Dissecting Model Failures in Abdominal Aortic Aneurysm Segmentation through Explainability-Driven Analysis

TL;DR

This paper introduces an explainability-guided framework for abdominal aortic aneurysm segmentation, improving model focus and accuracy by integrating attribution maps into the training and inference processes.

Contribution

It presents a novel XAI-driven encoder shaping method that aligns model focus with relevant structures and suppresses distractors, enhancing segmentation reliability.

Findings

Significant improvement over baseline in challenging cases

Effective suppression of irrelevant structures during segmentation

Demonstrated practical benefits in complex clinical scenarios

Abstract

Computed tomography image segmentation of complex abdominal aortic aneurysms (AAA) often fails because the models assign internal focus to irrelevant structures or do not focus on thin, low-contrast targets. Where the model looks is the primary training signal, and thus we propose an Explainable AI (XAI) guided encoder shaping framework. Our method computes a dense, attribution-based encoder focus map ("XAI field") from the final encoder block and uses it in two complementary ways: (i) we align the predicted probability mass to the XAI field to promote agreement between focus and output; and (ii) we route the field into a lightweight refinement pathway and a confidence prior that modulates logits at inference, suppressing distractors while preserving subtle structures. The objective terms serve only as control signals; the contribution is the integration of attribution guidance into representation and decoding. We evaluate clinically validated challenging cases curated for failure-prone scenarios. Compared to a base SAM setup, our implementation yields substantial improvements. The observed gains suggest that explicitly optimizing encoder focus via XAI guidance is a practical and effective principle for reliable segmentation in complex scenarios.