Predicting amyloid status in corticobasal syndrome using modified clinical criteria, magnetic resonance imaging and fluorodeoxyglucose positron emission tomography

Abstract

Introduction: Group comparisons demonstrate greater visuospatial and memory deficits and temporoparietal-predominant degeneration on neuroimaging in patients with corticobasal syndrome (CBS) found to have Alzheimer's disease (AD) pathology versus those with underlying frontotemporal lobar degeneration (FTLD). The value of these features in predicting underlying AD pathology in individual patients is unknown. The goal of this study is to evaluate the utility of modified clinical criteria and visual interpretations of magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET) for predicting amyloid deposition (as a surrogate of Alzheimer's disease neuropathology) in patients presenting with CBS.

Methods: In total, 25 patients meeting CBS core criteria underwent amyloid (Pittsburgh compound B; PIB) PET scans. Clinical records, MRI, and FDG scans were reviewed blinded to PIB results. Modified clinical criteria were used to classify CBS patients as temporoparietal variant CBS (tpvCBS) or frontal variant CBS (fvCBS). MRI and FDG-PET were classified based on the predominant atrophy/hypometabolism pattern (frontal or temporoparietal).

Results: A total of 9 out of 13 patients classified as tpvCBS were PIB+, compared to 2out of 12 patients classified as fvCBS (P < 0.01, sensitivity 82%, specificity 71% for PIB+ status). Visual MRI reads had 73% sensitivity and 46% specificity for PIB+ status with moderate intra-rater reliability (Cohen's kappa = 0.42). Visual FDG reads had higher sensitivity (91%) for PIB+ status with perfect intra-rater reliability (kappa = 1.00), though specificity was low (50%). PIB results were confirmed in all 8 patients with available histopathology (3 PIB+ with confirmed AD, 5 PIB- with FTLD).

Conclusions: Splitting CBS patients into frontal or temporoparietal clinical variants can help predict the likelihood of underlying AD, but criteria require further refinement. Temporoparietal-predominant neuroimaging patterns are sensitive but not specific for AD.

Figure 1

Typical FDG PET metabolic patterns and MRI atrophy patterns. FDG, fluorodeoxyglucose; MRI, magnetic resonance imaging; PET, positron emission tomography.

Figure 2

Voxel-wise FDG comparisons. Patterns of hypometabolism in CBS-PIB- and CBS-PIB+ compared with normal controls (NC) and compared with each other. Voxel-wise comparisons included sex, education and age as nuisance variables. T-score maps are rendered on the ch2.better template. All results are presented at a threshold of P <0.001, uncorrected for multiple comparisons. CBS-PIB-, corticobasal syndrome Pittsburgh compound negative; CBS-PIB+, corticobasal syndrome Pittsburgh compound B positive; FDG, fluorodeoxyglucose.

Figure 3

Neuropathology of patient 13. A. Angular gyrus immunostained against beta-amyloid (4G8). Arrows indicate neuritic plaques and arrowhead indicates cerebral amyloid angiopathy, a typical finding in Alzheimer’s disease patients (Scale bar: 250 μm); B. Inferior temporal gyrus immunostained against phospho-tau (CP-13). The arrows point to neurofibrillary tangles, characteristic of AD. Note their flame-like shape (Scale bar: 500 μm); C. Precentral gyrus immunostained against phospho-tau (CP-13). Arrows indicate ballooned neurons in the cortical deep layers, commonly seen in CBD (Scale bar: 500 μm); D. Precentral gyrus immunostained against phospho-tau (CP-13). The line divides the cortex to the right (cx) and the white matter to the left (WM). Note the striking positivity of white matter for phospho-tau, a feature seen in CBD but not in other tauopathies or AD. AD, Alzheimer’s disease; CBD, corticobasal degradation.