Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

1 Citation (Scopus)

Abstract

Mild cognitive impairment (MCI) is an intermediate condition between healthy ageing and dementia. The amnestic MCI is often a high risk factor for subsequent Alzheimer’s disease (AD) conversion. Some MCI patients never develop AD (MCI non-converters, or MCInc), but some do progress to AD (MCI converters, or MCIc). The purpose of this study was to predict future AD-conversion in patients with MCI using machine learning with sulcal morphology and cortical thickness measures as classification features. 32 sulci per subject were extracted from 1.5T T1-weighted ADNI database MRI scans of 90 MCIc and 104 MCInc subjects. We computed sulcal morphology features and cortical thickness measurements for support vector machine classification to identify structural patterns distinguishing future AD conversions. The linear kernel classifier trained with these features was able to predict 87.0% of MCI subjects as future converters, (89.7% sensitivity, 84.4% specificity, 0.94 AUC), using 10-fold cross-validation. These results using sulcal and cortical features are superior to the state-of-the-art methods. The most discriminating predictive features were observed in the temporal and frontal lobes in the left hemispheres, and in the entorhinal cortices, which is consistent with literature. However, we also observed structural changes in the cingulate and calcarine cortices, suggesting that the limbic and occipital lobe atrophy may be linked to AD conversion.
Original languageEnglish
Title of host publicationWorld Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic
EditorsLenka Lhotska, Lucie Sukupova, Igor Lacković, Geoffrey S. Ibbott
Number of pages6
Volume68
PublisherSpringer
Publication date1 Jan 2019
Edition1
Pages69-74
ISBN (Print)978-981-10-9034-9
ISBN (Electronic)978-981-10-9035-6
DOIs
Publication statusPublished - 1 Jan 2019
EventWorld Congress on Medical Physics and Biomedical Engineering, WC 2018 - Prague, Czech Republic
Duration: 3 Jun 20188 Jun 2018

Conference

ConferenceWorld Congress on Medical Physics and Biomedical Engineering, WC 2018
CountryCzech Republic
CityPrague
Period03/06/201808/06/2018
SeriesIFMBE Proceedings
Volume68(1)
ISSN1680-0737

Fingerprint

Alzheimer Disease
Occipital Lobe
Entorhinal Cortex
Gyrus Cinguli
Frontal Lobe
Temporal Lobe
Cognitive Dysfunction
Area Under Curve
Atrophy
Dementia
Magnetic Resonance Imaging
Databases
Sensitivity and Specificity

Keywords

  • MRI
  • Alzheimer’s disease
  • Mild cognitive impairment
  • Sulcal morphology
  • Cortical thickness
  • SVM classification

Cite this

Plocharski, M., & Østergaard, L. R. (2019). Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness. In L. Lhotska, L. Sukupova, I. Lacković, & G. S. Ibbott (Eds.), World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic (1 ed., Vol. 68, pp. 69-74). Springer. IFMBE Proceedings, Vol.. 68(1) https://doi.org/10.1007/978-981-10-9035-6_13
Plocharski, Maciej ; Østergaard, Lasse Riis. / Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness. World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic. editor / Lenka Lhotska ; Lucie Sukupova ; Igor Lacković ; Geoffrey S. Ibbott. Vol. 68 1. ed. Springer, 2019. pp. 69-74 (IFMBE Proceedings, Vol. 68(1)).
@inproceedings{8482a5af0ea5454b80a52b8f1a387260,
title = "Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness",
abstract = "Mild cognitive impairment (MCI) is an intermediate condition between healthy ageing and dementia. The amnestic MCI is often a high risk factor for subsequent Alzheimer’s disease (AD) conversion. Some MCI patients never develop AD (MCI non-converters, or MCInc), but some do progress to AD (MCI converters, or MCIc). The purpose of this study was to predict future AD-conversion in patients with MCI using machine learning with sulcal morphology and cortical thickness measures as classification features. 32 sulci per subject were extracted from 1.5T T1-weighted ADNI database MRI scans of 90 MCIc and 104 MCInc subjects. We computed sulcal morphology features and cortical thickness measurements for support vector machine classification to identify structural patterns distinguishing future AD conversions. The linear kernel classifier trained with these features was able to predict 87.0{\%} of MCI subjects as future converters, (89.7{\%} sensitivity, 84.4{\%} specificity, 0.94 AUC), using 10-fold cross-validation. These results using sulcal and cortical features are superior to the state-of-the-art methods. The most discriminating predictive features were observed in the temporal and frontal lobes in the left hemispheres, and in the entorhinal cortices, which is consistent with literature. However, we also observed structural changes in the cingulate and calcarine cortices, suggesting that the limbic and occipital lobe atrophy may be linked to AD conversion.",
keywords = "MRI, Alzheimer’s disease, Mild cognitive impairment, Sulcal morphology, Cortical thickness, SVM classification",
author = "Maciej Plocharski and {\O}stergaard, {Lasse Riis}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-981-10-9035-6_13",
language = "English",
isbn = "978-981-10-9034-9",
volume = "68",
pages = "69--74",
editor = "Lenka Lhotska and Lucie Sukupova and Igor Lacković and Ibbott, {Geoffrey S.}",
booktitle = "World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic",
publisher = "Springer",
address = "Germany",
edition = "1",

}

Plocharski, M & Østergaard, LR 2019, Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness. in L Lhotska, L Sukupova, I Lacković & GS Ibbott (eds), World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic. 1 edn, vol. 68, Springer, IFMBE Proceedings, vol. 68(1), pp. 69-74, World Congress on Medical Physics and Biomedical Engineering, WC 2018, Prague, Czech Republic, 03/06/2018. https://doi.org/10.1007/978-981-10-9035-6_13

Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness. / Plocharski, Maciej; Østergaard, Lasse Riis.

World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic. ed. / Lenka Lhotska; Lucie Sukupova; Igor Lacković; Geoffrey S. Ibbott. Vol. 68 1. ed. Springer, 2019. p. 69-74.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness

AU - Plocharski, Maciej

AU - Østergaard, Lasse Riis

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Mild cognitive impairment (MCI) is an intermediate condition between healthy ageing and dementia. The amnestic MCI is often a high risk factor for subsequent Alzheimer’s disease (AD) conversion. Some MCI patients never develop AD (MCI non-converters, or MCInc), but some do progress to AD (MCI converters, or MCIc). The purpose of this study was to predict future AD-conversion in patients with MCI using machine learning with sulcal morphology and cortical thickness measures as classification features. 32 sulci per subject were extracted from 1.5T T1-weighted ADNI database MRI scans of 90 MCIc and 104 MCInc subjects. We computed sulcal morphology features and cortical thickness measurements for support vector machine classification to identify structural patterns distinguishing future AD conversions. The linear kernel classifier trained with these features was able to predict 87.0% of MCI subjects as future converters, (89.7% sensitivity, 84.4% specificity, 0.94 AUC), using 10-fold cross-validation. These results using sulcal and cortical features are superior to the state-of-the-art methods. The most discriminating predictive features were observed in the temporal and frontal lobes in the left hemispheres, and in the entorhinal cortices, which is consistent with literature. However, we also observed structural changes in the cingulate and calcarine cortices, suggesting that the limbic and occipital lobe atrophy may be linked to AD conversion.

AB - Mild cognitive impairment (MCI) is an intermediate condition between healthy ageing and dementia. The amnestic MCI is often a high risk factor for subsequent Alzheimer’s disease (AD) conversion. Some MCI patients never develop AD (MCI non-converters, or MCInc), but some do progress to AD (MCI converters, or MCIc). The purpose of this study was to predict future AD-conversion in patients with MCI using machine learning with sulcal morphology and cortical thickness measures as classification features. 32 sulci per subject were extracted from 1.5T T1-weighted ADNI database MRI scans of 90 MCIc and 104 MCInc subjects. We computed sulcal morphology features and cortical thickness measurements for support vector machine classification to identify structural patterns distinguishing future AD conversions. The linear kernel classifier trained with these features was able to predict 87.0% of MCI subjects as future converters, (89.7% sensitivity, 84.4% specificity, 0.94 AUC), using 10-fold cross-validation. These results using sulcal and cortical features are superior to the state-of-the-art methods. The most discriminating predictive features were observed in the temporal and frontal lobes in the left hemispheres, and in the entorhinal cortices, which is consistent with literature. However, we also observed structural changes in the cingulate and calcarine cortices, suggesting that the limbic and occipital lobe atrophy may be linked to AD conversion.

KW - MRI

KW - Alzheimer’s disease

KW - Mild cognitive impairment

KW - Sulcal morphology

KW - Cortical thickness

KW - SVM classification

UR - http://www.scopus.com/inward/record.url?scp=85048262940&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-9035-6_13

DO - 10.1007/978-981-10-9035-6_13

M3 - Article in proceeding

SN - 978-981-10-9034-9

VL - 68

SP - 69

EP - 74

BT - World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic

A2 - Lhotska, Lenka

A2 - Sukupova, Lucie

A2 - Lacković, Igor

A2 - Ibbott, Geoffrey S.

PB - Springer

ER -

Plocharski M, Østergaard LR. Prediction of Alzheimer’s disease in mild cognitive impairment using sulcal morphology and cortical thickness. In Lhotska L, Sukupova L, Lacković I, Ibbott GS, editors, World Congress on Medical Physics and Biomedical Engineering, 3-8 June 2018, Prague, Czech Republic. 1 ed. Vol. 68. Springer. 2019. p. 69-74. (IFMBE Proceedings, Vol. 68(1)). https://doi.org/10.1007/978-981-10-9035-6_13