top of page

Coherent Raman Scattering (CRS) Microscopy

Stimulated Raman Histology (SRH)

SRH1.png
SRH2.png
SRH3.png
Stimulated Raman Histology SRH

Figure modified from Nature Biomedical Engineering, 1, 2 (see below) 

References:

Orringer, D.A., Pandian, B., Niknafs, Y.S., Hollon, T.C., Boyle, J., Lewis, S., Garrard, M., Hervey-Jumper, S.L., Garton, H.J., Maher, C.O. and Heth, J.A., 2017. Rapid intraoperative histology of unprocessed surgical specimens via fibre-laser-based stimulated Raman scattering microscopy. Nature biomedical engineering, 1(2), pp.1-13.

https://www.nature.com/articles/s41551-016-0027

Freudiger, C.W., Min, W., Saar, B.G., Lu, S., Holtom, G.R., He, C., Tsai, J.C., Kang, J.X. and Xie, X.S., 2008. Label-free biomedical imaging with high sensitivity by stimulated Raman scattering microscopy. Science, 322(5909), pp.1857-1861.

https://science.sciencemag.org/content/322/5909/1857

 

Freudiger, C.W., Yang, W., Holtom, G.R., Peyghambarian, N., Xie, X.S. and Kieu, K.Q., 2014. Stimulated Raman scattering microscopy with a robust fibre laser source. Nature photonics, 8(2), pp.153-159.

https://www.nature.com/articles/nphoton.2013.360

Artificial Intelligence (Research Use Only)

Figure was modified from Nature Medicine, 26, 1 (see below)

 

Artificial Intelligence (AI) based on Machine Learning (ML) is being widely explored for clinical applications and is poised to change the future of medicine. SRH images are perfect for AI/ML approaches in that they are based on detailed spectroscopic information of the native specimen and do not rely on manual staining and sectioning, which are known to cause significant site-to-site variation in traditional histologic data. Hollon et al. demonstrated in 2020 that a convolutional neuronal network (CNN) that was trained on over 2.5 million labeled image patches from over 415 patients was able to classify an SRH image into one of the 13 most common disease classes encountered in neuropathology.

 

The decision tree and examples for each class are shown in the figure. The output was validated on 278 independent samples from three (3) institutions, which were not included in the  training set. Based on these promising results and the ever-growing training dataset, Invenio is collaborating with our customers to develop AI-based image classification products that will serve as aids to surgeons and pathologists. Current  AI implementations are for research use only. Not for use in diagnostic procedures.

 

Additional references:

Hollon, T.C., Pandian, B., Adapa, A.R., Urias, E., Save, A.V., Khalsa, S.S.S., Eichberg, D.G., D’Amico, R.S., Farooq, Z.U., Lewis, S. and Petridis, P.D., 2020. Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks. Nature medicine, 26(1), pp.52-58.

https://www.nature.com/articles/s41591-019-0715-9

Hollon, T.C., Pandian, B., Urias, E., Save, A.V., Adapa, A.R., Srinivasan, S., Jairath, N.K., Farooq, Z., Marie, T., Al-Holou, W.N. and Eddy, K., 2021. Rapid, label-free detection of diffuse glioma recurrence using intraoperative stimulated Raman histology and deep neural networks. Neuro-oncology, 23(1), pp.144-155.

https://doi.org/10.1093/neuonc/noaa162

DICOM Integration

NIO DICOM Integration

Example of a typical integration of the NIO using its DICOM interface

bottom of page