Model-to-Data Approach for Deep Learning in Optical Coherence Tomography Intraretinal Fluid Segmentation

• Published in: JAMA ophthalmology Vol. 138; no. 10; p. 1017
• Main Authors: Mehta, Nihaal, Lee, Cecilia S, Mendonça, Luísa S M, Raza, Khadija, Braun, Phillip X, Duker, Jay S, Waheed, Nadia K, Lee, Aaron Y
• Format: Journal Article
• Language: English
• Published: United States 01.10.2020
• Subjects: Aged; Algorithms; Cross-Sectional Studies; Deep Learning; Female; Humans; Male; Neural Networks, Computer; Reproducibility of Results; Subretinal Fluid - diagnostic imaging; Tomography, Optical Coherence - methods; Wet Macular Degeneration - diagnosis
• ISSN: 2168-6165; 2168-6173; 2168-6173
• DOI: 10.1001/jamaophthalmol.2020.2769

Amid an explosion of interest in deep learning in medicine, including within ophthalmology, concerns regarding data privacy, security, and sharing are of increasing importance. A model-to-data approach, in which the model itself is transferred rather than data, can circumvent many of these challenges but has not been previously demonstrated in ophthalmology. To determine whether a model-to-data deep learning approach (ie, validation of the algorithm without any data transfer) can be applied in ophthalmology. This single-center cross-sectional study included patients with active exudative age-related macular degeneration undergoing optical coherence tomography (OCT) at the New England Eye Center from August 1, 2018, to February 28, 2019. Data were primarily analyzed from March 1 to June 20, 2019. Training of the deep learning model, using a model-to-data approach, in recognizing intraretinal fluid (IRF) on OCT B-scans. The model was trained (learning curve Dice coefficient, >80%) using 400 OCT B-scans from 128 participants (69 female [54%] and 59 male [46%]; mean [SD] age, 77.5 [9.1] years). In comparing the model with manual human grading of IRF pockets, no statistically significant difference in Dice coefficients or intersection over union scores was found (P > .05). A model-to-data approach to deep learning applied in ophthalmology avoided many of the traditional hurdles in large-scale deep learning, including data sharing, security, and privacy concerns. Although the clinical relevance of these results is limited at this time, this proof-of-concept study suggests that such a paradigm should be further examined in larger-scale, multicenter deep learning studies.