Decomposition‐based harmonization for quantitative PET imaging across scanners and radiotracers
Shilun Zhao, Qi Huang, Binbin Nie, Tianhao Zhang, Chuantao Zuo, Ge Zhang, Guangjuan Mao, Baoci ShanAbstract
Background
Quantitative positron emission tomography (PET) is widely applied in oncology, neuroscience, and clinical practice. However, its quantitative accuracy is often compromised by systematic variability arising from differences in scanners, acquisition protocols, and radiotracers, which limits the reliability of multicenter studies.
Purpose
To develop and validate PETHarmony, a novel voxel‐level harmonization framework for minimizing inter‐scanner and inter‐tracer variability.
Methods
PETHarmony utilizes a linear neural network to model covariates and singular value decomposition to isolate and remove variability in voxel space. Its performance was assessed in four scenarios: (i) using paired ‐FBB PET/CT and PET/MR scans ( N = 25, Huashan Hospital) to test the removal of scanner variability; (ii) using 20 repeated PET acquisitions of a NEMA NU‐2 IQ phantom to validate absolute quantitative accuracy; (iii) using paired ‐FBP and ‐PiB scans from GAAIN ( N = 46); and OASIS ( N = 84) to evaluate cross‐tracer consistency of cortical SUVR; and (iv) using unpaired multicenter data from ADNI ( N = 471; ‐FBP, ‐FTP, ‐FDG) to assess the impact on Alzheimer's disease (AD) classification. All harmonization procedures were conducted using leave‐one‐out cross‐validation or by training on unpaired data and applying the learned transformations to paired data.
Results
PETHarmony effectively eliminated voxel‐level discrepancies between PET/CT and PET/MR images ( reduced to n.s.). Phantom validation demonstrated that recovery coefficient curves were restored and closely aligned with the reference line, indicating improved quantitative accuracy. For cross‐tracer consistency, linear regression between ‐FBP and ‐PiB was markedly improved toward the line of identity ( y = x , R = 1). Specifically, in the GAAIN cohort, the regression line improved from y = 0.52 x + 0.52, = 0.89 to y = 0.93 x + 0.13, R = 0.97. In the OASIS cohort, it improved from y = 0.51 x + 0.55, = 0.87 to y = 0.95 x + 0.06, = 0.95. Furthermore, PETHarmony improved multicenter AD classification accuracy by 15.3% (‐FBP), 18.3% (‐FTP), and 21.7% (‐FDG).
Conclusions
PETHarmony achieves robust voxel‐level harmonization of multicenter PET data, significantly improving cross‐scanner and cross‐tracer consistency and enhancing diagnostic accuracy. It provides a practical solution for standardizing quantitative PET in multicenter oncology, neuroscience, and other clinical trials.