首页 / 院系成果 / 成果详情页

Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI 期刊论文

编号：

F66D5EFC7E51ABA14F0927FD861BDDC1
作者：

Zhou, Lei#*^[1]Zhang, Yuzhong^[1];Zhang, Jiadong^[2];Qian, Xuejun^[2];Gong, Chen^[3];Sun, Kun^[4];Ding, Zhongxiang^[5];Wang, Xing^[6];Li, Zhenhui(李振辉)^[7]Liu, Zaiyi^[8,9];Shen, Dinggang*^[2,10,11]
语种：

英文
期刊：

IEEE TRANSACTIONS ON MEDICAL IMAGING ISSN：0278-0062 2025 年 44 卷 1 期 (244 - 258) ; JAN
收录：
关键词：

Image segmentation Transformers Prototypes Breast tumors Tumors Decoding Medical diagnostic imaging Magnetic resonance imaging breast tumor segmentation hybrid network transformer prototype learning
摘要：

Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However, accurate segmentation of breast tumor is a challenging task, often necessitating the development of complex networks. To strike an optimal trade-off between computational costs and segmentation performance, we propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. Specifically, the hybrid network consists of a encoder-decoder architecture by stacking convolution and deconvolution layers. Effective 3D transformer layers are then implemented after the encoder subnetworks, to capture global dependencies between the bottleneck features. To improve the efficiency of hybrid network, two parallel encoder subnetworks are designed for the decoder and the transformer layers, respectively. To further enhance the discriminative capability of hybrid network, a prototype learning guided prediction module is proposed, where the category-specified prototypical features are calculated through online clustering. All learned prototypical features are finally combined with the features from decoder for tumor mask prediction. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network achieves superior performance than the state-of-the-art (SOTA) methods, while maintaining balance between segmentation accuracy and computation cost. Moreover, we demonstrate that automatically generated tumor masks can be effectively applied to identify HER2-positive subtype from HER2-negative subtype with the similar accuracy to the analysis based on manual tumor segmentation. The source code is available at https://github.com/ZhouL-lab/PLHN.
推荐引用方式
GB/T 7714：

Zhou Lei,Zhang Yuzhong,Zhang Jiadong, et al. Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI [J].IEEE TRANSACTIONS ON MEDICAL IMAGING,2025,44(1):244-258.
APA：

Zhou Lei,Zhang Yuzhong,Zhang Jiadong,Qian Xuejun,&Shen Dinggang.(2025).Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI .IEEE TRANSACTIONS ON MEDICAL IMAGING,44(1):244-258.
MLA：

Zhou Lei, et al. "Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI" .IEEE TRANSACTIONS ON MEDICAL IMAGING 44,1(2025):244-258.
入库时间：

2024/10/31 9:54:05
更新时间：

2025/2/11 22:27:26
条目包含文件：

文件类型：PDF,文件大小：

正在加载全文

未找到全文

浏览次数：45  下载次数：0

分享到：

浏览次数：45

下载次数：0

打印次数：0