Heterogeneity of Regional Brain Atrophy Patterns Associated with Distinct Progression Rates in Alzheimer's Disease

Abstract

We aimed to identify and characterize subtypes of Alzheimer's disease (AD) exhibiting different patterns of regional brain atrophy on MRI using age- and gender-specific norms of regional brain volumes. AD subjects included in the Alzheimer's Disease Neuroimaging Initiative study were classified into subtypes based on standardized values (Z-scores) of hippocampal and regional cortical volumes on MRI with reference to age- and gender-specific norms obtained from 222 cognitively normal (CN) subjects. Baseline and longitudinal changes of clinical characteristics over 2 years were compared across subtypes. Whole-brain-level gray matter (GM) atrophy pattern using voxel-based morphometry (VBM) and cerebrospinal fluid (CSF) biomarkers of the subtypes were also investigated. Of 163 AD subjects, 58.9% were classified as the "both impaired" subtype with the typical hippocampal and cortical atrophy pattern, whereas 41.1% were classified as the subtypes with atypical atrophy patterns: "hippocampal atrophy only" (19.0%), "cortical atrophy only" (11.7%), and "both spared" (10.4%). Voxel-based morphometric analysis demonstrated whole-brain-level differences in overall GM atrophy across the subtypes. These subtypes showed different progression rates over 2 years; and all subtypes had significantly lower CSF amyloid-β 1-42 levels compared to CN. In conclusion, we identified four AD subtypes exhibiting heterogeneous atrophy patterns on MRI with different progression rates after controlling the effects of aging and gender on atrophy with normative information. CSF biomarker analysis suggests the presence of Aβ neuropathology irrespective of subtypes. Such heterogeneity of MRI-based neuronal injury biomarker and related heterogeneous progression patterns should be considered in clinical trials and practice with AD patients.

Fig 1. Overall regional brain atrophy pattern of AD subtypes in voxel-based morphometry.

Voxel-wise whole-brain comparison of regional GM volume after correction for multiple comparisons using family-wise error correction at p < 0.05 (k = 100). (A) to (D) show the regional patterns of GM volume loss in each AD subtype compared with CN. (A) CN vs. BI, (B) CN vs. HA, (C) CN vs. CA and (D) CN vs. BS. GM, Gray matter; AD, Alzheimer’s disease; CN, Cognitively normal; BI, Both impaired; HA, Hippocampal atrophy only; CA, Cortical atrophy only; BS, Both spared.

Fig 2. Longitudinal changes of cognitive function over 2 years across AD subtypes.

Baseline, 1-year, and 2-year follow-up data on (A) MMSE indicating global cognition, (B) ADNI-Mem indicating memory function and (C) ADNI-EF indicating executive function are plotted, with means and standard errors. AD, Alzheimer’s disease; BI, Both impaired; HA, Hippocampal atrophy only; CA, Cortical atrophy only; BS, Both spared; MMSE; Mini-mental state examination; ADNI-Mem, composite score of memory function; ADNI-EF, composite score of executive function.

Fig 3. CSF biomarker levels.

The dot plots of CSF biomarkers in CN and AD subtypes. Bars indicates median and IQR. (A) CSF Aβ_1–42, (B) CSF t-tau, (C) CSF p-tau, (D) t-tau/Aβ_1–42 ratio, (E) p-tau/Aβ_1–42 ratio. CN, Cognitively normal; AD, Alzheimer’s disease; BI, Both impaired; HA, Hippocampal atrophy only; CA, Cortical atrophy only; BS, Both spared; CSF, Cerebrospinal fluid; Aβ_1–42 = Amyloid-β 1–42 peptide; t-tau, total tau; p-tau, phosphorylated tau.