Multimodal Data Fusion of Deep Learning and Dynamic Functional Connectivity Features to Predict Alzheimer’s Disease Progression *

2019 ◽  
Author(s):  
Anees Abrol ◽  
Zening Fu ◽  
Yuhui Du ◽  
Vince D. Calhoun
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Functional Connectivity ◽  
Data Fusion ◽  
Disease Progression ◽  
Dynamic Functional Connectivity ◽  
Multimodal Data ◽  
Multimodal Data Fusion

scholarly journals Cognitive Improvement is Correlated with Increased Dynamic Functional Connectivity of Default Mode Network by Personalized rTMS in Alzheimer's Disease

2021 ◽  
Author(s):  
Lili Wei ◽  
Jintao Wang ◽  
Yingchun Zhang ◽  
Luoyi Xu ◽  
Kehua Yang ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Functional Connectivity ◽  
Default Mode Network ◽  
Present Report ◽  
Verbal Learning ◽  
Dynamic Functional Connectivity ◽  
Default Mode ◽  
Cognitive Improvement ◽  
Promising Therapeutic Approach

Abstract Background Repetitive transcranial magnetic stimulation (rTMS) is thought to be a promising therapeutic approach for Alzheimer's disease patients. Methods In the present report, a double-blind, randomized, sham-controlled rTMS trial was conducted in mild-to-moderate Alzheimer's disease patients. High-frequency rTMS was delivered to a subject-specific left lateral parietal region that demonstrated highest functional connectivity with the hippocampus using resting-state fMRI. The Mini Mental State Examination (MMSE) and Philadelphia Verbal Learning Test (PVLT) were used to evaluate patients’ cognitive functions. Results Patients receiving active rTMS treatment (n = 31) showed a significant increase in the MMSE, PVLT-Immediate recall, and PVLT-Short Delay recall scores after two weeks of rTMS treatment, whereas patients who received sham rTMS (n = 27) did not show significant changes in these measures. Dynamic functional connectivity (dFC) magnitude of the default mode network (DMN) in the active-rTMS group showed a significant increase after two weeks of rTMS treatment, and no significant changes were found in the sham-rTMS group. There was a significantly positive correlation between changes of the MMSE and changes of the dFC magnitude of DMN in the active-rTMS group, but not the sham-rTMS group. Conclusions Our findings are novel in demonstrating the feasibility and effectiveness of the fMRI-guided rTMS treatment in Alzheimer's disease patients, and DMN might play a vital role in therapeutic effectiveness of rTMS in Alzheimer’s disease. Trial registration: China National Medical Research Platform (http://114.255.48.20/login, No:MR-33-20-004217), retrospectively registered 2020-12-23.

scholarly journals A Survey on Deep Learning for Multimodal Data Fusion

2020 ◽  
Vol 32 (5) ◽  
pp. 829-864 ◽  
Author(s):  
Jing Gao ◽  
Peng Li ◽  
Zhikui Chen ◽  
Jianing Zhang
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Data Fusion ◽  
High Volume ◽  
Fusion Method ◽  
Learning Models ◽  
Multimodal Data ◽  
Fusion Methods ◽  
Multimodal Data Fusion ◽  
Future Topics

With the wide deployments of heterogeneous networks, huge amounts of data with characteristics of high volume, high variety, high velocity, and high veracity are generated. These data, referred to multimodal big data, contain abundant intermodality and cross-modality information and pose vast challenges on traditional data fusion methods. In this review, we present some pioneering deep learning models to fuse these multimodal big data. With the increasing exploration of the multimodal big data, there are still some challenges to be addressed. Thus, this review presents a survey on deep learning for multimodal data fusion to provide readers, regardless of their original community, with the fundamentals of multimodal deep learning fusion method and to motivate new multimodal data fusion techniques of deep learning. Specifically, representative architectures that are widely used are summarized as fundamental to the understanding of multimodal deep learning. Then the current pioneering multimodal data fusion deep learning models are summarized. Finally, some challenges and future topics of multimodal data fusion deep learning models are described.

scholarly journals The heterogeneous functional architecture of the posteromedial cortex is associated with selective functional connectivity differences in Alzheimer’s disease

2019 ◽  
Author(s):  
Wasim Khan ◽  
Ali Amad ◽  
Vincent Giampietro ◽  
Emilio Werden ◽  
Sara De Simoni ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Functional Connectivity ◽  
Disease Progression ◽  
Large Scale ◽  
Posterior Cingulate Cortex ◽  
Subjective Memory ◽  
Functional Architecture ◽  
Human Connectome Project ◽  
Data Driven Approach

AbstractThe posteromedial cortex (PMC) is a key region involved in the development and progression of Alzheimer’s disease (AD). Previous studies have demonstrated a heterogenous functional architecture of the region, with different subdivisions reflecting distinct connectivity profiles. However, little is understood about PMC functional connectivity and its differential vulnerability to AD pathogenesis. Using a data-driven approach, we applied a constrained independent component analysis (ICA) on healthy adults from the Human Connectome Project (HCP) to characterise the distinct functional subdivisions and unique functional-anatomic connectivity patterns of the PMC. These connectivity profiles were subsequently quantified in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study, to examine functional connectivity differences in (1) AD patients and cognitively normal (CN) participants and (2) the entire AD pathological spectrum, ranging from CN participants and participants with subjective memory complaints (SMC), through to those with mild cognitive impairment (MCI), and finally, patients diagnosed with AD. Our findings revealed decreased functional connectivity in the anterior precuneus, dorsal posterior cingulate cortex, and the central precuneus in AD patients compared to CN participants. Functional abnormalities in these subdivisions were also related to high amyloid burden and lower hippocampal volumes. Across the entire AD spectrum, functional connectivity of the central precuneus was associated with disease progression and specific deficits in memory and executive function. These findings provide new evidence showing that specific vulnerabilities in PMC functional connectivity are associated with large-scale network disruptions in AD and that these patterns may be useful for elucidating potential biomarkers for measuring disease progression in future work.

scholarly journals Abnormal dynamic functional connectivity in Alzheimer’s disease

2020 ◽  
Vol 26 (9) ◽  
pp. 962-971 ◽  
Author(s):  
Yue Gu ◽  
Ying Lin ◽  
Liangliang Huang ◽  
Junji Ma ◽  
Jinbo Zhang ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Functional Connectivity ◽  
Dynamic Functional Connectivity

Hippocampus-Based Dynamic Functional Connectivity Mapping in the Early Stages of Alzheimer’s Disease

2021 ◽  
pp. 1-12
Author(s):  
Jianlin Wang ◽  
Pan Wang ◽  
Yuan Jiang ◽  
Zedong Wang ◽  
Hong Zhang ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Functional Connectivity ◽  
Anterior Lobe ◽  
Dynamic Functional Connectivity ◽  
Seed Point ◽  
Left And Right ◽  
The Common

Background: The hippocampus with varying degrees of atrophy was a crucial neuroimaging feature resulting in the declining memory and cognitive function in Alzheimer’s disease (AD). However, the abnormal dynamic functional connectivity (DFC) in both white matter (WM) and gray matter (GM) from the left and right hippocampus remains unclear. Objective: To explore the abnormal DFC within WM and GM from the left and right hippocampus across the different stages of AD. Methods: Current study employed the OASIS-3 dataset including 43 mild cognitive impairment (MCI), 71 pre-mild cognitive impairment (pre-MCI), and matched 87 normal cognitive (NC). Adopting the FMRIB’s Integrated Registration and Segmentation Tool, we obtained the left and right hippocampus mask. Based on above hippocampus mask as seed point, we calculated the DFC between left/right hippocampus and all voxel time series within whole brain. One-way ANOVA analysis was performed to estimate the abnormal DFC among MCI, pre-MCI, and NC groups. Results: We found that MCI and pre-MCI groups showed the common abnormalities of DFC in the Temporal_Mid_L, Cingulum_Mid_L, and Thalamus_L. Specific abnormalities were found in the Cerebelum_9_L and Precuneus of MCI group and Vermis_8 and Caudate_L of pre-MCI group. In addition, we found that DFC within WM regions also showed the common low DFC for the Cerebellum anterior lobe-WM, Corpus callosum, and Frontal lobe-WM in MCI and pre-MCI group. Conclusion: Our findings provided a novel information for discover the pathophysiological mechanisms of AD and indicate WM lesions were also an important cause of cognitive decline in AD.

scholarly journals Predicting Alzheimer’s disease progression using multi-modal deep learning approach

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Garam Lee ◽  
◽  
Kwangsik Nho ◽  
Byungkon Kang ◽  
Kyung-Ah Sohn ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Disease Progression ◽  
Learning Approach
Sign in / Sign up

Export Citation Format

Share Document