Differentiation of glioblastoma tissues using spontaneous Raman scattering with dimensionality reduction and data classification

Abstract

The neurosurgery of intracranial tumors is often complicated by the difficulty of distinguishing tumor center, infiltration area, and normal tissue. The current standard for intraoperative navigation is fluorescent diagnostics with a fluorescent agent. This approach can be further enhanced by measuring the Raman spectrum of the tissue, which would provide additional information on its composition even in the absence of fluorescence. However, for the Raman spectra to be immediately helpful for a neurosurgeon, they must be additionally processed. In this work, we analyzed the Raman spectra of human brain glioblastoma multiforme tissue samples obtained during the surgery and investigated several approaches to dimensionality reduction and data classification to distinguish different types of tissues. In our study two approaches to Raman spectra dimensionality reduction were approbated and as a result we formulated new technique combining both of them, principal component analysis after feature filtering based on the selection of those shifts which are corresponds the biochemical components providing the statistically significant differences between groups of examined tissues (center of glioblastoma multiforme, tissues from infiltration area and normally appeared white matter). We applied the support vector machine to classify tissues after dimensionality reduction of registered Raman spectra. The accuracy of the used classifier with principal component technique of dimensionality reduction for detecting malignant tissue (tumor edge and center) was 85% with sensitivity of 97% and specificity of 50%. With a combined technique of dimensionality reduction we obtained 90% accuracy with 92% selectivity and 86% specificity of tumor tissues classification.