Differential diagnosis of neurodegenerative diseases using structural MRI data

Juha Koikkalainen (Corresponding Author), Hannele Rhodius-Meester, Antti Tolonen, Frederik Barkhof, Betty Tijms, Alina W. Lemstra, Tong Tong, Ricardo Guerrero, Andreas Schuh, Christian Ledig, Daniel Rueckert, Hilkka Soininen, Anne M. Remes, Gunhild Waldemar, Steen Hasselbalch, Patrizia Mecocci, Wiesje Van Der Flier, Jyrki Lötjönen

Research output: Contribution to journalArticleScientificpeer-review

42 Citations (Scopus)

Abstract

Different neurodegenerative diseases can cause memory disorders and other cognitive impairments. The early detection and the stratification of patients according to the underlying disease are essential for an efficient approach to this healthcare challenge. This emphasizes the importance of differential diagnostics. Most studies compare patients and controls, or Alzheimer's disease with one other type of dementia. Such a bilateral comparison does not resemble clinical practice, where a clinician is faced with a number of different possible types of dementia. Here we studied which features in structural magnetic resonance imaging (MRI) scans could best distinguish four types of dementia, Alzheimer's disease, frontotemporal dementia, vascular dementia, and dementia with Lewy bodies, and control subjects. We extracted an extensive set of features quantifying volumetric and morphometric characteristics from T1 images, and vascular characteristics from FLAIR images. Classification was performed using a multi-class classifier based on Disease State Index methodology. The classifier provided continuous probability indices for each disease to support clinical decision making. A dataset of 504 individuals was used for evaluation. The cross-validated classification accuracy was 70.6% and balanced accuracy was 69.1% for the five disease groups using only automatically determined MRI features. Vascular dementia patients could be detected with high sensitivity (96%) using features from FLAIR images. Controls (sensitivity 82%) and Alzheimer's disease patients (sensitivity 74%) could be accurately classified using T1-based features, whereas the most difficult group was the dementia with Lewy bodies (sensitivity 32%). These results were notable better than the classification accuracies obtained with visual MRI ratings (accuracy 44.6%, balanced accuracy 51.6%). Different quantification methods provided complementary information, and consequently, the best results were obtained by utilizing several quantification methods. The results prove that automatic quantification methods and computerized decision support methods are feasible for clinical practice and provide comprehensive information that may help clinicians in the diagnosis making.
Original languageEnglish
Pages (from-to)435-449
JournalNeuroImage: Clinical
Volume11
DOIs
Publication statusPublished - 2016
MoE publication typeA1 Journal article-refereed

Fingerprint

Neurodegenerative Diseases
Differential Diagnosis
Magnetic Resonance Imaging
Dementia
Lewy Body Disease
Alzheimer Disease
Vascular Dementia
Frontotemporal Dementia
Memory Disorders
Blood Vessels
Delivery of Health Care

Keywords

  • Alzheimer's disease
  • classification
  • Dementia with Lewy bodies
  • frontotemporal lobar degeneration
  • MRI
  • neurodegenerative diseases
  • TBM
  • Vascular dementia
  • VBM
  • volumetr

Cite this

Koikkalainen, J., Rhodius-Meester, H., Tolonen, A., Barkhof, F., Tijms, B., Lemstra, A. W., ... Lötjönen, J. (2016). Differential diagnosis of neurodegenerative diseases using structural MRI data. NeuroImage: Clinical, 11, 435-449. https://doi.org/10.1016/j.nicl.2016.02.019
Koikkalainen, Juha ; Rhodius-Meester, Hannele ; Tolonen, Antti ; Barkhof, Frederik ; Tijms, Betty ; Lemstra, Alina W. ; Tong, Tong ; Guerrero, Ricardo ; Schuh, Andreas ; Ledig, Christian ; Rueckert, Daniel ; Soininen, Hilkka ; Remes, Anne M. ; Waldemar, Gunhild ; Hasselbalch, Steen ; Mecocci, Patrizia ; Van Der Flier, Wiesje ; Lötjönen, Jyrki. / Differential diagnosis of neurodegenerative diseases using structural MRI data. In: NeuroImage: Clinical. 2016 ; Vol. 11. pp. 435-449.
@article{701f06af76454d10bb114ad64edd42de,
title = "Differential diagnosis of neurodegenerative diseases using structural MRI data",
abstract = "Different neurodegenerative diseases can cause memory disorders and other cognitive impairments. The early detection and the stratification of patients according to the underlying disease are essential for an efficient approach to this healthcare challenge. This emphasizes the importance of differential diagnostics. Most studies compare patients and controls, or Alzheimer's disease with one other type of dementia. Such a bilateral comparison does not resemble clinical practice, where a clinician is faced with a number of different possible types of dementia. Here we studied which features in structural magnetic resonance imaging (MRI) scans could best distinguish four types of dementia, Alzheimer's disease, frontotemporal dementia, vascular dementia, and dementia with Lewy bodies, and control subjects. We extracted an extensive set of features quantifying volumetric and morphometric characteristics from T1 images, and vascular characteristics from FLAIR images. Classification was performed using a multi-class classifier based on Disease State Index methodology. The classifier provided continuous probability indices for each disease to support clinical decision making. A dataset of 504 individuals was used for evaluation. The cross-validated classification accuracy was 70.6{\%} and balanced accuracy was 69.1{\%} for the five disease groups using only automatically determined MRI features. Vascular dementia patients could be detected with high sensitivity (96{\%}) using features from FLAIR images. Controls (sensitivity 82{\%}) and Alzheimer's disease patients (sensitivity 74{\%}) could be accurately classified using T1-based features, whereas the most difficult group was the dementia with Lewy bodies (sensitivity 32{\%}). These results were notable better than the classification accuracies obtained with visual MRI ratings (accuracy 44.6{\%}, balanced accuracy 51.6{\%}). Different quantification methods provided complementary information, and consequently, the best results were obtained by utilizing several quantification methods. The results prove that automatic quantification methods and computerized decision support methods are feasible for clinical practice and provide comprehensive information that may help clinicians in the diagnosis making.",
keywords = "Alzheimer's disease, classification, Dementia with Lewy bodies, frontotemporal lobar degeneration, MRI, neurodegenerative diseases, TBM, Vascular dementia, VBM, volumetr",
author = "Juha Koikkalainen and Hannele Rhodius-Meester and Antti Tolonen and Frederik Barkhof and Betty Tijms and Lemstra, {Alina W.} and Tong Tong and Ricardo Guerrero and Andreas Schuh and Christian Ledig and Daniel Rueckert and Hilkka Soininen and Remes, {Anne M.} and Gunhild Waldemar and Steen Hasselbalch and Patrizia Mecocci and {Van Der Flier}, Wiesje and Jyrki L{\"o}tj{\"o}nen",
year = "2016",
doi = "10.1016/j.nicl.2016.02.019",
language = "English",
volume = "11",
pages = "435--449",
journal = "NeuroImage: Clinical",
issn = "2213-1582",
publisher = "Elsevier",

}

Koikkalainen, J, Rhodius-Meester, H, Tolonen, A, Barkhof, F, Tijms, B, Lemstra, AW, Tong, T, Guerrero, R, Schuh, A, Ledig, C, Rueckert, D, Soininen, H, Remes, AM, Waldemar, G, Hasselbalch, S, Mecocci, P, Van Der Flier, W & Lötjönen, J 2016, 'Differential diagnosis of neurodegenerative diseases using structural MRI data', NeuroImage: Clinical, vol. 11, pp. 435-449. https://doi.org/10.1016/j.nicl.2016.02.019

Differential diagnosis of neurodegenerative diseases using structural MRI data. / Koikkalainen, Juha (Corresponding Author); Rhodius-Meester, Hannele; Tolonen, Antti; Barkhof, Frederik; Tijms, Betty; Lemstra, Alina W.; Tong, Tong; Guerrero, Ricardo; Schuh, Andreas; Ledig, Christian; Rueckert, Daniel; Soininen, Hilkka; Remes, Anne M.; Waldemar, Gunhild; Hasselbalch, Steen; Mecocci, Patrizia; Van Der Flier, Wiesje; Lötjönen, Jyrki.

In: NeuroImage: Clinical, Vol. 11, 2016, p. 435-449.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Differential diagnosis of neurodegenerative diseases using structural MRI data

AU - Koikkalainen, Juha

AU - Rhodius-Meester, Hannele

AU - Tolonen, Antti

AU - Barkhof, Frederik

AU - Tijms, Betty

AU - Lemstra, Alina W.

AU - Tong, Tong

AU - Guerrero, Ricardo

AU - Schuh, Andreas

AU - Ledig, Christian

AU - Rueckert, Daniel

AU - Soininen, Hilkka

AU - Remes, Anne M.

AU - Waldemar, Gunhild

AU - Hasselbalch, Steen

AU - Mecocci, Patrizia

AU - Van Der Flier, Wiesje

AU - Lötjönen, Jyrki

PY - 2016

Y1 - 2016

N2 - Different neurodegenerative diseases can cause memory disorders and other cognitive impairments. The early detection and the stratification of patients according to the underlying disease are essential for an efficient approach to this healthcare challenge. This emphasizes the importance of differential diagnostics. Most studies compare patients and controls, or Alzheimer's disease with one other type of dementia. Such a bilateral comparison does not resemble clinical practice, where a clinician is faced with a number of different possible types of dementia. Here we studied which features in structural magnetic resonance imaging (MRI) scans could best distinguish four types of dementia, Alzheimer's disease, frontotemporal dementia, vascular dementia, and dementia with Lewy bodies, and control subjects. We extracted an extensive set of features quantifying volumetric and morphometric characteristics from T1 images, and vascular characteristics from FLAIR images. Classification was performed using a multi-class classifier based on Disease State Index methodology. The classifier provided continuous probability indices for each disease to support clinical decision making. A dataset of 504 individuals was used for evaluation. The cross-validated classification accuracy was 70.6% and balanced accuracy was 69.1% for the five disease groups using only automatically determined MRI features. Vascular dementia patients could be detected with high sensitivity (96%) using features from FLAIR images. Controls (sensitivity 82%) and Alzheimer's disease patients (sensitivity 74%) could be accurately classified using T1-based features, whereas the most difficult group was the dementia with Lewy bodies (sensitivity 32%). These results were notable better than the classification accuracies obtained with visual MRI ratings (accuracy 44.6%, balanced accuracy 51.6%). Different quantification methods provided complementary information, and consequently, the best results were obtained by utilizing several quantification methods. The results prove that automatic quantification methods and computerized decision support methods are feasible for clinical practice and provide comprehensive information that may help clinicians in the diagnosis making.

AB - Different neurodegenerative diseases can cause memory disorders and other cognitive impairments. The early detection and the stratification of patients according to the underlying disease are essential for an efficient approach to this healthcare challenge. This emphasizes the importance of differential diagnostics. Most studies compare patients and controls, or Alzheimer's disease with one other type of dementia. Such a bilateral comparison does not resemble clinical practice, where a clinician is faced with a number of different possible types of dementia. Here we studied which features in structural magnetic resonance imaging (MRI) scans could best distinguish four types of dementia, Alzheimer's disease, frontotemporal dementia, vascular dementia, and dementia with Lewy bodies, and control subjects. We extracted an extensive set of features quantifying volumetric and morphometric characteristics from T1 images, and vascular characteristics from FLAIR images. Classification was performed using a multi-class classifier based on Disease State Index methodology. The classifier provided continuous probability indices for each disease to support clinical decision making. A dataset of 504 individuals was used for evaluation. The cross-validated classification accuracy was 70.6% and balanced accuracy was 69.1% for the five disease groups using only automatically determined MRI features. Vascular dementia patients could be detected with high sensitivity (96%) using features from FLAIR images. Controls (sensitivity 82%) and Alzheimer's disease patients (sensitivity 74%) could be accurately classified using T1-based features, whereas the most difficult group was the dementia with Lewy bodies (sensitivity 32%). These results were notable better than the classification accuracies obtained with visual MRI ratings (accuracy 44.6%, balanced accuracy 51.6%). Different quantification methods provided complementary information, and consequently, the best results were obtained by utilizing several quantification methods. The results prove that automatic quantification methods and computerized decision support methods are feasible for clinical practice and provide comprehensive information that may help clinicians in the diagnosis making.

KW - Alzheimer's disease

KW - classification

KW - Dementia with Lewy bodies

KW - frontotemporal lobar degeneration

KW - MRI

KW - neurodegenerative diseases

KW - TBM

KW - Vascular dementia

KW - VBM

KW - volumetr

U2 - 10.1016/j.nicl.2016.02.019

DO - 10.1016/j.nicl.2016.02.019

M3 - Article

VL - 11

SP - 435

EP - 449

JO - NeuroImage: Clinical

JF - NeuroImage: Clinical

SN - 2213-1582

ER -