A 3D segmentation network of mandible from CT scan with combination of multiple convolutional modules and edge supervision in mandibular reconstruction. (November 2021)

• Record Type: Journal Article
• Authors: Xu, Jiangchang; Liu, Jiannan; Zhang, Dingzhong; Zhou, Zijie; Zhang, Chenping; Chen, Xiaojun
• Is Part Of: Computers in biology and medicine. Volume 138(2021)
• Publication Date: 2021-11
• Subjects: Mandible segmentation -- Automatic segmentation -- Edge supervision -- Convolutional neural network -- Mandibular reconstruction; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104925
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Mandibular reconstruction is a very complex surgery that demands removing the tumor, which is followed by reconstruction of the defective mandible. Accurate segmentation of the mandible plays an important role in its preoperative planning. However, there are many segmentation challenges including the connected boundaries of upper and lower teeth, blurred condyle edges, metal artifact interference, and different shapes of the mandibles with tumor invasion (MTI). Those manual or semi-automatic segmentation methods commonly used in clinical practice are time-consuming and have poor effects. The automatic segmentation methods are mainly developed for the mandible without tumor invasion (Non-MTI) rather than MTI and have problems such as under-segmentation. Given these problems, this paper proposed a 3D automatic segmentation network of the mandible with a combination of multiple convolutional modules and edge supervision. Firstly, the squeeze-and-excitation residual module is used for feature optimization to make the network focused more on the mandibular segmentation region. Secondly, the multi atrous convolution cascade module is adapted to implement a multi-scale feature search to extract more detailed features. Considering that most mandibular segmentation networks ignore the boundary information, the loss function combining region loss and edge loss is applied to further improve the segmentation performance. The final experiment shows that the proposed network can segment Non-MTI and MTI quickly and automatically with an average segmentation time of 7.41s for a CT scan. In the meantime, it also has a good segmentation accuracy. For Non-MTI segmentation, the dice coefficient (Dice) reaches 97.98 ± 0.36%, average surface distance (ASD) reaches 0.061 ± 0.016 mm, and 95% Hausdorff distance (95HD) reaches 0.484 ± 0.027 mm. For Non-MTI segmentation, the Dice reaches 96.90 ± 1.59%, ASD reaches 0.162 ± 0.107 mm, and 95HD reaches 1.161 ± 1.034 mm. Compared with other methods, the proposed method has better segmentation performance, effectively improving segmentation accuracy and reducing under-segmentation. It can greatly improve doctor's segmentation efficiency and will have a promising application prospect in mandibular reconstruction surgery in the future. Highlights: The combination of multiple convolutional modules is adopted to improve the segmentation performance of the network. The loss function combining region and edge loss is applied to further improve the segmentation performance. It can segment a normal mandible or with tumor invasion, and may have a promising application in mandibular reconstruction.