Gamma–positron imaging with tracers that emit a prompt \(\gamma\) (> 511 keV) is vulnerable to Compton down-scatter leaking into the 511-keV window and mimicking true annihilation pairs. Conventional Positron Emission Tomography (PET) systems reconstruct annihilation events without leveraging that the two 511-keV photons are not only orthogonally polarized but also produced in a Bell-entangled state. The polarization correlations of this entanglement imprint themselves in Compton scattering kinematics, particularly the relative azimuthal scattering angle ( \(\Delta \phi\) ), offering a physics-informed handle for event discrimination. We present a machine-learning framework that exploits these quantum-encoded features to resolve true lines of response (LORs) and reject random coincidences in a dual-panel cadmium zinc telluride (CZT) system. Detected events were categorized into one-photoelectric (1P) and Compton (1C) interaction patterns, yielding four candidate interaction sequences per event. Each event was represented as a 4 \(\times\) 21 feature matrix comprising spatial coordinates, energy deposits, and angular descriptors, including \(\Delta \phi\) and polar scattering angle \(\theta\) . Feature ablation with five-fold cross-validation revealed that the combination of energy and \(\Delta \phi\) provided the highest discriminative power (Area Under the Receiver Operating Characteristic Curve (ROC–AUC) 0.87–0.95), followed by energy alone (ROC–AUC 0.85–0.95), while inclusion of spatial coordinates with energy and \(\Delta \phi\) ranked third, achieving consistent performance across folds (ROC–AUC 0.81–0.91). These results demonstrate that incorporating entanglement-sensitive angular features into learning pipelines can suppress prompt contamination while preserving true LORs in a gamma-positron imaging system.
