Hans-Jürgen Huppertz1, Leona Möller2, Martin Südmeyer3, Rüdiger Hilker4, Elke Hattingen5, Karl Egger6, Florian Amtage7, Gesine Respondek2,8,9, Maria Stamelou2, Alfons Schnitzler3, Elmar H Pinkhardt10, Wolfgang H Oertel2, Susanne Knake2, Jan Kassubek11, Günter U Höglinger2,8,9. 1. Swiss Epilepsy Centre, Klinik Lengg, Zurich, Switzerland. 2. Department of Neurology, University Hospital Gießen and Marburg, Marburg, Germany. 3. Department of Neurology, Medical Faculty, Heinrich-Heine University, Düsseldorf, Germany. 4. Department of Neurology, Johann Wolfgang Goethe University, Frankfurt, Germany. 5. Department of Neuroradiology, Johann Wolfgang Goethe University, Frankfurt, Germany. 6. Department of Neuroradiology, Medical University Center Freiburg, Freiburg, Germany. 7. Department of Neurology, Medical University Center Freiburg, Freiburg, Germany. 8. Department of Neurology, Technische Universität München, Munich, Germany. 9. German Center for Neurodegenerative Diseases (DZNE), Munich, Germany. 10. Department of Neurology, University of Ulm, Ulm, Germany. 11. Department of Neurology, University of Ulm, Ulm, Germany. jan.kassubek@uni-ulm.de.
Abstract
BACKGROUND: Clinical differentiation of parkinsonian syndromes is still challenging. OBJECTIVES: A fully automated method for quantitative MRI analysis using atlas-based volumetry combined with support vector machine classification was evaluated for differentiation of parkinsonian syndromes in a multicenter study. METHODS: Atlas-based volumetry was performed on MRI data of healthy controls (n = 73) and patients with PD (204), PSP with Richardson's syndrome phenotype (106), MSA of the cerebellar type (21), and MSA of the Parkinsonian type (60), acquired on different scanners. Volumetric results were used as input for support vector machine classification of single subjects with leave-one-out cross-validation. RESULTS: The largest atrophy compared to controls was found for PSP with Richardson's syndrome phenotype patients in midbrain (-15%), midsagittal midbrain tegmentum plane (-20%), and superior cerebellar peduncles (-13%), for MSA of the cerebellar type in pons (-33%), cerebellum (-23%), and middle cerebellar peduncles (-36%), and for MSA of the parkinsonian type in the putamen (-23%). The majority of binary support vector machine classifications between the groups resulted in balanced accuracies of >80%. With MSA of the cerebellar and parkinsonian type combined in one group, support vector machine classification of PD, PSP and MSA achieved sensitivities of 79% to 87% and specificities of 87% to 96%. Extraction of weighting factors confirmed that midbrain, basal ganglia, and cerebellar peduncles had the largest relevance for classification. CONCLUSIONS: Brain volumetry combined with support vector machine classification allowed for reliable automated differentiation of parkinsonian syndromes on single-patient level even for MRI acquired on different scanners.
BACKGROUND: Clinical differentiation of parkinsonian syndromes is still challenging. OBJECTIVES: A fully automated method for quantitative MRI analysis using atlas-based volumetry combined with support vector machine classification was evaluated for differentiation of parkinsonian syndromes in a multicenter study. METHODS: Atlas-based volumetry was performed on MRI data of healthy controls (n = 73) and patients with PD (204), PSP with Richardson's syndrome phenotype (106), MSA of the cerebellar type (21), and MSA of the Parkinsonian type (60), acquired on different scanners. Volumetric results were used as input for support vector machine classification of single subjects with leave-one-out cross-validation. RESULTS: The largest atrophy compared to controls was found for PSP with Richardson's syndrome phenotype patients in midbrain (-15%), midsagittal midbrain tegmentum plane (-20%), and superior cerebellar peduncles (-13%), for MSA of the cerebellar type in pons (-33%), cerebellum (-23%), and middle cerebellar peduncles (-36%), and for MSA of the parkinsonian type in the putamen (-23%). The majority of binary support vector machine classifications between the groups resulted in balanced accuracies of >80%. With MSA of the cerebellar and parkinsonian type combined in one group, support vector machine classification of PD, PSP and MSA achieved sensitivities of 79% to 87% and specificities of 87% to 96%. Extraction of weighting factors confirmed that midbrain, basal ganglia, and cerebellar peduncles had the largest relevance for classification. CONCLUSIONS: Brain volumetry combined with support vector machine classification allowed for reliable automated differentiation of parkinsonian syndromes on single-patient level even for MRI acquired on different scanners.
Authors: Wolfgang Singer; Ann M Schmeichel; Mohammad Shahnawaz; James D Schmelzer; Bradley F Boeve; David M Sletten; Tonette L Gehrking; Jade A Gehrking; Anita D Olson; Rodolfo Savica; Mariana D Suarez; Claudio Soto; Phillip A Low Journal: Ann Neurol Date: 2020-08-01 Impact factor: 10.422
Authors: Sonja Schönecker; Franz Hell; Kai Bötzel; Elisabeth Wlasich; Nibal Ackl; Christine Süßmair; Markus Otto; Sarah Anderl-Straub; Albert Ludolph; Jan Kassubek; Hans-Jürgen Huppertz; Janine Diehl-Schmid; Lina Riedl; Carola Roßmeier; Klaus Fassbender; Epameinondas Lyros; Johannes Kornhuber; Timo Jan Oberstein; Klaus Fliessbach; Anja Schneider; Matthias L Schroeter; Johannes Prudlo; Martin Lauer; Holger Jahn; Johannes Levin; Adrian Danek Journal: J Neurol Date: 2018-12-01 Impact factor: 4.849
Authors: Günter U Höglinger; Jakob Schöpe; Maria Stamelou; Jan Kassubek; Teodoro Del Ser; Adam L Boxer; Stefan Wagenpfeil; Hans-Jürgen Huppertz Journal: Mov Disord Date: 2017-04-24 Impact factor: 10.338
Authors: Jennifer L Whitwell; Günter U Höglinger; Angelo Antonini; Yvette Bordelon; Adam L Boxer; Carlo Colosimo; Thilo van Eimeren; Lawrence I Golbe; Jan Kassubek; Carolin Kurz; Irene Litvan; Alexander Pantelyat; Gil Rabinovici; Gesine Respondek; Axel Rominger; James B Rowe; Maria Stamelou; Keith A Josephs Journal: Mov Disord Date: 2017-05-13 Impact factor: 10.338