OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, KU Leuven & Oral and Maxillofacial Surgery, University Hospitals Leuven, Kapucijnenvoer33, BE-3000 Leuven, Belgium.
OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, KU Leuven & Oral and Maxillofacial Surgery, University Hospitals Leuven, Kapucijnenvoer33, BE-3000 Leuven, Belgium; Department of Oral Medicine, Faculty of Dentistry, Mansoura University, 35516 Mansoura, Dakahlia, Egypt.
J Dent. 2022 Sep;124:104238. doi: 10.1016/j.jdent.2022.104238. Epub 2022 Jul 21.
The present study investigated the accuracy, consistency, and time-efficiency of a novel deep convolutional neural network (CNN) based model for the automated maxillofacial bone segmentation from cone beam computed tomography (CBCT) images.
A dataset of 144 scans was acquired from two CBCT devices and randomly divided into three subsets: training set (n = 110), validation set (n = 10) and testing set (n = 24). A three-dimensional (3D) U-Net (CNN) model was developed, and the achieved automated segmentation was compared with a manual approach.
The average time required for automated segmentation was 39.1 s with a 204-fold decrease in time consumption compared to manual segmentation (132.7 min). The model was highly accurate for identification of the bony structures of the anatomical region of interest with a dice similarity coefficient (DSC) of 92.6%. Additionally, the fully deterministic nature of the CNN model was able to provide 100% consistency without any variability. The inter-observer consistency for expert-based minor correction of the automated segmentation observed an excellent DSC of 99.7%.
The proposed CNN model provided a time-efficient, accurate, and consistent CBCT-based automated segmentation of the maxillofacial complex.
Automated segmentation of the maxillofacial complex could act as an alternative to the conventional segmentation techniques for improving the efficiency of the digital workflows. This approach could deliver accurate and ready-to-print3D models, essential to patient-specific digital treatment planning for orthodontics, maxillofacial surgery, and implant dentistry.
本研究旨在评估一种新型基于深度卷积神经网络（CNN）的模型，用于从锥形束 CT（CBCT）图像中自动分割颌面骨的准确性、一致性和效率。
从两台 CBCT 设备中获取了 144 个扫描的数据集，并将其随机分为三个子集：训练集（n=110）、验证集（n=10）和测试集（n=24）。开发了一个三维（3D）U-Net（CNN）模型，并将自动分割的结果与手动分割的结果进行了比较。
自动化分割的平均时间为 39.1 秒，与手动分割相比，时间消耗减少了 204 倍（132.7 分钟）。该模型对感兴趣的解剖区域的骨结构识别非常准确，其 Dice 相似系数（DSC）为 92.6%。此外，CNN 模型的完全确定性性质能够提供 100%的一致性，没有任何可变性。专家基于对自动分割进行少量修正的观察者间一致性观察到了极好的 DSC（99.7%）。
提出的 CNN 模型提供了一种基于 CBCT 的颌面复合体的高效、准确和一致的自动分割方法。
颌面复合体的自动分割可以替代传统的分割技术，提高数字化工作流程的效率。这种方法可以提供准确且可直接打印的 3D 模型，这对于正畸、颌面外科和种植牙的患者特定数字化治疗计划至关重要。
