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

Abstract

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.

Accepted for publication at IEEE International Symposium on Biomedical Imaging (ISBI) 2019

References in corpus (1)

• Empirical Evaluation of Rectified Activations in Convolutional Network

Cited by in corpus (6)

• U-Net and its variants for medical image segmentation: theory and applications
• Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
• Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification
• A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation
• An amplified-target loss approach for photoreceptor layer segmentation in pathological OCT scans
• Autonomous Uncertainty Quantification for Computational Point-of-care Sensors