Automated Detection And Classification Of Apical Periodontitis With Yolo Algorithms

Abstract

To develop a deep learning (DL) model based on convolutional neural network (CNN) architecture, for assessing the periapical health/disease of teeth, that would support decision-making during endodontic treatment. The protocol for this retrospective study was approved by the IRB. Periapical digital radiographs were collected, de-identified and scored (1-5) according to the periapical index by Ørstavik et al., 1986. A balanced dataset of periapical digital radiographs were labelled using Roboflow Annotate software. Data (n=5000 images) were pre-processed before splitting into training (68%), validation (19.5%), and testing (12.5%) groups. DL models were trained using the nano, small and medium versions of You Only Look Once (YOLOv8), (YOLOv11) and (YOLOv12) CNN architectures. Performance metrics included F1 score, Precision, Recall, and mean average precision (mAP50) of the 5 classes. Furthermore, the confusion matrix across the 5 classes and the background were used in the statistical evaluation of the results. The YOLOv11m displayed the best performance of all models showing a balance between accuracy (mAP50 of 84%) and computational requirements. The DL algorithms used showed a high success in inference of the PAI on unseen radiographs of different origins, and its use would offer better clinician- and patient-based outcomes.