Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks

Abstract

Retinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study

“…The development of deep-learning models that are capable of detecting multiple retinal conditions is an important area of active research. 34,35 In conclusion, this study provides more evidence that a deep-learning system can be deployed for large-scale diabetic retinopathy screenings with specialist-level accuracy in community settings in which screenings are typically managed by non-physician health-care personnel. To increase patient access to care, screening programmes might explore use of a deep-learning system, carefully evaluated for their settings, to extend screening to more centres.…”

Evaluating the Diagnostic Accuracy of a Novel Bayesian Decision-Making Algorithm for Vision Loss

“…Available electronic aids have focused on improving diagnostics by automating image analysis [ 9 , 10 , 11 , 12 ]. However, most of these AI-assisted technologies are designed to identify a single disease, in contrast to our algorithm that differentiates between diagnoses [ 19 ]. Furthermore, the difficulty of detecting rare diseases using images and deep learning methods is known [ 20 ].…”

Simple Code Implementation for Deep Learning–Based Segmentation to Evaluate Central Serous Chorioretinopathy in Fundus Photography

“…However, because the amount of data was small, we also used publicly accessible web data to improve model generalizability including the Retinal Fundus Multi-Disease Image Dataset and other studies providing fundus photographs of posterior serous retinal detachment. 16 , 17 In particular, the Retinal Fundus Multi-Disease Image Dataset had 98 fundus photographs of patients with CSC, which were labeled by two ophthalmologists. This process also aimed to further de-identify the materials.…”