Angelalign Technology Inc., No. 500 Zhengli Road, Yangpu District, Shanghai, 200433, China.
State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases & West China Hospital of Stomatology, Sichuan University, Chengdu, 610041, China.
Clin Oral Investig. 2024 Nov 28;28(12):663. doi: 10.1007/s00784-024-06061-y.
This study developed and evaluated a two-stage deep learning-based system for automatic segmentation of mandibular cortical bone, mandibular cancellous bone, maxillary cortical bone and maxillary cancellous bone on cone beam computed tomography (CBCT) images.
A dataset containing 155 CBCT scans acquired with different parameters was obtained. A two-stage deep learning-based system was developed for automatically segmenting jawbone structures. The Dice similarity coefficient (DSC) and average symmetric surface distance (ASSD) were used to assess the segmentation performance of the system by comparing the automatic segmentation results with the ground truth. The impact of dental and quality abnormalities on segmentation performance was analysed, and a comparison of automatic segmentation (AS) with manually refined segmentation (MRS) was reported.
The system achieved promising segmentation performance, with average DSC values of 93.69%, 96.83%, 86.14% and 95.57% and average ASSD values of 0.13 mm, 0.16 mm, 0.29 mm and 0.41 mm for the mandibular cortical bone, mandibular cancellous bone, maxillary cortical bone and maxillary cancellous bone, respectively. Quality abnormalities had a negative impact on segmentation performance. The performance metrics (DSCs > 98.8% and ASSDs < 0.1 mm) indicated high overlap between the AS and MRS.
The proposed system offers an accurate and time-efficient method for segmenting jawbone structures on CBCT images.
Automatically segmenting jawbone structures is essential in most digital dental workflows. The proposed system has considerable potential for application in digital clinical workflows to assist dentists in making more accurate diagnoses and developing patient-specific treatment plans.
本研究开发并评估了一种基于两阶段深度学习的方法，用于在锥形束 CT（CBCT）图像上自动分割下颌皮质骨、下颌松质骨、上颌皮质骨和上颌松质骨。
获得了包含 155 个不同参数采集的 CBCT 扫描的数据集。开发了一种基于两阶段深度学习的系统，用于自动分割颌骨结构。通过将自动分割结果与真实情况进行比较，使用 Dice 相似系数（DSC）和平均对称表面距离（ASSD）评估系统的分割性能。分析了牙齿和质量异常对分割性能的影响，并报告了自动分割（AS）与手动细化分割（MRS）的比较。
该系统实现了有前景的分割性能，平均 DSC 值分别为 93.69%、96.83%、86.14%和 95.57%，平均 ASSD 值分别为 0.13mm、0.16mm、0.29mm 和 0.41mm，用于下颌皮质骨、下颌松质骨、上颌皮质骨和上颌松质骨。质量异常对分割性能有负面影响。性能指标（DSC>98.8%和 ASSD<0.1mm）表明 AS 和 MRS 之间具有高度的重叠。
所提出的系统为 CBCT 图像上的颌骨结构分割提供了一种准确且高效的方法。
自动分割颌骨结构是大多数数字牙科工作流程的基础。该系统在数字临床工作流程中有很大的应用潜力，可以帮助牙医做出更准确的诊断并制定针对患者的治疗计划。
