PortalPublikationenMulticlass prediction of different dementia syndromes based ...

Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging

Standard

Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging. / Lampe, Leonie; Huppertz, Hans-Jürgen; Anderl-Straub, Sarah; Albrecht, Franziska; Ballarini, Tommaso; Bisenius, Sandrine; Mueller, Karsten; Niehaus, Sebastian; Fassbender, Klaus; Fliessbach, Klaus; Jahn, Holger; Kornhuber, Johannes; Lauer, Martin; Prudlo, Johannes; Schneider, Anja; Synofzik, Matthis; Kassubek, Jan; Danek, Adrian; Villringer, Arno; Diehl-Schmid, Janine; Otto, Markus; Schroeter, Matthias L; Deutsches FTLD-Konsortium.

in: NEUROIMAGE-CLIN, Jahrgang 37, 2023, S. 103320.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung

Harvard

Lampe, L, Huppertz, H-J, Anderl-Straub, S, Albrecht, F, Ballarini, T, Bisenius, S, Mueller, K, Niehaus, S, Fassbender, K, Fliessbach, K, Jahn, H, Kornhuber, J, Lauer, M, Prudlo, J, Schneider, A, Synofzik, M, Kassubek, J, Danek, A, Villringer, A, Diehl-Schmid, J, Otto, M, Schroeter, ML & Deutsches FTLD-Konsortium 2023, 'Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging', NEUROIMAGE-CLIN, Jg. 37, S. 103320. https://doi.org/10.1016/j.nicl.2023.103320

APA

Lampe, L., Huppertz, H-J., Anderl-Straub, S., Albrecht, F., Ballarini, T., Bisenius, S., Mueller, K., Niehaus, S., Fassbender, K., Fliessbach, K., Jahn, H., Kornhuber, J., Lauer, M., Prudlo, J., Schneider, A., Synofzik, M., Kassubek, J., Danek, A., Villringer, A., ... Deutsches FTLD-Konsortium (2023). Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging. NEUROIMAGE-CLIN, 37, 103320. https://doi.org/10.1016/j.nicl.2023.103320

Vancouver

Lampe L, Huppertz H-J, Anderl-Straub S, Albrecht F, Ballarini T, Bisenius S et al. Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging. NEUROIMAGE-CLIN. 2023;37:103320. https://doi.org/10.1016/j.nicl.2023.103320

Bibtex

@article{f793cbcbf3064dcead8ceb6589f47da5,
title = "Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging",
abstract = "INTRODUCTION: Dementia syndromes can be difficult to diagnose. We aimed at building a classifier for multiple dementia syndromes using magnetic resonance imaging (MRI).METHODS: Atlas-based volumetry was performed on T1-weighted MRI data of 426 patients and 51 controls from the multi-centric German Research Consortium of Frontotemporal Lobar Degeneration including patients with behavioral variant frontotemporal dementia, Alzheimer's disease, the three subtypes of primary progressive aphasia, i.e., semantic, logopenic and nonfluent-agrammatic variant, and the atypical parkinsonian syndromes progressive supranuclear palsy and corticobasal syndrome. Support vector machine classification was used to classify each patient group against controls (binary classification) and all seven diagnostic groups against each other in a multi-syndrome classifier (multiclass classification).RESULTS: The binary classification models reached high prediction accuracies between 71 and 95% with a chance level of 50%. Feature importance reflected disease-specific atrophy patterns. The multi-syndrome model reached accuracies of more than three times higher than chance level but was far from 100%. Multi-syndrome model performance was not homogenous across dementia syndromes, with better performance in syndromes characterized by regionally specific atrophy patterns. Whereas diseases generally could be classified vs controls more correctly with increasing severity and duration, differentiation between diseases was optimal in disease-specific windows of severity and duration.DISCUSSION: Results suggest that automated methods applied to MR imaging data can support physicians in diagnosis of dementia syndromes. It is particularly relevant for orphan diseases beside frequent syndromes such as Alzheimer's disease.",
author = "Leonie Lampe and Hans-J{\"u}rgen Huppertz and Sarah Anderl-Straub and Franziska Albrecht and Tommaso Ballarini and Sandrine Bisenius and Karsten Mueller and Sebastian Niehaus and Klaus Fassbender and Klaus Fliessbach and Holger Jahn and Johannes Kornhuber and Martin Lauer and Johannes Prudlo and Anja Schneider and Matthis Synofzik and Jan Kassubek and Adrian Danek and Arno Villringer and Janine Diehl-Schmid and Markus Otto and Schroeter, {Matthias L} and {FTLD Consortium Germany}",
note = "Copyright {\textcopyright} 2023. Published by Elsevier Inc.",
year = "2023",
doi = "10.1016/j.nicl.2023.103320",
language = "English",
volume = "37",
pages = "103320",
journal = "NEUROIMAGE-CLIN",
issn = "2213-1582",
publisher = "Elsevier BV",

}

RIS

TY - JOUR

T1 - Multiclass prediction of different dementia syndromes based on multi-centric volumetric MRI imaging

AU - Lampe, Leonie

AU - Huppertz, Hans-Jürgen

AU - Anderl-Straub, Sarah

AU - Albrecht, Franziska

AU - Ballarini, Tommaso

AU - Bisenius, Sandrine

AU - Mueller, Karsten

AU - Niehaus, Sebastian

AU - Fassbender, Klaus

AU - Fliessbach, Klaus

AU - Jahn, Holger

AU - Kornhuber, Johannes

AU - Lauer, Martin

AU - Prudlo, Johannes

AU - Schneider, Anja

AU - Synofzik, Matthis

AU - Kassubek, Jan

AU - Danek, Adrian

AU - Villringer, Arno

AU - Diehl-Schmid, Janine

AU - Otto, Markus

AU - Schroeter, Matthias L

AU - FTLD Consortium Germany

N1 - Copyright © 2023. Published by Elsevier Inc.

PY - 2023

Y1 - 2023

N2 - INTRODUCTION: Dementia syndromes can be difficult to diagnose. We aimed at building a classifier for multiple dementia syndromes using magnetic resonance imaging (MRI).METHODS: Atlas-based volumetry was performed on T1-weighted MRI data of 426 patients and 51 controls from the multi-centric German Research Consortium of Frontotemporal Lobar Degeneration including patients with behavioral variant frontotemporal dementia, Alzheimer's disease, the three subtypes of primary progressive aphasia, i.e., semantic, logopenic and nonfluent-agrammatic variant, and the atypical parkinsonian syndromes progressive supranuclear palsy and corticobasal syndrome. Support vector machine classification was used to classify each patient group against controls (binary classification) and all seven diagnostic groups against each other in a multi-syndrome classifier (multiclass classification).RESULTS: The binary classification models reached high prediction accuracies between 71 and 95% with a chance level of 50%. Feature importance reflected disease-specific atrophy patterns. The multi-syndrome model reached accuracies of more than three times higher than chance level but was far from 100%. Multi-syndrome model performance was not homogenous across dementia syndromes, with better performance in syndromes characterized by regionally specific atrophy patterns. Whereas diseases generally could be classified vs controls more correctly with increasing severity and duration, differentiation between diseases was optimal in disease-specific windows of severity and duration.DISCUSSION: Results suggest that automated methods applied to MR imaging data can support physicians in diagnosis of dementia syndromes. It is particularly relevant for orphan diseases beside frequent syndromes such as Alzheimer's disease.

AB - INTRODUCTION: Dementia syndromes can be difficult to diagnose. We aimed at building a classifier for multiple dementia syndromes using magnetic resonance imaging (MRI).METHODS: Atlas-based volumetry was performed on T1-weighted MRI data of 426 patients and 51 controls from the multi-centric German Research Consortium of Frontotemporal Lobar Degeneration including patients with behavioral variant frontotemporal dementia, Alzheimer's disease, the three subtypes of primary progressive aphasia, i.e., semantic, logopenic and nonfluent-agrammatic variant, and the atypical parkinsonian syndromes progressive supranuclear palsy and corticobasal syndrome. Support vector machine classification was used to classify each patient group against controls (binary classification) and all seven diagnostic groups against each other in a multi-syndrome classifier (multiclass classification).RESULTS: The binary classification models reached high prediction accuracies between 71 and 95% with a chance level of 50%. Feature importance reflected disease-specific atrophy patterns. The multi-syndrome model reached accuracies of more than three times higher than chance level but was far from 100%. Multi-syndrome model performance was not homogenous across dementia syndromes, with better performance in syndromes characterized by regionally specific atrophy patterns. Whereas diseases generally could be classified vs controls more correctly with increasing severity and duration, differentiation between diseases was optimal in disease-specific windows of severity and duration.DISCUSSION: Results suggest that automated methods applied to MR imaging data can support physicians in diagnosis of dementia syndromes. It is particularly relevant for orphan diseases beside frequent syndromes such as Alzheimer's disease.

U2 - 10.1016/j.nicl.2023.103320

DO - 10.1016/j.nicl.2023.103320

M3 - SCORING: Journal article

C2 - 36623349

VL - 37

SP - 103320

JO - NEUROIMAGE-CLIN

JF - NEUROIMAGE-CLIN

SN - 2213-1582

ER -