Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs

JAMA ◽  
2016 ◽  
Vol 316 (22) ◽  
pp. 2402 ◽  
Author(s):  
Varun Gulshan ◽  
Lily Peng ◽  
Marc Coram ◽  
Martin C. Stumpe ◽  
Derek Wu ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Deep Learning Algorithm ◽  
Fundus Photographs ◽  
Development And Validation ◽  
Retinal Fundus

Deep Learning-Based Diabetic Retinopathy Detection

2021 ◽  
Vol 11 (3) ◽  
pp. 38-48
Author(s):  
Mohamed Jebran P. ◽  
Sufia Banu
Keyword(s):  
Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Classification Performance ◽  
Learning Problems ◽  
Deep Learning Algorithm ◽  
Lesion Level ◽  
Fundus Photographs

Artificial intelligence (AI) is rapidly evolving from machine learning (ML) to deep learning (DL), which has ignited particular interest in ophthalmology as well. Deep learning has been applied in ophthalmology to fundus photographs, which achieve robust classification performance in the detection of diabetic retinopathy (DR). Diabetic retinopathy is a progressive condition observed in people who have had multiple years of diabetes mellitus. This paper focuses on examining how a deep learning algorithm can be applied for the detection and classification of diabetic retinopathy, both at the image level and at the lesion level. The performance of various neural networks is summarized by taking into account the sensitivity, precision, accuracy with respect to the size of the test datasets. Deep learning problems are discussed at the end.

scholarly journals Deep learning algorithm predicts diabetic retinopathy progression in individual patients

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Filippo Arcadu ◽  
Fethallah Benmansour ◽  
Andreas Maunz ◽  
Jeff Willis ◽  
Zdenka Haskova ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Vision Loss ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Single Visit ◽  
Deep Learning Algorithm ◽  
Frequent Monitoring ◽  
Severity Scores ◽  
Fundus Photographs

AbstractThe global burden of diabetic retinopathy (DR) continues to worsen and DR remains a leading cause of vision loss worldwide. Here, we describe an algorithm to predict DR progression by means of deep learning (DL), using as input color fundus photographs (CFPs) acquired at a single visit from a patient with DR. The proposed DL models were designed to predict future DR progression, defined as 2-step worsening on the Early Treatment Diabetic Retinopathy Diabetic Retinopathy Severity Scale, and were trained against DR severity scores assessed after 6, 12, and 24 months from the baseline visit by masked, well-trained, human reading center graders. The performance of one of these models (prediction at month 12) resulted in an area under the curve equal to 0.79. Interestingly, our results highlight the importance of the predictive signal located in the peripheral retinal fields, not routinely collected for DR assessments, and the importance of microvascular abnormalities. Our findings show the feasibility of predicting future DR progression by leveraging CFPs of a patient acquired at a single visit. Upon further development on larger and more diverse datasets, such an algorithm could enable early diagnosis and referral to a retina specialist for more frequent monitoring and even consideration of early intervention. Moreover, it could also improve patient recruitment for clinical trials targeting DR.

Sign in / Sign up

Export Citation Format

Share Document