P3-417: INDIVIDUALIZED STRUCTURAL CONNECTOME FOR DIAGNOSTIC AND PROGNOSTIC PREDICTION OF ALZHEIMER'S DISEASE

2006 ◽  
Vol 14 (7S_Part_23) ◽  
pp. P1266-P1267
Author(s):  
Yun Wang ◽  
Chenxiao Xu ◽  
Seonjoo Lee ◽  
Yaakov Stern ◽  
Jong Hun Kim ◽  
...  
2018 ◽  
Vol 2 (2) ◽  
pp. 241-258 ◽  
Author(s):  
Shelli R. Kesler ◽  
Paul Acton ◽  
Vikram Rao ◽  
William J. Ray

Neurodegeneration in Alzheimer’s disease (AD) is associated with amyloid-beta peptide accumulation into insoluble amyloid plaques. The five-familial AD (5XFAD) transgenic mouse model exhibits accelerated amyloid-beta deposition, neuronal dysfunction, and cognitive impairment. We aimed to determine whether connectome properties of these mice parallel those observed in patients with AD. We obtained diffusion tensor imaging and resting-state functional magnetic resonance imaging data for four transgenic and four nontransgenic male mice. We constructed both structural and functional connectomes and measured their topological properties by applying graph theoretical analysis. We compared connectome properties between groups using both binarized and weighted networks. Transgenic mice showed higher characteristic path length in weighted structural connectomes and functional connectomes at minimum density. Normalized clustering and modularity were lower in transgenic mice across the upper densities of the structural connectome. Transgenic mice also showed lower small-worldness index in higher structural connectome densities and in weighted structural networks. Hyper-correlation of structural and functional connectivity was observed in transgenic mice compared with nontransgenic controls. These preliminary findings suggest that 5XFAD mouse connectomes may provide useful models for investigating the molecular mechanisms of AD pathogenesis and testing the effectiveness of potential treatments.


NeuroImage ◽  
2018 ◽  
Vol 183 ◽  
pp. 438-455 ◽  
Author(s):  
Thomas H. Alderson ◽  
Arun L.W. Bokde ◽  
J.A. Scott Kelso ◽  
Liam Maguire ◽  
Damien Coyle

2019 ◽  
Vol 13 (3) ◽  
pp. 1791-1816
Author(s):  
Arkaprava Roy ◽  
Subhashis Ghosal ◽  
Jeffrey Prescott ◽  
Kingshuk Roy Choudhury

Author(s):  
F Ramírez-Toraño ◽  
Kausar Abbas ◽  
Ricardo Bruña ◽  
Silvia Marcos de Pedro ◽  
Natividad Gómez-Ruiz ◽  
...  

Abstract The concept of the brain has shifted to a complex system where different subnetworks support the human cognitive functions. Neurodegenerative diseases would affect the interactions among these subnetworks and, the evolution of impairment and the subnetworks involved would be unique for each neurodegenerative disease. In this study, we seek for structural connectivity traits associated with the family history of Alzheimer’s disease, i.e., early signs of subnetworks impairment due to Alzheimer’s disease.3. The sample in this study consisted of 123 first-degree Alzheimer’s disease relatives and 61 non-relatives. For each subject, structural connectomes were obtained using classical diffusion tensor imaging measures and different resolutions of cortical parcellation. For the whole sample, independent structural-connectome-traits were obtained under the framework of connICA. Finally, we tested the association of the structural-connectome-traits with different factors of relevance for Alzheimer’s disease by means of a multiple linear regression. The analysis revealed a structural-connectome-trait obtained from fractional anisotropy associated with the family history of Alzheimer’s disease. The structural-connectome-trait presents a reduced fractional anisotropy pattern in first-degree relatives in the tracts connecting posterior areas and temporal areas. The family history of Alzheimer’s disease structural-connectome-trait presents a posterior–posterior and posterior-temporal pattern, supplying new evidences to the cascading network failure model.


Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7259
Author(s):  
Deevyankar Agarwal ◽  
Gonçalo Marques ◽  
Isabel de la Torre-Díez ◽  
Manuel A. Franco Martin ◽  
Begoña García Zapiraín ◽  
...  

Alzheimer’s disease (AD) is a remarkable challenge for healthcare in the 21st century. Since 2017, deep learning models with transfer learning approaches have been gaining recognition in AD detection, and progression prediction by using neuroimaging biomarkers. This paper presents a systematic review of the current state of early AD detection by using deep learning models with transfer learning and neuroimaging biomarkers. Five databases were used and the results before screening report 215 studies published between 2010 and 2020. After screening, 13 studies met the inclusion criteria. We noted that the maximum accuracy achieved to date for AD classification is 98.20% by using the combination of 3D convolutional networks and local transfer learning, and that for the prognostic prediction of AD is 87.78% by using pre-trained 3D convolutional network-based architectures. The results show that transfer learning helps researchers in developing a more accurate system for the early diagnosis of AD. However, there is a need to consider some points in future research, such as improving the accuracy of the prognostic prediction of AD, exploring additional biomarkers such as tau-PET and amyloid-PET to understand highly discriminative feature representation to separate similar brain patterns, managing the size of the datasets due to the limited availability.


Sign in / Sign up

Export Citation Format

Share Document