Effects of hardware heterogeneity on the performance of SVM Alzheimer's disease classifier

• Published in: NeuroImage (Orlando, Fla.) Vol. 58; no. 3; pp. 785 - 792
• Main Authors: Abdulkadir, Ahmed, Mortamet, Bénédicte, Vemuri, Prashanthi, Jack, Clifford R., Krueger, Gunnar, Klöppel, Stefan
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.10.2011; Elsevier Limited
• Subjects: Accuracy; Alzheimer Disease - classification; Alzheimer Disease - diagnosis; Alzheimer's disease; Artificial Intelligence; Automation; Classifiers; Computers; Diagnostic systems; Field strength; Hardware; Humans; Image Interpretation, Computer-Assisted - instrumentation; Magnetic Resonance Imaging; MRI; Multi-site study; Scanners; Standard deviation; Studies; Support Vector Machine; Support vector machines; Support vector machines (SVM); Training; Magnetic resonance imaging; MRI; Alzheimer's disease; Support vector machines (SVM); Multi-site study

Fully automated machine learning methods based on structural magnetic resonance imaging (MRI) data can assist radiologists in the diagnosis of Alzheimer's disease (AD). These algorithms require large data sets to learn the separation of subjects with and without AD. Training and test data may c...