Multiplex coherent anti-Stokes Raman scattering microspectroscopy of brain tissue with higher ranking data classification for biomedical imaging

Abstract

Abstract. Multiplex coherent anti-Stokes Raman scattering (MCARS) microscopy was carried out to map a solid tumor in mouse brain tissue. The border between normal and tumor tissue was visualized using support vector machines (SVM) as a higher ranking type of data classification. Training data were collected separately in both tissue types, and the image contrast is based on class affiliation of the single spectra. Color coding in the image generated by SVM is then related to pathological information instead of single spectral intensities or spectral differences within the data set. The results show good agreement with the H&E stained reference and spontaneous Raman microscopy, proving the validity of the MCARS approach in combination with SVM. © The Authors.Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Comparison of optically‐derived biomarkers in healthy and brain tumor tissue under one‐ and two‐photon excitation

“…For enhanced tumor visualization at the meso and microscale, other optical techniques are applied, usually through an endomicroscope . State of the art endomicroscopes can be equipped with confocal reflectance and fluorescence imaging , Raman spectroscopy and coherent anti‐Stokes Raman scattering (CARS) microscopy , fluorescence lifetime imaging (FLIM) and two‐photon microscopy . Although each modality has its own advantages and limits when utilized in the surgical field, a recent solution has been to combine two or more modalities to alleviate their limitations on one hand, and to increase the information depth retrieved enabling more differentiated diagnostics.…”

“…FLIM however does not directly display morphological features of the sampled region and is thus best combined with other microscopic imaging modalities such as CARS or two photon imaging . Multimodal detection through an endomicroscope has mostly been applied to imaging of the upper and lower gastrointestinal tract or the heart , where microscopic features similar to that depicted by stained histopathological images are visualized.…”

Raman Imaging: An Impending Approach Towards Cancer Diagnosis

“…extended their study on virtual staining of colon cancer tissue using CARS coupled with second harmonic generation (SHG) for the fast tissue classification, which can be translated to clinical applications. Multiplex CARS has been utilized for the differentiation of healthy brain tissue from tumor in accordance with the difference in protein to lipid ratio [37] . In another report, Wong and co‐workers [38] applied deep learning algorithm in combination with CARS to segregate normal and cancerous lung tissues.…”

Multimodal Nonlinear Microscopy for Therapy Monitoring of Cold Atmospheric Plasma Treatment

“…In this context, it has been shown that multimodal nonlinear imaging, using different methods such as coherent anti-Stokes Raman scattering (CARS), two-photon excited autofluorescence (TPEF), two-photon excited fluorescence lifetime imaging (2P-FLIM) and second harmonic generation (SHG), is a powerful tool for the label-free characterization of the molecular composition of cells and tissues, enabling the visualization of the distribution of molecular markers with subcellular spatial resolution and the correlation of their function in tissue [15,16,17,18,19]. Using machine learning image processing algorithms, the nonlinear image data can be translated into biomedical information [20,21,22,23,24].…”