Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans

About

In this paper, we introduce a Bayesian deep learning based model for segmenting the photoreceptor layer in pathological OCT scans. Our architecture provides accurate segmentations of the photoreceptor layer and produces pixel-wise epistemic uncertainty maps that highlight potential areas of pathologies or segmentation errors. We empirically evaluated this approach in two sets of pathological OCT scans of patients with age-related macular degeneration, retinal vein oclussion and diabetic macular edema, improving the performance of the baseline U-Net both in terms of the Dice index and the area under the precision/recall curve. We also observed that the uncertainty estimates were inversely correlated with the model performance, underlying its utility for highlighting areas where manual inspection/correction might be needed.

Jos\'e Ignacio Orlando, Philipp Seeb\"ock, Hrvoje Bogunovi\'c, Sophie Klimscha, Christoph Grechenig, Sebastian Waldstein, Bianca S. Gerendas, Ursula Schmidt-Erfurth• 2019

Related benchmarks

TaskDatasetResultRank
Disruption DetectionA (AMD (early, CNV), DME, RVO) (test)
AUC67.12
6
Disruption DetectionLate AMD (GA) set B (test)
AUC91.01
6
Photoreceptor Layer SegmentationA (AMD (early, CNV), DME, RVO) (test)
AUC96.69
6
Photoreceptor Layer SegmentationLate AMD (GA) B (test)
AUC95
6
Showing 4 of 4 rows

Other info

Follow for update