type 1 diabetes mellitus. Because low-risk interventions are available to modify oxidized low-density lipoprotein, it is important to examine the relationships between this factor and the incidence of proliferative retinopathy and of macular edema, 2 important causes of visual impairment in people with type 1 diabetes.ObjectiveTo determine the association of oxidized low-density lipoprotein with the worsening of diabetic retinopathy and the incidence of proliferative retinopathy and of macular edema.Design, setting, and participantsOf 996 participants with type 1 diabetes in the Wisconsin Epidemiologic Study of Diabetic Retinopathy, 730 were examined up to 4 times (1990-1992, 1994-1996, 2005-2007, and 2012-2014) over 24 years and had assays of oxidized low-density lipoprotein and fundus photographs gradable for diabetic retinopathy and macular edema. Analyses started July 2014 and ended February 2015.Main outcomes and measuresWorsening of diabetic retinopathy, incidence of proliferative diabetic retinopathy, and incidence of macular edema as assessed via grading of color stereo film fundus photographs. The levels of oxidized low-density lipoprotein collected from serum samples at the time of each examination were measured in 2013 and 2014 from frozen serum.ResultsThe cohort at baseline had a mean (SD) level of oxidized low-density lipoprotein of 30.0 (8.5) U/L. While adjusting for duration of diabetes, glycated hemoglobin A1c level, and other factors, we found that neither the level of oxidized low-density lipoprotein at the beginning of a period nor the change in it over a certain period was associated with the incidence of proliferative diabetic retinopathy (hazard ratio [HR], 1.11 [95% CI, 0.91-1.35], P = .30; odds ratio [OR], 1.77 [95% CI, 0.99-3.17], P = .06), the incidence of macular edema (HR, 1.04 [95% CI, 0.83-1.29], P = .74; OR, 1.08 [95% CI, 0.44-2.61], P = .87), or the worsening of diabetic retinopathy (HR, 0.94 [95% CI, 0.83-1.07], P = .34; OR, 1.32 [95% CI, 0.83-2.09], P = .24).Conclusions and relevanceOur findings do not provide evidence for a relationship between increasing levels of serum oxidized low-density lipoprotein and the incidence of macular edema or the worsening of diabetic retinopathy in persons with type 1 diabetes. The potential increase in the HR for incident proliferative retinopathy, with an increase in oxidized low-density lipoprotein level over the preceding period, warrants further investigation of this relationship.

Project description:ImportanceMore than 60 million people in India have diabetes and are at risk for diabetic retinopathy (DR), a vision-threatening disease. Automated interpretation of retinal fundus photographs can help support and scale a robust screening program to detect DR.ObjectiveTo prospectively validate the performance of an automated DR system across 2 sites in India.Design, setting, and participantsThis prospective observational study was conducted at 2 eye care centers in India (Aravind Eye Hospital and Sankara Nethralaya) and included 3049 patients with diabetes. Data collection and patient enrollment took place between April 2016 and July 2016 at Aravind and May 2016 and April 2017 at Sankara Nethralaya. The model was trained and fixed in March 2016.InterventionsAutomated DR grading system compared with manual grading by 1 trained grader and 1 retina specialist from each site. Adjudication by a panel of 3 retinal specialists served as the reference standard in the cases of disagreement.Main outcomes and measuresSensitivity and specificity for moderate or worse DR or referable diabetic macula edema.ResultsOf 3049 patients, 1091 (35.8%) were women and the mean (SD) age for patients at Aravind and Sankara Nethralaya was 56.6 (9.0) years and 56.0 (10.0) years, respectively. For moderate or worse DR, the sensitivity and specificity for manual grading by individual nonadjudicator graders ranged from 73.4% to 89.8% and from 83.5% to 98.7%, respectively. The automated DR system's performance was equal to or exceeded manual grading, with an 88.9% sensitivity (95% CI, 85.8-91.5), 92.2% specificity (95% CI, 90.3-93.8), and an area under the curve of 0.963 on the data set from Aravind Eye Hospital and 92.1% sensitivity (95% CI, 90.1-93.8), 95.2% specificity (95% CI, 94.2-96.1), and an area under the curve of 0.980 on the data set from Sankara Nethralaya.Conclusions and relevanceThis study shows that the automated DR system generalizes to this population of Indian patients in a prospective setting and demonstrates the feasibility of using an automated DR grading system to expand screening programs.

Dataset Information

Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading.

Publications

Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets