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... Show moreThis 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 (SVM) and a deep convolutional neural network (CNN) approach based on structural MRI scans that underwent either minimal pre-processing or more extensive preprocessing into modulated gray matter (GM) maps. Classifiers were optimized and evaluated using cross validation in the Alzheimer's Disease Neuroimaging Initiative (ADNI; 334 AD, 520 CN). Trained classifiers were subsequently applied to predict conversion to AD in ADNI MCI patients (231 converters, 628 non converters) and in the independent Health-RI Parelsnoer Neurodegenerative Diseases Biobank data set. From this multi-center study representing a tertiary memory clinic population, we included 199 AD patients, 139 participants with subjective cognitive decline, 48 MCI patients converting to dementia, and 91 MCI patients who did not convert to dementia. AD-CN classification based on modulated GM maps resulted in a similar area-under-the-curve (AUC) for SVM (0.940; 95%CI: 0.924-0.955) and CNN (0.933; 95%CI: 0.918-0.948). Application to conversion prediction in MCI yielded significantly higher performance for SVM (AUC = 0.756; 95%CI: 0.720-0.788) than for CNN (AUC = 0.742; 95%CI: 0.709-0.776) (p < 0.01 for McNemar's test). In external validation, performance was slightly decreased. For AD-CN, it again gave similar AUCs for SVM (0.896; 95%CI: 0.855-0.932) and CNN (0.876; 95%CI: 0.836-0.913). For prediction in MCI, performances decreased for both SVM (AUC = 0.665; 95%CI: 0.576-0.760) and CNN (AUC = 0.702; 95%CI: 0.624-0.786). Both with SVM and CNN, classification based on modulated GM maps significantly outperformed classification based on minimally processed images (p = 0.01). Deep and conventional classifiers performed equally well for AD classification and their performance decreased only slightly when applied to the external cohort. We expect that this work on external validation contributes towards translation of machine learning to clinical practice. Show less
Heinen, R.; Groeneveld, O.N.; Barkhof, F.; Bresser, J. de; Exalto, L.G.; Kuijf, H.J.; ... ; TRACE-VCI Study Grp 2020
IntroductionIt is unknown whether different types of small vessel disease (SVD), differentially relate to brain atrophy and if co-occurring Alzheimer's disease pathology affects this relation... Show moreIntroductionIt is unknown whether different types of small vessel disease (SVD), differentially relate to brain atrophy and if co-occurring Alzheimer's disease pathology affects this relation.MethodsIn 725 memory clinic patients with SVD (mean age 67 +/- 8 years, 48% female) we compared brain volumes of those with moderate/severe white matter hyperintensities (WMHs; n = 326), lacunes (n = 132) and cerebral microbleeds (n = 321) to a reference group with mild WMHs (n = 197), also considering cerebrospinal fluid (CSF) amyloid status in a subset of patients (n = 488).ResultsWMHs and lacunes, but not cerebral microbleeds, were associated with smaller gray matter (GM) volumes. In analyses stratified by CSF amyloid status, WMHs and lacunes were associated with smaller total brain and GM volumes only in amyloid-negative patients. SVD-related atrophy was most evident in frontal (cortical) GM, again predominantly in amyloid-negative patients.DiscussionAmyloid status modifies the differential relation between SVD lesion type and brain atrophy in memory clinic patients. Show less
Increasing evidence recognizes Alzheimer's disease (AD) as a multifactorial and heterogeneous disease with multiple contributors to its pathophysiology, including vascular dysfunction. The recently... Show moreIncreasing evidence recognizes Alzheimer's disease (AD) as a multifactorial and heterogeneous disease with multiple contributors to its pathophysiology, including vascular dysfunction. The recently updated AD Research Framework put forth by the National Institute on Aging-Alzheimer's Association describes a biomarker-based pathologic definition of AD focused on amyloid, tau, and neuronal injury. In response to this article, here we first discussed evidence that vascular dysfunction is an important early event in AD pathophysiology. Next, we examined various imaging sequences that could be easily implemented to evaluate different types of vascular dysfunction associated with, and/or contributing to, AD pathophysiology, including changes in blood-brain barrier integrity and cerebral blood flow. Vascular imaging biomarkers of small vessel disease of the brain, which is responsible for >50% of dementia worldwide, including AD, are already established, well characterized, and easy to recognize. We suggest that these vascular biomarkers should be incorporated into the AD Research Framework to gain a better understanding of AD pathophysiology and aid in treatment efforts. (C) 2018 the Alzheimer's Association. Published by Elsevier Inc. All rights reserved. Show less
Aalten, P.; Ramakers, I.H.G.B.; Biessels, G.J.; Deyn, P.P. de; Koek, H.L.; OldeRikkert, M.G.M.; ... ; Flier, W.M. van der 2014
