Two Stages Segmentation Algorithm of Breast Tumor in DCE-MRI Based on Multi-Scale Feature and Boundary Attention Mechanism
Bing Li1,2,*, Liangyu Wang1, Xia Liu1,2, Hongbin Fan1, Bo Wang3, Shoudi Tong1
1
School of Automation, Harbin University of Science and Technology, Harbin, 150080, China
2
Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration, Harbin, 150080, China
3
School of Computer Engineering Technology, Guangdong Institute of Science and Technology, Zhuhai, 519090, China
* Corresponding Author: Bing Li. Email: libing@hrbust.edu.cn
(This article belongs to the Special Issue: Deep Learning in Computer-Aided Diagnosis Based on Medical Image)
Computers, Materials & Continua https://doi.org/10.32604/cmc.2024.052009
Received 20 March 2024; Accepted 24 May 2024; Published online 10 July 2024
Abstract
Nuclear magnetic resonance imaging of breasts often presents complex backgrounds. Breast tumors exhibit varying
sizes, uneven intensity, and indistinct boundaries. These characteristics can lead to challenges such as low accuracy
and incorrect segmentation during tumor segmentation. Thus, we propose a two-stage breast tumor segmentation
method leveraging multi-scale features and boundary attention mechanisms. Initially, the breast region of interest
is extracted to isolate the breast area from surrounding tissues and organs. Subsequently, we devise a fusion
network incorporating multi-scale features and boundary attention mechanisms for breast tumor segmentation.We
incorporate multi-scale parallel dilated convolution modules into the network, enhancing its capability to segment
tumors of various sizes through multi-scale convolution and novel fusion techniques. Additionally, attention
and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing
nonlocal dependencies in both spatial and channel domains. Furthermore, a hybrid loss function with boundary
weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance
capability through additional loss. The method was evaluated using breast data from 207 patients at Ruijin Hospital,
resulting in a 6.64% increase in Dice similarity coefficient compared to the benchmark U-Net. Experimental results
demonstrate the superiority of the method over other segmentation techniques, with fewer model parameters.
Keywords
Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI); breast tumor segmentation; multi-scale dilated convolution; boundary attention; the hybrid loss function with boundary weight
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
