Computerized histologic image predictor of cancer outcome

Project: Research projectResearch Project

Description

SUMMARY: There is an increased need for predictive and prognostic assays to distinguish more and lessaggressive phenotypes of cancer due to A) dramatic increase in cancer incidence and; B) improvements inearly diagnosis. Predictive assays in particular will allow for patients with less aggressive disease to be sparedmore aggressive treatment. Most prognostic tests in the US and Europe are based on gene expression assays(e.g. Oncotype DX (ODx)). Recent studies have shown extensive genetic heterogeneity among cancer cellsbetween tumors and even within the same tumor, suggesting that approaches for recommending therapy for apatient based on the ?average? molecular signal of many cells are overly simplistic. Interestingly, for a number of cancers, tumor grade (morphologic appearance on tissue as assessedqualitatively or semi-quantitatively by a pathologist) has been found to be highly correlated with diseaseoutcome. However pathologic grade tends to suffer from significant inter-observer variability. Digitzation ofhistological samples, or whole slide imaging, facilitates a quantitative approach towards evaluating diseaseprogression and predicting outcome, while also facilitating the adoption of telepathology. Recently, researchgroups (including our own) have begun to show that computer extracted measurements of tumor morphology(e.g. capturing nuclear orientation, texture, shape, architecture) from routine H&E stained cancer tissue imagescan predict disease aggressiveness and treatment outcome. By computationally interrogating the entire tumorlandscape and its most invasive elements from a standard H&E slide, these approaches can allow for moreaccurate capture of tumor heterogeneity, disease risk and hence the most appropriate treatment strategy. The goal of this academic-industrial partnership is to develop and validate a computerized histologicimage-based predictor (CHIP) to identify which early-stage, estrogen receptor positive (ER+) breast cancerpatients are candidates for hormonal therapy alone and which women are candidates for adjuvantchemotherapy based off analysis of the pathology slides derived from biopsy and surgical specimens. InspirataInc., a cancer diagnostics company which has recently licensed a number of histomorphometry basedtechnologies from the Madabhushi group, will bring quality management systems and production softwarestandards to help create a pre-commercial companion diagnostic test of the CHIP assay. Additionally InspirataInc. will build a complete regulatory pathway for successful translation of the assay in the US and abroad.Finally, the pre-commercial prototype of the CHIP assay will be independently validated using the samestrategy and data cohorts as ODx. Our approach has several advantages over molecular assays such as ODxin that it (1) can interrogate the entire expanse of the pathology image enabling a more accurate capture oftumor heterogeneity and hence disease risk, (2) is non-disruptive of pathology workflow, (3) non-destructive oftissue and would be substantially (4) cheaper (critical in low to middle income countries) and (5) faster.
StatusActive
Effective start/end date7/1/166/30/21

Funding

  • National Institutes of Health: $699,670.00

Fingerprint

Neoplasms
Pathology
Telepathology
Observer Variation
Genetic Heterogeneity
Workflow
Therapeutics
Routine Diagnostic Tests
Estrogen Receptors
Breast
Phenotype
Biopsy
Gene Expression
Incidence