Predicting primary progressive aphasias with support vector machine approaches in structural MRI data
Primary progressive aphasia (PPA) encompasses the three subtypes nonfluent/agrammatic variant PPA, semantic variant PPA, and the logopenic variant PPA, which are characterized by distinct patterns of language difficulties and regional brain atrophy. To validate the potential of structural magnetic r...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2017-01-01
|
Series: | NeuroImage: Clinical |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158217300372 |
_version_ | 1811198082511011840 |
---|---|
author | Sandrine Bisenius Karsten Mueller Janine Diehl-Schmid Klaus Fassbender Timo Grimmer Frank Jessen Jan Kassubek Johannes Kornhuber Bernhard Landwehrmeyer Albert Ludolph Anja Schneider Sarah Anderl-Straub Katharina Stuke Adrian Danek Markus Otto Matthias L. Schroeter |
author_facet | Sandrine Bisenius Karsten Mueller Janine Diehl-Schmid Klaus Fassbender Timo Grimmer Frank Jessen Jan Kassubek Johannes Kornhuber Bernhard Landwehrmeyer Albert Ludolph Anja Schneider Sarah Anderl-Straub Katharina Stuke Adrian Danek Markus Otto Matthias L. Schroeter |
author_sort | Sandrine Bisenius |
collection | DOAJ |
description | Primary progressive aphasia (PPA) encompasses the three subtypes nonfluent/agrammatic variant PPA, semantic variant PPA, and the logopenic variant PPA, which are characterized by distinct patterns of language difficulties and regional brain atrophy. To validate the potential of structural magnetic resonance imaging data for early individual diagnosis, we used support vector machine classification on grey matter density maps obtained by voxel-based morphometry analysis to discriminate PPA subtypes (44 patients: 16 nonfluent/agrammatic variant PPA, 17 semantic variant PPA, 11 logopenic variant PPA) from 20 healthy controls (matched for sample size, age, and gender) in the cohort of the multi-center study of the German consortium for frontotemporal lobar degeneration. Here, we compared a whole-brain with a meta-analysis-based disease-specific regions-of-interest approach for support vector machine classification. We also used support vector machine classification to discriminate the three PPA subtypes from each other. Whole brain support vector machine classification enabled a very high accuracy between 91 and 97% for identifying specific PPA subtypes vs. healthy controls, and 78/95% for the discrimination between semantic variant vs. nonfluent/agrammatic or logopenic PPA variants. Only for the discrimination between nonfluent/agrammatic and logopenic PPA variants accuracy was low with 55%. Interestingly, the regions that contributed the most to the support vector machine classification of patients corresponded largely to the regions that were atrophic in these patients as revealed by group comparisons. Although the whole brain approach took also into account regions that were not covered in the regions-of-interest approach, both approaches showed similar accuracies due to the disease-specificity of the selected networks. Conclusion, support vector machine classification of multi-center structural magnetic resonance imaging data enables prediction of PPA subtypes with a very high accuracy paving the road for its application in clinical settings. |
first_indexed | 2024-04-12T01:24:46Z |
format | Article |
id | doaj.art-ee88fbdebdb84ab6b10f738d441e7b4c |
institution | Directory Open Access Journal |
issn | 2213-1582 |
language | English |
last_indexed | 2024-04-12T01:24:46Z |
publishDate | 2017-01-01 |
publisher | Elsevier |
record_format | Article |
series | NeuroImage: Clinical |
spelling | doaj.art-ee88fbdebdb84ab6b10f738d441e7b4c2022-12-22T03:53:41ZengElsevierNeuroImage: Clinical2213-15822017-01-0114C33434310.1016/j.nicl.2017.02.003Predicting primary progressive aphasias with support vector machine approaches in structural MRI dataSandrine Bisenius0Karsten Mueller1Janine Diehl-Schmid2Klaus Fassbender3Timo Grimmer4Frank Jessen5Jan Kassubek6Johannes Kornhuber7Bernhard Landwehrmeyer8Albert Ludolph9Anja Schneider10Sarah Anderl-Straub11Katharina Stuke12Adrian Danek13Markus Otto14Matthias L. Schroeter15Max Planck Institute for Human Cognitive and Brain Sciences & Clinic for Cognitive Neurology, University Hospital Leipzig, GermanyMax Planck Institute for Human Cognitive and Brain Sciences & Clinic for Cognitive Neurology, University Hospital Leipzig, GermanyClinic and Polyclinic for Psychiatry & Psychotherapy, Technical University Munich, GermanyClinic and Polyclinic for Neurology, Saarland University Homburg, GermanyClinic and Polyclinic for Psychiatry & Psychotherapy, Technical University Munich, GermanyClinic and Polyclinic for Psychiatry and Psychotherapy, University of Bonn, GermanyDepartment of Neurology, University of Ulm, GermanyClinic for Psychiatry and Psychotherapy, Friedrich-Alexander University Erlangen-Nuremberg, GermanyDepartment of Neurology, University of Ulm, GermanyDepartment of Neurology, University of Ulm, GermanyClinic for Psychiatry and Psychotherapy, University of Goettingen, GermanyDepartment of Neurology, University of Ulm, GermanyMax Planck Institute for Human Cognitive and Brain Sciences & Clinic for Cognitive Neurology, University Hospital Leipzig, GermanyClinic of Neurology, Ludwig Maximilian University of Munich, GermanyDepartment of Neurology, University of Ulm, GermanyMax Planck Institute for Human Cognitive and Brain Sciences & Clinic for Cognitive Neurology, University Hospital Leipzig, GermanyPrimary progressive aphasia (PPA) encompasses the three subtypes nonfluent/agrammatic variant PPA, semantic variant PPA, and the logopenic variant PPA, which are characterized by distinct patterns of language difficulties and regional brain atrophy. To validate the potential of structural magnetic resonance imaging data for early individual diagnosis, we used support vector machine classification on grey matter density maps obtained by voxel-based morphometry analysis to discriminate PPA subtypes (44 patients: 16 nonfluent/agrammatic variant PPA, 17 semantic variant PPA, 11 logopenic variant PPA) from 20 healthy controls (matched for sample size, age, and gender) in the cohort of the multi-center study of the German consortium for frontotemporal lobar degeneration. Here, we compared a whole-brain with a meta-analysis-based disease-specific regions-of-interest approach for support vector machine classification. We also used support vector machine classification to discriminate the three PPA subtypes from each other. Whole brain support vector machine classification enabled a very high accuracy between 91 and 97% for identifying specific PPA subtypes vs. healthy controls, and 78/95% for the discrimination between semantic variant vs. nonfluent/agrammatic or logopenic PPA variants. Only for the discrimination between nonfluent/agrammatic and logopenic PPA variants accuracy was low with 55%. Interestingly, the regions that contributed the most to the support vector machine classification of patients corresponded largely to the regions that were atrophic in these patients as revealed by group comparisons. Although the whole brain approach took also into account regions that were not covered in the regions-of-interest approach, both approaches showed similar accuracies due to the disease-specificity of the selected networks. Conclusion, support vector machine classification of multi-center structural magnetic resonance imaging data enables prediction of PPA subtypes with a very high accuracy paving the road for its application in clinical settings.http://www.sciencedirect.com/science/article/pii/S2213158217300372Grey matterMulti-centerPrimary progressive aphasiaSupport vector machine classificationWhole brain approach |
spellingShingle | Sandrine Bisenius Karsten Mueller Janine Diehl-Schmid Klaus Fassbender Timo Grimmer Frank Jessen Jan Kassubek Johannes Kornhuber Bernhard Landwehrmeyer Albert Ludolph Anja Schneider Sarah Anderl-Straub Katharina Stuke Adrian Danek Markus Otto Matthias L. Schroeter Predicting primary progressive aphasias with support vector machine approaches in structural MRI data NeuroImage: Clinical Grey matter Multi-center Primary progressive aphasia Support vector machine classification Whole brain approach |
title | Predicting primary progressive aphasias with support vector machine approaches in structural MRI data |
title_full | Predicting primary progressive aphasias with support vector machine approaches in structural MRI data |
title_fullStr | Predicting primary progressive aphasias with support vector machine approaches in structural MRI data |
title_full_unstemmed | Predicting primary progressive aphasias with support vector machine approaches in structural MRI data |
title_short | Predicting primary progressive aphasias with support vector machine approaches in structural MRI data |
title_sort | predicting primary progressive aphasias with support vector machine approaches in structural mri data |
topic | Grey matter Multi-center Primary progressive aphasia Support vector machine classification Whole brain approach |
url | http://www.sciencedirect.com/science/article/pii/S2213158217300372 |
work_keys_str_mv | AT sandrinebisenius predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT karstenmueller predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT janinediehlschmid predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT klausfassbender predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT timogrimmer predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT frankjessen predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT jankassubek predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT johanneskornhuber predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT bernhardlandwehrmeyer predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT albertludolph predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT anjaschneider predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT sarahanderlstraub predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT katharinastuke predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT adriandanek predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT markusotto predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata AT matthiaslschroeter predictingprimaryprogressiveaphasiaswithsupportvectormachineapproachesinstructuralmridata |