In Silico Science

We are developing computational methods to enable basic science and clinical research through integration of imaging, genomic and clinical data in existing resources like the National Cancer Institute's The Cancer Genome Atlas. As part of this effort, we have developed software tools and novel approaches to describing tumor histology and correlating imaging observations with genomic and clinical features.

We have used these methods to carry out studies of glioma brain tumors with Drs. Daniel Brat and Joel Saltz, where we have investigated how elements of the tumor microenvironment influence gene expression patterns in glioblastomas and establish transcriptional programs that correspond with expression-based classifications. This work led to a prospective study that is investigating intra-tumoral variations in expression-based classifications using novel surgical techniques. In addition to our work on tumor microenvironment, we have also used public genomic/clinical databases to demonstrate the clinical relevance of gene expression classifications of glioblastomas in lower-grade gliomas.

LAD Cooper, DA Gutman, C Chisolm, C Appin, J Kong, Y Rong, T Kurc, EG Van Meir, JH Saltz, CS Moreno, DJ Brat, "The Tumor Microenvironment Strongly Impacts Master Transcriptional Regulators and Gene Expression Class of Glioblastoma," The American Journal of Pathology, 180(5), pp. 2108-2129, May 2012 [pubmed]

WC Rutledge, J Kong, J Gao, DA Gutman, LAD Cooper, C Apping, Y Park, L Scarpace, T Mikkelsen, ML Cohen, KD Aldape, RE McLendon, NL Lehman, CR Miller, MJ Schniederjan, CW Brennan, CS Moreno, JH Saltz, DJ Brat, "Tumor-infiltrating lymphocytes in glioblastoma are associated with specific genomic alterations and related to transcriptional class", Clinical Cancer Research, In Press [pubmed]

DA Gutman, LAD Cooper, SN Hwang, CA Holder, J Gao, TD Aurora, WD Dunn Jr, L Scarpace, T Mikkelsen, R Jain, M Wintermark, M Jilwan, P Raghavan, E Huang, RJ Clifford, P Mongkolwat, V Kleper, J Freymann, J Kirby, PO Zinn, CS Moreno, C Jaffe, R Colen, DL Rubin, JH Saltz, A Flanders, DJ Brat, "MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set", Radiology, 267(2), pp. 560-9, May 2013 [pubmed]

LAD Cooper, DA Gutman, Q Long, BA Johnson, SR Cholleti, T Kurc, JH Saltz, DJ Brat, CS Moreno, "The Proneural Molecular Signature is Enriched in Oligodendrogliomas and Predicts Im- proved Survival among Diffuse Gliomas," PLoS ONE, 5(9), e12548. doi:10.1371/journal.pone.0012548, September 2010 [pubmed]

SM Cork, B Kaur, NS Devi, LAD Cooper, JH Saltz, EM Sandberg, S Kaluz, EG Van Meir, "A proprotein convertase/MMP-14 proteolytic cascade releases a novel 40kDa vasculostatin from tumor suppressor BAI1," Oncogene, 31(50), pp. 5144-5152, February 2012 [pubmed]

Digital Pathology

We are developing image analysis methodology to generate rich and quantitative descriptions of tissues from high resolution whole-slide digital images. These images contain detailed information on hundreds of thousands of cells - what can be measured. What can analysis of this info reveal. What are we doing specifically.

LAD Cooper, J Kong, DA Gutman, F Wang, J Gao, C Appin, S Cholleti, T Pan, A Sharma, L Scarpace, T Mikkelsen, T Kurc, CS Moreno, DJ Brat, JH Saltz, "Integrated morphologic analysis for the identifcation and characterization of disease subtypes," Journal of the American Medical Informatics Association JAMIA, 19(2), pp. 317-323, March-April 2012 [pubmed]

LAD Cooper, J Kong, F Wang, T Kurc, CS Moreno, DJ Brat, JH Saltz, Morhpological Signatures and Genomic Correlates in Glioblastoma, The 8th IEEE International Symposium on Biomedical Imaging, Chicago, IL, March 2011 [pubmed]

LAD Cooper, AB Carter, AB Farris, F Wang, J Kong, DA Gutman, P Widener, TC Pan, SR Cholleti, A Sharma, T Kurc, DJ Brat, JH Saltz, "Digital Pathology: Data-Intensive Frontier in Medical Imaging," Proceedings of the IEEE, 100(4), pp. 991-1003, April 2012 [ieee]

Algorithms

Our lab conducts basic research in image processing and machine learning algorithms for analysis of biomedical data. Topics include robust segmentation and classification of microanatomy in whole-slide images under varying condtions, higher-order segmentation of histology by statistical geometric methods, and methods for clustering data with model-selection confidence measures.

We are also routinely involved in optimization and parallelization of algorithms to enable analysis of massive datasets. Using a combination of mathematical analysis to identify calculation shortcuts, programming techniques for Matlab including hybrid Matlab/C++ as well as parallelization strategies for execution on multicore/multisocket systems, we are able to enhance algorithm performance to reduce computation times and make analysis of larger datasets possible.

J Kong, LAD Cooper, F Wang, C Chisolm, CS Moreno, T Kurc, P Widener, DJ Brat, JH Saltz, A Comprehensive Framework for Classiffcation of Nuclei in Digital Microscopy Imaging: An Application to Diffuse Gliomas, The 8th IEEE International Symposium on Biomedical Imaging, Chicago, IL, March 2011 [pubmed]

LAD Cooper, JH Saltz, R Machiraju, K Huang, Two-Point Correlation as a Feature for Histology Images: Feature Space Structure and Correlation Updating, Mathematical Methods in Bioimage Analysis Workshop, 23rd IEEE Conference on Computer Vision and Pattern Recognition, pp.79-86, San Francisco, CA, June 2010 [ieee]

LAD Cooper, O Sertel, J Kong, G Lozanski, K Huang, M Gurcan, "Feature-Based Registration of Histopathology Images with Different Stains: An Application for Computerized Follicular Lymphoma Prognosis," Computer Programs and Methods in Biomedicine, 96(3), pp.182-92, May 2009 [pubmed]