The application of a unified Monte Carlo model in the training of artificial neural networks for the purpose of real-time in-vivo sensing of tissue optical properties

Alexander Doronin; Igor Meglinski

doi:10.1117/12.2518566

13 May 2019 The application of a unified Monte Carlo model in the training of artificial neural networks for the purpose of real-time in-vivo sensing of tissue optical properties

Alexander Doronin, Igor Meglinski

Author Affiliations +

Proceedings Volume 10982, Micro- and Nanotechnology Sensors, Systems, and Applications XI; 109820N (2019) https://doi.org/10.1117/12.2518566
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Current report consider development of a unified MC-based simulation platform for needs of Biomedical Optics and its practical use in the creation of novel Optical Diagnostics, Imaging and Sensing modalities aided by the Artificial Intelligence (AI) methods. It will be demonstrated how the developed MC platform can be utilized in the generation of validated lookup tables/labeled data sets and subsequent training of several configurations of Artificial Intelligence (AI) based methods for the purpose of real-time estimation of certain specific tissue properties of interest such as distributions of melanin, blood, oxygenation, etc. The prototypes of lightweight AI-empowered sensing solutions that could potentially be shrank onto a smartphone/wearable device form-factor will be presented and their performance will be compared with traditional spectroscopy-based methods using phantom and in vivo experimental data obtained during clinical studies.

Conference Presentation

Citation Download Citation

Alexander Doronin and Igor Meglinski "The application of a unified Monte Carlo model in the training of artificial neural networks for the purpose of real-time in-vivo sensing of tissue optical properties", Proc. SPIE 10982, Micro- and Nanotechnology Sensors, Systems, and Applications XI, 109820N (13 May 2019); https://doi.org/10.1117/12.2518566

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