English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Disease-specific regions outperform whole-brain approaches in identifying progressive supranuclear palsy: A multicentric MRI study

Mueller, K., Jech, R., Bonnet, C., Tintěra, J., Hanuška, J., Möller, H. E., et al. (2017). Disease-specific regions outperform whole-brain approaches in identifying progressive supranuclear palsy: A multicentric MRI study. Frontiers in Neuroscience, 11: 100. doi:10.3389/fnins.2017.00100.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-E5C7-B Version Permalink: http://hdl.handle.net/21.11116/0000-0003-BE04-3
Genre: Journal Article

Files

show Files
hide Files
:
Mueller_Jech_Bonnet_2017.pdf (Publisher version), 2MB
Name:
Mueller_Jech_Bonnet_2017.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Mueller, Karsten1, Author              
Jech, Robert 2, Author
Bonnet, Cecilia 2, Author
Tintěra, Jaroslav 2, Author
Hanuška, Jaromir 2, Author
Möller, Harald E.1, Author              
Fassbender, Klaus 2, Author
Ludolph, Albert 2, Author
Kassubek, Jan 2, Author
Otto, Markus2, Author
Růžička, Evžen 2, Author
Schroeter, Matthias L.3, Author              
The FTLDc Study Group, Author              
Affiliations:
1Methods and Development Unit Nuclear Magnetic Resonance, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634558              
2External Organizations, ou_persistent22              
3Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              

Content

show
hide
Free keywords: magnetic resonance imaging; progressive supranuclear palsy; atypical parkinsonism; support vector machine classification; voxel-based morphometry
 Abstract: To identify progressive supranuclear palsy (PSP), we combined voxel-based morphometry (VBM) and support vector machine (SVM) classification using disease-specific features in multicentric magnetic resonance imaging (MRI) data. Structural brain differences were investigated at four centers between 20 patients with PSP and 20 age-matched healthy controls with T1-weighted MRI at 3T. To pave the way for future application in personalized medicine, we applied SVM classification to identify PSP on an individual level besides group analyses based on VBM. We found a major decline in gray matter density in the brainstem, insula, and striatum, and also in frontomedian regions, which is in line with current literature. Moreover, SVM classification yielded high accuracy rates above 80% for disease identification in imaging data. Focusing analyses on disease-specific regions-of-interest (ROI) led to higher accuracy rates compared to a whole-brain approach. Using a polynomial kernel (instead of a linear kernel) led to an increased sensitivity and a higher specificity of disease detection. Our study supports the application of MRI for individual diagnosis of PSP, if combined with SVM approaches. We demonstrate that SVM classification provides high accuracy rates in multicentric data—a prerequisite for potential application in diagnostic routine.

Details

show
hide
Language(s): eng - English
 Dates: 2016-11-292017-02-152017-03-07
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: Peer
 Identifiers: DOI: 10.3389/fnins.2017.00100
PMC: PMC5339275
PMID: 28326008
Other: eCollection 2017
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : German Consortium for Frontotemporal Lobar Degeneration
Grant ID : O1GI1007A
Funding program : -
Funding organization : German Federal Ministry of Education and Research (BMBF)
Project name : -
Grant ID : PDF-IRG-1307
Funding program : -
Funding organization : Parkinson's Disease Foundation
Project name : -
Grant ID : MJFF-11362
Funding program : -
Funding organization : Michael J Fox Foundation
Project name : -
Grant ID : 16-13323S
Funding program : -
Funding organization : Czech Science Foundation GAČR
Project name : -
Grant ID : 16-28119A
Funding program : -
Funding organization : Czech Ministry of Health
Project name : PROGRES Q27
Grant ID : -
Funding program : -
Funding organization : Charles University

Source 1

show
hide
Title: Frontiers in Neuroscience
  Other : Front Neurosci
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Lausanne, Switzerland : Frontiers Research Foundation
Pages: - Volume / Issue: 11 Sequence Number: 100 Start / End Page: - Identifier: ISSN: 1662-4548
ISSN: 1662-453X
CoNE: https://pure.mpg.de/cone/journals/resource/1662-4548