An open source energy efficient hybrid Monte Carlo and machine learning algorithm for assessing light transport in turbid scattering media

Vinh Nguyen; Abigail Clennell; Vladislav V. Yakovlev; Alexander Doronin

doi:10.1117/12.3003641

12 March 2024 An open source energy efficient hybrid Monte Carlo and machine learning algorithm for assessing light transport in turbid scattering media

Vinh Nguyen, Abigail Clennell, Vladislav V. Yakovlev, Alexander Doronin

Author Affiliations +

Proceedings Volume 12841, Dynamics and Fluctuations in Biomedical Photonics XXI; 1284109 (2024) https://doi.org/10.1117/12.3003641
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

Fundamental understanding of complex effects of wave propagation in turbid media requires accurate computational techniques to take into account the effects of multiple scattering of light. We present an open-source Monte Carlo algorithm designed for energy-efficient processors, surpassing existing solutions in both accuracy and performance. Our implementation optimizes photon transport simulations using Apple’s low-power, high-performance M-family chips. Additionally, we explore integrating Machine Learning (ML) techniques to efficiently create a forward solver for the Radiative Transport Equation, identifying top-performing ML models. Our open-source software package integrates ML, optimizing photon transport simulations and facilitating customization for specific applications. Extensive validation against common solvers in biomedical imaging demonstrates comparable accuracy with significantly reduced computational time and energy consumption. This approach maintains accuracy while drastically reducing computational time and energy consumption, offering a promising emerging concept/solution for simulating light propagation in turbid media.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Vinh Nguyen, Abigail Clennell, Vladislav V. Yakovlev, and Alexander Doronin "An open source energy efficient hybrid Monte Carlo and machine learning algorithm for assessing light transport in turbid scattering media", Proc. SPIE 12841, Dynamics and Fluctuations in Biomedical Photonics XXI, 1284109 (12 March 2024); https://doi.org/10.1117/12.3003641

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