arXiv subjects

David Schote

Publications and source records attributed to David Schote.

7 recordsLinked to original sources

arXiv2026

Shimmer: End-to-End Open-Source Passive B0 Shimming Methodology for Low-Field MRI Magnets

Low-field MRI scanners based on permanent magnet arrays require accurate B0 shimming to achieve sufficient field homogeneity for imaging. Here, we present Shimmer, an open-source methodology for passive shimming of low-field MRI magnets using additional NdFeB magnets placed outside the main magnet array. The end-to-end methodology combines magnetic field mapping, magnetic field simulations, numerical optimization of shim magnet positions and orientations, and automated generation of 3D-printable shim holders. Continuous magnet rotations and several optimization strategies are considered and evaluated. The method was validated and applied to three different permanent magnet arrays ~50 mT in 200 mm diameter spherical volumes, reducing initial field inhomogeneities of 9361ppm, 31721 ppm and 34143 ppm to 888 ppm, 1812 ppm and 1602 ppm respectively. The improved homogeneity enabled undistorted MR imaging of a phantom. Shimmer provides a reproducible and adaptable approach for improving the performance of low-field MRI magnets.

physics.med-ph↗

arXiv2026

A Reference System for Open Source Portable Low-Field MRI

Despite its renewed attention, the pathway to point-of-care portable low-field MRI systems remains challenging, limiting adoption across research groups. Incomplete documentation limits reproducibility, causing redesign and complicating cross-system comparison. Moreover, non-standardized testing and characterization complicates ethical approval for clinical studies. We present an open-source reference system for portable low-field MRI designed to support replication, reproducibility, benchmarking, and quantitative comparison. The system is fully open source, based on a ~50 mT permanent magnet, and integrated with a cloud-native acquisition platform. Pulseq-based calibration, characterization, and imaging sequences assessed noise level, eddy currents, image-based SNR, and geometric accuracy. Quantitative T1, T2, and B0 mapping sequences were developed and evaluated against reference values. Initial results from independent replications at two sites were compared. The system reached a noise level of 1.4 relative to the thermal noise floor and short eddy-current decay constants of 27-32 us across all gradient channels. Geometric deviations were below 2 mm over the field of view. Image-based SNR were consistent between the independent replications. Measured T1 values closely matched specified values, with an average absolute error of 3.1(1.8)%, while T2 values were overestimated by 10.4(5.8)%. Simulations showed only marginal errors for both quantities, suggesting experimental error sources for T2 mapping. The reference system combines openly documented hardware, software, calibration procedures, phantoms, quantitative MRI, and simulation tools in a reproducible ecosystem, aiming to support cross-site comparability, reproducible research, and collaborative development of future portable low-field MRI technologies.

physics.med-ph↗

arXiv2026

Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionaries

State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction method, which is based on embedding data-driven information into a model-based convolutional dictionary regularization via neural network-inferred spatially adaptive sparsity level maps. By means of improved network design and dedicated training strategies, we extend the method to achieve filter-permutation invariance as well as the possibility to change the convolutional dictionary at inference time. We apply our method to low-field MRI and compare it to several other recent deep learning-based methods, also on in vivo data, where the benefit of using a different dictionary is demonstrated. We further assess the method's robustness when tested on in- and out-of-distribution data. When tested on the latter, the proposed method suffers less from the data distribution shift compared to the other learned methods, which we attribute to its reduced reliance on training data due to its underlying model-based reconstruction component.

eess.IV↗

arXiv2025

MRpro: open framework for model-based, learned, and quantitative MR imaging

We preseent an open-source image reconstruction package built upon PyTorch, enabling modern deep-learning reconstructions. It uses open data formats for input and output (ISMRMRD, DICOM, NIfTI), allowing easy integration into existing pipelines and support for data from different devices. The framework comprises three main areas. First, it provides unified data structures for the consistent manipulation of MR datasets and their associated metadata (e.g., k-space trajectories). Second, it offers a library of composable operators, proximable functionals, and optimization algorithms, including a unified Fourier operator for all common trajectories and operators specifically developed for low-field applications, such as a B0-correction operator. These components are used to create ready-to-use implementations of key reconstruction algorithms. Third, for deep learning, MRpro includes essential building blocks such as data-consistency layers, differentiable optimization layers, state-of-the-art backbone networks, and access to public datasets to facilitate reproducibility. We demonstrate MRpro across automatic reconstruction, iterative SENSE, deep-learning-based reconstruction, and quantitative parameter estimation. Applications use public and simulated datasets and measured lowfield data acquired at 0.3 T, 0.6 T, and 47 mT.

eess.IV↗

arXiv2025

MR imaging in the low-field: Leveraging the power of machine learning

Recent innovations in Magnetic Resonance Imaging (MRI) hardware and software have reignited interest in low-field ($<1\,\mathrm{T}$) and ultra-low-field MRI ($<0.1\,\mathrm{T}$). These technologies offer advantages such as lower power consumption, reduced specific absorption rate, reduced field-inhomogeneities, and cost-effectiveness, presenting a promising alternative for resource-limited and point-of-care settings. However, low-field MRI faces inherent challenges like reduced signal-to-noise ratio and therefore, potentially lower spatial resolution or longer scan times. This chapter examines the challenges and opportunities of low-field and ultra-low-field MRI, with a focus on the role of machine learning (ML) in overcoming these limitations. We provide an overview of deep neural networks and their application in enhancing low-field and ultra-low-field MRI performance. Specific ML-based solutions, including advanced image reconstruction, denoising, and super-resolution algorithms, are discussed. The chapter concludes by exploring how integrating ML with low-field MRI could expand its clinical applications and improve accessibility, potentially revolutionizing its use in diverse healthcare settings.

eess.IV↗

arXiv2023

Unrolled three-operator splitting for parameter-map learning in Low Dose X-ray CT reconstruction

We propose a method for fast and automatic estimation of spatially dependent regularization maps for total variation-based (TV) tomography reconstruction. The estimation is based on two distinct sub-networks, with the first sub-network estimating the regularization parameter-map from the input data while the second one unrolling T iterations of the Primal-Dual Three-Operator Splitting (PD3O) algorithm. The latter approximately solves the corresponding TV-minimization problem incorporating the previously estimated regularization parameter-map. The overall network is then trained end-to-end in a supervised learning fashion using pairs of clean-corrupted data but crucially without the need of having access to labels for the optimal regularization parameter-maps.

math.OC↗

arXiv2023

Learning Regularization Parameter-Maps for Variational Image Reconstruction using Deep Neural Networks and Algorithm Unrolling

We introduce a method for fast estimation of data-adapted, spatio-temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV)-minimization. Our approach is inspired by recent developments in algorithm unrolling using deep neural networks (NNs), and relies on two distinct sub-networks. The first sub-network estimates the regularization parameter-map from the input data. The second sub-network unrolls $T$ iterations of an iterative algorithm which approximately solves the corresponding TV-minimization problem incorporating the previously estimated regularization parameter-map. The overall network is trained end-to-end in a supervised learning fashion using pairs of clean-corrupted data but crucially without the need of having access to labels for the optimal regularization parameter-maps. We prove consistency of the unrolled scheme by showing that the unrolled energy functional used for the supervised learning $Γ$-converges as $T$ tends to infinity, to the corresponding functional that incorporates the exact solution map of the TV-minimization problem. We apply and evaluate our method on a variety of large scale and dynamic imaging problems in which the automatic computation of such parameters has been so far challenging: 2D dynamic cardiac MRI reconstruction, quantitative brain MRI reconstruction, low-dose CT and dynamic image denoising. The proposed method consistently improves the TV-reconstructions using scalar parameters and the obtained parameter-maps adapt well to each imaging problem and data by leading to the preservation of detailed features. Although the choice of the regularization parameter-maps is data-driven and based on NNs, the proposed algorithm is entirely interpretable since it inherits the properties of the respective iterative reconstruction method from which the network is implicitly defined.

math.OC↗