A diagnostic study on the detection of occlusal caries from a clinical photograph using a deep learning algorithm can be presented on the a hundred and first General Session of the IADR, which can be held at the side of the ninth Meeting of the Latin American Region and the twelfth World Congress on Preventive Dentistry on June 21-24, 2023, in Bogotá, Colombia.
The Interactive Talk presentation, “Automated Detection of Occlusal Caries Using Deep Learning Algorithm,” will happen on Saturday, June 24 at 4:25 p.m. Colombia Time (UTC-05:00) throughout the “Prevalence of Health Conditions and Risk Aspects” session.
The study by Chukwuebuka Elozona Ogwo of Temple University, Philadelphia, PA, USA sought to find out the accuracy, precision, and sensitivity of the YOLOv7 object detection algorithm in occlusal caries detection from clinical photographs and (2) develop software for occlusal caries detection.
Only consenting adults (>=18 years old) with everlasting dentition receiving care on the Temple University Kornberg School of Dentistry were included within the study. 300 intraoral photos of the occlusal surfaces of each mandibular and maxillary arches were collected by 4th-year dental students using the Coolpix L840 cameras. The pictures were annotated using Roboflow V4. After data preprocessing and augmentation, 845 images were generated and randomly split into three sets: training, validation, and testing – 70:20:10, respectively.
The info was then analyzed 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 ultimate algorithm was used to create software on Flask and deployed it on Heroku.
The algorithm resulted in 79.5% precision, 83% recall, an 81.2% F1-score, and 80% [email protected] rating within the detection of occlusal caries on a clinical photograph of each the mandibular and maxillary arches. The study yielded a promising results of AI in automating the detection of the carious lesion from a clinical photograph. When deployed as a phone app, it might function a vital tool for teledentistry and improve access to care.
Source:
International Association for Dental Research