Journal
JOURNAL OF BIOPHOTONICS
Volume 14, Issue 3, Pages -Publisher
WILEY-V C H VERLAG GMBH
DOI: 10.1002/jbio.202000385
Keywords
deep neural network; Fourier‐ transform infrared microscopy; representation learning; resonant mie scattering
Categories
Funding
- Deutsche Forschungsgemeinschaft [MO 2804/1-1]
Ask authors/readers for more resources
This study proposes a method to use deep neural networks to approximate the complex preprocessing function of infrared spectra, removing scattering components. The resulting model is significantly faster and shows strong generalization across different tissue types, while also revealing model uncertainty and band shifts in the amide I region using Bayesian machine learning approaches.
Infrared spectra obtained from cell or tissue specimen have commonly been observed to involve a significant degree of scattering effects, often Mie scattering, which probably overshadows biochemically relevant spectral information by a nonlinear, nonadditive spectral component in Fourier transform infrared (FTIR) spectroscopic measurements. Correspondingly, many successful machine learning approaches for FTIR spectra have relied on preprocessing procedures that computationally remove the scattering components from an infrared spectrum. We propose an approach to approximate this complex preprocessing function using deep neural networks. As we demonstrate, the resulting model is not just several orders of magnitudes faster, which is important for real-time clinical applications, but also generalizes strongly across different tissue types. Using Bayesian machine learning approaches, our approach unveils model uncertainty that coincides with a band shift in the amide I region that occurs when scattering is removed computationally based on an established physical model. Furthermore, our proposed method overcomes the trade-off between computation time and the corrected spectrum being biased towards an artificial reference spectrum.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available