| Presentation | 2022-09-15 Study of Detecting Oral Disease Using Oral Images Acquired by a Dermoscope and Deep Learning Yuta Suzuki, Jun Ohya, Toshihiro Okamoto, Nobuyuki Kaibuchi, Katsuhisa Sakaguchi, Kitaro Yoshimitsu, Eiji Fukuzawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we focused on a device called a dermoscope as a simple and minimally invasive diagnostic tool instead of endoscopy and staining of lesions, which are used in the diagnosis of oral diseases, and investigated a method for early detection of oral cancer. In this paper, we propose two methods: learning using Resnet50 and CPM (Chopped Picture Method), and 222 images of oral diseases taken using the USB microscope M3 manufactured by Scala Corporation, a type of dermoscope, are applied to the two methods. Consequently, the CPM method recognized oral cancer, leukoplakia, and normal areas with 94.3% accuracy. The effectiveness of the Dermoscope-based diagnostic method is confirmed, and the remaining issues are also discussed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Oral cancer / Dermoscope / Resnet / Chopped Picture Method |
| Paper # | MI2022-58 |
| Date of Issue | 2022-09-08 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2022/9/15(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Hidekata Hontani(Nagoya Inst. of Tech.) |
| Vice Chair | Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.) |
| Secretary | Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(Univ. of Hyogo) |
| Assistant | Takeshi Hara(Gifu Univ.) / Yoshito Otake(NAIST) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Study of Detecting Oral Disease Using Oral Images Acquired by a Dermoscope and Deep Learning |
| Sub Title (in English) | |
| Keyword(1) | Oral cancer |
| Keyword(2) | Dermoscope |
| Keyword(3) | Resnet |
| Keyword(4) | Chopped Picture Method |
| 1st Author's Name | Yuta Suzuki |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Jun Ohya |
| 2nd Author's Affiliation | Waseda University(Waseda Univ.) |
| 3rd Author's Name | Toshihiro Okamoto |
| 3rd Author's Affiliation | Tokyo Women's Medical Uvivercity(TWMU) |
| 4th Author's Name | Nobuyuki Kaibuchi |
| 4th Author's Affiliation | Tokyo Women's Medical Uvivercity(TWMU) |
| 5th Author's Name | Katsuhisa Sakaguchi |
| 5th Author's Affiliation | Tokyo Women's Medical Uvivercity(TWMU) |
| 6th Author's Name | Kitaro Yoshimitsu |
| 6th Author's Affiliation | Tokyo Women's Medical Uvivercity(TWMU) |
| 7th Author's Name | Eiji Fukuzawa |
| 7th Author's Affiliation | Waseda University/Yazaki Corp.(Waseda U./Yazaki) |
| Date | 2022-09-15 |
| Paper # | MI2022-58 |
| Volume (vol) | vol.122 |
| Number (no) | MI-188 |
| Page | pp.pp.39-44(MI), |
| #Pages | 6 |
| Date of Issue | 2022-09-08 (MI) |