Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders
This work addresses the challenge of chemical composition analysis in scientific domains like biology, offering incremental improvements for hyperspectral unmixing in Raman spectroscopy.
The paper tackled the problem of unmixing signals from mixtures of molecular species in Raman spectroscopy, which conventional methods struggle with in complex scenarios, and demonstrated that autoencoder-based algorithms provide improved accuracy, robustness, and efficiency compared to standard methods, including in biological settings like volumetric Raman imaging of cells.
Raman spectroscopy is widely used across scientific domains to characterize the chemical composition of samples in a non-destructive, 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 hyperspectral unmixing algorithms based on autoencoder neural networks, and we systematically validate them using both synthetic and experimental benchmark datasets created in-house. Our results demonstrate that unmixing autoencoders provide improved accuracy, robustness and efficiency compared to standard unmixing methods. We also showcase the applicability of autoencoders to complex biological settings by showing improved biochemical characterization of volumetric Raman imaging data from a monocytic cell.