Uncertainty-aware retinal layer segmentation in OCT through probabilistic signed distance functions

TL;DR

This paper introduces a probabilistic signed distance function approach for uncertainty-aware retinal layer segmentation in OCT scans, improving accuracy and robustness against noise and ambiguities.

Contribution

It proposes a novel method combining SDF and probabilistic modeling for more reliable retinal layer segmentation in OCT images.

Findings

Superior segmentation accuracy compared to existing methods

Effective uncertainty estimation in noisy and ambiguous cases

Potential for assessing retinal layer integrity as a disease biomarker

Abstract

In this paper, we present a new approach for uncertainty-aware retinal layer segmentation in Optical Coherence Tomography (OCT) scans using probabilistic signed distance functions (SDF). Traditional pixel-wise and regression-based methods primarily encounter difficulties in precise segmentation and lack of geometrical grounding respectively. To address these shortcomings, our methodology refines the segmentation by predicting a signed distance function (SDF) that effectively parameterizes the retinal layer shape via level set. We further enhance the framework by integrating probabilistic modeling, applying Gaussian distributions to encapsulate the uncertainty in the shape parameterization. This ensures a robust representation of the retinal layer morphology even in the presence of ambiguous input, imaging noise, and unreliable segmentations. Both quantitative and qualitative evaluations demonstrate superior performance when compared to other methods. Additionally, we conducted experiments on artificially distorted datasets with various noise types-shadowing, blinking, speckle, and motion-common in OCT scans to showcase the effectiveness of our uncertainty estimation. Our findings demonstrate the possibility to obtain reliable segmentation of retinal layers, as well as an initial step towards the characterization of layer integrity, a key biomarker for disease progression. Our code is available at \url{https://github.com/niazoys/RLS_PSDF}.