Enhancing multi-layer cerebral analysis in NIRS: a deep learning approach

Jingyi Wu; Jiachen Dou; Jana M. Kainerstorfer

doi:10.1117/12.3001930

13 March 2024 Enhancing multi-layer cerebral analysis in NIRS: a deep learning approach

Jingyi Wu, Jiachen Dou, Jana M. Kainerstorfer

Proceedings Volume PC12828, Neural Imaging and Sensing 2024; PC1282809 (2024) https://doi.org/10.1117/12.3001930
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

In this study, we present a physics-informed deep learning model for predicting partial pathlength and absorption changes in human brain using Near-Infrared Spectroscopy (NIRS). Leveraging the multi-layer modified Beer Lamber Law, our model overcomes the limitations of conventional approach that assumes tissue homogeneity. Trained on synthetic data generated from a multi-layer forward model, out model was tested on Monte Carlo simulations of both two and three-layer geometries, demonstrating robust performance despite encountering varying optical properties and anatomical complexities. Future work will focus on refining the model and testing it on multi-layer optical phantoms and human subjects.

Conference Presentation

Citation Download Citation

Jingyi Wu, Jiachen Dou, and Jana M. Kainerstorfer "Enhancing multi-layer cerebral analysis in NIRS: a deep learning approach", Proc. SPIE PC12828, Neural Imaging and Sensing 2024, PC1282809 (13 March 2024); https://doi.org/10.1117/12.3001930

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