Abstract
Many methods have been proposed in the literature for diagnosis of Alzheimer's disease (AD) in the early stages, among which the graph-based methods have been more popular, because of their capability to utilize the relational information among different brain regions. Here, we design a novel graph signal processing based integrated AD detection model using multimodal deep learning that simultaneously utilizes both the static and the dynamic brain connectivity based features extracted from resting-state fMRI (rs-fMRI) data to detect AD in the early stages. First, our earlier proposed state-space model (SSM) based graph connectivity dynamics characterization method is used to design a modified dynamic connectivity based AD detection model. After verifying its utility, this dynamic connectivity based model is integrated with our earlier designed static connectivity based AD detection model using the intermediate level integration approach of the multimodal deep learning, to construct our proposed integrated AD detection model. To verify the effectiveness of the designed AD detection models, the models are applied on the rs-fMRI data, extracted from ADNI dataset. Superior performance of our proposed AD diagnosis method corroborates its utility in AD detection application.
Highlights
Alzheimer's disease (AD) is a chronic neurological disease, causing degeneration of brain cells that results in memory loss and cognitive decline, and thereby hindering a person's independent functionality
To circumvent the drawbacks associated with the existing AD detection methods, in this work, we design a novel integrated AD detection model using the concepts of graph signal processing (GSP) that exploits both the static and the dynamic graph connectivity based features extracted from resting-state functional MRI (fMRI) signal for diagnosis of AD at the early stages
5 Conclusions In this paper, a novel GSP based integrated AD detection model is designed wherein both the static and the dynamic brain connectivity based features extracted from resting-state fMRI (rs-fMRI) data are simultaneously utilized for early detection of AD
Summary
Alzheimer's disease (AD) is a chronic neurological disease, causing degeneration of brain cells that results in memory loss and cognitive decline, and thereby hindering a person's independent functionality. In a similar work [5], Suk et al proposed a deep Boltzmann machine (DBM) based AD detection model wherein the discriminating features are extracted from the multimodal neuroimaging data using DBM that are used for training a support vector machine (SVM) classifier that acts as a final classifier These machine learning based approaches provided satisfactory results in AD detection, their performance is fundamentally limited by their inability to extract the additional relational information among distinct brain regions. To circumvent the drawbacks associated with the existing AD detection methods, in this work, we design a novel integrated AD detection model using the concepts of GSP that exploits both the static and the dynamic graph connectivity based features extracted from resting-state fMRI (rs-fMRI) signal for diagnosis of AD at the early stages. In this work, we design a graph signal processing based AD detection model using rs-fMRI data, more about which is explained
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
