Gaussian Processes (GP) are a powerful tool to capture the complex time-variations of a dataset. In the context of medical imaging analysis, they allow a robust modelling even in case of highly uncertain or incomplete datasets. Predictions from GP are dependent of the covariance kernel function selected to explain the data variance. To overcome this limitation, we propose a framework to identify the optimal covariance kernel function to model the data.The optimal kernel is defined as a composition of base kernel functions used to identify correlation patterns between data points. Our approach includes a modified version of the Compositional Kernel Learning (CKL) algorithm, in which we score the kernel families using a new energy function that depends both the Bayesian Information Criterion (BIC) and the explained variance score. We applied the proposed framework to model the progression of neurodegenerative diseases over time, in particular the progression of autosomal dominantly-inherited Alzheimer's disease, and use it to predict the time to clinical onset of subjects carrying genetic mutation.
KEYWORDS: Brain activation, Data modeling, Cognitive modeling, Statistical analysis, Near infrared spectroscopy, Brain, Hemodynamics, Brain mapping, Functional magnetic resonance imaging, Control systems
We evaluated frontal brain activation during a mixed attentional/working memory task with graded levels of difficulty in a group of 19 healthy subjects, by means of time-domain functional near-infrared spectroscopy (fNIRS). Brain activation was assessed, and load-related oxy- and deoxy-hemoglobin changes were studied. Generalized linear model (GLM) was applied to the data to explore the metabolic processes occurring during the mental effort and, possibly, their involvement in short-term memorization. GLM was applied to the data twice: for modeling the task as a whole and for specifically investigating brain activation at each cognitive load. This twofold employment of GLM allowed (1) the extraction and isolation of different information from the same signals, obtained through the modeling of different cognitive categories (sustained attention and working memory), and (2) the evaluation of model fitness, by inspection and comparison of residuals (i.e., unmodeled part of the signal) obtained in the two different cases. Results attest to the presence of a persistent attentional-related metabolic activity, superimposed to a task-related mnemonic contribution. Some hemispherical differences have also been highlighted frontally: deoxy-hemoglobin changes manifested a strong right lateralization, whereas modifications in oxy- and total hemoglobin showed a medial localization. The present work successfully explored the capability of fNIRS to detect the two neurophysiological categories under investigation and distinguish their activation patterns.
A multimodality approach based on fNIRS-EEG, fMRI-EEG and TMS was used on adult volunteers during
motor task aiming at optimizing a functional imaging procedure to be eventually used on patients with
movement disorders.
We evaluated the vascular response correlated to neural activity within a working memory "n-back" task in a population
of healthy volunteers by means of time-resolved near-infrared functional spectroscopy and Generalized Linear Models.
Moreover, we attempted a separation of purely cortical activation from non-cerebral contribution.
We evaluated frontal brain activation during a working memory task with graded levels of difficulty in a group of 19
healthy subjects, by means of time-resolved fNIRS technique. Brain activation was computed, and was then separated
into a "block-related" and a "tonic" components. Load-related increases of blood oxygenation were studied for the four
different levels of task difficulty. Generalized Linear Models were applied to the data in order to explore the metabolic
processes occurring during the mental effort and, possibly, their involvement in short term memorization. Results attest
the presence of a persistent attentional-related metabolic activity, superimposed to a task-related mnemonic contribution.
Moreover, a systemic component probably deriving from the extra-cerebral capillary bed was detected.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.