Mid-Infrared Spectroscopic Imaging for Tissue Histopathology
Michael J Walsh, Andre Kajdacsy-Balla, Rohit Bhargava. University of Illinois at Urbana-Champaign, Urbana, IL; University of Illinois at Chicago, Chicago, IL
Background: Histopathology is the gold standard for disease diagnosis. Current histopathological techniques use a panel of special stains and immunohistochemistry (IHC) to assess tissue architecture, determine cell types present and to classify cancers. Mid-Infrared (IR) spectroscopic imaging is a novel approach to derive chemical images from tissues based on their inherent biochemistry.
Design: Mid-IR images were obtained from over 1,000 individual patients using breast, prostate and colon tissue microarrays. Serial sections were stained with a panel of routinely used special stains and IHC stains. A modified Bayesian classifier was built to assign image pixels to the correct cell types and make a decision on disease state.
Results: Using Mid-IR imaging coupled with the modified Bayesian classifier it is possible to segment tissues into their constituent cell types from a single unstained tissue section. Accurate cell type classification as measured by average Area Under the Curve (AUC) for each of the tissues is typically very high (AUC>0.95). Furthermore, diagnosis of normal or cancerous tissue based on cell type classification of breast, prostate and colon tissue could be shown.
Conclusions: Mid-IR imaging coupled with Bayesian classification could potentially be a very valuable tool as an adjunct to current histopathological procedures, with the ability to take a single unstained tissue section and give a decision on the cell types present and disease state. Accurate cell type and disease type classification has been demonstrated in breast, prostate and colon.
Monday, March 19, 2012 1:00 PM
Poster Session II # 314, Monday Afternoon