Paper Abstract and Keywords |
Presentation |
2016-08-08 14:00
Automatic Segmentation of Cell Candidate Regions in Microscopy Images Based on Selective Enhancement Filter and Branch and Bound Algorithm Kouki Tsuji, Joo Kooi Tan, Hyoungseop Kim (Kyutech), Kazue Yoneda, Fumihiro Tanaka (University of Occupational and Environmental Health) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
CTCs (Circulating tumor cells) can be an informative biomarker. Analyzing them, doctors may easily evaluate therapeutic effects for malignant tumors. In this paper, we propose a method which detects cell candidate regions in microscopy images automatically. Our proposed method have three steps. In the first step, we extract the initial cell candidate regions in microscopy images based on the selective enhancement filter. In the second step, we judge whether the cell candidate region detected at the first step is a single cell or not, based on the SVM technique. In the third step, we separate regions connecting two cells and more into single cell regions based on the branch and bound algorithm. We evaluated the effectiveness of our method with the microscopy images. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
Circulating tumor cells / Cell segmentation / Selective enhancement filter / Support vector machine / Branch and bound algorithm / / / |
Reference Info. |
ITE Tech. Rep. |
Paper # |
|
Date of Issue |
|
ISSN |
|
Download PDF |
|