PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Hyperspectral stimulated Raman scattering (hsSRS) microscopy provides rich chemical and spatial information not regularly available to traditional microscopy methods. However, analysis of hsSRS images is often confounded by convolved and overlapping spectral features requiring use of machine learning methods to extract information. Here, we demonstrate the use of our recently published deep learning architecture (the U-within-U-Net) designed for hyperspectral images on hsSRS images. We demonstrate segmentation, classification, and prediction of orthogonal imaging modalities. We also show the architecture is applicable to other hyperspectral imaging modalities with implications for remote sensing and mass spectrometry imaging.
Bryce Manifold andDan Fu
"Deep learning for analysis of hyperspectral stimulated Raman scattering images", Proc. SPIE PC11973, Advanced Chemical Microscopy for Life Science and Translational Medicine 2022, PC119730Y (2 March 2022); https://doi.org/10.1117/12.2609800
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Bryce Manifold, Dan Fu, "Deep learning for analysis of hyperspectral stimulated Raman scattering images," Proc. SPIE PC11973, Advanced Chemical Microscopy for Life Science and Translational Medicine 2022, PC119730Y (2 March 2022); https://doi.org/10.1117/12.2609800