Harmonizing florbetapir and PiB PET measurements of cortical Aβ plaque burden using multiple regions-of-interest and machine learning techniques: An alternative to the Centiloid approach.

Abstract

Machine learning (ML) can optimize amyloid (Aβ) comparability among positron emission tomography (PET) radiotracers. Using multi-regional florbetapir (FBP) measures and ML, we report better Pittsburgh compound-B (PiB)/FBP harmonization of mean-cortical Aβ (mcAβ) than Centiloid. PiB-FBP pairs from 92 subjects in www.oasis-brains.org and 46 in www.gaain.org/centiloid-project were used as the training/testing sets. FreeSurfer-extracted FBP multi-regional Aβ and actual PiB mcAβ in the training set were used to train ML models generating synthetic PiB mcAβ. The correlation coefficient (R) between the synthetic/actual PiB mcAβ in the testing set was assessed. In the testing set, the synthetic/actual PiB mcAβ correlation R=0.985 (R2 =0.970) using artificial neural network was significantly higher (p≤6.6e-4) than the FBP/PiB correlation R=0.927 (R2 =0.860), improving total variance percentage (R2 ) from 86% to 97%. Other ML models such as partial least square, ensemble, and relevance vector regressions also improved R (p=9.677e-05 /0.045/0.0017). ML improved mcAβ comparability. Additional studies are needed for the generalizability to other amyloid tracers, and to tau PET. Highlights Centiloid is a calibration of the amyloid scale, not harmonization. Centiloid unifies the amyloid scale without improving inter-tracer association (R2 ). Machine learning (ML) can harmonize the amyloid scale by improving R2 . ML harmonization maps multi-regional florbetapir SUVRs to PiB mean-cortical SUVR. Artificial neural network ML increases Centiloid R2 from 86% to 97%.