| Presentation | 2018-02-20 Detection of Differentiated vs. Undifferentiated Colonies of iPS Cells Using CNN for Regression on Class Probability Kojiro Tanaka, Bisser Raytchev, Takio Kurita, Toru Tamaki, Kazufumi Kaneda, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Induced pluripotent stem(iPS) cells, which have the ability to differentiate into any other cell type in the body, are already revolutionizing medical therapy. Since a large number of undifferentiated human iPS cells must be prepared for use, the development of an automated culture system for iPS cells is considered to be crucial. Among the multiple procedures involve in the culture system, detection of good/bad cells and the subsequent elimination of bad cells appears to be one of the most important parts. In this paper we propose a method for detection of good/bad colonies of iPS cells by semantic segmentation. Instead of assigning a single class label to the whole patch, we divide local patches into sub-areas and calculate probability mass function(pmf) for each sub-area to preserve structural information, then learning is carried out by regression rather than classification. Experimental result on two dataset show that a CNN using the proposed method outperforms a classification-based CNN. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | iPS cells / regression / structural information / semantic segmentation / CNN |
| Paper # | PRMU2017-164,CNR2017-42 |
| Date of Issue | 2018-02-12 (PRMU, CNR) |
| Conference Information | |
| Committee | PRMU / CNR |
|---|---|
| Conference Date | 2018/2/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Tetsuo Ono(Hokkaido Univ.) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Masayuki Kanbara(NAIST) / Kazunori Takashio(Keio Univ.) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Masayuki Kanbara(Hokkaido Univ.) / Kazunori Takashio(Panasonic) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Wataru Mito(SECOM) / Yuka Kobayashi(Toshiba) / Tatsuya Ishihara(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Cloud Network Robotics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Detection of Differentiated vs. Undifferentiated Colonies of iPS Cells Using CNN for Regression on Class Probability |
| Sub Title (in English) | |
| Keyword(1) | iPS cells |
| Keyword(2) | regression |
| Keyword(3) | structural information |
| Keyword(4) | semantic segmentation |
| Keyword(5) | CNN |
| 1st Author's Name | Kojiro Tanaka |
| 1st Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| 2nd Author's Name | Bisser Raytchev |
| 2nd Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| 3rd Author's Name | Takio Kurita |
| 3rd Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| 4th Author's Name | Toru Tamaki |
| 4th Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| 5th Author's Name | Kazufumi Kaneda |
| 5th Author's Affiliation | Hiroshima University(Hiroshima Univ.) |
| Date | 2018-02-20 |
| Paper # | PRMU2017-164,CNR2017-42 |
| Volume (vol) | vol.117 |
| Number (no) | PRMU-442,CNR-443 |
| Page | pp.pp.109-114(PRMU), pp.109-114(CNR), |
| #Pages | 6 |
| Date of Issue | 2018-02-12 (PRMU, CNR) |