Machine learning in the field of dentistry

• Main Author: Lew, Chee Kian
• Other Authors: Mohammed Yakoob Siyal
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/167637
• Institution: Nanyang Technological University

Deep learning has been used to automate clinical operations because dental data is becoming more and more readily available. Due to the rising need for automated diagnostic imaging, object detection utilizing deep learning approaches has become more common in dentistry. This study aims to detect dental anomalies in categories such as inflammation, developmental and benign cyst neoplasia using a convolutional neural network. 304 dental panoramic images were used in this study. Images were sampled from Tufts Dental Database, and re annotated with Roboflow as it is a faster annotation tool to use. Detectron2’s Mask R-CNN model has been chosen as it is a state-of-the-art object detection model and has a short training time while also showing a good performance in baseline comparisons in COCO object detection contest. The model was able to detect the three classes chosen in the training set, however it struggles with the validation set.