Nonlinear neural network for hemodynamic model state and input estimation using fMRI data

• Published in: Biomedical signal processing and control Vol. 14; pp. 240 - 247
• Main Authors: Karam, Ayman M., Laleg-Kirati, Taous Meriem, Zayane, Chadia, Kashou, Nasser H.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-11-2014
• Subjects: Block design; BOLD; Event-related; fMRI; Hemodynamic model; Neural activity; Neural networks; Nonlinear autoregressive with exogenous input (NARX); State estimation; Nonlinear autoregressive with exogenous input (NARX); fMRI; Block design; Neural networks; Neural activity; Hemodynamic model; BOLD; Event-related; State estimation
• ISSN: 1746-8094
• DOI: 10.1016/j.bspc.2014.07.004

•We implemented NARX networks to estimate the hemodynamic states.•The method has been used to estimate the neural activity.•We optimized the structure of the NARX networks.•Blocked and event-related BOLD real data were used.•The method is accurate and robust even in the presence of signal noise.
Originally inspired by biological neural networks, artificial neural networks (ANNs) are powerful mathematical tools that can solve complex nonlinear problems such as filtering, classification, prediction and more. This paper demonstrates the first successful implementation of ANN, specifically nonlinear autoregressive with exogenous input (NARX) networks, to estimate the hemodynamic states and neural activity from simulated and measured real blood oxygenation level dependent (BOLD) signals. Blocked and event-related BOLD data are used to test the algorithm on real experiments. The proposed method is accurate and robust even in the presence of signal noise and it does not depend on sampling interval. Moreover, the structure of the NARX networks is optimized to yield the best estimate with minimal network architecture. The results of the estimated neural activity are also discussed in terms of their potential use.