Cluster Analysis and Decision Trees of MR Imaging in Patients Suffering Alzheimer’s

Hamou, Ali; Bauer, Michael; Lewden, Benoit; Simmons, Andrew; Zhang, Yi; Wahlund, Lars‐Olof; Tunnard, Catherine; Kłoszewska, Iwona; Mecozzi, Patrizia; Tsolaki, Magda; Vellas, Bruno; Muehlboeck, Sebastian; Evans, Alan C.; Julin, Per; Sjögren, Niclas; Spenger, Christian; Lovestone, Simon; Gwadry-Sridhar, Femida

doi:10.1007/978-3-642-12433-4_56

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Principal Components Analysis (PCA) (Eskildsen et al, 2013;Koikkalainen et al, 2011;Teipel et al, 2007;Westman et al, 2011) and Linear discriminant analysis (LDA) (Cho, et al, 2012;Coupe et al, 2012;Eskildsen et al, 2013;Liu et al, 2013;McEvoy et al, 2011) are well-known statistical classifiers which have been used for AD classification. Among other methods, there are artificial neural networks (ANNs) (Aguilar et al, 2013;Escudero, et al, 2011) or decision trees (DT) (Aguilar et al, 2013, Hamou et al, 2011, Querbes et al, 2009. All these works are based on anatomical MR imaging (MRI) biomarkers, such as volumetric or cortical thickness measures, to help discriminate AD subjects from elderly control or MCI subjects.…”

Section: Introductionmentioning

confidence: 99%

Classification of mild cognitive impairment and Alzheimer’s Disease with machine-learning techniques using 1H Magnetic Resonance Spectroscopy data

Munteanu

Fernández-Lozano

Mato‐Abad

et al. 2015

Expert Systems with Applications

View full text Add to dashboard Cite

Please cite this article as: Munteanu, C.R., Fernandez-Lozano, C., Abad, V.M., Fernández, S.P., Álvarez-Linera, J., Hernández-Tamames, J.A., Pazos, A., Classification of mild cognitive impairment and Alzheimer's disease with machine-learning techniques using 1 H Magnetic Resonance Spectroscopy data, Expert Systems with Applications (2015), doi: http://dx.Abstract Several magnetic resonance techniques have been proposed as non-invasive imaging biomarkers for the evaluation of disease progression and early diagnosis of Alzheimer's Disease (AD). This work is the first application of the Proton Magnetic Resonance Spectroscopy 1 H-MRS data and machine-learning techniques to the classification of AD. A gender-matched cohort of 260 subjects aged between 57 and 99 years from the Alzheimer's Disease Research Unit, of the Fundación CIEN-Fundación Reina Sofía has been used. A single-layer perceptron was found for AD prediction with only two spectroscopic voxel volumes (Tvol and CSFvol) in the left hippocampus, with an AUROC value of 0.866 (with TPR 0.812 and FPR 0.204) in a filter feature selection approach. These results suggest that knowing the composition of white and grey matter and cerebrospinal fluid of the spectroscopic voxel is essential in a 1 H-MRS study to improve the accuracy of the quantifications and classifications, particularly in those studies involving elder patients and neurodegenerative diseases.

show abstract