Study explores the use of deep learning algorithm to detect occlusal caries

deep learning algorithm to detect occlusal caries
Photo: milosljubicic 123rf

A diagnostic study on the detection of occlusal caries from a clinical photograph using a deep learning algorithm was presented at the recent 101st General Session of the IADR, held in conjunction with the 9th Meeting of the Latin American Region and the 12th World Congress on Preventive Dentistry on 21-24 June, 2023, in Bogotá, Colombia.

The study by a team at Temple University, in Pennsylvania, USA, sought to determine the accuracy, precision, and sensitivity of the YOLOv7 object detection algorithm in occlusal caries detection from clinical photographs and develop software for occlusal caries detection.

Only consenting adults with permanent dentition receiving care were included in the study. Three hundred intraoral photos of the occlusal surfaces of both mandibular and maxillary arches were collected using the Coolpix L840 cameras. The images were annotated using Roboflow V4. After data preprocessing and augmentation, 845 images were generated and randomly split into three sets: training, validation, and testing respectively.

The data was then analysed using the YOLO v7 at 100 epochs, with a batch size of 1 and image size of 1280×640. The algorithm performance metrics were mean average precision (mAP), recall (sensitivity), and precision (positive predictive value). The final algorithm was used to create software on Flask which was deployed on Heroku.

The algorithm resulted in 79.5 per cent precision, 83 per cent recall, an 81.2 per cent F1-score, and 80 per cent mAP@0.5 score in the detection of occlusal caries on a clinical photograph of both the mandibular and maxillary arches.

The study yielded a promising result of AI in automating the detection of the carious lesion from a clinical photograph. When deployed as a phone app, it may serve as an important tool for teledentistry and improve access to care.

Previous articleADA backs senate report to plug holes in public dental services
Next articleADA NSW celebrates landmark 95th anniversary 


Please enter your comment!
Please enter your name here