U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans
This addresses segmentation challenges in medical imaging for ophthalmology, specifically for pathological OCT analysis, though it appears incremental as it builds on U-Net with Bayesian uncertainty estimation.
The paper tackles photoreceptor layer segmentation in pathological OCT scans by introducing a Bayesian U-Net model that provides accurate segmentations and pixel-wise epistemic uncertainty maps. The result shows improved performance over baseline U-Net in terms of Dice index and area under the precision/recall curve on OCT scans of patients with age-related macular degeneration, retinal vein occlusion, and diabetic macular edema.
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.