arXiv AI November 5, 2026 By Ahmed Jaheen

Do Saliency Maps Fail Dense Breasts? A Chance-Normalized, Confounder-Aware Audit of Explanation Fairness in Mammography

The study evaluates whether saliency maps—visual explanations for mammography classifiers—perform differently on dense versus non‑dense breasts. Using 1,345 malignant CBIS‑DDSM images, the authors compared Grad‑CAM, Integrated Gradients, and occlusion maps, finding that Grad‑CAM peaks correctly identified 44% of dense‑breast lesions versus 58% of non‑dense ones. After adjusting for case mix (notably more calcifications in dense breasts), the performance gap narrowed, but occlusion maps still showed a significant deficit, and classifiers overall relied less on dense‑breast lesions than on an image‑only conspicuity baseline. The authors recommend reporting density‑specific performance gaps before and after adjustment, along with controls for conspicuity and lesion reliance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

safety

arXiv Computer Vision

Oct 9

Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification

The paper introduces a counterfactual data augmentation method that generates healthy mammograms by inpainting lesions with realistic normal tissue using a Denoising Diffusion Probabilistic Model and a RePaint-based sampling strategy. The generated healthy counterfactuals preserve patient-specific anatomy and match the quality of the original dataset, as confirmed by similarity metrics and radiologist assessment. When applied to four different classifier architectures on the VinDr-Mammo dataset, the augmentation improves sensitivity, especially at 80% fixed specificity, thereby enhancing the reliability of computer-aided breast cancer screening systems.

By In\^es Cruchinho Garcia, Mariana Mour\~ao, Francisco Maria Calisto, Carlos Santiago, Jacinto Nascimento

llms diffusion computer-vision multimodal

arXiv AI

Jul 16

MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentation

arXiv:2606. 28419v2 Announce Type: replace-cross Abstract: Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification.

By Teerath Kumar, Raja Vavekanand, Muhammad Turab

llms diffusion computer-vision benchmarks

arXiv AI

Jun 30

MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentatio

arXiv:2606. 28419v1 Announce Type: cross Abstract: Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification.

By Teerath Kumar, Raja Vavekanand, Muhammad Turab

llms diffusion computer-vision benchmarks

arXiv Machine Learning

Sep 23

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

arXiv:2609.25978v1 Announce Type: cross Abstract: Saliency maps are widely used to explain deep learning predictions in medical imaging, yet visually plausible explanations do not necessarily reflect...

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

llms computer-vision benchmarks

arXiv Computer Vision

Sep 4

Solving the Needle-in-a-Haystack Problem in Mammography Vision-Language Model with Differentiable Subset Sampling

The paper introduces TopKSigLIP, a vision‑language model tailored for mammography that tackles two key challenges: high‑resolution imaging and homogeneous radiology reports. It replaces standard CLIP training with a TopK‑Patch module that selects sparse high‑resolution patches likely to contain lesions, and a Sup‑sigmoid loss that uses soft labels from structured data instead of contrastive loss. TopKSigLIP outperforms existing open‑source mammography and general medical VLMs on zero‑shot tasks such as density assessment, BI‑RADS classification, finding subtyping, and cancer prediction, while also providing better lesion localization than Grad‑CAM.

By Young Seok Jeon, Beatrice Brown-Mulry, Rohan Satya Isaac, Anjana Dissanayaka, Theo Dapamede, Mohammadreza Chavoshi, Judy Gichoya, Hari Trivedi

llms multimodal benchmarks

arXiv Machine Learning

Oct 7

Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings

The paper introduces a Hybrid Cross-Modal Attention Network (HCMAN) that fuses mammogram images with structured clinical data using transformer-based cross‑modal attention. Trained on a locally collected dataset of 2,560 images from 1,024 Ethiopian patients, the model achieves 97.8% accuracy, 97.2% sensitivity, 98.3% specificity, and an AUC of 0.987, outperforming image‑only baselines and maintaining robustness to low‑quality images. Its lightweight design allows inference in under two seconds on a standard CPU, making it suitable for deployment in resource‑limited clinical settings.

By Simon Hadush Nrea (Mekelle University, Mekelle, Ethiopia), Filimon Gidey Gebremichael (Mekelle University, Mekelle, Ethiopia), Gebrekirstos Hagos Gebrekirstos (Clinical Oncologist London School of Hygiene and Tropical Medicine London, UK), Yaecob Girmay Gezahegn (Mekelle University, Mekelle, Ethiopia)

llms multimodal