Tooth Localization using YOLOv3 for Dental Diagnosis on Panoramic Radiographs

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2022/05/01

タイトル(英語): Tooth Localization using YOLOv3 for Dental Diagnosis on Panoramic Radiographs

著者名: Toan Huy Bui (Course of Science and Technology, Graduate School of Science and Technology, Tokai University), Kazuhiko Hamamoto (School of Information and Telecommunication Engineering, Tokai University), May Phu Paing (School of Engineering, King Mongkut

著者名(英語): Toan Huy Bui (Course of Science and Technology, Graduate School of Science and Technology, Tokai University), Kazuhiko Hamamoto (School of Information and Telecommunication Engineering, Tokai University), May Phu Paing (School of Engineering, King Mongkut's Institute of Technology Ladkrabang)

キーワード: panoramic radiograph，medical image processing，deep learning，object detection，computer-aided diagnosis

要約(英語): Oral health is one of most major concerns that affect the life quality of billions of people around the world. Diagnosis treatment usually takes time due to the lack of doctors compared to a huge number of patients. Many researchers proposed methods to make an early disease detection for patients to assist doctors using computer aid diagnosis (CAD). However, most previous methods are not end-to-end methods and still require human involvement. The biggest challenge is that most researchers do not provide a good tooth detection technique before diagnosis. Therefore, the main objective, that builds a system to assist doctors, remains unaccomplished or just fairly successful. This paper proposed a detection method to localize the tooth using the Yolov3 model as a base network in the dental panoramic radiograph. The method consists of two main parts: image preprocessing and tooth localization. Firstly, because deep learning requires a big dataset, the original image is applied augmentation technique to improve the size of the dataset as well as diversity. Then, each image is resized to fit the input layer of the network; however, to prevent the information loss and boost the performance, we keep the original ratio of the images and change the ratio of the input layer in the model that can fit the image ratio. Next, we feed images into Yolov3, which is specially modified to fit the problem, for training. We add more detection heads into the backbone and concatenate the previous head detection's result with a proper layer to produce a more preeminent result. The final assessment shows an impressive result that the method reaches 95.58% and 94.90% for precision and recall, respectively. As a result, our proposed method is more reliable and practical in the tooth localization field, as well as helpful to reduce the doctor’s effort.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.142 No.5 （2022） 特集：医用・生体工学関連技術

本誌掲載ページ: 557-562 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/142/5/142_557/_article/-char/ja/