Virtual brain tumor histopathology and immunohistochemistry with stimulated raman scattering microscopy.

Abstract

e13511 Background: Stimulated Raman scattering (SRS) microscopy is a label-free optical technique which uses the chemical composition of fresh tissue to generate image contrast. Prior work has demonstrated exceptional correlation between SRS images and H&E microscopy for detecting brain tumor infiltration ex vivo. However, SRS has not previously been suitable for a clinical environment. Further, SRS has utilized structural, rather than chemical, diagnostic features. We present the first clinical validation of SRS, as well as our work towards mutation-targeted SRS imaging. Methods: Implementation of SRS with a fiber laser source allowed sufficient stability for clinical deployment. Unprocessed specimens from 200 neurosurgical cases were imaged at the CH2 and CH3 vibrational modes, then processed to mimic the appearance of H&E staining. 30 cases were trialed in a simulated intraoperative consultation to assess concordance between SRS and cryosection microscopy. A multi-layer perceptron (MLP) model was then used to predict brain tumor diagnosis based on quantified image attributes. To explore the potential for chemically specific SRS, isogenic lines of normal human astrocyte were prepared, differing by the presence or absence of the R132H mutation in the isocitrate dehydrogenase 1 (IDH1) gene. IDH1 R132H cells accumulate high concentrations of the oncometabolite 2-hydroxyglutarate and display predictably altered metabolism. 200 Raman spectra were collected from 50 wild type (WT) and 50 R132H cells with the aim of detecting these changes. Each cell line was then submitted for targeted metabolomic analysis. Results: Excellent concordance was observed between SRS and frozen section histology ( κ >0.89). The MLP diagnosed brain tumor subtype with 90% accuracy. A robust spectral difference was observed between wild type and R132H cells, which showed concordance with metabolomic data. Conclusions: The diagnostic capability, ease of use and speed of SRS make it well-suited for integration into the operative workflow. Further, because SRS amplifies the Raman signal with no resonant background, the spectral differences observed may allow rapid differentiation of IDH1 WT and R132H cells with SRS.