Research
Print page Print page
Switch language
Rigshospitalet - a part of Copenhagen University Hospital
Published

Binary classification of ¹⁸F-flutemetamol PET using machine learning: comparison with visual reads and structural MRI

Research output: Contribution to journalJournal articleResearchpeer-review

Harvard

Vandenberghe, R, Nelissen, N, Salmon, E, Ivanoiu, A, Hasselbalch, S, Andersen, A, Kørner, EA, Minthon, L, Brooks, D, Van Laere, K & Dupont, P 2013, 'Binary classification of ¹⁸F-flutemetamol PET using machine learning: comparison with visual reads and structural MRI' NeuroImage, vol. 64, pp. 517-25. https://doi.org/10.1016/j.neuroimage.2012.09.015

APA

CBE

MLA

Vancouver

Author

Vandenberghe, Rik ; Nelissen, Natalie ; Salmon, Eric ; Ivanoiu, Adrian ; Hasselbalch, Steen ; Andersen, Allan ; Kørner, Ejnar Alex ; Minthon, Lennart ; Brooks, David ; Van Laere, Koen ; Dupont, Patrick. / Binary classification of ¹⁸F-flutemetamol PET using machine learning : comparison with visual reads and structural MRI. In: NeuroImage. 2013 ; Vol. 64. pp. 517-25.

Bibtex

@article{8657ff536ba74db2bb457922947410c9,
title = "Binary classification of ¹⁸F-flutemetamol PET using machine learning: comparison with visual reads and structural MRI",
abstract = "(18)F-flutemetamol is a positron emission tomography (PET) tracer for in vivo amyloid imaging. The ability to classify amyloid scans in a binary manner as 'normal' versus 'Alzheimer-like', is of high clinical relevance. We evaluated whether a supervised machine learning technique, support vector machines (SVM), can replicate the assignments made by visual readers blind to the clinical diagnosis, which image components have highest diagnostic value according to SVM and how (18)F-flutemetamol-based classification using SVM relates to structural MRI-based classification using SVM within the same subjects. By means of SVM with a linear kernel, we analyzed (18)F-flutemetamol scans and volumetric MRI scans from 72 cases from the (18)F-flutemetamol phase 2 study (27 clinically probable Alzheimer's disease (AD), 20 amnestic mild cognitive impairment (MCI), 25 controls). In a leave-one-out approach, we trained the (18)F-flutemetamol based classifier by means of the visual reads and tested whether the classifier was able to reproduce the assignment based on visual reads and which voxels had the highest feature weights. The (18)F-flutemetamol based classifier was able to replicate the assignments obtained by visual reads with 100{\%} accuracy. The voxels with highest feature weights were in the striatum, precuneus, cingulate and middle frontal gyrus. Second, to determine concordance between the gray matter volume- and the (18)F-flutemetamol-based classification, we trained the classifier with the clinical diagnosis as gold standard. Overall sensitivity of the (18)F-flutemetamol- and the gray matter volume-based classifiers were identical (85.2{\%}), albeit with discordant classification in three cases. Specificity of the (18)F-flutemetamol based classifier was 92{\%} compared to 68{\%} for MRI. In the MCI group, the (18)F-flutemetamol based classifier distinguished more reliably between converters and non-converters than the gray matter-based classifier. The visual read-based binary classification of (18)F-flutemetamol scans can be replicated using SVM. In this sample the specificity of (18)F-flutemetamol based SVM for distinguishing AD from controls is higher than that of gray matter volume-based SVM.",
author = "Rik Vandenberghe and Natalie Nelissen and Eric Salmon and Adrian Ivanoiu and Steen Hasselbalch and Allan Andersen and K{\o}rner, {Ejnar Alex} and Lennart Minthon and David Brooks and {Van Laere}, Koen and Patrick Dupont",
note = "Copyright {\circledC} 2012 Elsevier Inc. All rights reserved.",
year = "2013",
doi = "10.1016/j.neuroimage.2012.09.015",
language = "English",
volume = "64",
pages = "517--25",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press",

}

RIS

TY - JOUR

T1 - Binary classification of ¹⁸F-flutemetamol PET using machine learning

T2 - comparison with visual reads and structural MRI

AU - Vandenberghe, Rik

AU - Nelissen, Natalie

AU - Salmon, Eric

AU - Ivanoiu, Adrian

AU - Hasselbalch, Steen

AU - Andersen, Allan

AU - Kørner, Ejnar Alex

AU - Minthon, Lennart

AU - Brooks, David

AU - Van Laere, Koen

AU - Dupont, Patrick

N1 - Copyright © 2012 Elsevier Inc. All rights reserved.

PY - 2013

Y1 - 2013

N2 - (18)F-flutemetamol is a positron emission tomography (PET) tracer for in vivo amyloid imaging. The ability to classify amyloid scans in a binary manner as 'normal' versus 'Alzheimer-like', is of high clinical relevance. We evaluated whether a supervised machine learning technique, support vector machines (SVM), can replicate the assignments made by visual readers blind to the clinical diagnosis, which image components have highest diagnostic value according to SVM and how (18)F-flutemetamol-based classification using SVM relates to structural MRI-based classification using SVM within the same subjects. By means of SVM with a linear kernel, we analyzed (18)F-flutemetamol scans and volumetric MRI scans from 72 cases from the (18)F-flutemetamol phase 2 study (27 clinically probable Alzheimer's disease (AD), 20 amnestic mild cognitive impairment (MCI), 25 controls). In a leave-one-out approach, we trained the (18)F-flutemetamol based classifier by means of the visual reads and tested whether the classifier was able to reproduce the assignment based on visual reads and which voxels had the highest feature weights. The (18)F-flutemetamol based classifier was able to replicate the assignments obtained by visual reads with 100% accuracy. The voxels with highest feature weights were in the striatum, precuneus, cingulate and middle frontal gyrus. Second, to determine concordance between the gray matter volume- and the (18)F-flutemetamol-based classification, we trained the classifier with the clinical diagnosis as gold standard. Overall sensitivity of the (18)F-flutemetamol- and the gray matter volume-based classifiers were identical (85.2%), albeit with discordant classification in three cases. Specificity of the (18)F-flutemetamol based classifier was 92% compared to 68% for MRI. In the MCI group, the (18)F-flutemetamol based classifier distinguished more reliably between converters and non-converters than the gray matter-based classifier. The visual read-based binary classification of (18)F-flutemetamol scans can be replicated using SVM. In this sample the specificity of (18)F-flutemetamol based SVM for distinguishing AD from controls is higher than that of gray matter volume-based SVM.

AB - (18)F-flutemetamol is a positron emission tomography (PET) tracer for in vivo amyloid imaging. The ability to classify amyloid scans in a binary manner as 'normal' versus 'Alzheimer-like', is of high clinical relevance. We evaluated whether a supervised machine learning technique, support vector machines (SVM), can replicate the assignments made by visual readers blind to the clinical diagnosis, which image components have highest diagnostic value according to SVM and how (18)F-flutemetamol-based classification using SVM relates to structural MRI-based classification using SVM within the same subjects. By means of SVM with a linear kernel, we analyzed (18)F-flutemetamol scans and volumetric MRI scans from 72 cases from the (18)F-flutemetamol phase 2 study (27 clinically probable Alzheimer's disease (AD), 20 amnestic mild cognitive impairment (MCI), 25 controls). In a leave-one-out approach, we trained the (18)F-flutemetamol based classifier by means of the visual reads and tested whether the classifier was able to reproduce the assignment based on visual reads and which voxels had the highest feature weights. The (18)F-flutemetamol based classifier was able to replicate the assignments obtained by visual reads with 100% accuracy. The voxels with highest feature weights were in the striatum, precuneus, cingulate and middle frontal gyrus. Second, to determine concordance between the gray matter volume- and the (18)F-flutemetamol-based classification, we trained the classifier with the clinical diagnosis as gold standard. Overall sensitivity of the (18)F-flutemetamol- and the gray matter volume-based classifiers were identical (85.2%), albeit with discordant classification in three cases. Specificity of the (18)F-flutemetamol based classifier was 92% compared to 68% for MRI. In the MCI group, the (18)F-flutemetamol based classifier distinguished more reliably between converters and non-converters than the gray matter-based classifier. The visual read-based binary classification of (18)F-flutemetamol scans can be replicated using SVM. In this sample the specificity of (18)F-flutemetamol based SVM for distinguishing AD from controls is higher than that of gray matter volume-based SVM.

U2 - 10.1016/j.neuroimage.2012.09.015

DO - 10.1016/j.neuroimage.2012.09.015

M3 - Journal article

VL - 64

SP - 517

EP - 525

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -

ID: 36729246