PROJECT TITLE :

Nonparametric Hemodynamic Deconvolution of fMRI Using Homomorphic Filtering

ABSTRACT:

Functional magnetic resonance imaging (fMRI) is an indirect live of neural activity that is modeled as a convolution of the latent neuronal response and the hemodynamic response function (HRF). Since the sources of HRF variability will be nonneural in nature, the measured fMRI signal will not faithfully represent underlying neural activity. Thus, it's advantageous to deconvolve the HRF from the fMRI signal. But, since both latent neural activity and therefore the voxel-specific HRF is unknown, the deconvolution should be blind. Existing blind deconvolution approaches employ highly parameterized models, and it's unclear whether these models have an over fitting problem. So as to handle these issues, we one) present a nonparametric deconvolution methodology primarily based on homomorphic filtering to obtain the latent neuronal response from the fMRI signal and, a pair of) compare our approach to the simplest performing existing parametric model based mostly on the estimation of the biophysical hemodynamic model using the Cubature Kalman Filter/Smoother. We tend to hypothesized that if the results from nonparametric deconvolution closely resembled that obtained from parametric deconvolution, then the problem of over fitting during estimation in highly parameterized deconvolution models of fMRI might probably be over stated. Both simulations and experimental results demonstrate support for our hypothesis since the estimated latent neural response from both parametric and nonparametric methods were highly correlated in the visual cortex. Further, simulations showed that each methods were effective in recovering the simulated ground truth of the latent neural response.


Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here


PROJECT TITLE : Nonparametric joint shape and feature priors for segmentation of Dendritic spines - 2016 ABSTRACT: Multimodal form density estimation is a difficult task in many biomedical image segmentation problems. Existing
PROJECT TITLE :Proportional-Integral Stabilizing Control of a Class of MIMO Systems Subject to Nonparametric Uncertainties by Additive-State-Decomposition Dynamic Inversion DesignABSTRACT:Based mostly on the additive-state-decomposition
PROJECT TITLE :Nonparametric Estimation of Time-Varying Systems Using 2-D RegularizationABSTRACT:In this paper a nonparametric time-domain estimation methodology of linear time-varying systems from measured noisy knowledge is
PROJECT TITLE :Cognitive chaotic UWB-MIMO radar based on nonparametric Bayesian techniqueABSTRACT:This work presents a cognitive waveform choice mechanism for chaotic ultra-wideband multiple-input multiple-output (MIMO) radars.
PROJECT TITLE :Bayesian Nonparametric Reward Learning From DemonstrationABSTRACT:Learning from demonstration provides an attractive solution to the problem of teaching autonomous systems the way to perform complex tasks. Reward

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry