ReLaX: Retinal Layer Attribution for Guided Explanations of Automated Optical Coherence Tomography Classification

TL;DR

ReLaX is a deep learning framework that accurately classifies retinal diseases from OCT scans while providing detailed, layer-specific explanations to improve clinical interpretability and trust.

Contribution

It introduces a novel retinal layer attribution method that offers both qualitative and quantitative explanations, enhancing interpretability over previous pixel-level attribution techniques.

Findings

Achieves state-of-the-art accuracy in retinal pathology classification.

Provides detailed quantitative explanations of model decisions.

Combines heatmaps with segmentation for rich interpretability.

Abstract

30 million Optical Coherence Tomography (OCT) imaging tests are issued annually to diagnose various retinal diseases, but accurate diagnosis of OCT scans requires trained eye care professionals who are still prone to making errors. With better systems for diagnosis, many cases of vision loss caused by retinal disease could be entirely avoided. In this work, we present ReLaX, a novel deep learning framework for explainable, accurate classification of retinal pathologies which achieves state-of-the-art accuracy. Furthermore, we emphasize producing both qualitative and quantitative explanations of the model's decisions. While previous works use pixel-level attribution methods for generating model explanations, our work uses a novel retinal layer attribution method for producing rich qualitative and quantitative model explanations. ReLaX determines the importance of each retinal layer by combining heatmaps with an OCT segmentation model. Our work is the first to produce detailed quantitative explanations of a model's predictions in this way. The combination of accuracy and interpretability can be clinically applied for accessible, high-quality patient care.