Saved in:
Bibliographic Details
Main Authors: Sanghvi, Samyak, Miglani, Piyush, Shashikumar, Sarvesh, Borgavi, Kaustubh R, Singla, Veenu, Arora, Chetan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.19350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913051068858368
author Sanghvi, Samyak
Miglani, Piyush
Shashikumar, Sarvesh
Borgavi, Kaustubh R
Singla, Veenu
Arora, Chetan
author_facet Sanghvi, Samyak
Miglani, Piyush
Shashikumar, Sarvesh
Borgavi, Kaustubh R
Singla, Veenu
Arora, Chetan
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2604_19350
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms
Sanghvi, Samyak
Miglani, Piyush
Shashikumar, Sarvesh
Borgavi, Kaustubh R
Singla, Veenu
Arora, Chetan
Computer Vision and Pattern Recognition
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
title Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.19350