Automatically computed rating scales from MRI for patients with cognitive disorders

Juha R. Koikkalainen, Hanneke F.M. Rhodius-Meester, Kristian S. Frederiksen, Marie Bruun, Steen G. Hasselbalch, Marta Baroni, Patrizia Mecocci, Ritva Vanninen, Anne Remes, Hilkka Soininen, Mark van Gils, Wiesje M. van der Flier, Philip Scheltens, Frederik Barkhof, Timo Erkinjuntti, Jyrki M.P. Lötjönen (Corresponding Author),

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)

Abstract

Objectives: The aims of this study were to examine whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. Methods: A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA), and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N = 513) were used to develop the models and cross-validate them. The PredictND (N = 672) and ADNI (N = 752) cohorts were used for independent validation to test generalizability. Results: The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-left), 0.83/0.79 (MTA-right), 0.64/0.64 (GCA), and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75–0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer’s disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). Conclusions: MTA, GCA, and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less experienced readers. Key Points: • Visual rating scales used in diagnostics of cognitive disorders can be estimated computationally from MRI images with intraclass correlations ranging from 0.64 (GCA) to 0.84 (MTA). • Computed scales provided high diagnostic accuracy with single-subject data (area under the receiver operating curve range, 0.84–0.94).

Original languageEnglish
Pages (from-to)4937-4947
Number of pages11
JournalEuropean Radiology
Volume29
Issue number9
Early online date22 Feb 2019
DOIs
Publication statusPublished - 1 Sep 2019
MoE publication typeA1 Journal article-refereed

Fingerprint

Atrophy
Temporal Lobe
Dementia
Biomarkers
Frontotemporal Lobar Degeneration
Alzheimer Disease

Keywords

  • Atrophy
  • Cognition disorders
  • Magnetic resonance imaging

Cite this

Koikkalainen, J. R., Rhodius-Meester, H. F. M., Frederiksen, K. S., Bruun, M., Hasselbalch, S. G., Baroni, M. (2019). Automatically computed rating scales from MRI for patients with cognitive disorders. European Radiology, 29(9), 4937-4947. https://doi.org/10.1007/s00330-019-06067-1
Koikkalainen, Juha R. ; Rhodius-Meester, Hanneke F.M. ; Frederiksen, Kristian S. ; Bruun, Marie ; Hasselbalch, Steen G. ; Baroni, Marta ; Mecocci, Patrizia ; Vanninen, Ritva ; Remes, Anne ; Soininen, Hilkka ; van Gils, Mark ; van der Flier, Wiesje M. ; Scheltens, Philip ; Barkhof, Frederik ; Erkinjuntti, Timo ; Lötjönen, Jyrki M.P. / Automatically computed rating scales from MRI for patients with cognitive disorders. In: European Radiology. 2019 ; Vol. 29, No. 9. pp. 4937-4947.
@article{9b2a39e44b6040939654579f0000eeac,
title = "Automatically computed rating scales from MRI for patients with cognitive disorders",
abstract = "Objectives: The aims of this study were to examine whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. Methods: A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA), and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N = 513) were used to develop the models and cross-validate them. The PredictND (N = 672) and ADNI (N = 752) cohorts were used for independent validation to test generalizability. Results: The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-left), 0.83/0.79 (MTA-right), 0.64/0.64 (GCA), and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75–0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer’s disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). Conclusions: MTA, GCA, and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less experienced readers. Key Points: • Visual rating scales used in diagnostics of cognitive disorders can be estimated computationally from MRI images with intraclass correlations ranging from 0.64 (GCA) to 0.84 (MTA). • Computed scales provided high diagnostic accuracy with single-subject data (area under the receiver operating curve range, 0.84–0.94).",
keywords = "Atrophy, Cognition disorders, Magnetic resonance imaging",
author = "Koikkalainen, {Juha R.} and Rhodius-Meester, {Hanneke F.M.} and Frederiksen, {Kristian S.} and Marie Bruun and Hasselbalch, {Steen G.} and Marta Baroni and Patrizia Mecocci and Ritva Vanninen and Anne Remes and Hilkka Soininen and {van Gils}, Mark and {van der Flier}, {Wiesje M.} and Philip Scheltens and Frederik Barkhof and Timo Erkinjuntti and L{\"o}tj{\"o}nen, {Jyrki M.P.}",
year = "2019",
month = "9",
day = "1",
doi = "10.1007/s00330-019-06067-1",
language = "English",
volume = "29",
pages = "4937--4947",
journal = "European Radiology",
issn = "0938-7994",
publisher = "Springer",
number = "9",

}

Koikkalainen, JR, Rhodius-Meester, HFM, Frederiksen, KS, Bruun, M, Hasselbalch, SG, Baroni, M, Mecocci, P, Vanninen, R, Remes, A, Soininen, H, van Gils, M, van der Flier, WM, Scheltens, P, Barkhof, F, Erkinjuntti, T, Lötjönen, JMP 2019, 'Automatically computed rating scales from MRI for patients with cognitive disorders', European Radiology, vol. 29, no. 9, pp. 4937-4947. https://doi.org/10.1007/s00330-019-06067-1

Automatically computed rating scales from MRI for patients with cognitive disorders. / Koikkalainen, Juha R.; Rhodius-Meester, Hanneke F.M.; Frederiksen, Kristian S.; Bruun, Marie; Hasselbalch, Steen G.; Baroni, Marta; Mecocci, Patrizia; Vanninen, Ritva; Remes, Anne; Soininen, Hilkka; van Gils, Mark; van der Flier, Wiesje M.; Scheltens, Philip; Barkhof, Frederik; Erkinjuntti, Timo; Lötjönen, Jyrki M.P. (Corresponding Author).

In: European Radiology, Vol. 29, No. 9, 01.09.2019, p. 4937-4947.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Automatically computed rating scales from MRI for patients with cognitive disorders

AU - Koikkalainen, Juha R.

AU - Rhodius-Meester, Hanneke F.M.

AU - Frederiksen, Kristian S.

AU - Bruun, Marie

AU - Hasselbalch, Steen G.

AU - Baroni, Marta

AU - Mecocci, Patrizia

AU - Vanninen, Ritva

AU - Remes, Anne

AU - Soininen, Hilkka

AU - van Gils, Mark

AU - van der Flier, Wiesje M.

AU - Scheltens, Philip

AU - Barkhof, Frederik

AU - Erkinjuntti, Timo

AU - Lötjönen, Jyrki M.P.

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Objectives: The aims of this study were to examine whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. Methods: A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA), and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N = 513) were used to develop the models and cross-validate them. The PredictND (N = 672) and ADNI (N = 752) cohorts were used for independent validation to test generalizability. Results: The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-left), 0.83/0.79 (MTA-right), 0.64/0.64 (GCA), and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75–0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer’s disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). Conclusions: MTA, GCA, and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less experienced readers. Key Points: • Visual rating scales used in diagnostics of cognitive disorders can be estimated computationally from MRI images with intraclass correlations ranging from 0.64 (GCA) to 0.84 (MTA). • Computed scales provided high diagnostic accuracy with single-subject data (area under the receiver operating curve range, 0.84–0.94).

AB - Objectives: The aims of this study were to examine whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. Methods: A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA), and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N = 513) were used to develop the models and cross-validate them. The PredictND (N = 672) and ADNI (N = 752) cohorts were used for independent validation to test generalizability. Results: The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-left), 0.83/0.79 (MTA-right), 0.64/0.64 (GCA), and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75–0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer’s disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). Conclusions: MTA, GCA, and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less experienced readers. Key Points: • Visual rating scales used in diagnostics of cognitive disorders can be estimated computationally from MRI images with intraclass correlations ranging from 0.64 (GCA) to 0.84 (MTA). • Computed scales provided high diagnostic accuracy with single-subject data (area under the receiver operating curve range, 0.84–0.94).

KW - Atrophy

KW - Cognition disorders

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=85062029418&partnerID=8YFLogxK

U2 - 10.1007/s00330-019-06067-1

DO - 10.1007/s00330-019-06067-1

M3 - Article

AN - SCOPUS:85062029418

VL - 29

SP - 4937

EP - 4947

JO - European Radiology

JF - European Radiology

SN - 0938-7994

IS - 9

ER -

Koikkalainen JR, Rhodius-Meester HFM, Frederiksen KS, Bruun M, Hasselbalch SG, Baroni M et al. Automatically computed rating scales from MRI for patients with cognitive disorders. European Radiology. 2019 Sep 1;29(9):4937-4947. https://doi.org/10.1007/s00330-019-06067-1