2012 | OriginalPaper | Buchkapitel
Classifying Stem Cell Differentiation Images by Information Distance
verfasst von : Xianglilan Zhang, Hongnan Wang, Tony J. Collins, Zhigang Luo, Ming Li
Erschienen in: Machine Learning and Knowledge Discovery in Databases
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The ability of stem cells holds great potential for drug discovery and cell replacement therapy. To realize this potential, effective high content screening for drug candidates is required. Analysis of images from high content screening typically requires DNA staining to identify cell nuclei to do cell segmentation before feature extraction and classification. However, DNA staining has negative effects on cell growth, and segmentation algorithms err when compound treatments cause nuclear or cell swelling/shrinkage. In this paper, we introduced a novel Information Distance Classification (IDC) method, requiring no segmentation or feature extraction; hence no DNA staining is needed. In classifying 480 candidate compounds that may be used to stimulate stem cell differentiation, the proposed IDC method was demonstrated to achieve a 3% higher F
1
score than conventional analysis. As far as we know, this is the first work to apply information distance in high content screening.