MoSAIK (Motion Search with AI in K-space) is a new method that retrospectively estimates in-plane rigid-body motion directly from standard multi-coil TSE k-space data without requiring motion-free references, external navigators, or additional acquisitions. It uses a decoupled convolutional embedding and Transformer encoder to predict rotation and translation parameters, which are then incorporated into a motion-aware reconstruction. In both simulated and in-vivo tests, MoSAIK achieved low estimation errors and improved image quality, reducing visible artefacts while preserving anatomical detail.
arXiv:2604. 06482v2 Announce Type: replace-cross Abstract: Time-resolved volumetric MR imaging that reconstructs a 3D MRI within sub-seconds to resolve deformable motion is essential for motion-adaptive radiotherapy.
MIGA is a scan‑specific framework for accelerated 3D multi‑echo MRI that uses shared anisotropic Gaussian geometry, a coordinate‑conditioned multi‑output amplitude network, and explicit echo‑specific phase variables. The method jointly optimizes all components from undersampled multi‑coil k‑space data without requiring fully sampled training data. Experiments demonstrate that MIGA outperforms existing methods across various imaging tasks and acceleration factors, especially under stronger undersampling, and offers a favorable quality‑cost balance among full‑volume multi‑echo reconstruction techniques.
Three-dimensional multi-echo MRI provides rich anatomical and quantitative information, but repeated volumetric encoding prolongs acquisition and motivates k-space undersampling. Reconstructing unders...
arXiv:2610.19120v1 Announce Type: cross Abstract: Purpose: Free-breathing abdominal MRI is limited by respiratory motion, which introduces image artifacts and k-space inconsistencies. Existing recons...
arXiv:2610.24858v2 Announce Type: replace Abstract: Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorte...
The paper introduces a subject‑specific spatial‑angular Gaussian field for self‑supervised joint k‑q diffusion MRI reconstruction. It uses shared 3D Gaussian primitives that provide local spatial support while each primitive carries a continuous q‑conditioned tensor‑residual response, allowing the signal at each location to be synthesized from overlapping primitive responses. Experiments on three HCP diffusion shells with various acceleration settings show consistent improvements in missing‑direction DWI reconstruction, tensor‑derived metrics, and principal diffusion orientation estimation.
The paper introduces AGW-PBR, a brain MRI super‑resolution method that emphasizes tissue‑transition regions affected by the partial‑volume effect. It uses a low‑resolution backbone guided by Sobel edges, soft latent‑basis assignment, and grid‑anchored warping, while training‑time weights are derived from tissue‑mixture entropy computed from registered T1/T2/PD images. Experiments on IXI T2‑weighted scans at 2×, 4×, and 6× show improved full‑image reconstruction and regional fidelity, and the backbone also performs well on fastMRI data without PVE supervision.
arXiv:2607. 20136v1 Announce Type: cross Abstract: Slice-to-volume reconstruction (SVR) is the standard method for obtaining high-resolution (HR) 3D fetal brain volumes from motion-corrupted 2D MRI slice stacks acquired in multiple orientations.
The paper introduces FLEX‑MRI, a method that accelerates MRI reconstruction by partitioning the recovery process into a few finite intervals defined by progressive k‑space support changes. Instead of learning fine‑grained local dynamics, FLEX‑MRI directly learns the reconstruction change across each interval and employs stochastic exploration during inference to sample alternative transition paths. Experiments on multi‑coil MRI datasets demonstrate that FLEX‑MRI outperforms competing methods while keeping computational efficiency comparable to few‑step baselines.
Hankel Subspace Self‑Supervised Reconstruction (HSSRecon) is a scan‑specific framework for parallel MRI that partitions data by acquisition units before Hankel lifting and normalizes repeated Hankel copies. Instead of predicting missing k‑space directly, the network learns a compact complex‑valued Hankel subspace operator, and reconstruction is performed with a conjugate‑gradient solver enforcing hard data consistency. The method provides theoretical guarantees on uniqueness and error bounds, and demonstrates competitive performance on fastMRI brain data across multiple contrasts and sampling masks.
Hankel Subspace Self-Supervised Reconstruction (HSSRecon) is a scan‑specific framework for parallel MRI that partitions data by acquisition units before Hankel lifting and normalizes repeated Hankel copies. Instead of directly predicting missing k‑space data, the network learns a compact complex‑valued Hankel subspace operator, and reconstruction is performed with a conjugate‑gradient solver enforcing hard data consistency. The method is theoretically justified with proofs of positive definiteness, uniqueness, and error bounds, and demonstrates competitive performance on fastMRI brain data across multiple contrasts and sampling masks.
arXiv:2608. 16569v1 Announce Type: new Abstract: Accurate reconstruction of long-duration neural recordings is challenging because local field potentials (LFPs) are high-resolution, multichannel, transient, and variable across subjects.