PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction

TL;DR

PET-Adapter is a novel test-time domain adaptation framework that enhances PET image reconstruction quality across diverse clinical datasets without retraining, using physics-informed warm-starts and anatomical conditioning.

Contribution

It introduces a test-time adaptation method for PET reconstruction models pretrained on phantom data, improving generalization to clinical data without paired ground truth.

Findings

Outperforms existing methods in clinical datasets for full and limited-angle PET reconstruction.

Reduces diffusion steps from 50 to 2 without quality loss.

Demonstrates clinical feasibility and computational efficiency.

Abstract

Positron Emission Tomography (PET) image reconstruction is inherently challenged by Poisson noise and physical degradation factors, which are further exacerbated in limited-angle acquisitions. While deep learning methods demonstrate promising performance, their generalization to unseen clinical data distributions remains limited without extensive retraining. We propose PET-Adapter, a test-time domain adaptation framework for generative PET reconstruction models pretrained solely on phantom data. Our method enables adaptation to clinical datasets with varying anatomies, tracers, and scanner configurations without requiring paired ground truth. PET-Adapter introduces layer-wise low-rank anatomical conditioning during adaptation and Ordered Subset Expectation Maximization-based warm-starting that initializes the generation from physics-informed reconstructions, reducing diffusion steps from 50 to 2 without compromising quality. Experiments across multiple clinical datasets demonstrate superior 3D reconstruction performance in both full-angle and limited-angle settings, highlighting the clinical feasibility and computational efficiency of the proposed approach.