Multidimensional MRI reveals cortical astrogliosis linked to dementia in Alzheimer’s disease

Despite the presence of significant Alzheimer's disease pathology, characterized by amyloid β (Aβ) plaques and phosphorylated tau (pTau) tangles, some cognitively unimpaired elderly individuals do not inevitably develop dementia. Cortical astroglial inflammation, a ubiquitous feature of symptomatic Alzheimer's disease, shows a strong correlation with cognitive impairment severity, highlighting the influence of factors beyond classical pathology. However, non-invasively imaging neuroinflammation, particularly astrogliosis, using MRI remains a significant challenge. Here we sought to address this challenge and to leverage multidimensional (MD) MRI, a powerful approach that combines relaxation with diffusion MR contrasts, to map cortical astrogliosis in the human brain by accessing sub-voxel information. Our goal was to investigate whether MD-MRI can map astroglial pathology in the cerebral cortex, and if so, whether it can distinguish cognitively normal state from dementia in the presence of hallmark Alzheimer's disease neuropathological changes. We adopted a multimodal approach by integrating histological and MRI analyses using human postmortem brain samples from two independent discovery and replication cohorts. <i>Ex vivo</i> cerebral cortical tissue specimens were derived from two groups-non-demented individuals with varying levels of postmortem Alzheimer's disease pathology and individuals with both Alzheimer's disease pathology and dementia-and scanned using 7 T MRI. We acquired and processed MD-MRI, diffusion tensor, and quantitative T₁ and T₂ MRI data, followed by histopathology on the same tissue. By co-registering MRI and microscopy data, we performed quantitative multimodal analyses, leveraging targeted immunostaining to assess MD-MRI sensitivity and specificity towards Aβ, pTau, and glial fibrillary acidic protein (GFAP), a marker for astrogliosis. Our discovery analysis reveals a distinct MD-MRI signature of cortical astrogliosis, enabling the creation of predictive maps for cognitive state amid Alzheimer's disease neuropathological changes. Multiple linear regression analysis linked histological values to MRI changes, revealing that the MD-MRI cortical astrogliosis biomarker was significantly associated with GFAP burden (standardized <i>β</i> = 0.658/0.709, <i>p</i> _FDR < 0.0001), but not with Aβ (standardized <i>β</i> = 0.009/0.120, <i>p</i> _FDR = 0.913/0.274) or pTau (standardized <i>β</i> = -0.196/0.158, <i>p</i> _FDR = 0.051/0.251), for the discovery/replication groups, respectively. Conversely, none of the conventional MRI parameters showed significant associations with GFAP burden in the cortex. Finally, we showed that the MD-MRI-derived astrogliosis biomarker is the only MRI measure capable of predicting cognitive state. While the extent to which pathological glial activation contributes to neuronal damage and cognitive impairment in Alzheimer's disease is uncertain, developing a non-invasive imaging method to see its effects holds promise from a mechanistic perspective and as a potential predictor of cognitive outcomes.