Virtual staining of colon cancer tissue by label-free Raman micro-spectroscopy

Abstract

The great capability of the label-free classification of tissue via vibrational spectroscopy, like Raman or infrared imaging, is shown in numerous publications (review: Diem et al., J. Biophotonics, 2013, 6, 855-886). Herein, we present a new approach, virtual staining, that improves the Raman spectral histopathology (SHP) images of colorectal cancer tissue by combining the integrated Raman intensity image in the C-H stretching region (2800-3050 cm) with the pseudo-colour Raman image. This allows the display of fine structures such as the filamentous composition of muscle tissue. The morphology of the virtually stained images is in agreement with the gold standard in medical diagnosis, the haematoxylin-eosin staining. The virtual staining image also represents the whole biochemical fingerprint, and several tissue components including carcinoma were identified automatically with high sensitivity and specificity. For fast tissue classifications, a similar approach was applied on coherent anti-Stokes Raman scattering (CARS) spectral data that is faster and therefore potentially more suitable for clinical applications.

Subcellular orchestration of alpha-synuclein variants in Parkinson’s disease brains revealed by 3D multicolor STED microscopy

“…The workflow used for CARS microscopy is outlined in Supplementary Figure 11. The detection of the lipid and protein distribution was performed on native, dried samples 59,60 . A commercial setup (Leica TCS SP5…”

Revealing architectural order with quantitative label-free imaging and deep learning

“…Diffraction tomography was combined with U-Net for measuring 3D shape of immunological synapse (38). Raman scattering was combined with a random forest classifier (39) to identify of carcinoma regions in colon tissue. Among these approaches, the 3D U-Net models that translate brightfield stack to a fluorescence stack (40) are attractive for scalable analysis because they predict both localization and expression of specific molecules in 3D.…”

“…Machine learning models have recently enabled identification of structures in diverse label-free images, opening new opportunities for scalable analysis of label-free data. Some examples include: 3D U-Net model for predicting multiple organelles in cells from brightfield and DIC images (33); inception model for in silico 2D labeling of nuclei, cell types, and cell state (34) from phase contrast and DIC images; generative adversarial models for 2D prediction of histopathological stains from quantitative phase (35) and auto-fluorescence (36); 3D U-Net model for segmentation of immunological synapse from diffraction tomography (37); random forest classifiers for recognizing carcinoma in colon tissue from Raman scattering (38). Among the above approaches, 3D U-Net models that translate label-free image stacks to a fluorescence stacks (33) are attractive, because they predict both localization and expression of specific molecules in 3D.…”

Label‐free identification of myopathological features with coherent anti‐Stokes Raman scattering

“…Because of its high spatial resolution, CARS is able to separate cellular compartments in cells . Furthermore, CARS can be used to separate healthy and diseased tissue in skin cancer, colon cancer, and brain cancer and has been used to investigate smooth muscle in the colon and in blood vessels …”