Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yue, Dong, Jiahua, Peng, Chengtao, Wang, Qiuli, Song, Dan, Duan, Guiduo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909797620645888
author Zhang, Yue
Dong, Jiahua
Peng, Chengtao
Wang, Qiuli
Song, Dan
Duan, Guiduo
author_facet Zhang, Yue
Dong, Jiahua
Peng, Chengtao
Wang, Qiuli
Song, Dan
Duan, Guiduo
contents Accurate segmentation of breast tumors in magnetic resonance images (MRI) is essential for breast cancer diagnosis, yet existing methods face challenges in capturing irregular tumor shapes and effectively integrating local and global features. To address these limitations, we propose an uncertainty-gated deformable network to leverage the complementary information from CNN and Transformers. Specifically, we incorporates deformable feature modeling into both convolution and attention modules, enabling adaptive receptive fields for irregular tumor contours. We also design an Uncertainty-Gated Enhancing Module (U-GEM) to selectively exchange complementary features between CNN and Transformer based on pixel-wise uncertainty, enhancing both local and global representations. Additionally, a Boundary-sensitive Deep Supervision Loss is introduced to further improve tumor boundary delineation. Comprehensive experiments on two clinical breast MRI datasets demonstrate that our method achieves superior segmentation performance compared with state-of-the-art methods, highlighting its clinical potential for accurate breast tumor delineation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images
Zhang, Yue
Dong, Jiahua
Peng, Chengtao
Wang, Qiuli
Song, Dan
Duan, Guiduo
Image and Video Processing
Computer Vision and Pattern Recognition
Accurate segmentation of breast tumors in magnetic resonance images (MRI) is essential for breast cancer diagnosis, yet existing methods face challenges in capturing irregular tumor shapes and effectively integrating local and global features. To address these limitations, we propose an uncertainty-gated deformable network to leverage the complementary information from CNN and Transformers. Specifically, we incorporates deformable feature modeling into both convolution and attention modules, enabling adaptive receptive fields for irregular tumor contours. We also design an Uncertainty-Gated Enhancing Module (U-GEM) to selectively exchange complementary features between CNN and Transformer based on pixel-wise uncertainty, enhancing both local and global representations. Additionally, a Boundary-sensitive Deep Supervision Loss is introduced to further improve tumor boundary delineation. Comprehensive experiments on two clinical breast MRI datasets demonstrate that our method achieves superior segmentation performance compared with state-of-the-art methods, highlighting its clinical potential for accurate breast tumor delineation.
title Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.15758