Research ExplorerPublicationsBrain MRI in Progressive Supranuclear Palsy with Richardson'...

Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes

Standard

Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes. / Wattjes, Mike P; Huppertz, Hans-Jürgen; Mahmoudi, Nima; Stöcklein, Sophia; Rogozinski, Sophia; Wegner, Florian; Klietz, Martin; Apostolova, Ivayla; Levin, Johannes; Katzdobler, Sabrina; Buhmann, Carsten; Quattrone, Andrea; Berding, Georg; Brendel, Matthias; Barthel, Henryk; Sabri, Osama; Höglinger, Günter; Buchert, Ralph; Alzheimer’s Disease Neuroimaging Initiative.

In: MOVEMENT DISORD, Vol. 38, No. 10, 27.10.2023, p. 1891-1900.

Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review

Harvard

Wattjes, MP, Huppertz, H-J, Mahmoudi, N, Stöcklein, S, Rogozinski, S, Wegner, F, Klietz, M, Apostolova, I, Levin, J, Katzdobler, S, Buhmann, C, Quattrone, A, Berding, G, Brendel, M, Barthel, H, Sabri, O, Höglinger, G, Buchert, R & Alzheimer’s Disease Neuroimaging Initiative 2023, 'Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes', MOVEMENT DISORD, vol. 38, no. 10, pp. 1891-1900. https://doi.org/10.1002/mds.29527

APA

Wattjes, M. P., Huppertz, H-J., Mahmoudi, N., Stöcklein, S., Rogozinski, S., Wegner, F., Klietz, M., Apostolova, I., Levin, J., Katzdobler, S., Buhmann, C., Quattrone, A., Berding, G., Brendel, M., Barthel, H., Sabri, O., Höglinger, G., Buchert, R., & Alzheimer’s Disease Neuroimaging Initiative (2023). Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes. MOVEMENT DISORD, 38(10), 1891-1900. https://doi.org/10.1002/mds.29527

Vancouver

Wattjes MP, Huppertz H-J, Mahmoudi N, Stöcklein S, Rogozinski S, Wegner F et al. Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes. MOVEMENT DISORD. 2023 Oct 27;38(10):1891-1900. https://doi.org/10.1002/mds.29527

Bibtex

@article{53224af14ff144099b10a0e1e8fb9f30,
title = "Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes",
abstract = "BACKGROUND: Brain magnetic resonance imaging (MRI) is used to support the diagnosis of progressive supranuclear palsy (PSP). However, the value of visual descriptive, manual planimetric, automatic volumetric MRI markers and fully automatic categorization is unclear, particularly regarding PSP predominance types other than Richardson's syndrome (RS).OBJECTIVES: To compare different visual reading strategies and automatic classification of T1-weighted MRI for detection of PSP in a typical clinical cohort including PSP-RS and (non-RS) variant PSP (vPSP) patients.METHODS: Forty-one patients (21 RS, 20 vPSP) and 46 healthy controls were included. Three readers using three strategies performed MRI analysis: exclusively visual reading using descriptive signs (hummingbird, morning-glory, Mickey-Mouse), visual reading supported by manual planimetry measures, and visual reading supported by automatic volumetry. Fully automatic classification was performed using a pre-trained support vector machine (SVM) on the results of atlas-based volumetry.RESULTS: All tested methods achieved higher specificity than sensitivity. Limited sensitivity was driven to large extent by false negative vPSP cases. Support by automatic volumetry resulted in the highest accuracy (75.1% ± 3.5%) among the visual strategies, but performed not better than the midbrain area (75.9%), the best single planimetric measure. Automatic classification by SVM clearly outperformed all other methods (accuracy, 87.4%), representing the only method to provide clinically useful sensitivity also in vPSP (70.0%).CONCLUSIONS: Fully automatic classification of volumetric MRI measures using machine learning methods outperforms visual MRI analysis without and with planimetry or volumetry support, particularly regarding diagnosis of vPSP, suggesting the use in settings with a broad phenotypic PSP spectrum. {\textcopyright} 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.",
author = "Wattjes, {Mike P} and Hans-J{\"u}rgen Huppertz and Nima Mahmoudi and Sophia St{\"o}cklein and Sophia Rogozinski and Florian Wegner and Martin Klietz and Ivayla Apostolova and Johannes Levin and Sabrina Katzdobler and Carsten Buhmann and Andrea Quattrone and Georg Berding and Matthias Brendel and Henryk Barthel and Osama Sabri and G{\"u}nter H{\"o}glinger and Ralph Buchert and {Alzheimer{\textquoteright}s Disease Neuroimaging Initiative}",
note = "{\textcopyright} 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.",
year = "2023",
month = oct,
day = "27",
doi = "10.1002/mds.29527",
language = "English",
volume = "38",
pages = "1891--1900",
journal = "MOVEMENT DISORD",
issn = "0885-3185",
publisher = "John Wiley and Sons Inc.",
number = "10",

}

RIS

TY - JOUR

T1 - Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes

AU - Wattjes, Mike P

AU - Huppertz, Hans-Jürgen

AU - Mahmoudi, Nima

AU - Stöcklein, Sophia

AU - Rogozinski, Sophia

AU - Wegner, Florian

AU - Klietz, Martin

AU - Apostolova, Ivayla

AU - Levin, Johannes

AU - Katzdobler, Sabrina

AU - Buhmann, Carsten

AU - Quattrone, Andrea

AU - Berding, Georg

AU - Brendel, Matthias

AU - Barthel, Henryk

AU - Sabri, Osama

AU - Höglinger, Günter

AU - Buchert, Ralph

AU - Alzheimer’s Disease Neuroimaging Initiative

N1 - © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

PY - 2023/10/27

Y1 - 2023/10/27

N2 - BACKGROUND: Brain magnetic resonance imaging (MRI) is used to support the diagnosis of progressive supranuclear palsy (PSP). However, the value of visual descriptive, manual planimetric, automatic volumetric MRI markers and fully automatic categorization is unclear, particularly regarding PSP predominance types other than Richardson's syndrome (RS).OBJECTIVES: To compare different visual reading strategies and automatic classification of T1-weighted MRI for detection of PSP in a typical clinical cohort including PSP-RS and (non-RS) variant PSP (vPSP) patients.METHODS: Forty-one patients (21 RS, 20 vPSP) and 46 healthy controls were included. Three readers using three strategies performed MRI analysis: exclusively visual reading using descriptive signs (hummingbird, morning-glory, Mickey-Mouse), visual reading supported by manual planimetry measures, and visual reading supported by automatic volumetry. Fully automatic classification was performed using a pre-trained support vector machine (SVM) on the results of atlas-based volumetry.RESULTS: All tested methods achieved higher specificity than sensitivity. Limited sensitivity was driven to large extent by false negative vPSP cases. Support by automatic volumetry resulted in the highest accuracy (75.1% ± 3.5%) among the visual strategies, but performed not better than the midbrain area (75.9%), the best single planimetric measure. Automatic classification by SVM clearly outperformed all other methods (accuracy, 87.4%), representing the only method to provide clinically useful sensitivity also in vPSP (70.0%).CONCLUSIONS: Fully automatic classification of volumetric MRI measures using machine learning methods outperforms visual MRI analysis without and with planimetry or volumetry support, particularly regarding diagnosis of vPSP, suggesting the use in settings with a broad phenotypic PSP spectrum. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

AB - BACKGROUND: Brain magnetic resonance imaging (MRI) is used to support the diagnosis of progressive supranuclear palsy (PSP). However, the value of visual descriptive, manual planimetric, automatic volumetric MRI markers and fully automatic categorization is unclear, particularly regarding PSP predominance types other than Richardson's syndrome (RS).OBJECTIVES: To compare different visual reading strategies and automatic classification of T1-weighted MRI for detection of PSP in a typical clinical cohort including PSP-RS and (non-RS) variant PSP (vPSP) patients.METHODS: Forty-one patients (21 RS, 20 vPSP) and 46 healthy controls were included. Three readers using three strategies performed MRI analysis: exclusively visual reading using descriptive signs (hummingbird, morning-glory, Mickey-Mouse), visual reading supported by manual planimetry measures, and visual reading supported by automatic volumetry. Fully automatic classification was performed using a pre-trained support vector machine (SVM) on the results of atlas-based volumetry.RESULTS: All tested methods achieved higher specificity than sensitivity. Limited sensitivity was driven to large extent by false negative vPSP cases. Support by automatic volumetry resulted in the highest accuracy (75.1% ± 3.5%) among the visual strategies, but performed not better than the midbrain area (75.9%), the best single planimetric measure. Automatic classification by SVM clearly outperformed all other methods (accuracy, 87.4%), representing the only method to provide clinically useful sensitivity also in vPSP (70.0%).CONCLUSIONS: Fully automatic classification of volumetric MRI measures using machine learning methods outperforms visual MRI analysis without and with planimetry or volumetry support, particularly regarding diagnosis of vPSP, suggesting the use in settings with a broad phenotypic PSP spectrum. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

U2 - 10.1002/mds.29527

DO - 10.1002/mds.29527

M3 - SCORING: Journal article

C2 - 37545102

VL - 38

SP - 1891

EP - 1900

JO - MOVEMENT DISORD

JF - MOVEMENT DISORD

SN - 0885-3185

IS - 10

ER -