2017
DOI: 10.3389/fninf.2017.00016
|View full text |Cite
|
Sign up to set email alerts
|

Detection of Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Longitudinal Brain MRI

Abstract: Mild Cognitive Impairment (MCI) is an intermediate stage between healthy and Alzheimer's disease (AD). To enable early intervention it is important to identify the MCI subjects that will convert to AD in an early stage. In this paper, we provide a new method to distinguish between MCI patients that either convert to Alzheimer's Disease (MCIc) or remain stable (MCIs), using only longitudinal T1-weighted MRI. Currently, most longitudinal studies focus on volumetric comparison of a few anatomical structures, ther… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
30
0

Year Published

2018
2018
2021
2021

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 30 publications
(30 citation statements)
references
References 59 publications
0
30
0
Order By: Relevance
“…Especially the MCI subgroups are difficult to distinguish as they are in the same disease stage of the continuum. Longitudinal data could avoid the limitations of cross-sectional analyses [ 58–61 ], however in our cohort also no differences between the stable MCI patients and MCI converters were detected in the longitudinal analyses. Probably, this is due to a small sample size of available longitudinal MRI scans in MCI patients ( n = 50, of which 9 converters).…”
Section: Discussionmentioning
confidence: 82%
“…Especially the MCI subgroups are difficult to distinguish as they are in the same disease stage of the continuum. Longitudinal data could avoid the limitations of cross-sectional analyses [ 58–61 ], however in our cohort also no differences between the stable MCI patients and MCI converters were detected in the longitudinal analyses. Probably, this is due to a small sample size of available longitudinal MRI scans in MCI patients ( n = 50, of which 9 converters).…”
Section: Discussionmentioning
confidence: 82%
“…There is a growing interest in using machine learning to understand disease progression, and this is made possible by the available datasets for neurodegenerative disorders (Marcus et al, 2010). Researchers have used this longitudinal data to create brain development trajectories used to predict the risk of developing AD (Lawrence et al, 2017), to develop clinical symptom trajectories (Bhagwat et al, 2018) to extract essential brain features in MCI classification (Huang et al, 2017; Sun et al, 2017), and to investigate different stages of AD progression from a multi-modal imaging standpoint (Gray et al, 2012; Rodrigues et al, 2014; Nozadi et al, 2018). Similar work in Parkinson's disease used longitudinal connectome data as a marker for neurodegenerative progression (Peña-Nogales et al, 2018).…”
Section: Introductionmentioning
confidence: 99%
“…Table shows that the nested LOOCV method can select the optimal feature dimension for different between‐group comparisons and receives the best classification performance in this dimension. The accuracy rates obtained by the classification method and the feature combination strategy are all higher than those of previous studies . The accuracies, sensitivities, specificities, PPVs, NPVs and AUCs have been greatly improved after the combination of longitudinal time points (ie, bl + 12 m and bl + 12 m + 24 m).…”
Section: Discussionmentioning
confidence: 69%