paper-with-me

홈 › Papers

M-Gaussian: An Magnetic Gaussian Framework for Efficient Multi-Stack MRI Reconstruction

2026-02-24 · Kangyuan Zheng, Xuan Cai, Jiangqi Wang, Guixing Fu, Zhuoshuo Li, Yazhou Chen, Xinting Ge, Liangqiong Qu, Mengting Liu arxiv

Magnetic Resonance Imaging (MRI) is a crucial non-invasive imaging modality. In routine clinical practice, multi-stack thick-slice acquisitions are widely used to reduce scan time and motion sensitivity, particularly in challenging scenarios such as fetal brain imaging. However, the resulting severe through-plane anisotropy compromises volumetric analysis and downstream quantitative assessment, necessitating robust reconstruction of isotropic high-resolution volumes. Implicit neural representation methods, while achieving high quality, suffer from computational inefficiency due to complex network structures. We present M-Gaussian, adapting 3D Gaussian Splatting to MRI reconstruction. Our contributions include: (1) Magnetic Gaussian primitives with physics-consistent volumetric rendering, (2) neural residual field for high-frequency detail refinement, and (3) multi-resolution progressive training. Our method achieves an optimal balance between quality and speed. On the FeTA dataset, M-Gaussian achieves 40.31 dB PSNR while being 14 times faster, representing the first successful adaptation of 3D Gaussian Splatting to multi-stack MRI reconstruction.

📄 PDF Abstract BibTeX arXiv:2603.00145

Code (0)

등록된 구현이 없습니다.

Tasks

MRI Reconstruction

Similar Papers 제목 키워드 기반

Speeding up Magnetic Resonance Image Acquisition by Bayesian Multi-Slice Adaptive Compressed Sensing

2009-12-01 · NeurIPS 2009 12 · Matthias Seeger

We show how to sequentially optimize magnetic resonance imaging measurement designs over stacks of neighbouring image slices, by performing convex variational inference on a large scale non-Gaussian linear dynamical syst…

compressed sensingVariational Inference

Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRI

2026-01-30 · Yinsong Wang, Thomas Fletcher, Xinzhe Luo, Aine Travers Dineen 외 arxiv

Reconstructing 3D fetal MR volumes from motion-corrupted stacks of 2D slices is a crucial and challenging task. Conventional slice-to-volume reconstruction (SVR) methods are time-consuming and require multiple orthogonal…

Environmental Modeling Framework using Stacked Gaussian Processes

2016-12-09 · Kareem Abdelfatah, Junshu Bao, Gabriel Terejanu

A network of independently trained Gaussian processes (StackedGP) is introduced to obtain predictions of quantities of interest with quantified uncertainties. The main applications of the StackedGP framework are to integ…

Gaussian Processes

Scalable Magnetic Field SLAM in 3D Using Gaussian Process Maps

2018-04-05 · Manon Kok, Arno Solin

We present a method for scalable and fully 3D magnetic field simultaneous localisation and mapping (SLAM) using local anomalies in the magnetic field as a source of position information. These anomalies are due to the pr…

Position

Sparse Variational Contaminated Noise Gaussian Process Regression with Applications in Geomagnetic Perturbations Forecasting

2024-02-27 · Daniel Iong, Matthew McAnear, Yuezhou Qu, Shasha Zou 외

Gaussian Processes (GP) have become popular machine-learning methods for kernel-based learning on datasets with complicated covariance structures. In this paper, we present a novel extension to the GP framework using a c…

Gaussian ProcessesPrediction Intervalsregression