PaperScope
LIVE · 2026-09-23 05:40 UTC

Faithful Faithfulness Evaluations: Challenges & Pitfalls Learned from a Breast MRI Case Study

Peachapong Poolpol, Henrik H. J. Detjen, Eike Petersen

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.25978 v1
Submitted
2026-09-22

Abstract

Saliency maps are widely used to explain deep learning predictions in medical imaging, yet visually plausible explanations do not necessarily reflect a model's true decision process and may therefore mislead clinicians. We investigate this problem using a Vision Transformer-based breast MRI classifier trained on the ODELIA Breast MRI Challenge dataset and evaluate multiple saliency methods, including Last-layer Attention, Attention Rollout, Grad-SAM, Gradient Attention Rollout, GMAR, Grad-CAM, and HiResCAM. Our study highlights two often-overlooked challenges in perturbation-based faithfulness evaluation. First, method rankings depend strongly on the perturbation strategy, varying across intensity-based perturbations and transformer-based attention masking. Second, benchmarking saliency methods requires distinguishing between class-specific and class-agnostic explanations. To enable fair comparisons, we introduce non-class-specific variants of gradient-based methods and evaluate both settings separately. Across protocols, Grad-CAM and Gradient Attention Rollout consistently emerged as the strongest class-specific methods, although their relative ranking depended on the evaluation design. These findings expose important limitations of current saliency-based explainability approaches and highlight the need for more robust and standardized evaluation frameworks for trustworthy clinical AI systems.

Comment: Accepted at MICCAI iMIMIC Workshop 2026

arXiv abs page · PDF · same-day batch