Memory-enhanced and multi-domain learning-based deep unrolling network for medical image reconstruction

Objective. Reconstructing high-quality images from corrupted measurements remains a fundamental challenge in medical imaging. Recently, deep unrolling (DUN) methods have emerged as a promising solution, combining the interpretability of traditional iterative algorithms with the powerful representation capabilities of deep learning. However, their performance is often limited by weak information flow between iterative stages and a constrained ability to capture global features across stages-limitations that tend to worsen as the number of iterations increases.Approach. In this work, we propose a memory-enhanced (ME) and multi-domain learning-based DUN network for interpretable, high-fidelity medical image reconstruction. First, a ME module is designed to adaptively integrate historical outputs across stages, reducing information loss. Second, we introduce a cross-stage spatial-domain learning transformer (CS-SLFormer) to extract both local and non-local features within and across stages, improving reconstruction performance. Finally, a frequency-domain consistency learning module ensures alignment between reconstructed and ground truth images in the frequency domain, recovering fine image details.Main results. Comprehensive experiments evaluated on three representative medical imaging modalities (positron emission tomography (PET), magnetic resonance imaging, and computed tomography) show that the proposed method consistently outperforms state-of-the-art approaches in both quantitative metrics and visual quality. Specifically, our method achieved a peak signal-to-noise of 37.835 dB and an structural similarity index of 0.970 in 1%dose PET reconstruction.Significance. This study expands the use of model-driven deep learning in medical imaging, demonstrating the potential of ME DUN frameworks for high-quality reconstructions.