| Presentation | 2023-01-17 Oral Cytology Based on Representation Learning of Visually Salient Cells Kazuki Matsuo, Eiji Mitate, Tomoya Sakai, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We classify microscopically photographed cells for screening tests to find oral cancer in its early stages. Oral cancer is one of the most common malignancies and has a relatively high mortality rate. Early detection and diagnosis are very important to improve the survival rate.. Automatic classification of oral cells is required as a simple and early screening. Deep learning-based cell image classification tend to focus on the background rather than the cells because background is dominant. Cells are salient in images. We propose a representation learning that encourages a convolutional autoencoder to focus on salient cell regions. The trained encoder is applicable to automatic classification of oral cells. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | saliency map / convolutional autoencoder / deep learning |
| Paper # | MICT2022-44,MBE2022-44 |
| Date of Issue | 2023-01-10 (MICT, MBE) |
| Conference Information | |
| Committee | MBE / MICT / IEE-MBE |
|---|---|
| Conference Date | 2023/1/17(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Junichi Hori(Niigata Univ.) / Hirokazu Tanaka(Hiroshima City Univ.) |
| Vice Chair | Hisashi Yoshida(Kinki Univ.) / Chika Sugimoto(Yokohama National Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) |
| Secretary | Hisashi Yoshida(Setsunan Univ) / Chika Sugimoto(Tohoku Inst. of Tech.) / Daisuke Anzai(Okayama Pref. Univ.) / (Junshin Gakuen Univ.) |
| Assistant | Emi Yuda(Tohoku Univ) / Miki Kaneko(Osaka Univ.) / Takahiro Ito(Hiroshima City Univ) / Natsuki Nakayama(Nagoya Univ.) / Takuya Nishikawa(National Cerebral and Cardiovascular Center Hospital) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Healthcare and Medical Information Communication Technology / The Technical Committee on Medical and Biological Engineering |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Oral Cytology Based on Representation Learning of Visually Salient Cells |
| Sub Title (in English) | |
| Keyword(1) | saliency map |
| Keyword(2) | convolutional autoencoder |
| Keyword(3) | deep learning |
| 1st Author's Name | Kazuki Matsuo |
| 1st Author's Affiliation | Nagasaki University(Nagasaki Univ.) |
| 2nd Author's Name | Eiji Mitate |
| 2nd Author's Affiliation | Nagasaki University(Nagasaki Univ.) |
| 3rd Author's Name | Tomoya Sakai |
| 3rd Author's Affiliation | Nagasaki University(Nagasaki Univ.) |
| Date | 2023-01-17 |
| Paper # | MICT2022-44,MBE2022-44 |
| Volume (vol) | vol.122 |
| Number (no) | MICT-334,MBE-335 |
| Page | pp.pp.7-12(MICT), pp.7-12(MBE), |
| #Pages | 6 |
| Date of Issue | 2023-01-10 (MICT, MBE) |