Multi-model Deep Learning approach for segmentation of teeth and periapical lesions on Pantomographs

Abstract

IntroductionThe fields of medicine and dentistry are beginning to integrate Artificial Intelligence (AI) in diagnostics. This may reduce subjectivity and improved accuracy of diagnoses and treatment planning. Current evidence on pathology detection on Orthopantomograms (OPGs) indicates the presence or absence of disease in the entire radiographic image, with little evidence of relation of periapical pathology to the causative tooth. ObjectiveTo develop a Deep Learning (DL) AI model for the segmentation of periapical pathology and its relation to teeth on OPGs. Methodology250 OPGs were manually annotated by subject experts to lay down the ground truth for training AI algorithms on segmentation of periapical pathology. Two approaches were used for lesion detection: multi-models 1 and 2, utilizing U-net and Mask RCNN algorithms, respectively. The resulting segmented lesions generated on the testing dataset were superimposed with results of teeth segmentation and numbering algorithms trained separately to relate lesions to causative teeth. Hence, both multi-model approaches related periapical pathology to the causative teeth on OPG. ResultsThe performance metrics of lesion segmentation carried out by U-net are as follows: accuracy=98.1%, precision=84.5%, re-call=80.3%, F-1 score=82.2%, dice index=75.2%, and IoU=67.6%. Mask RCNN carried out lesion segmentation with an accuracy of 46.7%, precision of 80.6%, recall of 55%, and F-1 score of 63.1%. ConclusionIn this study, the multi-model approach successfully related periapical pathology to the causative tooth on OPGs. However, U-net outperformed Mask RCNN in the tasks performed, suggesting that U-net will remain standard for medical image segmentation tasks. Further training of the models on other findings and an increased number of images will lead to automation of the dental diagnostic workflow. Clinical Relevance: The application of AI for detection of periapical disease on OPG with the causative tooth identified directs a clinician towards further area-specific examination to confirm the presence and extent of disease.