# Mask-Guided Multi-Channel SwinUNETR Framework for Robust MRI Classification

## TL;DR

This paper introduces a robust MRI classification framework using a mask-guided multi-channel SwinUNETR model, incorporating breast region masking and ensemble learning, achieving high performance in a multi-center breast cancer diagnosis challenge.

## Contribution

The novel contribution is a mask-guided multi-channel SwinUNETR framework that enhances MRI classification robustness and generalizability for breast cancer detection.

## Key findings

- Achieved second place in the ODELIA challenge leaderboard.
- Demonstrated improved robustness with breast region masking and ensemble learning.
- Shared publicly available codebase for reproducibility.

## Abstract

Breast cancer is one of the leading causes of cancer-related mortality in women, and early detection is essential for improving outcomes. Magnetic resonance imaging (MRI) is a highly sensitive tool for breast cancer detection, particularly in women at high risk or with dense breast tissue, where mammography is less effective. The ODELIA consortium organized a multi-center challenge to foster AI-based solutions for breast cancer diagnosis and classification. The dataset included 511 studies from six European centers, acquired on scanners from multiple vendors at both 1.5 T and 3 T. Each study was labeled for the left and right breast as no lesion, benign lesion, or malignant lesion. We developed a SwinUNETR-based deep learning framework that incorporates breast region masking, extensive data augmentation, and ensemble learning to improve robustness and generalizability. Our method achieved second place on the challenge leaderboard, highlighting its potential to support clinical breast MRI interpretation. We publicly share our codebase at https://github.com/smriti-joshi/bcnaim-odelia-challenge.git.