SNRAware: Improved Deep Learning MRI Denoising with SNR Unit Training and G-factor Map Augmentation
Microsoft Research（微软研究院）；National Institutes of Health（美国国立卫生研究院）；University College London（伦敦大学学院）；Barts Health NHS Trust（巴特保健国民保健信托基金）
Hui Xue, Sarah M. Hooper, Iain Pierce, Rhodri H. Davies, John Stairs, Joseph Naegele, Adrienne E. Campbell-Washburn, Charlotte Manisty, James C. Moon, Thomas A.… 展开作者
Hui Xue, Sarah M. Hooper, Iain Pierce, Rhodri H. Davies, John Stairs, Joseph Naegele, Adrienne E. Campbell-Washburn, Charlotte Manisty, James C. Moon, Thomas A. Treibel, Peter Kellman, Michael S. Hansen
To develop and evaluate a new deep learning MR denoising method that leverages quantitative noise distribution information from the reconstruction process to improve denoising performance and generalization.
This retrospective study trained 14 different transformer and convolutional models with two backbone architectures on a large dataset of 2,885,236 images from 96,605 cardiac retro-gated cine complex series acquired at 3T. The proposed training scheme, termed SNRAware, leverages knowledge of the MRI reconstruction process to improve denoising performance by simulating large, high quality, and diverse synthetic datasets, and providing quantitative information about the noise distribution to the model. In-distribution testing was performed on a hold-out dataset of 3000 samples with performance measured using PSNR and SSIM, with ablation comparison without the noise augmentation. Out-of-distribution tests were conducted on cardiac real-time cine, first-pass cardiac perfusion, and neuro and spine MRI, all acquired at 1.5T, to test model generalization across imaging sequences, dynamically changing contrast, different anatomies, and field strengths. The best model found in the in-distribution test generalized well to out-of-distribution samples, delivering 6.5x and 2.9x CNR improvement for real-time cine and perfusion imaging, respectively. Further, a model trained with 100% cardiac cine data generalized well to a T1 MPRAGE neuro 3D scan and T2 TSE spine MRI.
Hybrid Learning: A Novel Combination of Self-Supervised and Supervised Learning for Joint MRI Reconstruction and Denoising in Low-Field MRI
New York University Grossman School of Medicine（纽约大学格罗斯曼医学院）；NYU Tandon School of Engineering（纽约大学坦登工程学院）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）
NexOP: Joint Optimization of NEX-Aware k-space Sampling and Image Reconstruction for Low-Field MRI
Department of Electrical and Computer Engineering, Technion – Israel Institute of Technology（电气与计算机工程系，技术学院–以色列理工学院）；May-Blum-Dahl Technion Human MRI Research Center, Technion - Israel Institute of Technology（May-Blum-Dahl技术学院人类MRI研究中心，技术学院–以色列理工学院）；Department of Biomedical Engineering, Technion – Israel Institute of Technology（生物医学工程系，技术学院–以色列理工学院）
The acquisition of MRI images offers a trade-off in terms of acquisition time, spatial/temporal resolution and signal-to-noise ratio (SNR). Thus, for instance, increasing the time efficiency of MRI often comes at the expense of reduced SNR. This, in turn, necessitates the use of post-processing tools for noise rejection, which makes image de-noising an indispensable component of computer assistance diagnosis. In the field of MRI, a multitude of image de-noising methods have been proposed hitherto. In this paper, the application of a particular class of de-noising algorithms - known as non-loca…
Deep learning (DL) has shown promise for faster, high quality accelerated MRI reconstruction. However, supervised DL methods depend on extensive amounts of fully-sampled (labeled) data and are sensitive to out-of-distribution (OOD) shifts, particularly low signal-to-noise ratio (SNR) acquisitions. To alleviate this challenge, we propose Noise2Recon, a model-agnostic, consistency training method for joint MRI reconstruction and denoising that can use both fully-sampled (labeled) and undersampled (unlabeled) scans in semi-supervised and self-supervised settings. With limited or no labeled traini…
In Fourier-based medical imaging, sampling below the Nyquist rate results in an underdetermined system, in which linear reconstructions will exhibit artifacts. Another consequence of under-sampling is lower signal to noise ratio (SNR) due to fewer acquired measurements. Even if an oracle provided the information to perfectly disambiguate the underdetermined system, the reconstructed image could still have lower image quality than a corresponding fully sampled acquisition because of the reduced measurement time. The effects of lower SNR and the underdetermined system are coupled during reconstr…
Self-supervised learning has shown great promise due to its capability to train deep learning MRI reconstruction methods without fully-sampled data. Current self-supervised learning methods for physics-guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network and the other to define the training loss. In this study, we propose an improved self-supervised learning strategy that more efficiently uses the acquired data to train a physics-guided reconstruction network without a database of fully-sampl…
We formulate a physics-informed compressed sensing (PICS) method for the reconstruction of velocity fields from noisy and sparse phase-contrast magnetic resonance signals. The method solves an inverse Navier-Stokes boundary value problem, which permits us to jointly reconstruct and segment the velocity field, and at the same time infer hidden quantities such as the hydrodynamic pressure and the wall shear stress. Using a Bayesian framework, we regularize the problem by introducing a priori information about the unknown parameters in the form of Gaussian random fields. This prior information is…
Sun Yat-sen University（中山大学）；The Chinese University of Hong Kong（香港中文大学）；Royal Brompton Hospital（皇家布朗普顿医院）；Imperial College London（伦敦帝国理工学院）
The long acquisition time has limited the accessibility of magnetic resonance imaging (MRI) because it leads to patient discomfort and motion artifacts. Although several MRI techniques have been proposed to reduce the acquisition time, compressed sensing in magnetic resonance imaging (CS-MRI) enables fast acquisition without compromising SNR and resolution. However, existing CS-MRI methods suffer from the challenge of aliasing artifacts. This challenge results in the noise-like textures and missing the fine details, thus leading to unsatisfactory reconstruction performance. To tackle this chal…
Robust multi-coil MRI reconstruction via self-supervised denoising
Stanford University（斯坦福大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Intel Corporation（英特尔公司）；MD Anderson Cancer Center（MD安德森癌症中心）；Dell Medical School Department of Diagnostic Medicine（德克萨斯大学戴维斯医学中心诊断医学系）；Oden Institute for Computational Engineering and Sciences（奥登计算工程与科学研究院）
Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRI
Massachusetts General Hospital, Harvard Medical School（马萨诸塞总医院，哈佛医学院）；University of Twente（特文特大学）；University of Copenhagen（哥本哈根大学）；University College London（伦敦大学学院）；Massachusetts Institute of Technology（麻省理工学院）；Danish Research Centre for Magnetic Resonance（丹麦磁共振研究中心）；Yale School of Medicine（耶鲁大学医学院）
Quality control (QC) of MR images is essential to ensure that downstream analyses such as segmentation can be performed successfully. Currently, QC is predominantly performed visually and subjectively, at significant time and operator cost. We aim to automate the process using a probabilistic network that estimates segmentation uncertainty through a heteroscedastic noise model, providing a measure of task-specific quality. By augmenting training images with k-space artefacts, we propose a novel CNN architecture to decouple sources of uncertainty related to the task and different k-space artefa…
Simultaneous Image Quality Improvement and Artefacts Correction in Accelerated MRI
Translational Radiomics, Luxembourg Institute of Health, Luxembourg（转化放射组学，卢森堡健康研究所，卢森堡）；In-Vivo Imaging Platform, Luxembourg Institute of Health, Luxembourg（活体成像平台，卢森堡健康研究所，卢森堡）；Faculty of Electrical Engineering and Communication, Brno University of Technology, Czech Republic（电气工程与通信学院，布拉格技术大学，捷克共和国）；Institute of Scientific Instruments of the Czech Academy of Sciences, Czech Republic（捷克科学院科学仪器研究所，捷克共和国）
Department of Computing, Imperial College London（帝国理工学院计算机系）；National Heart & Lung Institute, Imperial College London（帝国理工学院国家心肺研究所）；Cardiovascular Research Centre, Royal Brompton Hospital（皇家布朗普顿医院心血管研究中心）
Understanding the structure of the heart at the microscopic scale of cardiomyocytes and their aggregates provides new insights into the mechanisms of heart disease and enables the investigation of effective therapeutics. Diffusion Tensor Cardiac Magnetic Resonance (DT-CMR) is a unique non-invasive technique that can resolve the microscopic structure, organisation, and integrity of the myocardium without the need for exogenous contrast agents. However, this technique suffers from relatively low signal-to-noise ratio (SNR) and frequent signal loss due to respiratory and cardiac motion. Current D…
Ultra-Strong Gradient Diffusion MRI with Self-Supervised Learning for Prostate Cancer Characterization
University College London（伦敦大学学院）；Cardiff University（卡迪夫大学）；Siemens Healthcare Ltd（西门子医疗有限公司）；Siemens Healthcare GmbH（西门子医疗股份公司）；University Medical Center Utrecht（乌得勒支大学医学中心）
Arterial spin labeling (ASL) allows to quantify the cerebral blood flow (CBF) by magnetic labeling of the arterial blood water. ASL is increasingly used in clinical studies due to its noninvasiveness, repeatability and benefits in quantification. However, ASL suffers from an inherently low-signal-to-noise ratio (SNR) requiring repeated measurements of control/spin-labeled (C/L) pairs to achieve a reasonable image quality, which in return increases motion sensitivity. This leads to clinically prolonged scanning times increasing the risk of motion artifacts. Thus, there is an immense need of adv…
We investigated whether a combination of k-space undersampling and variable density averaging enhances image quality for low-SNR MRI acquisitions. We implemented 3D Cartesian k-space prospective undersampling with a variable number of averages for each k-line. The performance of this compressed sensing with variable-density averaging (CS-VDA) method was evaluated in retrospective analysis of fully sampled phantom MRI measurements, as well as for prospectively accelerated in vivo 3D brain and knee MRI scans. Both phantom and in vivo results showed that acquisitions using the CS-VDA approach res…
Distortion-Corrected Diffusion MRI Using Rotated-View EPI and Joint Field-Map/Image Estimation with Gaussian Primitives
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, and the School of Computation, Information and Technology, TUM（慕尼黑工业大学(TUM)医疗与医学人工智能教席、TUM大学医院、计算信息与技术学院）；Neuroimaging Technology Research Center, Department of Radiology and Biomedical Imaging, University of California, San Francisco（加州大学旧金山分校放射与生物医学影像系神经影像技术研究中心）；Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences（中国科学院精密测量科学与技术创新研究院）；Department of Radiology, Stanford University（斯坦福大学放射学系）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心(MCML)）；Department of Computing, Imperial College London（伦敦帝国理工学院计算系）
Fast-RF-Shimming: Accelerate RF Shimming in 7T MRI using Deep Learning
Department of Electrical and Computer Engineering, Vanderbilt University（电气与计算机工程系，范德比尔特大学）；Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center（范德比尔特大学医学中心影像科学研究院）；Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center（放射学与放射科学系，范德比尔特大学医学中心）；Computational Science and Engineering Division, Oak Ridge National Laboratory（计算科学与工程 division，橡树岭国家实验室）；Department of Computer Science, Vanderbilt University（计算机科学系，范德比尔特大学）
Low-Cost and Detunable Wireless Resonator Glasses for Enhanced Eye MRI with Concurrent High-Quality Whole Brain MRI
Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center（范德堡大学成像科学研究所，范德堡大学医学中心）；Department of Electrical and Computer Engineering, Vanderbilt University（范德堡大学电气与计算机工程系）；Philips（飞利浦）；Department of Biomedical Engineering, Vanderbilt University（范德堡大学生物医学工程系）；Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center（范德堡大学医学中心放射学与放射科学系）
A Trust-Guided Approach to MR Image Reconstruction with Side Information
NYU Center for Data Science（纽约大学数据科学中心）；Bernard and Irene Schwartz Center for Biomedical Imaging（伯纳德和艾琳·施瓦茨生物医学成像中心）；NYU Grossman School of Medicine（纽约大学格罗斯曼医学院）；Courant Institute of Mathematical Sciences（库朗数学科学研究所）
Purpose: To introduce, develop, and evaluate a novel denoising technique for diffusion MRI that leverages non-linear redundancy in the data to boost the SNR while preserving signal information. Methods: We exploit non-linear redundancy of the dMRI data by means of Kernel Principal Component Analysis (KPCA), a non-linear generalization of PCAto reproducing kernel Hilbert spaces. By mapping the signal to a high-dimensional space, better redundancy is achieved despite nonlinearities in the data thereby enabling better denoising than linear PCA. We implement KPCA with a Gaussian kernel, with param…
Magnetic fields associated with currents flowing in tissue can be measured non-invasively by means of zero-field-encoded ultra-low-field magnetic resonance imaging (ULF MRI) enabling current density imaging (CDI) and possibly conductivity mapping of human head tissues. Since currents applied to a human are limited by safety regulations and only a small fraction of the current passes through the relatively high-resistive skull, a sufficient signal-to-noise ratio (SNR) may be difficult to obtain when using this method. In this work, we study the relationship between the image SNR and the SNR of …
Purpose of this study was to evaluate the effect of a robust magnetic resonance reconstruction pipeline equipped with a deep convolutional neural network on the overall image quality, in terms of Gibbs artifact reduction, and SNR improvement. Sixteen (16) healthy volunteers enrolled in this study and were imaged at 3T. Representative images of each image series that were reconstructed through the pipeline that leverages a deep learning (DL) algorithm were retrospectively benchmarked against corresponding images reconstructed through a conventional pipeline. DL-reconstructed images showed signi…
Background: Prostate cancer is one of the most common forms of cancer found in males making early diagnosis important. Magnetic resonance imaging (MRI) has been useful in visualizing and localizing tumor candidates and with the use of endorectal coils (ERC), the signal-to-noise ratio (SNR) can be improved. The coils introduce intensity inhomogeneities and the surface coil intensity correction built into MRI scanners is used to reduce these inhomogeneities. However, the correction typically performed at the MRI scanner level leads to noise amplification and noise level variations. Methods: In t…
Purpose: We address the challenge of inaccurate parameter estimation in diffusion MRI when the signal-to-noise ratio (SNR) is very low, as in the spinal cord. The accuracy of conventional maximum-likelihood estimation (MLE) depends highly on initialisation. Unfavourable choices could result in suboptimal parameter estimates. Current methods to address this issue, such as grid search (GS) can increase computation time substantially. Methods: We propose a machine learning (ML) informed MLE approach that combines conventional MLE with ML approaches synergistically. ML-based methods have been deve…
Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital（马萨诸塞州总医院阿蒂努拉·A·马蒂诺斯生物医学成像中心）；Department of Radiology, Harvard Medical School（哈佛医学院放射学系）；Department of Biomedical Engineering, Tsinghua University（清华大学生物医学工程系）；Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology（麻省理工学院哈佛-麻省理工健康科学与技术部）
The noise in diffusion-weighted images (DWIs) decreases the accuracy and precision of diffusion tensor magnetic resonance imaging (DTI) derived microstructural parameters and leads to prolonged acquisition time for achieving improved signal-to-noise ratio (SNR). Deep learning-based image denoising using convolutional neural networks (CNNs) has superior performance but often requires additional high-SNR data for supervising the training of CNNs, which reduces the practical feasibility. We develop a self-supervised deep learning-based method entitled "SDnDTI" for denoising DTI data, which does n…
A wearable, stretchable radio-frequency coil for extremity imaging in low-field MRI systems
The Institute for Instrumentation in Molecular Imaging (I3M), CSIC–Universitat Politècnica de València（分子成像仪器研究所（I3M），西班牙瓦伦西亚理工大学）；C.J. Gorter MRI Center, Department of Radiology, Leiden University Medical Center（莱顿大学医学中心放射科 C.J. Gorter 磁共振中心）；PhysioMRI Tech
PURPOSE: Multi-exponential relaxometry is a powerful tool for characterizing tissue, but generally requires high image signal-to-noise ratio (SNR). This work evaluates the use of principal-component-analysis (PCA) denoising to mitigate these SNR demands and improve the precision of relaxometry measures. METHODS: PCA denoising was evaluated using both simulated and experimental MRI data. Bi-exponential transverse relaxation signals were simulated for a wide range of acquisition and sample parameters, and experimental data were acquired from three excised and fixed mouse brains. In both cases, s…
Object This study proposes a scale space based algorithm for automated segmentation of single-shot tagged images of modest SNR. Furthermore the algorithm was designed for analysis of discontinuous or shearing types of motion, i.e. segmentation of broken tag patterns. Materials and methods The proposed algorithm utilizes non-linear scale space for automatic segmentation of single-shot tagged images. The algorithm's ability to automatically segment tagged shearing motion was evaluated in a numerical simulation and in vivo. A typical shearing deformation was simulated in a Shepp-Logan phantom all…
Prepolarized Magnetic Resonance Imaging (PMRI) is a long-established technique conceived to counteract the loss in signal-to-noise ratio (SNR) inherent to low-field MRI systems. When it comes to hard biological tissues and solid-state matter, PMRI is severely restricted by their ultra-short characteristic relaxation times. Here we demonstrate that efficient hard tissue prepolarization is within reach with a special-purpose 0.26 T scanner designed for dental MRI and equipped with suitable high-power electronics. We have characterized the performance of a 0.5 T prepolarizer module which can be s…
Purpose: Double diffusion encoding (DDE) MRI enables the estimation of microscopic diffusion anisotropy, yielding valuable information on tissue microstructure. A recent study proposed that the acquisition of rotationally invariant DDE metrics, typically obtained using a spherical "5-design", could be greatly simplified by assuming Gaussian diffusion, facilitating reduced acquisition times that are more compatible with clinical settings. Here, we aim to validate the new minimal acquisition scheme against the standard DDE 5-design, and to quantify the proposed method's noise robustness to facil…
Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin（电气与计算机工程系Chandra家族部门德克萨斯大学奥斯汀分校）；Department of Imaging Physics MD Anderson Cancer Center（成像物理系MD安德森癌症中心）；Department of Diagnostic Medicine The University of Texas at Austin Dell Medical School（诊断医学系德克萨斯大学奥斯汀分校Dell医学院）；Oden Institute for Computational Engineering and Sciences The University of Texas at Austin（计算工程与科学学院Oden研究所德克萨斯大学奥斯汀分校）
Optically-powered Low Power Low Noise Amplifiers for MRI
Division of Medical Physics, Department of Diagnostic and Interventional Radiology, Medical Center – University of Freiburg, Faculty of Medicine – University of Freiburg（弗赖堡大学医学院医学中心诊断与介入放射学系医学物理分部）；Microsystems for Biomedical Imaging Group, Department of Microsystems Engineering, University of Freiburg（弗赖堡大学微系统工程学院生物医学成像微系统小组）
