Takumi Morishita1, Chisako Muramatsu2, Yuta Seino3, Ryo Takahashi4, Tatsuro Hayashi4, Wataru Nishiyama5, Xiangrong Zhou3, Takeshi Hara3, Akitoshi Katsumata5, Hiroshi Fujita3. 1. Gifu University, Graduate School of Natural Science and Technology, Department of Intelligence Science and Engineering, Gifu, Japan. 2. Shiga University, Faculty of Data Science, Hikone, Japan. 3. Gifu University, Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu, Japan. 4. Media Co., Ltd, Tokyo, Japan. 5. Asahi University, School of Dentistry, Department of Oral Radiology, Mizuho, Japan.
Abstract
Purpose: The purpose of our study was to analyze dental panoramic radiographs and contribute to dentists' diagnosis by automatically extracting the information necessary for reading them. As the initial step, we detected teeth and classified their tooth types in this study. Approach: We propose single-shot multibox detector (SSD) networks with a side branch for 1-class detection without distinguishing the tooth type and for 16-class detection (i.e., the central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, and third molar, distinguished by the upper and lower jaws). In addition, post-processing was conducted to integrate the results of the two networks and categorize them into 32 classes, differentiating between the left and right teeth. The proposed method was applied to 950 dental panoramic radiographs obtained at multiple facilities, including a university hospital and dental clinics. Results: The recognition performance of the SSD with a side branch was better than that of the original SSD. In addition, the detection rate was improved by the integration process. As a result, the detection rate was 99.03%, the number of false detections was 0.29 per image, and the classification rate was 96.79% for 32 tooth types. Conclusions: We propose a method for tooth recognition using object detection and post-processing. The results show the effectiveness of network branching on the recognition performance and the usefulness of post-processing for neural network output.
Purpose: The purpose of our study was to analyze dental panoramic radiographs and contribute to dentists' diagnosis by automatically extracting the information necessary for reading them. As the initial step, we detected teeth and classified their tooth types in this study. Approach: We propose single-shot multibox detector (SSD) networks with a side branch for 1-class detection without distinguishing the tooth type and for 16-class detection (i.e., the central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, and third molar, distinguished by the upper and lower jaws). In addition, post-processing was conducted to integrate the results of the two networks and categorize them into 32 classes, differentiating between the left and right teeth. The proposed method was applied to 950 dental panoramic radiographs obtained at multiple facilities, including a university hospital and dental clinics. Results: The recognition performance of the SSD with a side branch was better than that of the original SSD. In addition, the detection rate was improved by the integration process. As a result, the detection rate was 99.03%, the number of false detections was 0.29 per image, and the classification rate was 96.79% for 32 tooth types. Conclusions: We propose a method for tooth recognition using object detection and post-processing. The results show the effectiveness of network branching on the recognition performance and the usefulness of post-processing for neural network output.
Authors: Dmitry V Tuzoff; Lyudmila N Tuzova; Michael M Bornstein; Alexey S Krasnov; Max A Kharchenko; Sergey I Nikolenko; Mikhail M Sveshnikov; Georgiy B Bednenko Journal: Dentomaxillofac Radiol Date: 2019-03-05 Impact factor: 2.419