Advanced statistical techniques applied to comprehensive FTIR spectra on human colonic tissues

Abstract

Purpose: Colon cancer is a major public health problem due to its high disease rate and death toll worldwide. The use of FTIR microscopy in the field of cancer diagnosis has become attractive over the past 20 years. In the present study, the authors investigated the potential of FTIR microscopy to define spectral changes among normal, polyp, and cancer human colonic biopsied tissues.

Methods: A large database of FTIR microscopic spectra was compiled from 230 human colonic biopsies. The database was divided into five subgroups: Normal, cancerous tissues, and three stages of benign colonic polyps, namely, mild, moderate, and severe polyps, which are precursors of carcinoma. All biopsied tissue sections were classified concurrently by an expert pathologist. The authors applied the principal components analysis (PCA) model to reduce the dimension of the original data size to 13 principal components.

Results: While PCA analysis shows only partial success in distinguishing among cancer, polyp, and the normal tissues, multivariate analysis (e.g., LDA) shows a promising distinction even within the polyp subgroups.

Conclusions: Good classification accuracy among normal, polyp, and cancer groups was achieved with a success rate of approximately 85%. These results strongly support the potential of developing FTIR microscopy as a simple, reagent-free tool for early detection of colon cancer and, in particular, for discriminating among the benign premalignant colonic polyps having increasing degrees of dysplasia severity (mild, moderate, and severe).