Premium
Data‐driven full‐resolution model of amyloid, hypometabolism and atrophy changes over Alzheimer's disease progression
Author(s) -
Nader Clement Abi,
Ayache Nicholas,
Robert Philippe,
Lorenzi Marco
Publication year - 2020
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1002/alz.042874
Subject(s) - atrophy , alzheimer's disease neuroimaging initiative , neuroscience , disease , neuroimaging , magnetic resonance imaging , amyloid (mycology) , pathological , precuneus , pathology , cognition , psychology , medicine , cognitive impairment , radiology
Abstract Background Neurodegenerative disorders such as Alzheimer’s disease (AD) are characterized by morphological and molecular changes of the brain, ultimately leading to cognitive and behavioral decline. A comprehensive model of the brain’s spatio‐temporal changes in AD would be a valuable instrument for improving our understanding of the disease dynamics, and for tracking disease progression in clinical trials. Method We propose a spatio‐temporal generative model of disease progression, aimed at disentangling and quantifying the independent dynamics of changes observed in datasets of multi‐modal imaging data. Our data consists of AV45‐PET, FDG‐PET, and structural magnetic resonance images (MRI), representing respectively amyloid deposition, glucose metabolism and gray matter atrophy for 544 individuals (137 healthy, 293 affected by mild cognitive impairment, and 114 AD patients). The model is based on a monotonicity constraint, which forces the spatio‐temporal image trajectories to evolve from a normal to a pathological stage. Moreover, we aim at automatically inferring the disease severity of a patient with respect to the estimated trajectory. Results The estimated spatio‐temporal processes at stake in AD are shown in Figure 1. The model identifies specific brain areas and their evolution in time in terms of gray matter atrophy, glucose metabolism, and amyloid concentration. The model describes a gray matter loss encompassing a large extent of the brain with a focus on cortical areas, but also targets subcortical areas such as the hippocampi. Concerning the glucose metabolism, the model identifies a pattern of hypometabolism involving most of the brain regions that tends to plateau, while also detecting a linear pattern of hypometabolism targeting areas such as the precuneus and the parietal lobe. Finally, the model highlights an increase of amyloid deposition mapping most of brain regions, such as the parietal and frontal lobes, while exhibiting a differential pattern of amyloid deposition targeting mostly frontal, temporal, occipital areas and precuneus. Moreover, the time‐scale associated with these spatio‐temporal processes strongly correlates with the clinical evolution of the disease (Figure 2). Conclusion The presented disease progression allows to disentangle differential temporal progression patterns mapping brain regions key to neurodegeneration, while revealing a disease‐specific time scale associated to the clinical diagnosis.