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

• URL: http://arxiv.org/abs/2508.20621v1
• Date: Thu, 28 Aug 2025 10:11:24 GMT
• Title: Mask-Guided Multi-Channel SwinUNETR Framework for Robust MRI Classification
• Authors: Smriti Joshi, Lidia Garrucho, Richard Osuala, Oliver Diaz, Karim Lekadir,
• Abstract summary: ODELIA consortium organized a challenge to foster AI-based solutions for breast cancer diagnosis and classification.<n> dataset included 511 studies from six European centers, acquired on scanners from multiple vendors at both 1.5 T and 3 T.<n>We developed a SwinUNETR-based deep learning framework that incorporates breast region masking, extensive data augmentation, and ensemble learning to improve robustness and generalizability.
• Score: 1.2545070841185901
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• MeisenMeister: A Simple Two Stage Pipeline for Breast Cancer Classification on MRI [3.2340954609207646]
  The ODELIA Breast MRI Challenge 2025 addresses a critical issue in breast cancer screening.<n>This write-up provides a comprehensive overview of our approach to the challenge.
  arXiv  Detail & Related papers  (2025-10-31T09:53:59Z)
• A European Multi-Center Breast Cancer MRI Dataset [32.81686559528397]
  The ODELIA consortium has made this multi-centre dataset publicly available to assist in developing AI tools for the detection of breast cancer on MRI.<n>Recent guidelines by the European Society of Breast Imaging recommend breast MRI as a supplemental screening tool for women with dense breast tissue.<n>The ODELIA consortium has made this multi-centre dataset publicly available to assist in developing AI tools for the detection of breast cancer on MRI.
  arXiv  Detail & Related papers  (2025-05-31T08:45:02Z)
• Mammo-Clustering: A Multi-views Tri-level Information Fusion Context Clustering Framework for Localization and Classification in Mammography [13.581151516877238]
  Mammography images typically have extremely high resolution, with lesions occupying only a very small area.<n>Down-sampling in neural networks can easily lead to the loss of microcalcifications or subtle structures.<n>We propose a Context Clustering Network with triple information fusion.
  arXiv  Detail & Related papers  (2024-09-23T10:17:13Z)
• A Large Model for Non-invasive and Personalized Management of Breast Cancer from Multiparametric MRI [19.252851972152957]
  We develop a large mixture-of-modality-experts model (MOME) that integrates multi-parametric MRI information within a unified structure.<n>MOME matches four senior radiologists' performance in identifying breast cancer and outperforms a junior radiologist.
  arXiv  Detail & Related papers  (2024-08-08T05:04:13Z)
• Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging [82.74877848011798]
  The prevalence of breast cancer continues to grow, affecting about 300,000 females in the United States in 2023. The gold-standard Scarff-Bloom-Richardson (SBR) grade has been shown to consistently indicate a patient's response to chemotherapy. In this paper, we study the efficacy of deep learning for breast cancer grading based on synthetic correlated diffusion (CDI$s$) imaging.
  arXiv  Detail & Related papers  (2023-04-12T15:08:34Z)
• A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data [82.74877848011798]
  Cancer-Net BCa is a multi-institutional open-source benchmark dataset of volumetric CDI$s$ imaging data of breast cancer patients. Cancer-Net BCa is publicly available as a part of a global open-source initiative dedicated to accelerating advancement in machine learning to aid clinicians in the fight against cancer.
  arXiv  Detail & Related papers  (2023-04-12T05:41:44Z)
• Multi-Head Feature Pyramid Networks for Breast Mass Detection [48.24995569980701]
  We propose the multi-head feature pyramid module (MHFPN) to solve the problem of unbalanced focus of target boxes during feature map fusion. Experimental studies show that, comparing to the SOTA detection baselines, our method improves by 6.58% (in AP@50) and 5.4% (in TPR@50) on the commonly used INbreast dataset.
  arXiv  Detail & Related papers  (2023-02-22T03:02:52Z)
• High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection [48.88813637974911]
  Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. High-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. This study aims to improve the mass detection performance in high-density breasts using synthetic high-density full-field digital mammograms.
  arXiv  Detail & Related papers  (2022-09-20T15:57:12Z)
• Learned super resolution ultrasound for improved breast lesion characterization [52.77024349608834]
  Super resolution ultrasound localization microscopy enables imaging of the microvasculature at the capillary level. In this work we use a deep neural network architecture that makes effective use of signal structure to address these challenges. By leveraging our trained network, the microvasculature structure is recovered in a short time, without prior PSF knowledge, and without requiring separability of the UCAs.
  arXiv  Detail & Related papers  (2021-07-12T09:04:20Z)
• Joint 2D-3D Breast Cancer Classification [22.031221319016353]
  Digital mammograms (DM or 2D mammogram) and digital breast tomosynthesis (DBT or 3D mammogram) are the two types of mammography imagery used in clinical practice for breast cancer detection and diagnosis. We propose an innovative convolutional neural network (CNN) architecture for breast cancer classification, which uses both 2D and 3D mammograms, simultaneously.
  arXiv  Detail & Related papers  (2020-02-27T19:08:16Z)
• Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
  We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
  arXiv  Detail & Related papers  (2020-02-03T22:25:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.