Hyperspectral Unmixing for Raman Spectroscopy via Physics-Constrained Autoencoders

Abstract

Raman spectroscopy is widely used across life and material sciences to characterize the chemical composition of samples in a nondestructive, label-free manner. Many applications entail the unmixing of signals from mixtures of molecular species to identify the individual components present and their proportions, yet conventional methods for chemometrics often struggle with complex mixture scenarios encountered in practice. Here, we develop autoencoder neural network models for hyperspectral unmixing of Raman spectroscopy data, which we systematically validate using synthetic and experimental benchmark datasets we created in-house. Our results demonstrate that autoencoders provide improved accuracy, robustness and efficiency compared to standard unmixing methods. We also showcase the applicability of our approach to complex biological settings by showing improved biochemical characterization of volumetric Raman imaging data from a human leukemia monocytic cell line.