High-fidelity hyperspectral SRS imaging by permutation noise2noise denoiser (PEND)

Guangrui Ding

doi:10.1117/12.3001751

13 March 2024 High-fidelity hyperspectral SRS imaging by permutation noise2noise denoiser (PEND)

Guangrui Ding

Proceedings Volume PC12855, Advanced Chemical Microscopy for Life Science and Translational Medicine 2024; PC128551C (2024) https://doi.org/10.1117/12.3001751
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

Stimulated Raman scattering (SRS) microscopy has emerged as a valuable tool with manifold biomedical applications. Due to the physical limits of Raman cross section, enhancing chemical information bandwidths comes at the price of decreasing the signal-to-noise ratio (SNR). One appealing approach to combat the physical limits is denoising. In this work, we propose a self-supervised Noise2Noise 3D Unet denoiser for three-dimensional SRS imaging. To demonstrate the limit-breaking capability, we denoised three types of three-dimensional SRS datasets, including hyperspectral, volumetric, and longitudinal, under extreme experimental conditions with low SNR. Our results highlight the potential for boosting the physical limits by integration of instrumentation and computation.

Conference Presentation

Citation Download Citation

Guangrui Ding "High-fidelity hyperspectral SRS imaging by permutation noise2noise denoiser (PEND)", Proc. SPIE PC12855, Advanced Chemical Microscopy for Life Science and Translational Medicine 2024, PC128551C (13 March 2024); https://doi.org/10.1117/12.3001751

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available