| Presentation | 2021-03-16 Contrastive Learningを用いた肺野CT画像からCOVID-19の自動判定 Sota Kato, Kazuhiro Hotta, Masahiro Oda, Kensaku Mori, Yoshito Otake, Masahiro Hashimoto, Toshiaki Akashi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a method for automatically classifying COVID-19 cases from CT images of lung fields. Currently, CT images of lung fields are used for diagnosis of pneumonia, but pneumonia caused by COVID-19 is sometimes confused with normal CT images. However, pneumonia due to COVID-19 may be confused with normal CT images, which may lead to delayed diagnosis when prompt measures such as isolation are required. In this paper, we we aim to establish an automatic COVID-19 classification method based on deep learning from CT volumes. The proposed method is classified between COVID-19 pneumonia and other diseases using Contrastive Learning, which has been attracting attention in the field of image recognition. We achieved 80% accuracy in five cross-validation experiments. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | COVID-19 / Image Diagnosis / 3DCNN / Contrastive Learning |
| Paper # | MI2020-66 |
| Date of Issue | 2021-03-08 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2021/3/15(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Imaging |
| Chair | Yoshiki Kawata(Tokushima Univ.) |
| Vice Chair | Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
| Secretary | Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
| Assistant | Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | JPN-ONLY |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | |
| Sub Title (in English) | |
| Keyword(1) | COVID-19 |
| Keyword(2) | Image Diagnosis |
| Keyword(3) | 3DCNN |
| Keyword(4) | Contrastive Learning |
| 1st Author's Name | Sota Kato |
| 1st Author's Affiliation | Meijo University(Meijo Univ.) |
| 2nd Author's Name | Kazuhiro Hotta |
| 2nd Author's Affiliation | Meijo University(Meijo Univ.) |
| 3rd Author's Name | Masahiro Oda |
| 3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 4th Author's Name | Kensaku Mori |
| 4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 5th Author's Name | Yoshito Otake |
| 5th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 6th Author's Name | Masahiro Hashimoto |
| 6th Author's Affiliation | Keio University(Keio Univ.) |
| 7th Author's Name | Toshiaki Akashi |
| 7th Author's Affiliation | Juntendo University(Juntendo Univ.) |
| Date | 2021-03-16 |
| Paper # | MI2020-66 |
| Volume (vol) | vol.120 |
| Number (no) | MI-431 |
| Page | pp.pp.82-86(MI), |
| #Pages | 5 |
| Date of Issue | 2021-03-08 (MI) |