Presentation | 2021-07-09 [Short Paper] Construction of Subtype Classifier for Malignant Lymphoma based on H&E-stained Images using Immuno-stainning Data Yuki Hirono, Noriaki Hashimoto, Kugler Mauricio, Tatsuya Yokota, Miharu Nagaishi, Hiroaki Miyoshi, Koichi Oshima, Ichiro Takeuchi, Hidekata Hontani, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In pathological diagnosis of malignant lymphoma, a HE image is observed at first and then a set of immunostained images are observed to determine the subtype. Observing the HE image, pathologists infer the candidates of the subtypes, determine the set of immunostains needed for identifying the subtype, and finally identify the subtype by observing if the specimen is positively stained by each of the immunostains. The information from HE images is the candidates of the subtypes and a set of immunostains needed for the subtype identification. The proposed method hence constructs a decision tree for inferring the set of subtype candidates and the set of the immunostains from an input HE image. Each node of the decision tree infers if a set of specific immunostains is needed for the subtype identification. We used a set of pairs of a HE image and the text data that describes the diagnosed subtype and the set of immunostains. The multiple-instance learning (MIL) is employed for the training as we have no labels indicating the cancerous regions in the HE images. The outline of the proposed method and some results of initial studies are reported. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | pathological image / malignant lymphoma / H&E-stained image / immuno-staining data / neural network / multiple instance learning |
Paper # | MI2021-16 |
Date of Issue | 2021-07-01 (MI) |
Conference Information | |
Committee | MI |
---|---|
Conference Date | 2021/7/8(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Medical imaging, physics, and recognition |
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 | Hotaka Takizawa(Tsukuba 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) | [Short Paper] Construction of Subtype Classifier for Malignant Lymphoma based on H&E-stained Images using Immuno-stainning Data |
Sub Title (in English) | |
Keyword(1) | pathological image |
Keyword(2) | malignant lymphoma |
Keyword(3) | H&E-stained image |
Keyword(4) | immuno-staining data |
Keyword(5) | neural network |
Keyword(6) | multiple instance learning |
1st Author's Name | Yuki Hirono |
1st Author's Affiliation | Nagoya Institute of Technology(NIT) |
2nd Author's Name | Noriaki Hashimoto |
2nd Author's Affiliation | Institute of Physical and Chemical Research(RIKEN) |
3rd Author's Name | Kugler Mauricio |
3rd Author's Affiliation | Nagoya Institute of Technology(NIT) |
4th Author's Name | Tatsuya Yokota |
4th Author's Affiliation | Nagoya Institute of Technology(NIT) |
5th Author's Name | Miharu Nagaishi |
5th Author's Affiliation | Kurume Universiy(Kurume Univ.) |
6th Author's Name | Hiroaki Miyoshi |
6th Author's Affiliation | Kurume Universiy/The Japanese Society of Pathology(Kurume Univ./JSP) |
7th Author's Name | Koichi Oshima |
7th Author's Affiliation | Kurume Universiy/The Japanese Society of Pathology(Kurume Univ./JSP) |
8th Author's Name | Ichiro Takeuchi |
8th Author's Affiliation | Nagoya Institute of Technology/Institute of Physical and Chemical Research(NIT/RIKEN) |
9th Author's Name | Hidekata Hontani |
9th Author's Affiliation | Nagoya Institute of Technology(NIT) |
Date | 2021-07-09 |
Paper # | MI2021-16 |
Volume (vol) | vol.121 |
Number (no) | MI-98 |
Page | pp.pp.31-32(MI), |
#Pages | 2 |
Date of Issue | 2021-07-01 (MI) |