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

arXiv: https://arxiv.org/abs/2603.24801 · HTML: https://mlsanity.com/paper/2603.24801/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [Cross-Entropy Loss Functions: Theoretical Analysis and Applications](https://mlsanity.com/paper/2304.07288/) (2023)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation](https://mlsanity.com/paper/2307.08473/) (2023)
- [Segment anything, from space?](https://mlsanity.com/paper/2304.13000/) (2023)
- [Segment Anything without Supervision](https://mlsanity.com/paper/2406.20081/) (2024)
- [ACC-UNet: A Completely Convolutional UNet model for the 2020s](https://mlsanity.com/paper/2308.13680/) (2023)
- [Realizable H-Consistent and Bayes-Consistent Loss Functions for Learning to Defer](https://mlsanity.com/paper/2407.13732/) (2024)
- [Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models](https://mlsanity.com/paper/2310.12995/) (2023)
- [Segment Anything, Even Occluded](https://mlsanity.com/paper/2503.06261/) (2025)
- [Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior](https://mlsanity.com/paper/2508.00235/) (2025)

## Abstract (arXiv)

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.