Accelerated Bayesian MR Image Reconstruction
نویسندگان
چکیده
This paper concerns reconstruction of 2D and 3D MR images from raw, sparsely and nonuniformly sampled k-space signals. In particular, it pertains to iterative Bayesian image reconstruction and acceleration of the attendant convergence to the ‘Maximum A Posteriori’ (MAP) image. Significant acceleration is achieved by weighting of the Likelihood term with the inverse of the sampling density. In addition, weighting can reduce the sensitivity to measurement errors in samples that have been assigned a low weight. We present applications to 2D sparse spiral scanning and 3D random scanning. Keywords—2D/3D image reconstruction, sparse sampling, prior knowledge, Bayesian estimation, convergence speed, likelihood weighting
منابع مشابه
A Bayesian approach for image denoising in MRI
Magnetic Resonance Imaging (MRI) is a notable medical imaging technique that is based on Nuclear Magnetic Resonance (NMR). MRI is a safe imaging method with high contrast between soft tissues, which made it the most popular imaging technique in clinical applications. MR Imagechr('39')s visual quality plays a vital role in medical diagnostics that can be severely corrupted by existing noise duri...
متن کاملImproving the quality of ultrasound images using Bayesian estimators
Medical ultrasound imaging due to close behavior of cancer tumors to body tissues has a low contrast. This problem with synthetic aperture imaging method has been addressed. Although the synthetic aperture imaging technique solved the low-contrast problem of ultrasound images, to an acceptable limit, but the performance of these methods is not even acceptable when the signal to noise ratio (SNR...
متن کاملImproved k-t FOCUSS using a sparse Bayesian learning
Introduction: In dynamic MRI, spatio-temporal resolution is a very important issue. Recently, compressed sensing approach has become a highly attracted imaging technique since it enables accelerated acquisition without aliasing artifacts. Our group has proposed an l1-norm based compressed sensing dynamic MRI called k-t FOCUSS which outperforms the existing methods. However, it is known that the...
متن کاملBayesian PET image reconstruction
We developed a maximum a posterior (MAP) reconstruction method for positron emission tomography (PET) image reconstruction incorporating magnetic resonance (MR) image information, with the joint entropy between the PET and MR image features serving as the regularization constraint. A non-parametric method was used to estimate the joint probability density of the PET and MR images. Using realist...
متن کاملDeep Residual Learning for Accelerated MRI using Magnitude and Phase Networks
Objective: Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts from artifact corrupted images. Methods: The deep residual learnin...
متن کامل