Removing non-resonant background of CARS signal with generative adversarial network
Ziyi Luo, Xiangcong Xu, Danying Lin, Junle Qu, Fangrui Lin, Jia Li
Abstract
Coherent anti-Stokes Raman scattering (CARS) microscopy requires the removal of non-resonant background (NRB) to ensure spectral accuracy and quality. This study introduces a deep-learning-based algorithm that leverages its enhanced capability for NRB removal and spectra retrieval. A generative adversarial network is trained using simulated noisy CARS data, enabling straightforward analysis of real CARS spectra obtained from pork belly and living mice brains. The results highlight the algorithm's ability to accurately extract vibrational information in the CH region. Importantly, this method eliminates the need for additional experimental measurements or extensive data preprocessing or postprocessing.