Ilya Goldberg
Research FellowHead, Image Informatics and Computational Biology Unit,
NIH, National Institute on Aging
Biography:
Ilya G. Goldberg received his BS in Biochemistry from the University of Wisconsin-Madison in 1990, and his PhD. in Biochemistry and Cell Biology from the Johns Hopkins University School of Medicine in 1997. After a post-doc in crystallography at Harvard, he started the Open Microscopy Environment (OME) project as a post-doc at MIT. In 2002, he returned to Baltimore and joined the Laboratory of Genetics at the National Institute on Aging, where he started the Image Informatics and Computational Biology Unit (IICBU), dedicated to quantitative morphometry and systematic functional genomics.
Talk Title: Pattern Analysis for Scoring Visual Assays Using OME and WND-CHARM
Abstract: WND-CHARM is a general pattern recognition tool for analyzing 2D image data. In contrast to model-based image analysis, this algorithm is trained by example using control images. There are no parameter adjustments necessary when analyzing images from different imaging modes and contrast techniques including fluorescence, bright- field, DIC, and phase-contrast. The method is effective for analyzing high-throughput imaging data such as image-based screens with well-defined positive and negative controls, typically producing 100% accurate classifications. In addition, the method can be used to quantify image similarity, which allows it to be used in imaging problems requiring interpolation and clustering. A demonstration of this capability is the discovery that the morphological changes associated with aging in both C. elegans and mouse tissues progresses through discrete stages rather than being a continuous process.