MSRA-Net: Tumor segmentation network based on Multi-scale Residual Attention

Yuxuan Wu; Huiyan Jiang; Wenbo Pang

doi:10.1016/j.compbiomed.2023.106818

MSRA-Net: Tumor segmentation network based on Multi-scale Residual Attention

Comput Biol Med. 2023 May:158:106818. doi: 10.1016/j.compbiomed.2023.106818. Epub 2023 Mar 22.

Authors

Yuxuan Wu¹, Huiyan Jiang², Wenbo Pang¹

Affiliations

¹ Software College, Northeastern University, No. 195, Chuangxin Road, Hunnan District, Shenyang, 110169, Liaoning, China.
² Software College, Northeastern University, No. 195, Chuangxin Road, Hunnan District, Shenyang, 110169, Liaoning, China. Electronic address: hyjiang@mail.neu.edu.cn.

PMID: 36966557
DOI: 10.1016/j.compbiomed.2023.106818

Abstract

Automatic Medical segmentation of medical images is an important part in the field of computer medical diagnosis, among which tumor segmentation is an important branch of medical image segmentation. Accurate automatic segmentation method is very important in medical diagnosis and treatment. Positron emission computed tomography (PET) and X-ray computed tomography (CT) images are widely used in medical image segmentation to help doctors accurately locate information such as tumor location and shape, providing metabolic and anatomical information, respectively. At present, PET/CT images have not been effectively combined in the research of medical image segmentation, and the complementary semantic information between the superficial and deep layers of neural network has not been ensured. To solve the above problems, this paper proposed a Multi-scale Residual Attention network (MSRA-Net) for tumor segmentation of PET/CT. We first use an attention-fusion based approach to automatically learn the tumor-related areas of PET images and weaken the irrelevant area. Then, the segmentation results of PET branch are processed to optimize the segmentation results of CT branch by using attention mechanism. The proposed neural network (MSRA-Net) can effectively fuse PET image and CT image, which can improve the precision of tumor segmentation by using complementary information of the multi-modal image, and reduce the uncertainty of single modal image segmentation. Proposed model uses multi-scale attention mechanism and residual module, which fuse multi-scale features to form complementary features of different scales. We compare with state-of-the-art medical image segmentation methods. The experiment showed that the Dice coefficient of the proposed network in soft tissue sarcoma and lymphoma datasets increased by 8.5% and 6.1% respectively compared with UNet, showing a significant improvement.

Keywords: Attentional mechanism; Feature selection; Multi-modal fusion; Multi-scale feature.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Humans
Image Processing, Computer-Assisted
Learning
Neoplasms* / diagnostic imaging
Neural Networks, Computer
Positron Emission Tomography Computed Tomography*
Positron-Emission Tomography