Scale-Space Diagnostic Criterion for Microscopic Image Analysis
Abstract
In this paper, a new criterion for diagnostics of hematopoietic tumors from images of cell nuclei of lymphatic nodes is presented. A method for image analysis of lymphatic node specimens is developed on the basis of the scale-space approach. A diagnostically important criterion is defined as a total amount of points of spatial intensity extrema in the families of blurred images generated by the given image of a cell nucleus. The procedure for calculating criterion values is presented. Testing of the obtained criterion is carried out using different classifiers. The accuracy of diagnostics is greater than 81% for collective classifiers.
Cite
Text
Gurevich and Murashov. "Scale-Space Diagnostic Criterion for Microscopic Image Analysis." European Conference on Computer Vision, 2004. doi:10.1007/978-3-540-27816-0_35Markdown
[Gurevich and Murashov. "Scale-Space Diagnostic Criterion for Microscopic Image Analysis." European Conference on Computer Vision, 2004.](https://mlanthology.org/eccv/2004/gurevich2004eccv-scale/) doi:10.1007/978-3-540-27816-0_35BibTeX
@inproceedings{gurevich2004eccv-scale,
title = {{Scale-Space Diagnostic Criterion for Microscopic Image Analysis}},
author = {Gurevich, Igor B. and Murashov, Dmitry},
booktitle = {European Conference on Computer Vision},
year = {2004},
pages = {408-416},
doi = {10.1007/978-3-540-27816-0_35},
url = {https://mlanthology.org/eccv/2004/gurevich2004eccv-scale/}
}