estimate coil sensitivities

Long MRI acquisition times hinder clinical efficiency and exacerbate motion artifacts. Conventional parallel imaging techniques (e.g., SENSE) rely on pre-acquired coil sensitivity maps, entailing complex calibration procedures and susceptibility to spatial misalignment. This paper proposes an end-to-end deep learning framework that jointly estimates coil sensitivity maps and reconstructs images directly from 4× undersampled multi-channel k-space data—eliminating the need for separate calibration scans. To our knowledge, this is the first method enabling joint sensitivity and image learning from a single undersampled acquisition. The architecture features two co-optimized branches: a sensitivity estimation module and a U-Net-based reconstruction module. Evaluated on brain MRI data from 10 subjects, the method yields reconstructions with visual quality comparable to SENSE; although PSNR and SSIM are marginally lower, it achieves substantially improved robustness and clinical practicality.

To address the ill-posedness of magnetic particle imaging (MPI) image reconstruction, this paper proposes a training-free plug-and-play (PnP) framework. The method uniquely integrates a zero-shot deep image prior (ZS-DIP) denoiser with ℓ¹-sparse regularization within the PnP architecture, eliminating reliance on task-specific training data; a hybrid validation strategy is further introduced for robust hyperparameter selection. Experiments on the 3D Open MPI dataset demonstrate that the proposed approach outperforms benchmark methods—including PP-MPI—in both quantitative metrics (e.g., PSNR, SSIM) and visual fidelity, while exhibiting strong robustness to noise. Compared to existing supervised or data-intensive approaches requiring large-scale annotated datasets or dedicated network training, our method significantly reduces computational and data acquisition costs and enhances generalizability. This work establishes a novel unsupervised paradigm for MPI reconstruction.

To address the non-destructive testing (NDT) challenges posed by increased interconnect depth and structural complexity in advanced packaging, this paper proposes a spatial-physical hybrid current density reconstruction method. Unlike conventional magnetic field inversion relying solely on FFT, our approach unifies SQUID microscopy magnetometry, I/Q-channel signal modeling, and image geometric alignment within a single inversion framework—incorporating eddy-current suppression, rotation/tilt misalignment correction, and Biot–Savart law constraints. Experimental results demonstrate effective compensation of 0.30-radian real-world image distortion, a 0.3% improvement in I-channel image sharpness, significant noise reduction in the Q-channel, and substantial gains in current reconstruction accuracy and imaging reliability. This work establishes a scalable, physics-informed paradigm for online NDT of 3D integrated packages.

In imaging inverse problems (e.g., MRI reconstruction, image denoising), full-reference image quality (FRIQ) metrics—such as PSNR, SSIM, and LPIPS—cannot be computed without ground-truth images, hindering trustworthy deployment in safety-critical domains like healthcare. This paper introduces the first distribution-free, error-controlled framework for quantifying FRIQ uncertainty by integrating conformal prediction with MCMC-based approximate posterior sampling. Our method requires no ground-truth supervision and yields rigorously calibrated confidence intervals for any deep-prior-based reconstruction model’s FRIQ scores, guaranteeing exact coverage probability at a user-specified significance level (e.g., 90%). We validate the approach on image denoising and accelerated MRI reconstruction tasks, demonstrating reliable uncertainty calibration across diverse noise levels and acceleration factors. The implementation is publicly available.

MRI denoising is hindered by the reliance of supervised learning on paired clean/noisy images, where acquiring ground-truth clean data is prohibitively expensive. To address this, we propose Coil2Coil (C2C), the first fully self-supervised MRI denoising method leveraging multi-channel phased-array coil data. C2C exploits the inherent spatial diversity and statistical independence of noise across coil channels: it constructs pseudo-label pairs via coil-group splitting and recombination—requiring no additional scans or ground-truth images. Integrated with sensitivity normalization and adaptation to the Noise2Noise framework, C2C employs a U-Net architecture for end-to-end training. Evaluated on both synthetic and real DICOM datasets, C2C matches supervised methods in performance while substantially outperforming existing self-supervised approaches. Crucially, its residuals exhibit no structured correlations, confirming effective noise separation. The method is plug-and-play compatible, demonstrating strong potential for clinical deployment.

This work addresses the high computational cost of geometric mapping under spatially varying fields at high resolutions by proposing a resolution-agnostic neural surrogate model. The method operates without reliance on fixed grids or ground-truth solution labels, leveraging coordinate-augmented multi-resolution field encoding to predict mapping positions at arbitrary point sets. A geometry-aware unsupervised loss is formulated by integrating variational energy, diffusion equilibration, and quasiconformal theory. Experimental results demonstrate that the approach achieves efficient, accurate, and resolution-flexible geometric parameterization in both quasiconformal mapping and density equilibration tasks, significantly enhancing computational efficiency and generalization capability.

This work addresses the low spatial resolution of magnetic particle imaging (MPI) reconstructions, a limitation inadequately tackled by existing super-resolution methods that either rely on training data or employ simplistic interpolation, often compromising detail recovery and generalization. The authors propose a zero-shot super-resolution MPI reconstruction method that integrates super-resolution directly into an energy minimization framework, leveraging a pre-trained Gaussian denoiser via a plug-and-play strategy—eliminating the need for additional training data. This approach represents the first zero-shot, training-free super-resolution technique for MPI, effectively enhancing spatial resolution while avoiding hallucinatory artifacts. The framework is inherently generalizable, accommodating diverse regularizers and imaging tasks. Experimental results demonstrate consistent and significant improvements in reconstruction quality on both synthetic and real MPI data, underscoring its practicality and robustness.

This work addresses the limitation of conventional MRI super-resolution methods, which overlook the intrinsic physical coupling between resolution and signal-to-noise ratio by treating the task as a deterministic mapping. The authors propose a physics-aware dynamic-resolution reconstruction framework that leverages coordinate-driven, resolution-agnostic 2D Gaussian splatting rendering to generate high-quality images. Key innovations include a Gaussian representation integrating anatomical and imaging-system priors, physics-based modeling of tissue parameters, prior-guided initialization of Gaussian kernels with a covariance dictionary, and a meta-learning pretraining strategy to mitigate the scarcity of paired training data. The method achieves state-of-the-art performance on both dynamic-resolution datasets and standard benchmarks, demonstrating substantial potential for clinical translation.

Traditional plug-and-play (PnP) methods approximate the maximum a posteriori (MAP) solution using MMSE denoisers, often leading to reconstruction distortions; conversely, direct MAP optimization frequently converges to cartoonish results due to score estimation errors. To address these limitations, this work proposes ProxiMAP, a novel iterative MAP approximation framework that dynamically adjusts the noise schedule to align the residual noise at each iteration with the denoiser’s training distribution. This alignment ensures the denoiser operates within its reliable regime and implicitly enforces early stopping. Based on this principle, we design a plug-and-play ProxiMAP module and a computationally efficient hybrid variant. Experiments demonstrate that our approach significantly enhances reconstruction sharpness and quality across diverse inverse problems—including deblurring, inpainting, super-resolution, and phase retrieval—with the hybrid version achieving comparable or superior performance to full substitution schemes at substantially lower computational cost.

This work addresses the limitations of existing diffusion-based MRI reconstruction methods, which rely on large networks, opaque time-conditioning mechanisms, and offline-estimated coil sensitivity maps, leading to poor interpretability and limited adaptability across acquisition protocols. To overcome these issues, the authors propose a novel paradigm that jointly reconstructs both the image and coil sensitivities within an end-to-end framework. Central to this approach is a parameter-efficient Gaussian mixture product diffusion model serving as an interpretable image prior, complemented by a smoothness prior on coil sensitivities. The resulting method enables k-space trajectory-adaptive reconstruction, achieving rapid convergence and strong robustness under shifts in contrast and anatomical distribution as well as varying sampling trajectories, thereby significantly enhancing denoising and reconstruction performance.