Diagnostic effectiveness of quantitative [¹⁸F]flutemetamol PET imaging for detection of fibrillar amyloid β using cortical biopsy histopathology as the standard of truth in subjects with idiopathic normal pressure hydrocephalus

Abstract

Introduction: PET imaging of amyloid-β (Aβ) in vivo holds promise for aiding in earlier diagnosis and intervention in Alzheimer's disease (AD) and mild cognitive impairment. AD-like Aβ pathology is a common comorbidity in patients with idiopathic normal pressure hydrocephalus (iNPH). Fifty patients with iNPH needing ventriculo-peritoneal shunting or intracranial pressure monitoring underwent [18F]flutemetamol PET before (N = 28) or after (N = 22) surgery. Cortical uptake of [18F]flutemetamol was assessed visually by blinded reviewers, and also quantitatively via standard uptake value ratio (SUVR) in specific neocortical regions in relation to either cerebellum or pons reference region: the cerebral cortex of (prospective studies) or surrounding (retrospective studies) the biopsy site, the contralateral homolog, and a calculated composite brain measure. Aβ pathology in the biopsy specimen (standard of truth [SoT]) was measured using Bielschowsky silver and thioflavin S plaque scores, percentage area of grey matter positive for monoclonal antibody to Aβ (4G8), and overall pathology impression. We set out to find (1) which pair(s) of PET SUVR and pathology SoT endpoints matched best, (2) whether quantitative measures of [18F]flutemetamol PET were better for predicting the pathology outcome than blinded image examination (BIE), and (3) whether there was a better match between PET image findings in retrospective vs. prospective studies.

Results: Of the 24 possible endpoint/SoT combinations, the one with composite-cerebellum SUVR and SoT based on overall pathology had the highest Youden index (1.000), receiver operating characteristic area under the curve (1.000), sensitivity (1.000), specificity (1.000), and sum of sensitivity and specificity for the pooled data as well as for the retrospective and prospective studies separately (2.00, for all 3). The BIE sum of sensitivity and specificity, comparable to that for quantitation, was highest using Bielschowsky silver as SoT for all SUVRs (ipsilateral, contralateral, and composite, for both reference regions). The composite SUVR had a 100% positive predictive value (both reference regions) for the overall pathology diagnosis. All SUVRs had a 100% negative predictive value for the Bielschowsky silver result.

Conclusion: Bielschowsky silver stain and overall pathology judgment showed the strongest associations with imaging results.

Figure 1

Examples of abnormal and normal [¹⁸F]flutemetamol positron emission tomography (PET) and corresponding magnetic resonance (MR) or computed tomography (CT) imaging and histopathology. Panel a) [¹⁸F]Flutemetamol PET imaging correlates with histopathology (Study D). Amyloid plaques were determined in biopsy samples by 4G8 imunohistochemistry (IHC). Neuritic plaques were identified in serial sections using a modified Bielschowsky silver stain. Panel b) [¹⁸F]Flutemetamol PET images were obtained either retrospectively after biopsy (Studies A and C) or prospectively before biopsy (Studies B and D). Small cortical biopsies were taken during shunt placement and histopathology was correlated to standard uptake value ratio (SUVR) measures in volumes of interest (VOIs) either ipsilateral or contralateral to the site of biopsy.

Figure 2

Receiver-operator curves by pathology standard of truth for each SUVR type: a) 4G8, b) Bielschowsky silver stain, c) Thioflavin S, and d) Overall Pathology. The composite-cerebellum/overall pathology pair had the largest ROC AUC (1.000). ROC AUCs for composite-cerebellum/and contralateral-pons/Bielschowsky silver were nearly as large (both 0.9815).

Figure 3

Diagnostic efficacy by SUVR type (a – c using cerebellum as reference region, d – f using pons as reference region) for each pathology standard of truth (within each group from left to right: 4G8 [blue], Bielschowsky Silver [rust], Thioflavin S [green], and Overall Pathology [purple]). Horizontal axis: Groups of bars from left to right represent Sensitivity, Specificity, Accuracy, PPV, and NPV. Vertical axis: Percentage (maximum 100%). Error bars represent 95% confidence intervals.