Facial and mandibular landmark tracking with habitual head posture estimation using linear and fiducial markers.

This study compared the accuracy of facial landmark measurements using deep learning-based fiducial marker (FM) and arbitrary width reference (AWR) approaches. It quantitatively analysed mandibular hard and soft tissue lateral excursions and head tilting from consumer camera footage of 37 participants. A custom deep learning system recognised facial landmarks for measuring head tilt and mandibular lateral excursions. Circular fiducial markers (FM) and inter-zygion measurements (AWR) were validated against physical measurements using electrognathography and electronic rulers. Results showed notable differences in lower and mid-face estimations for both FM and AWR compared to physical measurements. The study also demonstrated the comparability of both approaches in assessing lateral movement, though fiducial markers exhibited variability in mid-face and lower face parameter assessments. Regardless of the technique applied, hard tissue movement was typically seen to be 30% less than soft tissue among the participants. Additionally, a significant number of participants consistently displayed a 5 to 10° head tilt.

Experimental validation of computer-vision methods for the successful detection of endodontic treatment obturation and progression from noisy radiographs.

PURPOSE: (1) To evaluate the effects of denoising and data balancing on deep learning to detect endodontic treatment outcomes from radiographs. (2) To develop and train a deep-learning model and classifier to predict obturation quality from radiomics. METHODS: The study conformed to the STARD 2015 and MI-CLAIMS 2021 guidelines. 250 deidentified dental radiographs were collected and augmented to produce 2226 images. The dataset was classified according to endodontic treatment outcomes following a set of customized criteria. The dataset was denoised and balanced, and processed with YOLOv5s, YOLOv5x, and YOLOv7 models of real-time deep-learning computer vision. Diagnostic test parameters such as sensitivity (Sn), specificity (Sp), accuracy (Ac), precision, recall, mean average precision (mAP), and confidence were evaluated. RESULTS: Overall accuracy for all the deep-learning models was above 85%. Imbalanced datasets with noise removal led to YOLOv5x's prediction accuracy to drop to 72%, while balancing and noise removal led to all three models performing at over 95% accuracy. mAP saw an improvement from 52 to 92% following balancing and denoising. CONCLUSION: The current study of computer vision applied to radiomic datasets successfully classified endodontic treatment obturation and mishaps according to a custom progressive classification system and serves as a foundation to larger research on the subject matter.