The system described in the article is composed of robust image enhancement; multispectral identification of putative cells and segmentation of clustered cells; and finally, a rule based refinement using statistical morphological attributes of the cells.
The robustness and accuracy of the system has been tested by fluorescent microscopy experts who have visually inspected the segmented images; and by comparing the results of the system on unseen benchmark data sets of cells followed by evaluation of the segmentation result in different exposure times.
NovellusDx’s algorithm team compared its proprietary algorithm to state-of-the-art systems and showed it does better on most performance parameters. To date, the system has been used to accumulate data from over 500 million segmented cells each expressing specific set of genomic alterations.
Read the full article at: https://link.springer.com/chapter/10.1007/978-3-319-60964-5_66