Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.09.01.278259v1?rss=1 Authors: Oakley, J. D., Sodhi, S. K., Russakoff, D. B., Choudhry, N. Abstract: Purpose: To evaluate the performance of a deep learning-based, fully automated, multi-class, macular fluid segmentation algorithm relative to expert annotations in a heterogeneous population of confirmed wet age-related macular degeneration (wAMD) subjects. Methods: Twenty-two swept-source optical coherence tomography (SS-OCT) volumes of the macula from 22 from different individuals with wAMD were manually annotated by two expert graders. These results were compared using cross-validation (CV) to automated segmentations using a deep learning-based algorithm encoding spatial information about retinal tissue as an additional input to the network. The algorithm detects and delineates fluid regions in the OCT data, differentiating between intra- and sub-retinal fluid (IRF, SRF), as well as fluid resulting from in serous pigment epithelial detachments (PED). Standard metrics for fluid detection and quantification were used to evaluate performance. Results: The per slice receiver operating characteristic (ROC) area under the curves (AUCs) for each of these fluid types were 0.90, 0.94 and 0.94 for IRF, SRF and PED, respectively. Per volume results were 0.94 and 0.88 for IRF and PED (SRF being present in all cases). The correlation of fluid volume between the expert graders and the algorithm were 0.99 for IRF, 0.99 for SRF and 0.82 for PED. Conclusions: Automated, deep learning-based segmentation is able to accurately detect and quantify different macular fluid types in SS-OCT data on par with expert graders. Copy rights belong to original authors. Visit the link for more info