# XAI-Driven Diagnosis of Generalization Failure in State-Space Cerebrovascular Segmentation Models: A Case Study on Domain Shift Between RSNA and TopCoW Datasets

arXiv: https://arxiv.org/abs/2512.13977 · HTML: https://mlsanity.com/paper/2512.13977/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions](https://mlsanity.com/paper/2401.03495/) (2024)
- [The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography](https://mlsanity.com/paper/2312.17670/) (2023)
- [Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping](https://mlsanity.com/paper/2002.11434/) (2020)
- [Domain Generalization for Medical Image Analysis: A Review](https://mlsanity.com/paper/2310.08598/) (2023)
- [Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2306.05254/) (2023)
- [A Survey on Trustworthiness in Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2407.15851/) (2024)
- [A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyond](https://mlsanity.com/paper/2410.02362/) (2024)
- [MambaVesselNet++: A Hybrid CNN-Mamba Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2507.19931/) (2025)
- [Multi-Domain Brain Vessel Segmentation Through Feature Disentanglement](https://mlsanity.com/paper/2510.00665/) (2025)
- [Efficiency vs. Efficacy: Assessing the Compression Ratio-Dice Score Relationship through a Simple Benchmarking Framework for Cerebrovascular 3D Segmentation](https://mlsanity.com/paper/2510.03769/) (2025)
- [A Quantitative Evaluation Framework for Explainable AI in Semantic Segmentation](https://mlsanity.com/paper/2510.24414/) (2025)
- [AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography](https://mlsanity.com/paper/2511.17724/) (2025)

## Abstract (arXiv)

The clinical deployment of deep learning models in medical imaging is severely hindered by domain shift. This challenge, where a high-performing model fails catastrophically on external datasets, is a critical barrier to trustworthy AI. Addressing this requires moving beyond simple performance metrics toward deeper understanding, making Explainable AI (XAI) an essential diagnostic tool in medical image analysis. We present a rigorous, two-phase approach to diagnose the generalization failure of state-of-the-art State-Space Models (SSMs), specifically UMamaba, applied to cerebrovascular segmentation. We first established a quantifiable domain gap between our Source (RSNA CTA Aneurysm) and Target (TopCoW Circle of Willis CT) datasets, noting significant differences in Z-resolution and background noise. The model's Dice score subsequently plummeted from 0.8604 (Source) to 0.2902 (Target). In the second phase, which is our core contribution, we utilized Seg-XRes-CAM to diagnose the cause of this failure. We quantified the model's focus by measuring the overlap between its attention maps and the Ground Truth segmentations, and between its attention maps and its own Prediction Mask. Our analysis proves the model failed to generalize because its attention mechanism abandoned true anatomical features in the Target domain. Quantitative metrics confirm the model's focus shifted away from the Ground Truth vessels (IoU~0.101 at 0.3 threshold) while still aligning with its own wrong predictions (IoU~0.282 at 0.3 threshold). This demonstrates the model learned spurious correlations, confirming XAI is a powerful diagnostic tool for identifying dataset bias in emerging architectures.