Dental disease detection on periapical radiographs based on deep convolutional neural networks
- 2 March 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in International Journal of Computer Assisted Radiology and Surgery
- Vol. 16 (4), 649-661
- https://doi.org/10.1007/s11548-021-02319-y
Abstract
Objectives It is with a great prospect to develop an auxiliary diagnosis system for dental periapical radiographs based on deep convolutional neural networks (CNNs), and the indications and performances should be investigated. The aim of this study is to train CNNs for lesion detections on dental periapical radiographs, to evaluate performances across disease categories, severity levels, and train strategies. Methods Deep CNNs with region proposal techniques were constructed for disease detections on clinical dental periapical radiographs, including decay, periapical periodontitis, and periodontitis, leveled as mild, moderate, and severe. Four strategies were carried out to train corresponding networks with all disease and level categories (baseline), all disease categories (Net A), each disease category (Net B), and each level category (Net C) and validated by a fivefold cross-validation method afterward. Metrics, including intersection over union (IoU), precision, recall, and average precision (AP), were compared across diseases, severity levels, and train strategies by analysis of variance. Results Lesions were detected with precision and recall generally between 0.5 and 0.6 on each kind of disease. The influence of train strategy, disease category, and severity level were all statistically significant on performances (P < .001). Decay and periapical periodontitis lesions were detected with precision, recall, and AP values less than 0.25 for mild level, while 0.2–0.3 for moderate level and 0.5–0.6 for severe level. Net A performed similar to baseline (P > 0.05 for IoU, precision, and recall), while Net B and Net C performed slightly better than baseline under certain circumstances (P < 0.05), but Net C failed to predict mild decay. Conclusions The deep CNNs are able to detect diseases on clinical dental periapical radiographs. This study reveals that the CNNs prefer to detect lesions with severe levels, and it is better to train the CNNs with customized strategy for each disease.Keywords
Funding Information
- National Natural Science Foundation of China (51705006)
- Program for New Clinical Techniques and Therapies of Peking University School and Hospital of Stomatology (PKUSSNCT-19A08)
- Open fund of Shanxi Province Key Laboratory of Oral Diseases Prevention and New Materials
This publication has 35 references indexed in Scilit:
- Dental biometrics: Human identification based on teeth and dental works in bitewing radiographsPattern Recognition, 2012
- An effective classification and numbering system for dental bitewing radiographs using teeth region and contour informationPattern Recognition, 2010
- Hierarchical contour matching for dental X-ray radiographsPattern Recognition, 2008
- Automatic clinical image segmentation using pathological modeling, PCA and SVMEngineering Applications of Artificial Intelligence, 2006
- Teeth Segmentation in Digitized Dental X-Ray Films Using Mathematical MorphologyIEEE Transactions on Information Forensics and Security, 2006
- A content-based system for human identification based on bitewing dental X-ray imagesPattern Recognition, 2005
- A system for human identification from X-ray dental radiographsPattern Recognition, 2005
- Matching of dental X-ray images for human identificationPattern Recognition, 2004
- Clinical efficacy of dental radiography in the detection of dental caries and periodontal diseasesOral Surgery, Oral Medicine, Oral Pathology, 1986
- Examiner Reliability in Dental RadiographyJournal of Dental Research, 1986