Paper: | FR-PM-PS4.10 |
Session: | Cellular and Molecular Image Analysis |
Time: | Friday, April 7, 13:30 - 14:50 |
Presentation: |
Poster
|
Title: |
Topology Preserving Stacs Segmentation of Protein Subcellular Location Images |
Authors: |
Lionel Coulot; Ecole Polytechnique Fédérale de Lausanne (EPFL) | | |
| Heather Kirschner; Carnegie Mellon University | | |
| Amina Chebira; Carnegie Mellon University | | |
| José M. F. Moura; Carnegie Mellon University | | |
| Jelena Kovacevic; Carnegie Mellon University | | |
| Elvira Garcia Osuna; Carnegie Mellon University | | |
| Robert F. Murphy; Carnegie Mellon University | | |
Abstract: |
We present an algorithm for the segmentation of multicell fluorescence microscopy images. Such images abound and an algorithm robust to different experimental conditions as well as cell types is becoming a necessity. In cellular imaging, among the most often used algorithms is seeded watershed, which tends to oversegment, splitting the cells, as well as create segmented regions much larger than a true cell. We present an algorithm which segments with tight contours by building upon an active contour algorithm---STACS. We adapt the algorithm to suit the needs of our data and use another technique, topology preservation, to build our topology preserving STACS (TPSTACS). Our algorithm significantly outperforms the seeded watershed both visually as well as by standard measures of segmentation quality: recall/precision, area similarity and area overlap. |