ISA-Net: Improved spatial attention network for PET-CT tumor segmentation. (November 2022)

• Record Type: Journal Article
• Authors: Huang, Zhengyong; Zou, Sijuan; Wang, Guoshuai; Chen, Zixiang; Shen, Hao; Wang, Haiyan; Zhang, Na; Zhang, Lu; Yang, Fan; Wang, Haining; Liang, Dong; Niu, Tianye; Zhu, Xiaohua; Hu, Zhanli
• Is Part Of: Computer methods and programs in biomedicine. Volume 226(2022)
• Publication Date: 2022-11
• Subjects: Tumor segmentation -- Multimodal PET-CT -- Deep learning -- Attention network; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107129
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Proposed an improved spatial attention method based on multi-modal data, which can make full use of the differences and complementarities between different modal data. We analyze and discuss the influence of different weighting factors assigned to each modality on the fusion results. In the encoding stage, each channel extracts feature information separately, and then performs fusion in the decoding stage to realize information complementarity Special internal structure design can highlight the tumor region location information and suppress the non-tumor region location information and prevent model degradation effectively. Experimental results show that our method improves the segmentation accuracy and has good generalization. Abstract: Background and Objective: Achieving accurate and automated tumor segmentation plays an important role in both clinical practice and radiomics research. Segmentation in medicine is now often performed manually by experts, which is a laborious, expensive and error-prone task. Manual annotation relies heavily on the experience and knowledge of these experts. In addition, there is much intra- and interobserver variation. Therefore, it is of great significance to develop a method that can automatically segment tumor target regions. Methods: In this paper, we propose a deep learning segmentation method based on multimodal positron emission tomography-computed tomography (PET-CT), which combines the high sensitivity of PET and the precise anatomical information of CT. We design an improved spatial attention network(ISA-Net) to increase the accuracy of PET or CT in detecting tumors, which uses multi-scale convolution operation to extract feature information and can highlight the tumor region location information and suppress the non-tumor region location information. In addition, our network uses dual-channel inputs in the coding stage and fuses them in the decoding stage, which can take advantage of the differences and complementarities between PET and CT. Results: We validated the proposed ISA-Net method on two clinical datasets, a soft tissue sarcoma(STS) and a head and neck tumor(HECKTOR) dataset, and compared with other attention methods for tumor segmentation. The DSC score of 0.8378 on STS dataset and 0.8076 on HECKTOR dataset show that ISA-Net method achieves better segmentation performance and has better generalization. Conclusions: The method proposed in this paper is based on multi-modal medical image tumor segmentation, which can effectively utilize the difference and complementarity of different modes. The method can also be applied to other multi-modal data or single-modal data by proper adjustment.