KerNL: Kernel-Based Nonlinear Approach to Parallel MRI Reconstruction

The conventional calibration-based parallel imaging method assumes a linear relationship between the acquired multi-channel k-space data and the unacquired missing data, where the linear coefficients are estimated using some auto-calibration data. In this paper, we first analyze the model errors in the conventional calibration-based methods and demonstrate the nonlinear relationship. Then, a much more general nonlinear framework is proposed for auto-calibrated parallel imaging. In this framework, kernel tricks are employed to represent the general nonlinear relationship between acquired and unacquired k-space data without increasing the computational complexity. Identification of the nonlinear relationship is still performed by solving linear equations. Experimental results demonstrate that the proposed method can achieve reconstruction quality superior to GRAPPA and NL-GRAPPA at high net reduction factors.

• Publication year

  2019

• Venue

  IEEE Transactions on Medical Imaging

• Publication date

  2019-01-01

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1109/TMI.2018.2864197PMID 30106676PMCID PMC6422679
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Fast GRAPPA reconstruction with random projection

  2015cited by this paper
• Sparsity-Promoting Calibration for GRAPPA Accelerated Parallel MRI Reconstruction

  2013cited by this paper
• Calibrationless parallel imaging reconstruction based on structured low‐rank matrix completion

  2013cited by this paper
• Efficient GRAPPA reconstruction using random projection

  2013cited by this paper
• Nonlinear GRAPPA: A kernel approach to parallel MRI reconstruction

  2012influential reference
• Denoising sparse images from GRAPPA using the nullspace method

  2011cited by this paper
• Calibrationless parallel MRI using CLEAR

  2011cited by this paper
• Combination of compressed sensing and parallel imaging for highly accelerated first‐pass cardiac perfusion MRI

  2010cited by this paper
• Parallel MRI Using Phased Array Coils

  2010cited by this paper
• SPIRiT: Iterative self‐consistent parallel imaging reconstruction from arbitrary k‐space

  2010cited by this paper
• Accelerating SENSE using compressed sensing

  2009cited by this paper
• A nonlinear regularization strategy for GRAPPA calibration.

  2009cited by this paper
• Robust GRAPPA reconstruction and its evaluation with the perceptual difference model

  2008cited by this paper
• Sparsesense: Application of compressed sensing in parallel MRI

  2008cited by this paper
• Comparison of reconstruction accuracy and efficiency among autocalibrating data‐driven parallel imaging methods

  2008cited by this paper
• Joint image reconstruction and sensitivity estimation in SENSE (JSENSE)

  2007cited by this paper
• Parallel imaging reconstruction for arbitrary trajectories using k‐space sparse matrices (kSPA)

  2007cited by this paper
• Robust GRAPPA reconstruction

  2006cited by this paper
• 3Parallel magnetic resonance imaging with adaptive radius in k‐space (PARS): Constrained image reconstruction using k‐space locality in radiofrequency coil encoded data

  2005cited by this paper
• SMASH, SENSE, PILS, GRAPPA: How to Choose the Optimal Method

  2004cited by this paper
• Generalized autocalibrating partially parallel acquisitions (GRAPPA)

  2002cited by this paper
• Advances in sensitivity encoding with arbitrary k‐space trajectories

  2001cited by this paper
• VD‐AUTO‐SMASH imaging

  2001cited by this paper
• Sensitivity profiles from an array of coils for encoding and reconstruction in parallel (SPACE RIP)

  2000cited by this paper
• Partially parallel imaging with localized sensitivities (PILS)

  2000cited by this paper
• SENSE: Sensitivity encoding for fast MRI

  1999cited by this paper
• An algorithmic theory of learning: Robust concepts and random projection

  1999cited by this paper
• AUTO-SMASH: A self-calibrating technique for SMASH imaging

  1998cited by this paper
• Simultaneous acquisition of spatial harmonics (SMASH): Fast imaging with radiofrequency coil arrays

  1997cited by this paper

• fRAKI: k-space deep learning with offline data-universal and online scan-specific priors

  2025cites this paper
• Dual-domain faster Fourier convolution based network for MR image reconstruction

  2024cites this paper
• Image Reconstruction for Accelerated MR Scan With Faster Fourier Convolutional Neural Networks

  2024cites this paper
• Cascade dual-domain swin-conv-unet for MRI reconstruction

  2024cites this paper
• An Exploration of Parallel Imaging System for Very-Low-Field (50 mT) MRI Scanner

  2024cites this paper
• Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks

  2023cites this paper
• Recent advances in highly accelerated 3D MRI

  2023cites this paper
• Accelerating MR Parameter Mapping Using Nonlinear Compressive Manifold Learning and Regularized Pre-Imaging

  2022cites this paper
• Virtual Conjugate Coil for Improving KerNL Reconstruction

  2022cites this paper
• On the shape of convolution kernels in MRI reconstruction: Rectangles versus ellipsoids

  2022cites this paper
• Fusion of 3D lung CT and serum biomarkers for diagnosis of multiple pathological types on pulmonary nodules

  2021cites this paper
• A Wide Multimodal Dense U-Net for Fast Magnetic Resonance Imaging

  2021cites this paper
• Systematic Analysis and Review of Magnetic Resonance Imaging (MRI) Reconstruction Techniques.

  2021cites this paper
• Improved parallel magnetic resonance imaging reconstruction with multiple variable density sampling

  2021cites this paper
• An impulse noise removal model algorithm based on logarithmic image prior for medical image

  2021cites this paper
• Group feature selection for enhancing information gain in MRI reconstruction

  2021cites this paper
• Broad Learning Enhanced 1H-MRS for Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus

  2020cites this paper
• SURE‐based automatic parameter selection for ESPIRiT calibration

  2020cites this paper
• Improved parallel MR imaging with accurate coil sensitivity estimation using iterative adaptive support

  2019cites this paper
• Learning How to Interpolate Fourier Data With Unknown Autoregressive Structure: An Ensemble-Based Approach

  2019cites this paper
• Segmentation of Prostate Peripheral Zone based on Multi-scale Features Enhancement

  2019cites this paper
• LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space

  2019cites this paper
• SURE-based Automatic Parameter Selection For ESPIRiT Calibration

  2018cites this paper
• A Divide-and-Conquer Approach to Compressed Sensing MRI

  2018cites this paper