Presentation
13 March 2024 Enhancing multi-layer cerebral analysis in NIRS: a deep learning approach
Author Affiliations +
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
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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
Advertisement
Advertisement
KEYWORDS
Data modeling

Near infrared spectroscopy

Absorption

Brain tissue

Anatomy

Deep learning

Education and training

Back to Top