Removing non-resonant background from broadband CARS using a physics-informed neural network

Muddiman, Ryan; O’Dwyer, Kevin; Camp, Charles H.; Hennelly, Bryan M.

doi:10.1039/d3ay01131c

Cited by 6 publications

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Recent Progress in Deep Learning for Improving Coherent Anti‐Stokes Raman Scattering Microscopy

Yao,

Lin,

Luo

et al. 2024

Laser & Photonics Reviews

View full text Add to dashboard Cite

Coherent anti‐Stokes Raman scattering (CARS) microscopy is a powerful label‐free imaging technique that leverages biomolecular vibrations and is widely used in different fields. However, its intrinsic non‐resonant background (NRB) can distort Raman signals and compromise spectral fidelity. Conventional data analysis methods for CARS encounter a bottleneck in achieving high accuracy. Furthermore, CARS requires balancing imaging speed against image quality. In recent years, endeavors in deep learning have effectively overcome these obstacles, advancing the development of CARS. This review highlights the research that applies deep learning to mitigate NRB, classify CARS data for disease identification, and denoise images. Each approach is delineated in terms of network architecture, training data, and loss functions. Finally, the challenges in this field is discussed and using the latest deep learning advancement is suggested to enhance the reliability and efficiency of CARS microscopy.

show abstract

Recent Progress in Deep Learning for Improving Coherent Anti‐Stokes Raman Scattering Microscopy

Yao,

Lin,

Luo

et al. 2024

Laser & Photonics Reviews

View full text Add to dashboard Cite

show abstract

Removing non-resonant background of CARS signal with generative adversarial network

Luo,

Xu,

Lin

et al. 2024

Applied Physics Letters

View full text Add to dashboard Cite

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.

show abstract

Spectral interferometric polarization-CARS for hyperspectral imaging

Muddiman,

Hennelly

2023

Optics in Health Care and Biomedical Optics XIII

Self Cite

View full text Add to dashboard Cite

The third-order nonlinear nature of Broadband CARS means it has the inherent capability to produce label-free images using vibrational information as contrast. The speed of the technique is several orders of magnitude greater than spontaneous Raman spectroscopy. This has implications for enabling diagnostics in areas such as histology, immunology and cytology. The major drawback in BCARS currently preventing these applications is mainly the nonresonant background, present due to degenerate four-wave mixing. This background can be removed using the tensorial properties of the electronic susceptibility. This technique is known as spectral interferometric polarization CARS (SIP-CARS). We show an implementation of SIP-CARS on highly resonant polymer beads for spectroscopic imaging using two sequential BCARS scans to probe different components of the susceptibility tensor.

show abstract

Removing non-resonant background from broadband CARS using a physics-informed neural network

Abstract: Broadband Coherent Anti-Stokes Raman Scattering (BCARS) is capable of producing high-quality Raman spectra spanning broad bandwidths, 400-4000 cm−1, with millisecond acquisition times. Raw BCARS spectra, however, are a coherent combination...

Cited by 6 publications

References 26 publications

Recent Progress in Deep Learning for Improving Coherent Anti‐Stokes Raman Scattering Microscopy

Recent Progress in Deep Learning for Improving Coherent Anti‐Stokes Raman Scattering Microscopy

Removing non-resonant background of CARS signal with generative adversarial network

Spectral interferometric polarization-CARS for hyperspectral imaging

Contact Info

Product

Resources

About