Toward improving fine needle aspiration cytology by applying Raman microspectroscopy

摘要: ABSTRACT. Medical diagnosis of biopsies performed by fine needle aspiration has to be very reliable. Therefore, pathologists/cytologists need additional biochemical information on single cancer cells for an accurate diagnosis. Accordingly, we applied three different classification models discriminating various features six breast cell lines analyzing Raman microspectroscopic data. The statistical evaluations are implemented linear discriminant analysis (LDA) and support vector machines (SVM). For the first model, a total 61,580 spectra from 110 discriminated at cell-line level with accuracy 99.52% using SVM. LDA based data achieved 94.04% their origin (solid tumor versus pleural effusion). In third classified subtypes. results show 97.45% specificities 97.78%, 99.11%, 98.97% subtypes basal-like, HER2+/ER-, luminal, respectively. These confirmed gene expression patterns, which important prognostic in This work shows applicability spectroscopy handling cancer-relevant advanced medical single-cell level.