Medical image database system using computer assisted detection (CAD) system

2016 Fiscal Year Final Research Report

• Project/Area Number: 26293402
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Pathobiological dentistry/Dental radiology
• Research Institution: Asahi University
• Principal Investigator: Katsumta Akitshi 朝日大学, 歯学部, 教授 (30195143)
• Co-Investigator(Kenkyū-buntansha): 藤田 廣志 岐阜大学, 医学(系)研究科(研究院), 教授 (10124033)
• Co-Investigator(Renkei-kenkyūsha): HARA Takeshi 岐阜大学, 医学(系)研究科, 准教授 (10283285) ; MATSUOKA Masato 朝日大学, 歯学部, 講師 (20199772) ; IIDA Yukihiro 朝日大学, 歯学部, 講師 (60350873) ; ARIJI Eiichirou 愛知学院大学, 歯学部, 教授 (00150459) ; ARIJI Yoshiko 愛知学院大学, 歯学部, 准教授 (60232063) ; MURAMATSU Chisako 岐阜大学, 医学(系)研究科, 准教授 (80509422)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: コンピュータ支援診断・検出 / パノラマX線撮影 / 歯科用CT

Outline of Final Research Achievements

We developed computer programs that scans dental panoramic radiographs and dental cone-beam CT images to screen possible osteoporosis and to detect the type of tooth.
These programs were evaluated using clinical images in a certified dental image library that established for this project.
The diagnostic sensitivity to detect possible osteoporosis was 94.5%, and the specificity was 94.9%. An algorism using deep convolutional neural network enabled to classified the type tooth correctly in more than 90% of cases.

Free Research Field

歯科放射線学