We have described how a mass spectrometry-based (MSI) chemical imaging data workflow can be used in a pathology workflow to automatically identify region-specific lipid patterns in colorectal cancer. This results in highly accurate (greater than 98%) identification of pixels according to morphology – cancer, healthy mucosa, smooth muscle and microvasculature.
MSI uses technologies that reveal how hundreds or thousands of chemical components are distributed in a tissue sample. Our work originated as a project in the Imperial BRC and specific advances included the use of multivariate image modelling to the 2D-topographical metabolic data collected from tissue sections.
This research demonstrates the potential of a chemo-informatics based strategy for imaging MSI data. Chemo-informatics is the use of computer and informational techniques applied to a range of problems in the field of chemistry. The research will support future hospital pathology services in automatic tissue annotation and thus rapid diagnostics in a number of therapeutic areas including cancer and inflammatory disease diagnostics.
It will accelerate while augmenting, and potentially replacing, conventional histopathology with a potential and significant lowering of healthcare costs.