Cross-cohort generalizability of deep and conventional machine learning for MRI-based diagnosis and prediction of Alzheimer’s disease

• Published in: NeuroImage clinical Vol. 31; p. 102712
• Main Authors: Bron, Esther E., Klein, Stefan, Papma, Janne M., Jiskoot, Lize C., Venkatraghavan, Vikram, Linders, Jara, Aalten, Pauline, De Deyn, Peter Paul, Biessels, Geert Jan, Claassen, Jurgen A.H.R., Middelkoop, Huub A.M., Smits, Marion, Niessen, Wiro J., van Swieten, John C., van der Flier, Wiesje M., Ramakers, Inez H.G.B., van der Lugt, Aad
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2021; Elsevier
• Subjects: Alzheimer’s disease; Convolutional Neural Network; External validation; Radiology; Regular; Support vector machine; Convolutional Neural Network; Support vector machine; Alzheimer’s disease; External validation

This work validates the generalizability of MRI-based classification of Alzheimer’s disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD in individuals with mild cognitive impairment (MCI). We used a conventional support vector machine (SV...