Individual tooth detection and identification from dental panoramic X-ray images via point-wise localization and distance regularization

• Published in: Artificial intelligence in medicine Vol. 111; p. 101996
• Main Authors: Chung, Minyoung, Lee, Jusang, Park, Sanguk, Lee, Minkyung, Lee, Chae Eun, Lee, Jeongjin, Shin, Yeong-Gil
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2021
• Subjects: Distance regularized point regression; Individual tooth detection; Panoramic X-ray image detection; Point-wise object detection; Tooth identification; Distance regularized point regression; Individual tooth detection; Panoramic X-ray image detection; Point-wise object detection; Tooth identification
• ISSN: 0933-3657; 1873-2860
• DOI: 10.1016/j.artmed.2020.101996

•Integration of a point-based detection method and fixed 32-point regression in a cascaded fashion.•The proposed method does not require any additional classification methods for tooth identification.•Introduction of a novel distance regularization loss between neighboring teeth to improve the regression.•Multitask training of box parameters and the marginal offset vector of the center point to improve the accuracy of detection. Dental panoramic X-ray imaging is a popular diagnostic method owing to its very small dose of radiation. For an automated computer-aided diagnosis system in dental clinics, automatic detection and identification of individual teeth from panoramic X-ray images are critical prerequisites. In this study, we propose a point-wise tooth localization neural network by introducing a spatial distance regularization loss. The proposed network initially performs center point regression for all the anatomical teeth (i.e., 32 points), which automatically identifies each tooth. A novel distance regularization penalty is employed on the 32 points by considering L2 regularization loss of Laplacian on spatial distances. Subsequently, teeth boxes are individually localized using a multitask neural network on a patch basis. A multitask offset training is employed on the final output to improve the localization accuracy. Our method successfully localizes not only the existing teeth but also missing teeth; consequently, highly accurate detection and identification are achieved. The experimental results demonstrate that the proposed algorithm outperforms state-of-the-art approaches by increasing the average precision of teeth detection by 15.71 % compared to the best performing method. The accuracy of identification achieved a precision of 0.997 and recall value of 0.972. Moreover, the proposed network does not require any additional identification algorithm owing to the preceding regression of the fixed 32 points regardless of the existence of the teeth.