A unified deep learning framework for cross-platform harmonization of multi-tracer PET quantification in neurodegenerative disease.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41912831.
- Also identified by DOI 10.1038/s41746-026-02570-0.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Quantitative PET underpins diagnosis and treatment monitoring in neurodegenerative disease, yet systematic biases between PET-MRI and PET-CT preclude threshold transfer and cross-site comparability. We developed and validated the first unified, anatomically guided deep-learning framework to harmonize PET-MRI quantification to PET-CT standards across multiple tracers and scanner manufacturers. The model learns CT-anchored attenuation representations using a vision transformer autoencoder, aligns MRI features to the CT space via contrastive objectives, and performs attention-guided residual correction. In paired same-day scans (N = 70; <sup>18</sup>F-FDG, <sup>18</sup>F-florbetaben, and <sup>18</sup>F-florzolotau), cross-platform bias fell by >80% while preserving inter-regional biological topology. The framework generalized zero-shot to held-out tracers (<sup>18</sup>F-florbetapir and <sup>18</sup>F-FP-CIT) without retraining. Multicenter validation (N = 420; three sites, four vendors) reduced amyloid Centiloid discrepancies from 23.6 to 4.1 (close to, though slightly above, PET-CT test-retest variability) and aligned tau SUVR thresholds. These results support more consistent cross-platform diagnostic cut-offs and reliable longitudinal monitoring when patients transition between modalities, establishing a practical route to scalable, radiation-sparing quantitative PET in therapeutic workflows.