TMSF-Net: Multi-series fusion network with treeconnect for colorectal tumor segmentation. (March 2022)

• Record Type: Journal Article
• Authors: Chen, Cheng; Zhou, Kangneng; Wang, Huilin; Lu, YuanYuan; Wang, Zhiliang; Xiao, Ruoxiu; Lu, Tingting
• Is Part Of: Computer methods and programs in biomedicine. Volume 215(2022)
• Publication Date: 2022-03
• Subjects: Colorectal tumor -- Image segmentation -- Multi-series CT Image -- TMSF-Net -- Treeconnect; 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.2021.106613
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Effective and stable 3D colorectal tumor segmentation from CT images was applied. Three-series colorectal tumor CT images of each case were collected, which enrich information features. Multi-series fusion network with treeconnect (TMSF-Net) was proposed and established. Its multi-branch realized collaborative training and fusion. 3D data augmentation strategy was applied in training stage to prevent network overfitting. 3D Treeconnect was introduced to fusion feature from different branch in TMSF-Net, which generated new feature maps using less connection. Abstract: Purpose: Colorectal tumors are common clinical diseases. Automatic segmentation of colorectal tumors captured in computed tomography (CT) images can provide numerous possibilities for computer-assisted treatment. Obtaining large datasets is expensive, and completing labeling is time- and manpower-consuming. To solve the challenge using a limited pathological dataset, this paper proposes a multi-series fusion network with treeconnect (TMSF-Net), which can automatically achieve colorectal tumor segmentation using CT images. Methods: To drive the TMSF-Net, three-series enhanced CT images were collected from all patients to improve the data characteristics. In the TMSF-Net, the coding path was designed as a three-branch structure to realize the feature extraction of the different series. Subsequently, the three branches were merged to start the feature analysis in the decoding path. To achieve the objective of feature fusion, different layers in the decoding path fused feature maps from the upper layer in the encoding path to achieve a cross-scale fusion. In addition, to reduce the problem of parameter redundancy, this study adopted a three-dimensional treeconnect to complete data connection on three branches. Results: A total of 22 cases were conducted by ablation and comparative experiments to test the TMSF-Net. The results showed that the TMSF-Net can improve the network performance by multiseries fusion, and its expressiveness is better than many classic networks. Conclusion: The TMSF-Net is a many-to-one structure network, which can enhance the network learning ability and improve the analysis of potential features. Therefore, it yields good results in colorectal tumor segmentation. It can provide a new direction for neural network models based on feature fusion.