| Presentation | 2023-09-08 A Study on Identifying Gender Differences Using Deep Learning from Retinal Fundus Images Shota Tsutsui, Ichiro Maruko, Moeko Kawai, Yoichi Kato, Jun Ohya, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Previous studies show that a properly designed and trained deep learning algorithm is capable to identify the gender of a person from the person's fundus images although the obvious difference in male and female fundus images is unknown. In this paper, we extend LIME, one of the Explainable AI, to RGB channels, and consider the regions (obtained by segmentation into super-pixels) and colors as a basis for deep learning classification. The results of Mann-Whitney's U test on the color of the classification basis area suggested that there were slight color differences by gender in certain areas of the fundus image (e.g., optic disc), similar to the results shown by LIME extended to RGB. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Explainable AI / Retina fundus images / Deep learning / LIME |
| Paper # | MI2023-17 |
| Date of Issue | 2023-09-01 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2023/9/8(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Ryo Haraguchi(Univ. of Hyogo) |
| Vice Chair | Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.) |
| Secretary | Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(NAIST) |
| Assistant | Takeshi Hara(Gifu Univ.) / Kenichi Morooka(Okayama Univ.) |
| 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) | A Study on Identifying Gender Differences Using Deep Learning from Retinal Fundus Images |
| Sub Title (in English) | |
| Keyword(1) | Explainable AI |
| Keyword(2) | Retina fundus images |
| Keyword(3) | Deep learning |
| Keyword(4) | LIME |
| 1st Author's Name | Shota Tsutsui |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Ichiro Maruko |
| 2nd Author's Affiliation | Tokyo Women's Medical University(TWMU) |
| 3rd Author's Name | Moeko Kawai |
| 3rd Author's Affiliation | Tokyo Women's Medical University(TWMU) |
| 4th Author's Name | Yoichi Kato |
| 4th Author's Affiliation | Waseda University(Waseda Univ.) |
| 5th Author's Name | Jun Ohya |
| 5th Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2023-09-08 |
| Paper # | MI2023-17 |
| Volume (vol) | vol.123 |
| Number (no) | MI-185 |
| Page | pp.pp.8-11(MI), |
| #Pages | 4 |
| Date of Issue | 2023-09-01 (MI) |