Bao Jiahao, Tan Zongcai, Sun Yifeng, Xu Xinyu, Liu Huazhen, Cui Weiyi, Yang Yang, Cheng Mengjia, Wang Yiming, Ku Congshuang, Ho Yuen Ka, Zhu Jiayi, Fan Linfeng, Qian Dahong, Shen Shunyao, Wen Yaofeng, Yu Hongbo
1 Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, College of Stomatology, Shanghai Jiao Tong University, National Center for Stomatology, National Clinical Research Center for Oral Diseases, Shanghai Research Institute of Stomatology, Shanghai Key Laboratory of Stomatology, Shanghai, China.
Hamlyn Centre for Robotic Surgery, Institute of Global Health Innovation, Imperial College London, London, United Kingdom.
Front Bioeng Biotechnol. 2025 May 8;13:1580502. doi: 10.3389/fbioe.2025.1580502. eCollection 2025.
Accurate segmentation of craniomaxillofacial (CMF) structures and individual teeth is essential for advancing computer-assisted CMF surgery. This study developed CMF-ELSeg, a novel fully automatic multi-structure segmentation model based on deep ensemble learning.
A total of 143 CMF computed tomography (CT) scans were retrospectively collected and manually annotated by experts for model training and validation. Three 3D U-Net-based deep learning models (V-Net, nnU-Net, and 3D UX-Net) were benchmarked. CMF-ELSeg employed a coarse-to-fine cascaded architecture and an ensemble approach to integrate the strengths of these models. Segmentation performance was evaluated using Dice score and Intersection over Union (IoU) by comparing model predictions to ground truth annotations. Clinical feasibility was assessed through qualitative and quantitative analyses.
In coarse segmentation of the upper skull, mandible, cervical vertebra, and pharyngeal cavity, 3D UX-Net and nnU-Net achieved Dice scores above 0.96 and IoU above 0.93. For fine segmentation and classification of individual teeth, the cascaded 3D UX-Net performed best. CMF-ELSeg improved Dice scores by 3%-5% over individual models for facial soft tissue, upper skull, mandible, cervical vertebra, and pharyngeal cavity segmentation, and maintained high accuracy Dice > 0.94 for most teeth. Clinical evaluation confirmed that CMF-ELSeg performed reliably in patients with skeletal malocclusion, fractures, and fibrous dysplasia.
CMF-ELSeg provides high-precision segmentation of CMF structures and teeth by leveraging multiple models, serving as a practical tool for clinical applications and enhancing patient-specific treatment planning in CMF surgery.
准确分割颅颌面（CMF）结构和单个牙齿对于推进计算机辅助CMF手术至关重要。本研究开发了CMF-ELSeg，这是一种基于深度集成学习的新型全自动多结构分割模型。
回顾性收集了143例CMF计算机断层扫描（CT）图像，并由专家进行手动标注，用于模型训练和验证。对三个基于3D U-Net的深度学习模型（V-Net、nnU-Net和3D UX-Net）进行了基准测试。CMF-ELSeg采用了从粗到细的级联架构和集成方法来整合这些模型的优势。通过将模型预测与地面真值标注进行比较，使用Dice分数和交并比（IoU）评估分割性能。通过定性和定量分析评估临床可行性。
在上颅骨、下颌骨、颈椎和咽腔的粗分割中，3D UX-Net和nnU-Net的Dice分数高于0.96，IoU高于0.93。对于单个牙齿的精细分割和分类，级联3D UX-Net表现最佳。CMF-ELSeg在面部软组织、上颅骨、下颌骨、颈椎和咽腔分割方面比单个模型的Dice分数提高了3%-5%，并且大多数牙齿的Dice分数保持在>0.94的高精度。临床评估证实，CMF-ELSeg在患有骨骼错牙合、骨折和纤维发育不良的患者中表现可靠。
CMF-ELSeg通过利用多个模型提供了CMF结构和牙齿的高精度分割，作为临床应用的实用工具，并增强了CMF手术中针对患者的治疗计划。
