-
61.
公开(公告)号:US10685429B2
公开(公告)日:2020-06-16
申请号:US15893891
申请日:2018-02-12
发明人: Katrin Mentl , Boris Mailhe , Mariappan S. Nadar
摘要: The present embodiments relate to denoising medical images. By way of introduction, the present embodiments described below include apparatuses and methods for machine learning sparse image representations with deep unfolding and deploying the machine learnt network to denoise medical images. Iterative thresholding is performed using a deep neural network by training each layer of the network as an iteration of an iterative shrinkage algorithm. The deep neural network is randomly initialized and trained independently with a patch-based approach to learn sparse image representations for denoising image data. The different layers of the deep neural network are unfolded into a feed-forward network trained end-to-end.
-
公开(公告)号:US10573031B2
公开(公告)日:2020-02-25
申请号:US15832967
申请日:2017-12-06
发明人: Boris Mailhe , Benjamin L. Odry , Xiao Chen , Mariappan S. Nadar
摘要: Deep reinforcement machine learning is used to control denoising (e.g., image regularizer) in iterative reconstruction for MRI compressed sensing. Rather than requiring different machine-learnt networks for different scan settings (e.g., acceleration of the MR compressed sensing), reinforcement learning creates a policy of actions to provide denoising and data fitting through iterations of the reconstruction given a range of different scan settings. This allows a user to scan as appropriate for the patient, the MR system, the application, and/or preferences while still providing an optimized reconstruction under sampling resulting from the MR compressed sensing.
-
63.
公开(公告)号:US20200051239A1
公开(公告)日:2020-02-13
申请号:US16214339
申请日:2018-12-10
发明人: Sandro Braun , Boris Mailhe , Xiao Chen , Benjamin L. Odry , Mariappan S. Nadar
摘要: For classifying magnetic resonance image quality or training to classify magnetic resonance image quality, deep learning is used to learn features distinguishing between corrupt images base on simulation and measured similarity. The deep learning uses synthetic data without quality annotation, allowing a large set of training data. The deep-learned features are then used as input features for training a classifier using training data annotated with ground truth quality. A smaller training data set may be needed to train the classifier due to the use of features learned without the quality annotation.
-
64.
公开(公告)号:US20200041597A1
公开(公告)日:2020-02-06
申请号:US16238554
申请日:2019-01-03
发明人: Guillaume Daval Frerot , Xiao Chen , Mariappan S. Nadar , Peter Speier , Mathias Nittka , Boris Mailhe , Simon Arberet
摘要: Machine training a network for and use of the machine-trained network are provided for tissue parameter estimation for a magnetic scanner using magnetic resonance fingerprinting. The machine-trained network is trained to both reconstruct a fingerprint image or fingerprint and to estimate values for multiple tissue parameters in magnetic resonance fingerprinting. The reconstruction of the fingerprint image or fingerprint may reduce noise, such as aliasing, allowing for more accurate estimation of the values of the multiple tissue parameters from the under sampled magnetic resonance fingerprinting information.
-
65.
公开(公告)号:US20200005497A1
公开(公告)日:2020-01-02
申请号:US16199392
申请日:2018-11-26
发明人: Simon Arberet , Boris Mailhe , Xiao Chen , Mariappan S. Nadar
摘要: Systems and methods are provided for iterative reconstruction of a magnetic resonance image using magnetic resonance fingerprinting. An image series is estimated according to the following four steps: a gradient step to improve data consistency, fingerprint matching, spatial regularization, and a merging step. The fingerprint matching and spatial regularization steps are performed in parallel.
-
公开(公告)号:US10324155B2
公开(公告)日:2019-06-18
申请号:US15272867
申请日:2016-09-22
IPC分类号: G01R33/56 , G01R33/563 , G01R33/567
摘要: A computer-implemented method for sparse recovery of fiber orientations using a multidimensional Prony method for use in tractography applications includes performing magnetic resonance imaging to acquire a plurality of sparse signal measurements using a q-space sampling scheme which enforces a lattice structure with a predetermined number of collinear samples. Next, for each voxel included in the plurality of sparse signal measurements, a computer system is used to perform a parameter estimation process. This process includes translating a portion of the sparse signal measurements corresponding to the voxel into a plurality of Sparse Approximate Prony Method (SAPM) input parameters, and applying a SAPM process to the SAPM input parameters to recover a number of fiber populations, a plurality of orientation vectors, and a plurality of amplitude scalars. Then, one or more tractograms are generated using the number of fiber populations, the orientation vectors, and the amplitude scalars recovered for each voxel.
-
公开(公告)号:US10302714B2
公开(公告)日:2019-05-28
申请号:US15705889
申请日:2017-09-15
发明人: Xiao Chen , Mariappan S. Nadar , Benjamin L. Odry , Boris Mailhe
摘要: Systems and methods are provided for automatically designing RF pulses using a reinforcement machine-learnt classifier. Data representing an object and a selected outcome is accessed. A reinforcement learnt method identifies the RF pulse sequence that generates a result within a predefined value of the selected outcome. An MRI scanner images the object using the RF pulse sequence.
-
公开(公告)号:US10133964B2
公开(公告)日:2018-11-20
申请号:US15471079
申请日:2017-03-28
发明人: Yi Guo , Boris Mailhe , Xiao Chen , Mariappan S. Nadar
摘要: A method for training a system for reconstructing a magnetic resonance image includes: under-sampling image data from each of a plurality of fully-sampled images; and inputting the under-sampled image data to a multi-scale neural network comprising sequentially connected layers. Each layer has an input for receiving input image data and an output for outputting reconstructed image data. Each layer performs a process comprising: decomposing the array of input image data; applying a thresholding function to the decomposed image data, to form a shrunk data, the thresholding function outputting a value asymptotically approaching one when the thresholding function receives an input having a magnitude greater than a first value, reconstructing the shrunk data for combining with a reconstructed image data output by another one of the layers to form updated reconstructed image data, and machine-learning at least one parameter of the decomposing, the thresholding function, or the reconstructing.
-
69.
公开(公告)号:US20180268526A1
公开(公告)日:2018-09-20
申请号:US15986910
申请日:2018-05-23
摘要: The present embodiments relate to denoising medical images. By way of introduction, the present embodiments described below include apparatuses and methods for machine learning sparse image representations with deep unfolding and deploying the machine learnt network to denoise medical images. Iterative thresholding is performed using a deep neural network by training each layer of the network as an iteration of an iterative shrinkage algorithm. The deep neural network is randomly initialized and trained independently with a patch-based approach to learn sparse image representations for denoising image data. The different layers of the deep neural network are unfolded into a feed-forward network trained end-to-end.
-
公开(公告)号:US10061004B2
公开(公告)日:2018-08-28
申请号:US14573515
申请日:2014-12-17
发明人: Boris Mailhe , Qiu Wang , Johannes Flake , Mariappan S. Nadar , Laszlo Lazar , Yuanhsi Chen
IPC分类号: G01V3/00 , G01R33/561 , G01R33/56
CPC分类号: G01R33/5611 , G01R33/5608
摘要: A computer-implemented method for reconstructing magnetic resonance images using a parallel computing platform comprising a host unit and a graphical processing device includes receiving a plurality of coil data sets from a magnetic resonance imaging system, each respective coil data set comprising scanner data and a coil sensitivity map associated with a distinct coil included in the magnetic resonance imaging system. An iterative compressed-sensing reconstruction process is applied to reconstruct an image based on the plurality of coil data sets. Each iteration of the iterative compressed-sensing reconstruction process comprises: individually transferring the plurality of coil data sets from the host unit to the graphical processing device using a plurality of asynchronous data streams, overlapping with transfer of the plurality of coil data sets, optimizing a plurality of data fidelity values on the graphical processing device, each respective data fidelity value corresponding to a distinct coil data set, and computing an estimated image on the graphical processing device based on the plurality of data fidelity values.
-
-
-
-
-
-
-
-
-