Diagnosis of colon cancer by attenuated total reflectance-fourier transform infrared microspectroscopy and soft independent modeling of class analogy

Abstract

This study tries to demonstrate that attenuated total reflectance-fourier transform infrared (ATR-FTIR) microspectroscopy in combination with chemometric methods can reliably distinguish malignant colon tissues from healthy ones. It is important to explore a noninvasive and rapid method for detection of colon cancer biopsies. Initially, principal component analysis was applied to examine the degree of separation between tissue samples. Soft independent modeling of class analogy (SIMCA) was also employed to evaluate the prediction accuracy of ATR-FTIR microspectroscopy for the diagnosis of colon cancer. There were significant differences in the fourier transform infrared spectra of normal and cancerous colon biopsies in the 1,800-900 cm(-1) spectral region. The SIMCA results demonstrated that the accuracy, specificity, and sensitivity of the proposed diagnostic method were 93.3, 100, and 88.2%, respectively, which could help satisfy clinical diagnostic requirements.