Deep learning-enabled Inference of 3D molecular absorption distribution of biological cells from IR spectra.

Infrared spectroscopy delivers abundant information about the chemical composition, as well as the structural and optical properties of intact samples in a non-destructive manner. We present a deep convolutional neural network which exploits all of this information and solves full-wave inverse scattering problems and thereby obtains the 3D optical, structural and chemical properties from infrared spectroscopic measurements of intact micro-samples. The proposed model encodes scatter-distorted infrared spectra and infers the distribution of the complex refractive index function of concentrically spherical samples, such as many biological cells. The approach delivers simultaneously the molecular absorption, sample morphology and effective refractive index in both the cell wall and interior from a single measured spectrum. The model is trained on simulated scatter-distorted spectra, where absorption in the distinct layers is simulated and the scatter-distorted spectra are estimated by analytic solutions of Maxwell's equations for samples of different sizes. This allows for essentially real-time deep learning-enabled infrared diffraction micro-tomography, for a large subset of biological cells.

An automated approach for fringe frequency estimation and removal in infrared spectroscopy and hyperspectral imaging of biological samples.

In infrared spectroscopy of thin film samples, interference introduces distortions in spectra, commonly referred to as fringes. Fringes may alter absorbance peak ratios, which hampers the spectral analysis. We have previously introduced extended multiplicative signal correction (EMSC) for fringes correction. In the current article, we provide a robust open-source algorithm for fringe correction in infrared spectroscopy and propose several improvements to the Fringe EMSC model. The suggested algorithm achieves a more precise fringe frequency estimation by mean centering of the measured spectrum and applying a window function prior to the Fourier transform. It selects two frequencies from a user defined number of maxima in the Fourier domain. The improved Fringe EMSC algorithm is validated on two experimental datasets, one of them being a hyperspectral image. Techniques for separating sample spectra from background spectra in hyperspectral images, and techniques to identify spectra affected by fringes are also provided.