188 663

Cited 7 times in

The diagnostic potential of multimodal neuroimaging measures in Parkinson's disease and atypical parkinsonism

 Chang-Hyun Park  ;  Phil Hyu Lee  ;  Seung-Koo Lee  ;  Seok Jong Chung  ;  Na-Young Shin 
 BRAIN AND BEHAVIOR, Vol.10(11) : e01808, 2020-11 
Journal Title
Issue Date
Parkinson's disease ; functional MRI ; machine learning ; multiple system atrophy ; progressive supranuclear palsy ; structural MRI
Introduction: For the diagnosis of Parkinson's disease (PD) and atypical parkinsonism (AP) using neuroimaging, structural measures have been largely employed since structural abnormalities are most noticeable in the diseases. Functional abnormalities have been known as well, though less clearly seen, and thus, the addition of functional measures to structural measures is expected to be more informative for the diagnosis. Here, we aimed to assess whether multimodal neuroimaging measures of structural and functional alterations could have potential for enhancing performance in diverse diagnostic classification problems.

Methods: For 77 patients with PD, 86 patients with AP comprising multiple system atrophy and progressive supranuclear palsy, and 53 healthy controls (HC), structural and functional MRI data were collected. Gray matter (GM) volume was acquired as a structural measure, and GM regional homogeneity and degree centrality were acquired as functional measures. The measures were used as predictors individually or in combination in support vector machine classifiers for different problems of distinguishing between HC and each diagnostic type and between different diagnostic types.

Results: In statistical comparisons of the measures, structural alterations were extensively seen in all diagnostic types, whereas functional alterations were limited to specific diagnostic types. The addition of functional measures to the structural measure generally yielded statistically significant improvements to classification accuracy, compared to the use of the structural measure alone.

Conclusion: We suggest the fusion of multimodal neuroimaging measures as an effective strategy that could generally cope with diverse prediction problems of clinical concerns.
Files in This Item:
T202006015.pdf Download
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Neurology (신경과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers
Yonsei Authors
Lee, Seung Koo(이승구) ORCID logo https://orcid.org/0000-0001-5646-4072
Lee, Phil Hyu(이필휴) ORCID logo https://orcid.org/0000-0001-9931-8462
Chung, Seok Jong(정석종) ORCID logo https://orcid.org/0000-0001-6086-3199
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.