MSU-Net: Multi-scale Sensitive U-Net based on pixel-edge-region level collaborative loss for nasopharyngeal MRI segmentation

• Published in: Computers in biology and medicine 2023-06, Vol.159, p.106956-106956, Article 106956
• Main Authors: Hao, Yuanquan, Jiang, Huiyan, Diao, Zhaoshuo, Shi, Tianyu, Liu, Lizhi, Li, Haojiang, Zhang, Weijing
• Format: Article
• Language: English
• Subjects: Collaboration; Deep learning; Feature extraction; Humans; Image processing; Image Processing, Computer-Assisted; Image segmentation; Information retrieval; Information Storage and Retrieval; Lesions; Magnetic Resonance Imaging; Medical image segmentation; Medical imaging; Modules; Multi-modalities MRI; Nasopharyngeal carcinoma; Nasopharynx; Nasopharynx - diagnostic imaging; Pixels; Radiation therapy; Semantics; Throat cancer; U-Net
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106956

Radiotherapy is the traditional treatment of early nasopharyngeal carcinoma (NPC). Automatic accurate segmentation of risky lesions in the nasopharynx is crucial in radiotherapy. U-Net has been proved its effective medical image segmentation ability. However, the great difference in the structure and size of nasopharynx among different patients requires a network that pays more attention to multi-scale information. In this paper, we propose a multi-scale sensitive U-Net (MSU-Net) based on pixel-edge-region level collaborative loss (LCo−PER) for NPC segmentation task. A series of novel feature fusion modules based on spatial continuity and multi-scale semantic are proposed for extracting multi-level features while efficiently searching for all size lesions. A spatial continuity information extraction module (SCIEM) is proposed for effectively using the spatial continuity information of context slices to search small lesions. And a multi-scale semantic feature extraction module (MSFEM) is proposed for extracting features of different receptive fields. LCo−PER is proposed for the network training which makes network model could take into account the size of different lesions. The global Dice, Precision, Recall and IOU of the testing set are 84.50%, 97.48%, 84.33% and 82.41%, respectively. The results show that our method is better than the other state-of-the-art methods for NPC segmentation which obtain higher accuracy and effective segmentation performance. •A multi-scale sensitive U-Net (MSU-Net) based on pixel-edge-region level collaborative loss is proposed for the segmentation of nasopharyngeal carcinoma.•Triple-modalities MRI of each patient has been collected. A series of novel feature fusion modules based on spatial continuity and multi-scale semantic are proposed for extracting multi-level features while efficiently searching for small lesions.•A pixel-edge-region level collaborative loss is proposed for the training of the proposed network to take into account multi-scale lesions.