Background: Mortality in cancer patients is directly attributable to the ability of cancer cells to metastasize to distant sites from the primary tumor. This migration of tumor cells begins with a remodeling of the local tumor microenvironment, including changes to the extracellular matrix and the recruitment of stromal cells, both of which facilitate invasion of tumor cells into the bloodstream. In breast cancer, it has been proposed that the alignment of collagen fibers surrounding tumor epithelial cells can serve as a quantitative image-based biomarker for survival of invasive ductal carcinoma patients. Specific types of collagen alignment have been identified for their prognostic value and now these tumor associated collagen signatures (TACS) are central to several clinical specimen imaging trials. Here, we implement the semi-automated acquisition and analysis of this TACS candidate biomarker and demonstrate a protocol that will allow consistent scoring to be performed throughout large patient cohorts.
Methods: Using large field of view high resolution microscopy techniques, image processing and supervised learning methods, we are able to quantify and score features of collagen fiber alignment with respect to adjacent tumor-stromal boundaries.
Results: Our semi-automated technique produced scores that have statistically significant correlation with scores generated by a panel of three human observers. In addition, our system generated classification scores that accurately predicted survival in a cohort of 196 breast cancer patients. Feature rank analysis reveals that TACS positive fibers are more well-aligned with each other, are of generally lower density, and terminate within or near groups of epithelial cells at larger angles of interaction.
Conclusion: These results demonstrate the utility of a supervised learning protocol for streamlining the analysis of collagen alignment with respect to tumor stromal boundaries.
Keywords: Breast cancer; collagen; image processing; machine learning.