Abstract
Gamma-positron imaging with tracers that emit a prompt γ (> 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 ([Formula: see text]), 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 × 21 feature matrix comprising spatial coordinates, energy deposits, and angular descriptors, including [Formula: see text] and polar scattering angle θ. Feature ablation with five-fold cross-validation revealed that the combination of energy and [Formula: see text] 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 [Formula: see text] 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.