Erratum: Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI (NeuroImage: Clinical (2018) 20 (188–196), (S2213158218302262), (10.1016/j.nicl.2018.07.014))

Rogier A. Feis, Mark J. R. J. Bouts, Jessica L. Panman, Lize C. Jiskoot, Elise G. P. Dopper, Tijn M. Schouten, Frank de Vos, Jeroen van der Grond, John C. van Swieten, Serge A. R. B. Rombouts

Research output: Contribution to journalErratumAcademicpeer-review

Abstract

Background: Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification. Methods: Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC). Results: The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.582, p = 0.078). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.642 (p = 0.032). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.684, p = 0.004). Conclusions: FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.
Original languageEnglish
Article number101718
JournalNeuroImage: Clinical
DOIs
Publication statusPublished - 2019

Cite this

Feis, Rogier A. ; Bouts, Mark J. R. J. ; Panman, Jessica L. ; Jiskoot, Lize C. ; Dopper, Elise G. P. ; Schouten, Tijn M. ; de Vos, Frank ; van der Grond, Jeroen ; van Swieten, John C. ; Rombouts, Serge A. R. B. / Erratum: Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI (NeuroImage: Clinical (2018) 20 (188–196), (S2213158218302262), (10.1016/j.nicl.2018.07.014)). In: NeuroImage: Clinical. 2019.
@article{8ce0bc3482c44ad796b8d5c959f37a8f,
title = "Erratum: Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI (NeuroImage: Clinical (2018) 20 (188–196), (S2213158218302262), (10.1016/j.nicl.2018.07.014))",
abstract = "Background: Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification. Methods: Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC). Results: The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.582, p = 0.078). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.642 (p = 0.032). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.684, p = 0.004). Conclusions: FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.",
author = "Feis, {Rogier A.} and Bouts, {Mark J. R. J.} and Panman, {Jessica L.} and Jiskoot, {Lize C.} and Dopper, {Elise G. P.} and Schouten, {Tijn M.} and {de Vos}, Frank and {van der Grond}, Jeroen and {van Swieten}, {John C.} and Rombouts, {Serge A. R. B.}",
year = "2019",
doi = "10.1016/j.nicl.2019.101718",
language = "English",
journal = "NeuroImage: Clinical",
issn = "2213-1582",
publisher = "Elsevier BV",

}

Erratum: Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI (NeuroImage: Clinical (2018) 20 (188–196), (S2213158218302262), (10.1016/j.nicl.2018.07.014)). / Feis, Rogier A.; Bouts, Mark J. R. J.; Panman, Jessica L.; Jiskoot, Lize C.; Dopper, Elise G. P.; Schouten, Tijn M.; de Vos, Frank; van der Grond, Jeroen; van Swieten, John C.; Rombouts, Serge A. R. B.

In: NeuroImage: Clinical, 2019.

Research output: Contribution to journalErratumAcademicpeer-review

TY - JOUR

T1 - Erratum: Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI (NeuroImage: Clinical (2018) 20 (188–196), (S2213158218302262), (10.1016/j.nicl.2018.07.014))

AU - Feis, Rogier A.

AU - Bouts, Mark J. R. J.

AU - Panman, Jessica L.

AU - Jiskoot, Lize C.

AU - Dopper, Elise G. P.

AU - Schouten, Tijn M.

AU - de Vos, Frank

AU - van der Grond, Jeroen

AU - van Swieten, John C.

AU - Rombouts, Serge A. R. B.

PY - 2019

Y1 - 2019

N2 - Background: Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification. Methods: Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC). Results: The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.582, p = 0.078). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.642 (p = 0.032). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.684, p = 0.004). Conclusions: FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.

AB - Background: Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification. Methods: Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC). Results: The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.582, p = 0.078). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.642 (p = 0.032). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.684, p = 0.004). Conclusions: FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85062151061&origin=inward

UR - https://www.ncbi.nlm.nih.gov/pubmed/30827922

U2 - 10.1016/j.nicl.2019.101718

DO - 10.1016/j.nicl.2019.101718

M3 - Erratum

JO - NeuroImage: Clinical

JF - NeuroImage: Clinical

SN - 2213-1582

M1 - 101718

ER -