Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders

Journal article

Raman spectroscopy is widely used across scientific domains 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 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.

Authors: Georgiev, D; Fernández-Galiana, Á; Pedersen, SV; Papadopoulos, G; Xie, R

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: National Academy of Sciences
• Journal: Proceedings of the National Academy of Sciences
• Volume: 121
• Issue: 45
• Article number: e2407439121
• Place of publication: United States
• Publication date: 2024-10-29
• Acceptance date: 2024-09-10
• DOI: 10.1073/pnas.2407439121
• EISSN: 1091-6490
• ISSN: 0027-8424
• Pmid: 39471214
• Language: English
• Keywords: Raman spectroscopy; shyperspectral unmixing; machine learning; autoencoder; chemometrics