MRI-guided versus OSEM Amyloid Brain PET Reconstruction for Reader Agreement, Visual Consistency, and Diagnostic Accuracy.

Abstract

Background Ordered-subset expectation-maximization (OSEM) PET reconstruction is limited by spatial resolution and partial-volume effects, contributing to interreader variability and false positives and highlighting the need for more comprehensive alternative approaches. Purpose To evaluate whether MRI-guided brain PET reconstruction improves inter-reader agreement, visual consistency, diagnostic performance, and Centiloid (CL)-based quantitative separation of amyloid status compared with OSEM reconstruction. Materials and Methods In this retrospective multireader diagnostic accuracy study conducted at a single institution, consecutive brain fluorine 18 (¹⁸F)-florbetapir PET/MRI scans (September 2019 to December 2024) were analyzed. For each scan, OSEM and MRI-guided PET reconstructions were generated. Four blinded readers independently interpreted both reconstructions in separate sessions, recording amyloid status (β-amyloid [Aβ]-/Aβ+), diagnostic confidence (three-point scale), and image quality (five-point scale). The consensus-derived reference standard (Aβ-/Aβ+) was not fully independent. Diagnostic performance was assessed using generalized linear mixed-effects models. Interreader agreement was assessed using Fleiss κ, and quantitative measures (CL values and standardized uptake value ratios) were compared between reconstructions. <i>P</i> values were adjusted for multiple comparisons. Results A total of 120 patients (120 scans; median age, 74.8 years [IQR, 68.7-78.3 years]; 66 males) were included. MRI-guided reconstruction improved interreader agreement for amyloid status (Fleiss κ, 0.91 vs 0.79; absolute increase, 0.12 [95% CI: 0.05, 0.20]; <i>P</i> < .001), with greatest improvement in the posterior cingulate cortex and precuneus (κ, 0.82 vs 0.74; <i>P</i> = .03). Specificity improved from 91.6% (95% CI: 85.7, 96.5) to 99.2% (95% CI: 98.4, 99.7), reducing false positives from 8.1% (14 of 166) to 0.8% (two of 168) (<i>P</i> < .001) relative to the reference standard. CL separation was preserved between Aβ- and Aβ+ groups (MRI-guided: -4.24 vs 89.74; OSEM: 0.84 vs 89.0; both <i>P</i> < .001), with lower median CL values in Aβ- scans (-4.24 vs 0.84; <i>P</i> = .01). Conclusion MRI-guided amyloid brain PET reconstruction showed higher interreader agreement and fewer false-positive classifications than OSEM reconstruction and preserved CL-based separation between the Aβ- and Aβ+ groups. © RSNA, 2026 <i>Supplemental material is available for this article.</i> See also the editorial by Bedmutha in this issue.