Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI
- 29 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (1) , 244-258
Abstract
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 tradeoff 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 sub-networks 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.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62131015, 62250710165, U23A20295, 61906121, 82300122)
- STI 2030-Major Project (2022ZD0209000)
- Shanghai Municipal Central Guided Local Science and Technology Development Fund (YDZX20233100001001)
- Science and Technology Commission of Shanghai Municipality (21010502600)
- Key Research and Development Program of Guangdong Province, China (21010502600)
This publication has 40 references indexed in Scilit:
- Self-aware and Cross-Sample Prototypical Learning for Semi-supervised Medical Image Segmentation2023
- Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation2023
- SMESwin Unet: Merging CNN and Transformer for Medical Image Segmentation2022
- CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation2021
- TransBTS: Multimodal Brain Tumor Segmentation Using Transformer2021
- Breast cancer early detection: A phased approach to implementationCancer, 2020
- 3D Dilated Multi-fiber Network for Real-Time Brain Tumor Segmentation in MRI2019
- Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation2019
- Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration2018
- Screening for breast cancer with mammographyCochrane Database of Systematic Reviews, 2013