Neural implicit k-space representations (NIK) have shown promising results for dynamic magnetic resonance imaging (MRI) at high temporal resolutions. Yet, reducing acquisition time, and thereby available training data, results in severe performance drops due to overfitting. To address this, we introduce a novel self-supervised k-space loss function L PISCO , applicable for regularization of NIK-based reconstructions. The proposed loss function is based on the concept of parallel imaging-inspired self-consistency (PISCO), enforcing a consistent global k-space neighborhood relationship without requiring additional data. Quantitative and qualitative evaluations on static and dynamic MR reconstructions show that integrating PISCO significantly improves NIK representations, making it a competitive dynamic reconstruction method without constraining the temporal resolution. Particularly at high acceleration factors (R ≥ 50), NIK with PISCO can avoid temporal oversmoothing of state-of-the-art methods and achieves superior spatio-temporal reconstruction quality. Furthermore, an extensive analysis of the loss assumptions and stability shows PISCO’s potential as versatile self-supervised k-space loss function for further applications and architectures. Code is available at: https://github.com/compai-lab/2025-pisco-spieker

Motion represents one of the major challenges in magnetic resonance imaging (MRI). Since the MR signal is acquired in frequency space, any motion of the imaged object leads to complex artefacts in the reconstructed image in addition to other MR imaging artefacts. Deep learning has been frequently proposed for motion correction at several stages of the reconstruction process. The wide range of MR acquisition sequences, anatomies and pathologies of interest, and motion patterns (rigid vs. deformable and random vs. regular) makes a comprehensive solution unlikely. To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials. This review identifies differences and synergies in underlying data usage, architectures, training and evaluation strategies. We critically discuss general trends and outline future directions, with the aim to enhance interaction between different application areas and research fields.

Water-fat separation is a non-linear non-convex parameter estimation problem in magnetic resonance imaging typically solved using spatial constraints. However, there is still limited knowledge on how to separate in vivo three chemical species in the presence of magnetic field inhomogeneities. The proposed method uses multiple graph-cuts in a hierarchical multi-resolution framework to perform robust chemical species separation in the breast for subjects with and without silicone implants. Experimental results show that the proposed method can decrease the computational time for water-fat separation and perform accurate water-fat-silicone separation with only a limited number of acquired echo images at 3 T. The silicone-separated images have an improved spatial resolution and image contrast compared to conventional scans used for regular monitoring of the silicone implant's integrity.

Motion during diffusion encodings leads to different phase errors in different shots of multishot diffusion-weighted acquisitions. Phase error incoherence among shots results in undesired signal cancellation when data from all shots are combined. Motion-induced phase error correction for multishot diffusion-weighted imaging (DWI) has been studied extensively and there exist multiple phase error correction algorithms. A commonly used correction method is the direct phase subtraction (DPS). DPS, however, can suffer from incomplete phase error correction due to the aliasing of the phase errors in the high spatial resolution phases. Furthermore, improper sampling density compensation is also a possible issue of DPS. Recently, motion-induced phase error correction was incorporated in the conjugate gradient (CG) image reconstruction procedure to get a nonlinear phase correction method that is also applicable to parallel DWI. Although the CG method overcomes the issues of DPS, its computational requirement is high. Further, CG restricts to sensitivity encoding (SENSE) for parallel reconstruction. In this paper, a new time-efficient and flexible k-space and image-space combination (KICT) algorithm for rigid body motion-induced phase error correction is introduced. KICT estimates the motion-induced phase errors in image space using the self-navigated capability of the variable density spiral trajectory. The correction is then performed in k -space. The algorithm is shown to overcome the problem of aliased phase errors. Further, the algorithm preserves the phase of the imaging object and receiver coils in the corrected k -space data, which is important for parallel imaging applications. After phase error correction, any parallel reconstruction method can be used. The KICT algorithm is tested with both simulated and in vivo data with both multishot single-coil and multishot multicoil acquisitions. We show that KICT correction results in diffusion-weighted images with higher signal-to-noise ratio (SNR) and fractional anisotropy (FA) maps with better resolved fiber tracts as compared to DPS. In peripheral-gated acquisitions, KICT is comparable to the CG method.