Shridar Ganesan

Other : Other: Dr. Ganesan holds intellectual property rights on patents held by Rutgers, The State University New Jersey (awardee institution) on methods for image analysis of histology of ER+ breast cancers for prognosis. These patents do not have any IP value at this time.

Image Mining for Comparative Analysis of Expression Patterns in Tissue Microarray

PROJECT NARRATIVE: During the first phase of this research project our team successfully designed, developed and evaluated (a) a library of analytical and computational tools for performing automated registration, segmentation, feature extraction, and classification of imaged microtissue samples; (b) data models and grid-enabled tools for performing large-scale indexing, organizing, and archiving imaged microscopy specimens and experimental results; (c) query capabilities to support reliable identification and retrieval of those imaged tissue samples from within distributed, 'gold-standard' archives of consensus-graded cases which exhibit staining and expression signatures which are most similar to those of a given query; and (d) methods and resources to support seamless, high-throughput analyses of specimens. The overarching goals of this renewal application are to build upon progress made in the first phase of the project by developing and evaluating a new family of multi-stage, searching algorithms to facilitate quick, reliable interrogation of large-scale, clinical and research, microscopy applications including whole-slide imaging and tissue microarray; developing and evaluating a suite of high-throughput services capable of automatically detecting, archiving and indexing user-specified objects (e.g. tissues, cells) in large collections of images and implement extensions to the data models and support for optimized pipeline selection. These capabilities will enable large-scale correlative outcomes studies and support expansion of the 'gold-standard' image archives and correlated clinical repositories. The services will take advantage of state-of-the-art parallel CPU-GPU machines and the searching algorithms described in Aim 1; optimizing the imaging, computational and content-based image retrieval algorithms and tools using a wide range of different tissues, cancer types and biomarkers to support clinical and research experiments and studies involving patient stratification, quality-control, and outcomes assessment; and deploying the analytical tools, data models, user-centered interfaces and reference libraries of imaged specimens to participating adopter sites to conduct open-set usability and performance studies and make these resources available to the clinical and research communities as open source software and resources to support future development and testing of new hypotheses, algorithms and methods.