Presentation | 2019-09-04 Domain-adversarial multiple instance learning for subtype classification of malignant lymphoma Daisuke Fukushima, Ryoichi Koga, Noriaki Hashimoto, Kaho Ko, Masato Nakaguro, Kei Kohno, Shigeo Nakamura, Hidekata Hontani, Ichiro Takeuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We classify subtypes of malignant lymphoma using convolutional neural network with digital pathological images as input for computer-aided diagnosis. Generally, when the input image is large, the patch image is extracted from the entire sample. However, when we have no information for tumor regions in the sample, it is difficult that correct labels are apprppriately given to each patch image. We address such a problem using multiple instance learning. In addition, it is known that the variety of staining condition of the input pathological image affects the performance of image analysis. We confirmed that the classification accuracy was improved using domain-adversarial learning. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | pathological image / malignant lymphoma / onvolutional neural network / multiple instance learning / domain-adversarial learning |
Paper # | PRMU2019-15,MI2019-34 |
Date of Issue | 2019-08-28 (PRMU, MI) |
Conference Information | |
Committee | PRMU / MI / IPSJ-CVIM |
---|---|
Conference Date | 2019/9/4(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yoichi Sato(Univ. of Tokyo) / Yoshiki Kawata(Tokushima Univ.) |
Vice Chair | Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT) / Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
Secretary | Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX) / Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
Assistant | Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.) / Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Medical Imaging / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Domain-adversarial multiple instance learning for subtype classification of malignant lymphoma |
Sub Title (in English) | |
Keyword(1) | pathological image |
Keyword(2) | malignant lymphoma |
Keyword(3) | onvolutional neural network |
Keyword(4) | multiple instance learning |
Keyword(5) | domain-adversarial learning |
1st Author's Name | Daisuke Fukushima |
1st Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech) |
2nd Author's Name | Ryoichi Koga |
2nd Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech) |
3rd Author's Name | Noriaki Hashimoto |
3rd Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech) |
4th Author's Name | Kaho Ko |
4th Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech) |
5th Author's Name | Masato Nakaguro |
5th Author's Affiliation | Nagoya University Hospital(Nagoya Univ. Hospital) |
6th Author's Name | Kei Kohno |
6th Author's Affiliation | Nagoya University Hospital(Nagoya Univ. Hospital) |
7th Author's Name | Shigeo Nakamura |
7th Author's Affiliation | Nagoya University Hospital(Nagoya Univ. Hospital) |
8th Author's Name | Hidekata Hontani |
8th Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst of Tech) |
9th Author's Name | Ichiro Takeuchi |
9th Author's Affiliation | Nagoya Institute of Technology/RIKEN/National Institute for Materials Science(Nagoya Inst. of Tech/RIKEN/NIMS) |
Date | 2019-09-04 |
Paper # | PRMU2019-15,MI2019-34 |
Volume (vol) | vol.119 |
Number (no) | PRMU-192,MI-193 |
Page | pp.pp.19-24(PRMU), pp.19-24(MI), |
#Pages | 6 |
Date of Issue | 2019-08-28 (PRMU, MI) |