arXiv cs.AI· Ahmed Jaheen·· 12 小时前AI 评分31
显著性图在致密乳腺上失效？乳腺钼靶解释公平性的机会归一化与混杂因素审计
Do Saliency Maps Fail Dense Breasts? A Chance-Normalized, Confounder-Aware Audit of Explanation Fairness in Mammography
AI 导读
研究在 1,345 张 CBIS-DDSM 恶性视图上评估三种 CNN 的 Grad-CAM、Integrated Gradients 与遮挡图，发现未校正时 Grad-CAM 峰值在致密乳腺病灶上的命中率为 44%，非致密为 58%。
正文 · 原文
Abstract:Saliency maps, offered as evidence that mammography classifiers use the cancer, are untested in dense breasts, which can hide cancers. We tested whether they locate cancers worse there, and why. On 1,345 malignant CBIS-DDSM views, we scored three CNNs' Grad-CAM, Integrated Gradients and occlusion maps by whether their peak hits the lesion and a chance-normalized lesion-to-background saliency ratio (bits; +1 doubles it). Unadjusted gaps were large: Grad-CAM peaks hit 44% of dense vs. 58% of non-dense lesions. Case mix, chiefly more calcifications in dense breasts, explained about half or more of each gap. Occlusion kept a significant average of -0.56 bit gap. Controls also implicate the classifiers: unadjusted gaps exceeded an image-only conspicuity map's, and models relied less on dense-breast lesions. We recommend reporting density gaps before and after case-mix adjustment, per classifier, with conspicuity and lesion-reliance controls.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05909 [cs.CV] |
| (or arXiv:2611.05909v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05909 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ahmed Jaheen [view email]
[v1]
Wed, 4 Nov 2026 04:01:32 UTC (1,027 KB)
来源：arXiv cs.AI · arxiv.org