Automatic 3-Dimensional Cephalometric Landmarking via Deep Learning

Abstract

The increasing use of 3-dimensional (3D) imaging by orthodontists and maxillofacial surgeons to assess complex dentofacial deformities and plan orthognathic surgeries implies a critical need for 3D cephalometric analysis. Although promising methods were suggested to localize 3D landmarks automatically, concerns about robustness and generalizability restrain their clinical use. Consequently, highly trained operators remain needed to perform manual landmarking. In this retrospective diagnostic study, we aimed to train and evaluate a deep learning (DL) pipeline based on SpatialConfiguration-Net for automatic localization of 3D cephalometric landmarks on computed tomography (CT) scans. A retrospective sample of consecutive presurgical CT scans was randomly distributed between a training/validation set ( n = 160) and a test set ( n = 38). The reference data consisted of 33 landmarks, manually localized once by 1 operator( n = 178) or twice by 3 operators ( n = 20, test set only). After inference on the test set, 1 CT scan showed “very low” confidence level predictions; we excluded it from the overall analysis but still assessed and discussed the corresponding results. The model performance was evaluated by comparing the predictions with the reference data; the outcome set included localization accuracy, cephalometric measurements, and comparison to manual landmarking reproducibility. On the hold-out test set, the mean localization error was 1.0 ± 1.3 mm, while success detection rates for 2.0, 2.5, and 3.0 mm were 90.4%, 93.6%, and 95.4%, respectively. Mean errors were −0.3 ± 1.3° and −0.1 ± 0.7 mm for angular and linear measurements, respectively. When compared to manual reproducibility, the measurements were within the Bland–Altman 95% limits of agreement for 91.9% and 71.8% of skeletal and dentoalveolar variables, respectively. To conclude, while our DL method still requires improvement, it provided highly accurate 3D landmark localization on a challenging test set, with a reliability for skeletal evaluation on par with what clinicians obtain.

Using a New Deep Learning Method for 3D Cephalometry in Patients With Cleft Lip and Palate

“…The data showed that our method was more accurate in identifying the mandibular parts than previous studies. 5,11,12 However, the error of our points was similar to or even better than theirs. In addition, the manual measurements process took 15 minutes, but we only needed 16 seconds.…”

“…Three-dimensional CT-based cephalometric imaging has recently been widely used to comprehensively evaluate carried out relying on manual measurements, which is time-consuming, labor-intensive, and relies heavily on the operator’s judgment 13 . In recent years, some scholars have begun to carry out deep learning algorithms based on fully automatic 3D cephalometric marking points, achieving relatively good accuracy and good results 5–12 . By automating measurement, time, and effort can be significantly reduced, lowering the burden on clinicians.…”

Three-Dimensional Cranio-Facial Landmark Detection in Series of CT Slices, Using Multi-Phased Regression Networks

“…It is very versatile. Some attempts to utilize deep learning for automatic 3D landmark prediction have been reported [45,49,51,58,59].…”

“…A knowledge-based method [43] was reported in 2015. Some kinds of learning based methods [44][45][46][47][48][49][50][51] have been reported. In our experience with 2D cephalograms [27,28], multi-phased deep learning system was able to predict coordinate values in high precision.…”

Data-Driven Dental, Oral, and Craniofacial Analytics: Here to Stay

“…To use such data fully and appropriately, there has been a concomitant explosion in data analytics, notably including the application of AI. This special issue highlights the application of AI for developing clinically relevant tools, for example, evaluating factors contributing to the long-term survival of root canal treatments using data from the National Dental Practice Based Research Network ( Thyvalikakath et al 2022 ), the diagnosis of oral squamous cell carcinoma ( Yanget al 2022 ), automated 3-dimensional (3D) cephalometric landmarking ( Dot et al 2022 ), the prediction of 3D postorthodontia facial changes in adults ( Park et al 2022 ), the predictive classification of tooth removal procedures ( de Graaf et al 2022 ), and the association of components of computer-aided design/computer-aided manufacturing resins with clinical outcomes ( Li et al 2022 ).…”