Feasibility study for diagnosis of stomach adenoma and cancer using IR spectroscopy

Abstract

The feasibility of infrared (IR) spectroscopy as a biomedical analysis tool for the diagnosis of stomach malignancy including adenoma and cancer has been studied using unstained biopsy samples. Biopsy samples were acquired from II subjects. IR spectra were collected for these samples using a microscope (aperture: 25 mu m x 25 mu m). The samples were stained again and the spots where the IR spectra were collected were re-examined by a pathologist to ensure the spectra represented the correct diagnostic information. The spectral features were compared among the averaged spectra of normal and malignant tissues. The spectral contrasts could be correlated to the differences in the molecular structure of the membrane lipids of the two tissue types as well as the variation in their glycogen contents. However, the spectral features between the adenoma and cancer tissues could not be distinguished. Initially we used principal component analysis (PCA) to examine the degree of separation between tissue types. Soft independent modeling of class analogies (SINICA) was employed to evaluate the prediction accuracy of IR spectroscopy for the diagnosis of stomach adenoma and cancer. The prediction accuracies for normal, adenoma and cancer tissues were 77%, 30% and 87%, respectively, using SIMCA. IR microscopy successfully differentiated normal and malignant tissues. However, a more sophisticated algorithm will be required in order to effectively extract relevant information for the differentiation between stomach adenoma and cancer. (C) 2007 Elsevier B.V. All rights reserved.