| Autor: |
Buhl S; Institute for Computer Science, Vision and Computational Intelligence, South Westphalia University of Applied Sciences, Frauenstuhlweg 31, 58644 Iserlohn, Germany., Neumann B; Institute for Computer Science, Vision and Computational Intelligence, South Westphalia University of Applied Sciences, Frauenstuhlweg 31, 58644 Iserlohn, Germany., Schäfer SC; Institute for Computer Science, Vision and Computational Intelligence, South Westphalia University of Applied Sciences, Frauenstuhlweg 31, 58644 Iserlohn, Germany., Severing AL; Institute for Computer Science, Vision and Computational Intelligence, South Westphalia University of Applied Sciences, Frauenstuhlweg 31, 58644 Iserlohn, Germany. |
| Abstrakt: |
This paper presents a method of separating cells that are connected to each other forming clusters. The difference to many other publications covering similar topics is that the cell types we are dealing with form clusters of highly varying morphology. An advantage of our method is that it can be universally used for different cell types. The segmentation method is based on a growth simulation starting from the nuclei areas. To start the evaluation, the cells need to be made visible with a histological stain, in our case with the May-Grünwald solution. After the staining process has been completed, the nuclei areas can be distinguished from the other cell areas by a histogram backprojection algorithm. The presented method can, in addition to histological stained cells, also be applied to fluorescent-stained cells. |
