Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment

Maciej Plocharski, Lasse Riis Østergaard, The Alzheimer’s Disease Neuroimaging Initiative

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

Abstract

Prominent changes in sulcal morphology and cortical thickness characterize the neurodegeneration in Alzheimer’s disease (AD). A combination of these measures has a potential of predicting AD and distinguishing it from mild cognitive impairment (MCI) and cognitively normal control subjects (CN). The purpose of this study was to propose a machine learning and pattern recognition approach of combining sulcal morphology features and cortical thickness measures as biomarkers for AD. Sulcal features (depth, length, mean and Gaussian curvature, surface area) and cortical thickness measures were extracted from 241 T1 MRI scans from ADNI database (81 AD, 75 MCI, 85 CN). SVM classifiers provided the highest accuracy of 95.0%, 93.0% sensitivity, and 97.0% specificity (AUC of 0.95) when classifying CN and AD. The majority of the features were located in the left hemisphere, which in AD is reported to be more severely affected by atrophy, and to lose gray matter faster than the right. Results indicate that a combination of sulcal and cortical features provides high classification results, which are competitive with the state-of-the-art techniques.
Original languageEnglish
Title of host publicationImage Analysis : 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings
EditorsMichael Felsberg, Per-Erik Forssén, Jonas Unger, Ida-Maria Sintorn
Number of pages12
PublisherSpringer
Publication date2019
Pages427-438
ISBN (Print)978-3-030-20204-0
ISBN (Electronic)978-3-030-20205-7
DOIs
Publication statusPublished - 2019
Event21st Scandinavian Conference on Image Analysis, SCIA 2019 - Norrköping, Sweden
Duration: 11 Jun 201913 Jun 2019

Conference

Conference21st Scandinavian Conference on Image Analysis, SCIA 2019
CountrySweden
CityNorrköping
Period11/06/201913/06/2019
SeriesLecture Notes in Computer Science
Volume11482
ISSN0302-9743

Keywords

  • Alzheimer’s disease
  • Feature extraction
  • Morphology
  • Pattern recognition
  • SVM

Cite this

Plocharski, M., Østergaard, L. R., & The Alzheimer’s Disease Neuroimaging Initiative (2019). Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment. In M. Felsberg, P-E. Forssén, J. Unger, & I-M. Sintorn (Eds.), Image Analysis: 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings (pp. 427-438). Springer. Lecture Notes in Computer Science, Vol.. 11482 https://doi.org/10.1007/978-3-030-20205-7_35
Plocharski, Maciej ; Østergaard, Lasse Riis ; The Alzheimer’s Disease Neuroimaging Initiative. / Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment. Image Analysis: 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings. editor / Michael Felsberg ; Per-Erik Forssén ; Jonas Unger ; Ida-Maria Sintorn. Springer, 2019. pp. 427-438 (Lecture Notes in Computer Science, Vol. 11482).
@inproceedings{e1f090c8604f44baabe530f824db2af3,
title = "Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment",
abstract = "Prominent changes in sulcal morphology and cortical thickness characterize the neurodegeneration in Alzheimer’s disease (AD). A combination of these measures has a potential of predicting AD and distinguishing it from mild cognitive impairment (MCI) and cognitively normal control subjects (CN). The purpose of this study was to propose a machine learning and pattern recognition approach of combining sulcal morphology features and cortical thickness measures as biomarkers for AD. Sulcal features (depth, length, mean and Gaussian curvature, surface area) and cortical thickness measures were extracted from 241 T1 MRI scans from ADNI database (81 AD, 75 MCI, 85 CN). SVM classifiers provided the highest accuracy of 95.0{\%}, 93.0{\%} sensitivity, and 97.0{\%} specificity (AUC of 0.95) when classifying CN and AD. The majority of the features were located in the left hemisphere, which in AD is reported to be more severely affected by atrophy, and to lose gray matter faster than the right. Results indicate that a combination of sulcal and cortical features provides high classification results, which are competitive with the state-of-the-art techniques.",
keywords = "Alzheimer’s disease, Feature extraction, Morphology, Pattern recognition, SVM",
author = "Maciej Plocharski and {\O}stergaard, {Lasse Riis} and {The Alzheimer’s Disease Neuroimaging Initiative}",
year = "2019",
doi = "10.1007/978-3-030-20205-7_35",
language = "English",
isbn = "978-3-030-20204-0",
pages = "427--438",
editor = "Michael Felsberg and Per-Erik Forss{\'e}n and Jonas Unger and Ida-Maria Sintorn",
booktitle = "Image Analysis",
publisher = "Springer",
address = "Germany",

}

Plocharski, M, Østergaard, LR & The Alzheimer’s Disease Neuroimaging Initiative 2019, Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment. in M Felsberg, P-E Forssén, J Unger & I-M Sintorn (eds), Image Analysis: 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings. Springer, Lecture Notes in Computer Science, vol. 11482, pp. 427-438, 21st Scandinavian Conference on Image Analysis, SCIA 2019, Norrköping, Sweden, 11/06/2019. https://doi.org/10.1007/978-3-030-20205-7_35

Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment. / Plocharski, Maciej; Østergaard, Lasse Riis; The Alzheimer’s Disease Neuroimaging Initiative.

Image Analysis: 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings. ed. / Michael Felsberg; Per-Erik Forssén; Jonas Unger; Ida-Maria Sintorn. Springer, 2019. p. 427-438.

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

TY - GEN

T1 - Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment

AU - Plocharski, Maciej

AU - Østergaard, Lasse Riis

AU - The Alzheimer’s Disease Neuroimaging Initiative

PY - 2019

Y1 - 2019

N2 - Prominent changes in sulcal morphology and cortical thickness characterize the neurodegeneration in Alzheimer’s disease (AD). A combination of these measures has a potential of predicting AD and distinguishing it from mild cognitive impairment (MCI) and cognitively normal control subjects (CN). The purpose of this study was to propose a machine learning and pattern recognition approach of combining sulcal morphology features and cortical thickness measures as biomarkers for AD. Sulcal features (depth, length, mean and Gaussian curvature, surface area) and cortical thickness measures were extracted from 241 T1 MRI scans from ADNI database (81 AD, 75 MCI, 85 CN). SVM classifiers provided the highest accuracy of 95.0%, 93.0% sensitivity, and 97.0% specificity (AUC of 0.95) when classifying CN and AD. The majority of the features were located in the left hemisphere, which in AD is reported to be more severely affected by atrophy, and to lose gray matter faster than the right. Results indicate that a combination of sulcal and cortical features provides high classification results, which are competitive with the state-of-the-art techniques.

AB - Prominent changes in sulcal morphology and cortical thickness characterize the neurodegeneration in Alzheimer’s disease (AD). A combination of these measures has a potential of predicting AD and distinguishing it from mild cognitive impairment (MCI) and cognitively normal control subjects (CN). The purpose of this study was to propose a machine learning and pattern recognition approach of combining sulcal morphology features and cortical thickness measures as biomarkers for AD. Sulcal features (depth, length, mean and Gaussian curvature, surface area) and cortical thickness measures were extracted from 241 T1 MRI scans from ADNI database (81 AD, 75 MCI, 85 CN). SVM classifiers provided the highest accuracy of 95.0%, 93.0% sensitivity, and 97.0% specificity (AUC of 0.95) when classifying CN and AD. The majority of the features were located in the left hemisphere, which in AD is reported to be more severely affected by atrophy, and to lose gray matter faster than the right. Results indicate that a combination of sulcal and cortical features provides high classification results, which are competitive with the state-of-the-art techniques.

KW - Alzheimer’s disease

KW - Feature extraction

KW - Morphology

KW - Pattern recognition

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85066883309&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-20205-7_35

DO - 10.1007/978-3-030-20205-7_35

M3 - Article in proceeding

SN - 978-3-030-20204-0

SP - 427

EP - 438

BT - Image Analysis

A2 - Felsberg, Michael

A2 - Forssén, Per-Erik

A2 - Unger, Jonas

A2 - Sintorn, Ida-Maria

PB - Springer

ER -

Plocharski M, Østergaard LR, The Alzheimer’s Disease Neuroimaging Initiative. Sulcal and Cortical Features for Classification of Alzheimer’s Disease and Mild Cognitive Impairment. In Felsberg M, Forssén P-E, Unger J, Sintorn I-M, editors, Image Analysis: 21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings. Springer. 2019. p. 427-438. (Lecture Notes in Computer Science, Vol. 11482). https://doi.org/10.1007/978-3-030-20205-7_35