Publication

Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases

van Veen, R., Talavera Martinez, L., Kogan, R. V., Meles, S., Mudali, D., Roerdink, J. B. T. M., Massa, F., Grazzini, M., Obeso, J. A., Rodriguez-Oroz, M. C., Leenders, K., Renken, R., de Vries, J. J. G. & Biehl, M., 2018, Volume 310: Applications of Intelligent Systems. Petkov, N., Strisciuglio, N. & Travieso-González, C. (eds.). Vol. 310. p. 280-289 10 p. (Frontiers in Artificial Intelligence and Applications).

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

APA

van Veen, R., Talavera Martinez, L., Kogan, R. V., Meles, S., Mudali, D., Roerdink, J. B. T. M., ... Biehl, M. (2018). Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases. In N. Petkov, N. Strisciuglio, & C. Travieso-González (Eds.), Volume 310: Applications of Intelligent Systems (Vol. 310, pp. 280-289). (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-929-4-280

Author

van Veen, Rick ; Talavera Martinez, Lidia ; Kogan, Rosalie Vered ; Meles, Sanne ; Mudali, Deborah ; Roerdink, J.B.T.M. ; Massa, Federico ; Grazzini, Matteo ; Obeso, J.A. ; Rodriguez-Oroz, M.C. ; Leenders, Klaus ; Renken, Remco ; de Vries, J.J.G. ; Biehl, Michael. / Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases. Volume 310: Applications of Intelligent Systems. editor / N. Petkov ; N. Strisciuglio ; C. Travieso-González. Vol. 310 2018. pp. 280-289 (Frontiers in Artificial Intelligence and Applications).

Harvard

van Veen, R, Talavera Martinez, L, Kogan, RV, Meles, S, Mudali, D, Roerdink, JBTM, Massa, F, Grazzini, M, Obeso, JA, Rodriguez-Oroz, MC, Leenders, K, Renken, R, de Vries, JJG & Biehl, M 2018, Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases. in N Petkov, N Strisciuglio & C Travieso-González (eds), Volume 310: Applications of Intelligent Systems. vol. 310, Frontiers in Artificial Intelligence and Applications, pp. 280-289. https://doi.org/10.3233/978-1-61499-929-4-280

Standard

Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases. / van Veen, Rick; Talavera Martinez, Lidia; Kogan, Rosalie Vered; Meles, Sanne; Mudali, Deborah; Roerdink, J.B.T.M.; Massa, Federico; Grazzini, Matteo; Obeso, J.A.; Rodriguez-Oroz, M.C.; Leenders, Klaus; Renken, Remco; de Vries, J.J.G.; Biehl, Michael.

Volume 310: Applications of Intelligent Systems. ed. / N. Petkov; N. Strisciuglio; C. Travieso-González. Vol. 310 2018. p. 280-289 (Frontiers in Artificial Intelligence and Applications).

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Vancouver

van Veen R, Talavera Martinez L, Kogan RV, Meles S, Mudali D, Roerdink JBTM et al. Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases. In Petkov N, Strisciuglio N, Travieso-González C, editors, Volume 310: Applications of Intelligent Systems. Vol. 310. 2018. p. 280-289. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-929-4-280


BibTeX

@inbook{e55160badd2d4547b53bf51f6453f6cb,
title = "Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases",
abstract = "Alzheimer's disease (AD) and Parkinson's disease (PD) are two common, progressive neurodegenerative brain disorders. Their diagnosis is very challenging at an early disease stage, if based on clinical symptoms only. Brain imaging techniques such as [18F]-fluoro-deoxyglucose positron emission tomography (FDG-PET) can provide important additional information with respect to changes in the cerebral glucose metabolism. In this study, we use machine learning techniques to perform an automated classification of FDG-PET data. The approach is based on the extraction of features by applying the scaled subprofile model with principal component analysis (SSM/PCA) in order to extract characteristics patterns of glucose metabolism. These features are then used for discriminating healthy controls, PD and AD patients by means of two machine learning frameworks: Generalized Matrix Learning Vector Quantization (GMLVQ) with local and global relevance matrices, and Support Vector Machines (SVMs) with a linear kernel. Datasets from different neuroimaging centers are considered. Results obtained for the individual centers, show that reliable classification is possible. We demonstrate, however, that cross-center classification can be problematic due to potential center-specific characteristics of the available FDG-PET data.",
author = "{van Veen}, Rick and {Talavera Martinez}, Lidia and Kogan, {Rosalie Vered} and Sanne Meles and Deborah Mudali and J.B.T.M. Roerdink and Federico Massa and Matteo Grazzini and J.A. Obeso and M.C. Rodriguez-Oroz and Klaus Leenders and Remco Renken and {de Vries}, J.J.G. and Michael Biehl",
year = "2018",
doi = "10.3233/978-1-61499-929-4-280",
language = "English",
isbn = "978-1-61499-928-7",
volume = "310",
series = "Frontiers in Artificial Intelligence and Applications",
pages = "280--289",
editor = "N. Petkov and N. Strisciuglio and C. Travieso-Gonz{\'a}lez",
booktitle = "Volume 310: Applications of Intelligent Systems",

}

RIS

TY - CHAP

T1 - Machine Learning Based Analysis of FDG-PET Image Data for the Diagnosis of Neurodegenerative Diseases

AU - van Veen, Rick

AU - Talavera Martinez, Lidia

AU - Kogan, Rosalie Vered

AU - Meles, Sanne

AU - Mudali, Deborah

AU - Roerdink, J.B.T.M.

AU - Massa, Federico

AU - Grazzini, Matteo

AU - Obeso, J.A.

AU - Rodriguez-Oroz, M.C.

AU - Leenders, Klaus

AU - Renken, Remco

AU - de Vries, J.J.G.

AU - Biehl, Michael

PY - 2018

Y1 - 2018

N2 - Alzheimer's disease (AD) and Parkinson's disease (PD) are two common, progressive neurodegenerative brain disorders. Their diagnosis is very challenging at an early disease stage, if based on clinical symptoms only. Brain imaging techniques such as [18F]-fluoro-deoxyglucose positron emission tomography (FDG-PET) can provide important additional information with respect to changes in the cerebral glucose metabolism. In this study, we use machine learning techniques to perform an automated classification of FDG-PET data. The approach is based on the extraction of features by applying the scaled subprofile model with principal component analysis (SSM/PCA) in order to extract characteristics patterns of glucose metabolism. These features are then used for discriminating healthy controls, PD and AD patients by means of two machine learning frameworks: Generalized Matrix Learning Vector Quantization (GMLVQ) with local and global relevance matrices, and Support Vector Machines (SVMs) with a linear kernel. Datasets from different neuroimaging centers are considered. Results obtained for the individual centers, show that reliable classification is possible. We demonstrate, however, that cross-center classification can be problematic due to potential center-specific characteristics of the available FDG-PET data.

AB - Alzheimer's disease (AD) and Parkinson's disease (PD) are two common, progressive neurodegenerative brain disorders. Their diagnosis is very challenging at an early disease stage, if based on clinical symptoms only. Brain imaging techniques such as [18F]-fluoro-deoxyglucose positron emission tomography (FDG-PET) can provide important additional information with respect to changes in the cerebral glucose metabolism. In this study, we use machine learning techniques to perform an automated classification of FDG-PET data. The approach is based on the extraction of features by applying the scaled subprofile model with principal component analysis (SSM/PCA) in order to extract characteristics patterns of glucose metabolism. These features are then used for discriminating healthy controls, PD and AD patients by means of two machine learning frameworks: Generalized Matrix Learning Vector Quantization (GMLVQ) with local and global relevance matrices, and Support Vector Machines (SVMs) with a linear kernel. Datasets from different neuroimaging centers are considered. Results obtained for the individual centers, show that reliable classification is possible. We demonstrate, however, that cross-center classification can be problematic due to potential center-specific characteristics of the available FDG-PET data.

U2 - 10.3233/978-1-61499-929-4-280

DO - 10.3233/978-1-61499-929-4-280

M3 - Chapter

SN - 978-1-61499-928-7

VL - 310

T3 - Frontiers in Artificial Intelligence and Applications

SP - 280

EP - 289

BT - Volume 310: Applications of Intelligent Systems

A2 - Petkov, N.

A2 - Strisciuglio, N.

A2 - Travieso-González, C.

ER -

ID: 72195440