Deep learning for 3D cephalometric landmarking with heterogeneous multi-center CBCT dataset.

Cephalometric analysis is critically important and common procedure prior to orthodontic treatment and orthognathic surgery. Recently, deep learning approaches have been proposed for automatic 3D cephalometric analysis based on landmarking from CBCT scans. However, these approaches have relied on uniform datasets from a single center or imaging device but without considering patient ethnicity. In addition, previous works have considered a limited number of clinically relevant cephalometric landmarks and the approaches were computationally infeasible, both impairing integration into clinical workflow. Here our aim is to analyze the clinical applicability of a light-weight deep learning neural network for fast localization of 46 clinically significant cephalometric landmarks with multi-center, multi-ethnic, and multi-device data consisting of 309 CBCT scans from Finnish and Thai patients. The localization performance of our approach resulted in the mean distance of 1.99 ± 1.55 mm for the Finnish cohort and 1.96 ± 1.25 mm for the Thai cohort. This performance turned out to be clinically significant i.e., ≤ 2 mm with 61.7% and 64.3% of the landmarks with Finnish and Thai cohorts, respectively. Furthermore, the estimated landmarks were used to measure cephalometric characteristics successfully i.e., with ≤ 2 mm or ≤ 2° error, on 85.9% of the Finnish and 74.4% of the Thai cases. Between the two patient cohorts, 33 of the landmarks and all cephalometric characteristics had no statistically significant difference (p < 0.05) measured by the Mann-Whitney U test with Benjamini-Hochberg correction. Moreover, our method is found to be computationally light, i.e., providing the predictions with the mean duration of 0.77 s and 2.27 s with single machine GPU and CPU computing, respectively. Our findings advocate for the inclusion of this method into clinical settings based on its technical feasibility and robustness across varied clinical datasets.

Reproducibility analysis of automated deep learning based localisation of mandibular canals on a temporal CBCT dataset.

Preoperative radiological identification of mandibular canals is essential for maxillofacial surgery. This study demonstrates the reproducibility of a deep learning system (DLS) by evaluating its localisation performance on 165 heterogeneous cone beam computed tomography (CBCT) scans from 72 patients in comparison to an experienced radiologist's annotations. We evaluated the performance of the DLS using the symmetric mean curve distance (SMCD), the average symmetric surface distance (ASSD), and the Dice similarity coefficient (DSC). The reproducibility of the SMCD was assessed using the within-subject coefficient of repeatability (RC). Three other experts rated the diagnostic validity twice using a 0-4 Likert scale. The reproducibility of the Likert scoring was assessed using the repeatability measure (RM). The RC of SMCD was 0.969 mm, the median (interquartile range) SMCD and ASSD were 0.643 (0.186) mm and 0.351 (0.135) mm, respectively, and the mean (standard deviation) DSC was 0.548 (0.138). The DLS performance was most affected by postoperative changes. The RM of the Likert scoring was 0.923 for the radiologist and 0.877 for the DLS. The mean (standard deviation) Likert score was 3.94 (0.27) for the radiologist and 3.84 (0.65) for the DLS. The DLS demonstrated proficient qualitative and quantitative reproducibility, temporal generalisability, and clinical validity.

Comparison of deep learning segmentation and multigrader-annotated mandibular canals of multicenter CBCT scans.

Deep learning approach has been demonstrated to automatically segment the bilateral mandibular canals from CBCT scans, yet systematic studies of its clinical and technical validation are scarce. To validate the mandibular canal localization accuracy of a deep learning system (DLS) we trained it with 982 CBCT scans and evaluated using 150 scans of five scanners from clinical workflow patients of European and Southeast Asian Institutes, annotated by four radiologists. The interobserver variability was compared to the variability between the DLS and the radiologists. In addition, the generalisation of DLS to CBCT scans from scanners not used in the training data was examined to evaluate its out-of-distribution performance. The DLS had a statistically significant difference (p < 0.001) with lower variability to the radiologists with 0.74 mm than the interobserver variability of 0.77 mm and generalised to new devices with 0.63 mm, 0.67 mm and 0.87 mm (p < 0.001). For the radiologists' consensus segmentation, used as a gold standard, the DLS showed a symmetric mean curve distance of 0.39 mm, which was statistically significantly different (p < 0.001) compared to those of the individual radiologists with values of 0.62 mm, 0.55 mm, 0.47 mm, and 0.42 mm. These results show promise towards integration of DLS into clinical workflow to reduce time-consuming and labour-intensive manual tasks in implantology.

Evaluation of voice commands for mode change in virtual reality implant planning procedure.

PURPOSE: In dental implantology, the optimal placement of dental implants is important to meet functional and aesthetic requirements. Planning dental implants in virtual three-dimensional (3D) environment is possible using virtual reality (VR) technologies. The three-dimensional stereoscopic virtual reality environment offers advantages over three-dimensional projection on a two-dimensional display. The use of voice commands in virtual reality environment to replace button presses and other simple actions frees the user's hands and eyes for other tasks. METHODS: Six dentomaxillofacial radiologists experimented using a prototype version of a three-dimensional virtual reality implant planning tool, and used two different tool selection methods, using either only button presses or also voice commands. We collected objective measurements of the results and subjective data of the participant experience to compare the two conditions. RESULTS: The tool was approved by the experts and they were able to do the multiple-implant planning satisfactorily. The radiologists liked the possibility to use the voice commands. Most of the radiologists were willing to use the tool as part of their daily work routines. CONCLUSION: The voice commands were useful, natural, and accurate for mode change, and they could be expanded to other tasks. Button presses and the voice commands should be both available and used in parallel. The input methods can be further improved based on the expert comments.

Evaluation of virtual handles for dental implant manipulation in virtual reality implant planning procedure.

PURPOSE: Many surgical complications can be prevented by careful operation planning and preoperative evaluation of the anatomical features. Virtual dental implant planning in three-dimensional stereoscopic virtual reality environment has advantages over three-dimensional projections on two-dimensional screens. In the virtual environment, the anatomical areas of the body can be assessed and interacted with in six degrees-of-freedom. Our aim was to make a preliminary evaluation of how professional users perceive the use of the virtual environment on their field. METHODS: We prepared a novel implementation of a virtual dental implant planning system and conducted a small-scale user study with four dentomaxillofacial radiologists to evaluate the usability of direct and indirect interaction in a planning task. RESULTS: We found that all four participants ranked direct interaction, planning the implant placement without handles, to be better than the indirect condition where the implant model had handles. CONCLUSION: The radiologists valued the three-dimensional environment for three-dimensional object manipulation even if usability issues of the handles affected the feel of use and the evaluation results. Direct interaction was seen as easy, accurate, and natural.

Deep Learning Method for Mandibular Canal Segmentation in Dental Cone Beam Computed Tomography Volumes.

Accurate localisation of mandibular canals in lower jaws is important in dental implantology, in which the implant position and dimensions are currently determined manually from 3D CT images by medical experts to avoid damaging the mandibular nerve inside the canal. Here we present a deep learning system for automatic localisation of the mandibular canals by applying a fully convolutional neural network segmentation on clinically diverse dataset of 637 cone beam CT volumes, with mandibular canals being coarsely annotated by radiologists, and using a dataset of 15 volumes with accurate voxel-level mandibular canal annotations for model evaluation. We show that our deep learning model, trained on the coarsely annotated volumes, localises mandibular canals of the voxel-level annotated set, highly accurately with the mean curve distance and average symmetric surface distance being 0.56 mm and 0.45 mm, respectively. These unparalleled accurate results highlight that deep learning integrated into dental implantology workflow could significantly reduce manual labour in mandibular canal annotations.