Department of Plastic and Reconstructive Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine.
Department of Automation, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China.
J Craniofac Surg. 2023;34(2):809-812. doi: 10.1097/SCS.0000000000009105. Epub 2023 Jan 9.
Hemifacial microsomia (HFM) is one of the most common congenital craniofacial condition often accompanied by masseter muscle involvement. U-Net neural convolution network for masseter segmentation is expected to achieve an efficient evaluation of masseter muscle.
A database was established with 108 patients with HFM from June 2012 to June 2019 in our center. Demographic data, OMENS classification, and 1-mm layer thick 3-dimensional computed tomography were included. Two radiologists manually segmented masseter muscles in a consensus reading as the ground truth. A test set of 20 cases was duplicated into 2 groups: an experimental group with the intelligent algorithm and a control group with manual segmentation. The U-net follows the design of 3D RoI-Aware U-Net with overlapping window strategy and references to our previous study of masseter segmentation in a healthy population system. Sorensen dice-similarity coefficient (DSC) muscle volume, average surface distance, recall, and time were used to validate compared with the ground truth.
The mean DSC value of 0.794±0.028 for the experiment group was compared with the manual segmentation (0.885±0.118) with α=0.05 and a noninferiority margin of 15%. In addition, higher DSC was reported in patients with milder mandible deformity ( r =0.824, P <0.05). Moreover, intelligent automatic segmentation takes only 6.4 seconds showing great efficiency.
We first proposed a U-net neural convolutional network and achieved automatic segmentation of masseter muscles in patients with HFM. It is a great attempt at intelligent diagnosis and evaluation of craniofacial diseases.
半侧颜面短小症（HFM）是最常见的先天性颅面畸形之一，常伴有咀嚼肌受累。U-Net 神经卷积网络有望实现对咀嚼肌的高效评估。
我们中心建立了一个包含 2012 年 6 月至 2019 年 6 月 108 例 HFM 患者的数据库，包括人口统计学数据、OMENS 分类和 1mm 层厚的三维 CT。两位放射科医生在共识阅读中手动分割咀嚼肌作为金标准。将 20 例测试集分为两组：智能算法实验组和手动分割对照组。U-net 采用 3D RoI-Aware U-Net 的设计，具有重叠窗口策略，并参考了我们之前在健康人群系统中对咀嚼肌分割的研究。Sorensen 骰子相似系数（DSC）肌肉体积、平均表面距离、召回率和时间用于与金标准进行验证比较。
实验组的平均 DSC 值为 0.794±0.028，与手动分割（0.885±0.118）相比，α=0.05，非劣效性边界为 15%。此外，下颌骨畸形较轻的患者报告的 DSC 更高（ r =0.824，P <0.05）。此外，智能自动分割仅需 6.4 秒，效率极高。
我们首次提出了一种 U-net 神经卷积网络，实现了 HFM 患者咀嚼肌的自动分割。这是对颅面疾病智能诊断和评估的一次重大尝试。
