User Tools

Site Tools


7a.019.DU - Image Informatics for the Characterization of Molecular Subtypes in Breast Carcinoma Tissue

Project - Summary

Histological examination of tumor and biopsy specimens remains the key diagnostic tool for pathology diagnosis and staging. The availability of large-scale architectural information and fine-scale features can serve as important cues from which to judge the aggressiveness of the tumor and the patient’s prognosis. The predictive capabilities of histological image analysis, enhanced by informatics techniques, may be harnessed to objectively and reproducibly distinguish tumor subtypes. The key advantage of this approach tackles the two major criticisms of molecular subtyping: 1) the lack of spatial information, that makes gene expression analysis susceptible to artifacts in the presence of tumor heterogeneity, can be overcome with image analysis; 2) by defining tumor molecular subtype morphologically with a reduced number of variables (on the order of tens, rather than thousands), the “curse of dimensionality” no longer places a constraint on our ability to define groups based on pattern analysis.

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
David Breen PI (215) 895-1626 Drexel University
Dr. Mark Zarella Co-PI (215) 762-8657 Drexel University
Callan Powell Student Not available Not available Drexel University
Jessica Hoban Student Not available Not available Drexel University
Dr. Fernando U. Garcia Co-PI & Project Mentor (215) 537-6911 Cancer Treatment Centers of America (CTCA)

Project - Novelty of Approach

In comparison to molecular techniques, which have not proven to be reliable, we aim to develop subtyping methods based on image analysis of histologic tissue. The central hypothesis of our work is that histological images contain information that can objectively be utilized to classify tumors into distinct molecular subtypes. We further hypothesize that these subtypes consist of an elaboration of existing subtypes discovered using IHC and gene expression analysis, and that many more subtypes exist than have previously been characterized. These morphological subtypes likely consist of morphological variants of existing subtypes as well as previously-undiscovered subtypes.

Project - Deliverables

1 Novel algorithms for molecular subtype identification and prediction of genetic traits from visual tissue analysis
2 Implemented prototype software
3 Research publications

Project - Benefits to IAB

1) Extension of our biomedical image informatics framework.

2) Techniques that will help IAB members classify tissue samples to improve/personalize patient care and specimen analysis.

Project - Documents

FilenameFilesizeLast modified
7a.019.du_2018_fall_meeting_poster.pptx888.9 KiB2019/08/13 15:02
7a.019.du_quad_chart_2018_spring_meeting.pptx63.2 KiB2019/08/13 15:02
7a.019.du_executive_summary.docx51.5 KiB2019/08/13 15:02
7a.019.du_mid-year_report.docx238.1 KiB2019/08/13 15:02
7a.019.du_confluence_project_page.pdf142.2 KiB2019/08/13 15:02
7a.019.du_powerpoint_presentation.pptx586.2 KiB2019/08/13 15:02
projects/year7/7a.019.du.txt · Last modified: 2019/08/14 08:57 by sally.johnson