Noninvasive breast tumors detection based on saliva protein surface enhanced Raman spectroscopy and regularized multinomial regression

Abstract

This study aims to present a noninvasive breast tumors detection method using saliva protein surface enhanced Raman spectroscopy (SERS) and regularized multinomial regression (RMR) techniques through human saliva sample. Saliva proteins SERS spectra are acquired from 33 healthy subjects, 33 patients with benign breast tumors, and 31 patients with malignant breast tumors. RMR is employed for classifying measured SERS spectra. The study results showed that for RMR diagnostic model, the diagnostic accuracy of 92.78% (85/97), 95.87% (93/97), and 88.66% (86/97) are acquired, while discriminating among the normal group, the benign breast tumor group, and the malignant breast tumor group. This study indicated that saliva protein SERS technology combined with RMR algorithm has great potentiality in noninvasive breast tumors detection.