# Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms

Source: [Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms](<https://www.sota2.com/research/paper/69e85bed7d0172140ec811dd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-23T05:00:12.895Z

Authors: Samyak Sanghvi, Piyush Miglani, Sarvesh Shashikumar, Kaustubh R Borgavi, Veenu Singla, Chetan Arora

Published: 2026-04-21T11:33:04.000Z

## Abstract

Vision Transformers $(\\texttt{ViT})$ have become the architecture of choice for many computer vision tasks, yet their performance in computer-aided diagnostics remains limited. Focusing on breast cancer detection from mammograms, we identify two main causes for this shortfall. First, medical images are high-resolution with small abnormalities, leading to an excessive number of tokens and making it difficult for the softmax-based attention to localize and attend to relevant regions. Second, medical image classification is inherently fine-grained, with low inter-class and high intra-class variability, where standard cross-entropy training is insufficient. To overcome these challenges, we propose a framework with three key components: (1) Region of interest $(\\texttt{RoI})$ based token reduction using an object detection model to guide attention; (2) contrastive learning between selected $\\texttt{RoI}$ to enhance fine-grained discrimination through hard-negative based training; and (3) a $\\texttt{DINOv2}$ pretrained $\\texttt{ViT}$ that captures localization-aware, fine-grained features instead of global $\\texttt{CLIP}$ representations. Experiments on public mammography datasets demonstrate that our method achieves superior performance over existing baselines, establishing its effectiveness and potential clinical utility for large-scale breast cancer screening. Our code is available for reproducibility here: https://aih-iitd.github.io/publications/attend-what-matters

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Mammography Classification on VinDr](<https://www.sota2.com/research/sota/mammography-classification-on-vindr.md>): Mammography Classification; VinDr; ROC AUC: 0.866.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.19350>)

[PDF](<https://arxiv.org/pdf/2604.19350.pdf>)
