A Quality Pre-Processor for Biological Cell Images
Adele P. Peskin, Karen Kafadar, Alden A. Dima
We have developed a method to rapidly test the quality of a biological image, to identify appropriate segmentation methods, if any, that will render high quality segmentations for the cells within that image. The key contribution is the development of a measure of the clarity of a biological cell within an image, that can be quickly and directly used to select a segmentation method during a high content screening process. Our quality index is an objective measure calculated from the image; we show that it does indeed correlate well with subjective assessments of image quality. Our method of defining this index is based on the gradient of the pixel intensity field at the cell edges and on the distribution of pixel intensities just inside the cell edges. In addition, we have developed a technique to synthesize sets of biological cells with varying qualities, to create standardized images for testing a wide variety of segmentation methods. We show that the differences in the quality indices reflect well the observed differences in resulting masks of the same cell imaged under a variety of conditions.
Computational Bioimaging 2009
5th International Symposium on Visual Computing
, Kafadar, K.
and Dima, A.
A Quality Pre-Processor for Biological Cell Images, Computational Bioimaging 2009
5th International Symposium on Visual Computing , Las Vegas, NV, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903070
(Accessed February 23, 2024)