🤖 AI Summary
To address the degradation in reconstruction quality under high acceleration factors and the lack of case-adaptive sampling strategies in dynamic cardiac MRI, this paper proposes an end-to-end learnable framework that jointly optimizes time-varying sampling patterns and image reconstruction. We introduce the first case-level adaptive dynamic sampler (ADS) co-trained with the vSHARP reconstruction network, supporting both frame-specific and unified sampling schemes. Key innovations include differentiable sampling modeling, gradient-through optimization, and parameterization of 1D/2D k-space trajectories—overcoming limitations of conventional fixed or random sampling. Extensive experiments demonstrate significant improvements under high acceleration: higher SSIM and pSNR, and lower NMSE compared to standard vSHARP and dataset-level optimized sampling baselines. The proposed method achieves superior reconstruction fidelity while enabling patient-specific sampling adaptation.
📝 Abstract
$ extbf{Background:}$ Accelerating dynamic MRI is vital for advancing clinical applications and improving patient comfort. Commonly, deep learning (DL) methods for accelerated dynamic MRI reconstruction typically rely on uniformly applying non-adaptive predetermined or random subsampling patterns across all temporal frames of the dynamic acquisition. This approach fails to exploit temporal correlations or optimize subsampling on a case-by-case basis. $ extbf{Purpose:}$ To develop an end-to-end approach for adaptive dynamic MRI subsampling and reconstruction, capable of generating customized sampling patterns maximizing at the same time reconstruction quality. $ extbf{Methods:}$ We introduce the End-to-end Adaptive Dynamic Sampling and Reconstruction (E2E-ADS-Recon) for MRI framework, which integrates an adaptive dynamic sampler (ADS) that adapts the acquisition trajectory to each case for a given acceleration factor with a state-of-the-art dynamic reconstruction network, vSHARP, for reconstructing the adaptively sampled data into a dynamic image. The ADS can produce either frame-specific patterns or unified patterns applied to all temporal frames. E2E-ADS-Recon is evaluated under both frame-specific and unified 1D or 2D sampling settings, using dynamic cine cardiac MRI data and compared with vSHARP models employing standard subsampling trajectories, as well as pipelines where ADS was replaced by parameterized samplers optimized for dataset-specific schemes. $ extbf{Results:}$ E2E-ADS-Recon exhibited superior reconstruction quality, especially at high accelerations, in terms of standard quantitative metrics (SSIM, pSNR, NMSE). $ extbf{Conclusion:}$ The proposed framework improves reconstruction quality, highlighting the importance of case-specific subsampling optimization in dynamic MRI applications.