| Item type |
SIG Technical Reports(1) |
| 公開日 |
2018-05-03 |
| タイトル |
|
|
タイトル |
Automatic Image Analysis for Biomedical Research: Rapid Drug Susceptibility Testing and Investigation of Cell Specialization in Early Embryo |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Automatic Image Analysis for Biomedical Research: Rapid Drug Susceptibility Testing and Investigation of Cell Specialization in Early Embryo |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
D論セッション1 |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
Osaka University |
| 著者所属 |
|
|
|
Carnegie Mellon University |
| 著者所属 |
|
|
|
Osaka University |
| 著者所属(英) |
|
|
|
en |
|
|
Osaka University |
| 著者所属(英) |
|
|
|
en |
|
|
Carnegie Mellon University |
| 著者所属(英) |
|
|
|
en |
|
|
Osaka University |
| 著者名 |
Andrey, Grushnikov
Takeo, Kanade
Yasushi, Yagi
|
| 著者名(英) |
Andrey, Grushnikov
Takeo, Kanade
Yasushi, Yagi
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Cell analysis is one of the core procedures done frequently during the course of research in a number of fields, including bacteriology and embryology. It is often done manually, examining images gathered with a microscope. This approach is labor-intensive and lacks reproducibility, emphasizing the importance of an automatic solution for the cell analysis problem. This work presents image processing based automation solutions for two cell analysis problems: drug susceptibility testing and early-stage embryo segmentation. The first problem we solved for a recently introduced device, by processing its images that contained cells. Cells were detected, their features extracted and used as input for SVM predicting drug susceptibility. The solution of the second problem involved applying 3D level set with custom energy functions for processing Z-stacks of fluorescence microscopy images. Both tasks were implemented as stand-alone tools, showed high accuracy on the respective datasets. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Cell analysis is one of the core procedures done frequently during the course of research in a number of fields, including bacteriology and embryology. It is often done manually, examining images gathered with a microscope. This approach is labor-intensive and lacks reproducibility, emphasizing the importance of an automatic solution for the cell analysis problem. This work presents image processing based automation solutions for two cell analysis problems: drug susceptibility testing and early-stage embryo segmentation. The first problem we solved for a recently introduced device, by processing its images that contained cells. Cells were detected, their features extracted and used as input for SVM predicting drug susceptibility. The solution of the second problem involved applying 3D level set with custom energy functions for processing Z-stacks of fluorescence microscopy images. Both tasks were implemented as stand-alone tools, showed high accuracy on the respective datasets. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA11131797 |
| 書誌情報 |
研究報告コンピュータビジョンとイメージメディア（CVIM）
巻 2018-CVIM-212,
号 36,
p. 1-14,
発行日 2018-05-03
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8701 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-CVIM18212036.pdf (9.2 MB)
