A deep learning algorithm can detect metastases in sections of lymph nodes from women with breast cancer; and a deep learning system (DLS) has high sensitivity and specificity for identifying diabetic retinopathy, according to two studies published online December 12 in the Journal of the American Medical Association.
Babak Ehteshami Bejnordi, from the Radboud University Medical Center in Nijmegen, Netherlands, and colleagues compared the performance of automated deep learning algorithms for detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer with pathologists' diagnoses in a diagnostic setting. The researchers found that the area under the receiver operating characteristic curve (AUC) ranged from 0.556 to 0.994 for the algorithms. The lesion-level, true-positive fraction achieved for the top-performing algorithm was comparable to that of the pathologist without a time constraint at a mean of 0.0125 false-positives per normal whole-slide image. Daniel Shu Wei Ting, M.D., Ph.D., from the Singapore National Eye Center, and colleagues assessed the performance of a DLS for detecting referable diabetic retinopathy and related eye diseases using 494,661 retinal images. The researchers found that the AUC of the DLS for referable diabetic retinopathy was 0.936, and sensitivity and specificity were 90.5 and 91.6 percent, respectively.
In an evaluation of retinal photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy, according to a study published online by JAMA. Among individuals with diabetes, the prevalence of diabetic retinopathy is approximately 29 percent in the United States. Most guidelines recommend annual screening for those with no retinopathy or mild diabetic retinopathy and repeat examination in 6 months for moderate diabetic retinopathy. Retinal photography with manual interpretation is a widely accepted screening tool for diabetic retinopathy. Automated grading of diabetic retinopathy has potential benefits such as increasing efficiency and coverage of screening programs; reducing barriers to access; and improving patient outcomes by providing early detection and treatment.
Question How does the performance of an automated deep learning algorithm compare with manual grading by ophthalmologists for identifying diabetic retinopathy in retinal fundus photographs? Finding In 2 validation sets of 9963 images and 1748 images, at the operating point selected for high specificity, the algorithm had 90.3% and 87.0% sensitivity and 98.1% and 98.5% specificity for detecting referable diabetic retinopathy, defined as moderate or worse diabetic retinopathy or referable macular edema by the majority decision of a panel of at least 7 US board-certified ophthalmologists. At the operating point selected for high sensitivity, the algorithm had 97.5% and 96.1% sensitivity and 93.4% and 93.9% specificity in the 2 validation sets. Meaning Deep learning algorithms had high sensitivity and specificity for detecting diabetic retinopathy and macular edema in retinal fundus photographs. 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.
Varadarajan, Avinash, Bavishi, Pinal, Raumviboonsuk, Paisan, Chotcomwongse, Peranut, Venugopalan, Subhashini, Narayanaswamy, Arunachalam, Cuadros, Jorge, Kanai, Kuniyoshi, Bresnick, George, Tadarati, Mongkol, Silpa-archa, Sukhum, Limwattanayingyong, Jirawut, Nganthavee, Variya, Ledsam, Joe, Keane, Pearse A, Corrado, Greg S, Peng, Lily, Webster, Dale R
Diabetic eye disease is one of the fastest growing causes of preventable blindness. With the advent of anti-VEGF (vascular endothelial growth factor) therapies, it has become increasingly important to detect center-involved diabetic macular edema. However, center-involved diabetic macular edema is diagnosed using optical coherence tomography (OCT), which is not generally available at screening sites because of cost and workflow constraints. Instead, screening programs rely on the detection of hard exudates as a proxy for DME on color fundus photographs, often resulting in high false positive or false negative calls. To improve the accuracy of DME screening, we trained a deep learning model to use color fundus photographs to predict DME grades derived from OCT exams. Our "OCT-DME" model had an AUC of 0.89 (95% CI: 0.87-0.91), which corresponds to a sensitivity of 85% at a specificity of 80%. In comparison, three retinal specialists had similar sensitivities (82-85%), but only half the specificity (45-50%, p<0.001 for each comparison with model). The positive predictive value (PPV) of the OCT-DME model was 61% (95% CI: 56-66%), approximately double the 36-38% by the retina specialists. In addition, we used saliency and other techniques to examine how the model is making its prediction. The ability of deep learning algorithms to make clinically relevant predictions that generally require sophisticated 3D-imaging equipment from simple 2D images has broad relevance to many other applications in medical imaging.