Ayidh Alqahtani Khalid, Jacobs Reinhilde, Smolders Andreas, Van Gerven Adriaan, Willems Holger, Shujaat Sohaib, Shaheen Eman
Department of Imaging and Pathology, Faculty of Medicine, KU Leuven and Department of Oral and Maxillofacial Surgery, OMFS IMPATH Research Group, University Hospitals Leuven, Leuven, Belgium.
Department of Oral and Maxillofacial Surgery and Diagnostic Sciences, College of Dentistry, Sattam bin Abdulaziz University, AlKharj, Saudi Arabia.
Eur J Orthod. 2023 Mar 31;45(2):169-174. doi: 10.1093/ejo/cjac047.
Tooth segmentation and classification from cone-beam computed tomography (CBCT) is a prerequisite for diagnosis and treatment planning in the majority of digital dental workflows. However, an accurate and efficient segmentation of teeth in the presence of metal artefacts still remains a challenge. Therefore, the following study aimed to validate an automated deep convolutional neural network (CNN)-based tool for the segmentation and classification of teeth with orthodontic brackets on CBCT images.
A total of 215 CBCT scans (1780 teeth) were retrospectively collected, consisting of pre- and post-operative images of the patients who underwent combined orthodontic and orthognathic surgical treatment. All the scans were acquired with NewTom CBCT device. A complete dentition with orthodontic brackets and high-quality images were included. The dataset were randomly divided into three subsets with random allocation of all 32 tooth classes: training set (140 CBCT scans-400 teeth), validation set (35 CBCT scans-100 teeth), and test set (pre-operative: 25, post-operative: 15 = 40 CBCT scans-1280 teeth). A multiclass CNN-based tool was developed and its performance was assessed for automated segmentation and classification of teeth with brackets by comparison with a ground truth.
The CNN model took 13.7 ± 1.2 s for the segmentation and classification of all the teeth on a single CBCT image. Overall, the segmentation performance was excellent with a high intersection over union (IoU) of 0.99. Anterior teeth showed a significantly lower IoU (P < 0.05) compared to premolar and molar teeth. The dice similarity coefficient score of anterior (0.99 ± 0.02) and premolar teeth (0.99 ± 0.10) in the pre-operative group was comparable to the post-operative group. The classification of teeth to the correct 32 classes had a high recall rate (99.9%) and precision (99%).
The proposed CNN model outperformed other state-of-the-art algorithms in terms of accuracy and efficiency. It could act as a viable alternative for automatic segmentation and classification of teeth with brackets.
The proposed method could simplify the existing digital workflows of orthodontics, orthognathic surgery, restorative dentistry, and dental implantology by offering an accurate and efficient automated segmentation approach to clinicians, hence further enhancing the treatment predictability and outcomes.
在大多数数字化牙科工作流程中，从锥束计算机断层扫描（CBCT）中进行牙齿分割和分类是诊断和治疗计划的前提条件。然而，在存在金属伪影的情况下准确、高效地分割牙齿仍然是一个挑战。因此，以下研究旨在验证一种基于深度卷积神经网络（CNN）的自动化工具，用于在CBCT图像上对带有正畸托槽的牙齿进行分割和分类。
回顾性收集了总共215例CBCT扫描（1780颗牙齿），包括接受正畸和正颌联合手术治疗患者的术前和术后图像。所有扫描均使用NewTom CBCT设备获取。纳入了带有正畸托槽的完整牙列和高质量图像。数据集被随机分为三个子集，所有32个牙类随机分配：训练集（140例CBCT扫描 - 400颗牙齿）、验证集（35例CBCT扫描 - 100颗牙齿）和测试集（术前：25例，术后：15例 = 40例CBCT扫描 - 1280颗牙齿）。开发了一种基于多类CNN的工具，并通过与真实情况比较来评估其对带有托槽牙齿的自动分割和分类性能。
CNN模型在单张CBCT图像上对所有牙齿进行分割和分类需要13.7 ± 1.2秒。总体而言，分割性能出色，交并比（IoU）高达0.99。与前磨牙和磨牙相比，前牙的IoU显著更低（P < 0.05）。术前组前牙（0.99 ± 0.02）和前磨牙（0.99 ± 0.10）的骰子相似系数得分与术后组相当。牙齿正确分类到32个类别中的召回率很高（99.9%），精度也很高（99%）。
所提出的CNN模型在准确性和效率方面优于其他现有算法。它可以作为对带有托槽牙齿进行自动分割和分类的可行替代方法。
所提出的方法可以通过为临床医生提供准确、高效的自动分割方法，简化正畸、正颌手术、修复牙科和牙种植学现有的数字化工作流程，从而进一步提高治疗的可预测性和效果。
