Lawrence Berkeley National Laboratory masthead A-Z Index Berkeley Lab masthead U.S. Department of Energy logo Phone Book Jobs Search
Tech Transfer
Licensing Interest Form Receive Customized Tech Alerts

Classification of Tumor Composition and Delineation of Cellular Regions via Dictionary and Sparse Coding

IB-2013-173

APPLICATIONS OF TECHNOLOGY:

ADVANTAGES:

ABSTRACT:
Berkeley Lab researchers Bahram Parvin, Hang Chang, and Yin Zhou have developed a technology enabling pathologists to quantify tumor composition via cell-by-cell profiling and distinct regions of histopathology. The Berkeley Lab technology can lead to pre-identification of aberrant regions in tissue, saving pathologists’ time; assess frequency and organization of cellular processes such as mitosis; enable precision medicine by sifting through large amounts of data; and quantify tissue composition for assessing tumor-stroma interactions as a function of individual cells in each compartment. These improvements will lead to improved predictive models.

This is the first attempt to use spatial pyramid matching (SPM) to classify tumor histopathology using engineered or learned features. Using a learned dictionary, excellent performance has been achieved even with a small number of training samples across independent data sets of tumors. The Berkeley Lab technology is extensible to other cell-based assays.

Existing techniques for image-based classification of tissue histology using aggregated indices from a large cohort are hindered due to large technical and biological variations always present in such large-cohort data. The Berkeley team’s algorithms to classify tissue histology — based on strong representations of morphometric context and built on nuclear-level morphometric features at various locations and scales within the SPM framework — have been found to be extensible to different tumor types; robust despite wide technological and biological variations; invariant to different nuclear segmentation strategies; and scalable with varying sample size making them effective across multiple tumor types with a limited number of training samples.


DEVELOPMENT STAGE: Proven principle. The technology has been evaluated on distinct data sets collected from The Cancer Genome Atlas. Details of these tests are described in the publications linked below.

STATUS: Patent pending. Available for license or collaborative research.

FOR MORE INFORMATION:

Chang H., Nayak N., Spellman P., Parvin B., “Characterization of tissue histopathology via predictive sparse decomposition and spatial pyramid matching,” Medical Image Computing and Computer Assisted Intervention. 2013;16 (Pt 2):91-8.

Nayak N., Chang H., Borowsky A., Spellman P., Parvin B., “Classification of Tumor Histopathology via Sparse Feature Learning,” Proc IEEE Int Symp Biomed Imaging. Apr. 2013. doi: 10.1109/ISBI.2013.6556499.

Chang H., Borowsky A., Spellman P., Parvin B., “Classification of Tumor Histology via Morphometric Context,” Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. Jun. 2013. doi: 10.1109/CVPR.2013.286.

REFERENCE NUMBER: 2013-173

See More Biotech & Medicine Technologies