公开(公告)号：US12106401B2

公开(公告)日：2024-10-01

申请号：US17075411

申请日：2020-10-20

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Mehmet Akcakaya ,  Burhaneddin Yaman ,  Seyed Amir Hossein Hosseini

IPC分类号： G06T11/00 ,  G06N3/04 ,  G06N3/08 ,  G16H30/40

CPC分类号： G06T11/005 ,  G06N3/04 ,  G06N3/08 ,  G16H30/40

摘要： Self-supervised training of machine learning (“ML”) algorithms for reconstruction in inverse problems are described. These techniques do not require fully sampled training data. As an example, a physics-based ML reconstruction can be trained without requiring fully-sampled training data. In this way, such ML-based reconstruction algorithms can be trained on existing databases of undersampled images or in a scan-specific manner.

公开(公告)号：US11714152B2

公开(公告)日：2023-08-01

申请号：US16858922

申请日：2020-04-27

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Mehmet Akcakaya ,  Steen Moeller ,  Chi Zhang

IPC分类号： G01R33/58 ,  G01R33/56 ,  G06N3/08 ,  G06N3/048 ,  G01R33/565

CPC分类号： G01R33/58 ,  G01R33/5608 ,  G06N3/048 ,  G06N3/08 ,  G01R33/56545

摘要： Images are reconstructed from undersampled k-space data using a residual machine learning algorithm (e.g., a ResNet architecture) to estimate missing k-space lines from acquired k-space data with improved noise resilience. Using a residual machine learning algorithm provides for combining the advantages of both linear and nonlinear k-space reconstructions. The linear residual connection can implement a convolution that estimates most of the energy in k-space, and the multi-layer machine learning algorithm can be implemented with nonlinear activation functions to estimate imperfections, such as noise amplification due to coil geometry, that arise from the linear component.

公开(公告)号：US11231475B2

公开(公告)日：2022-01-25

申请号：US16853308

申请日：2020-04-20

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Steen Moeller ,  Mehmet Akcakaya ,  Seng-Wei Chieh

IPC分类号： G01R33/56 ,  G01R33/561 ,  G01R33/565 ,  G01R33/58 ,  G01R33/48

摘要： A fully sampled calibration data set, which may be Cartesian k-space data, is used to obtain targeted and optimal interpolation kernels for non-regularly sampled data. The calibration data are self-calibration data obtained from a time-averaged image, or re-sampled data. ACS data are resampled for calibration of region-specific kernels. Subsequently, an explicit noise-based regularized solution can be utilized to estimate region-specific kernels for reconstruction.

公开(公告)号：US10962617B2

公开(公告)日：2021-03-30

申请号：US15947167

申请日：2018-04-06

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA ,  RUPRECHT-KARLS UNIVERSITY OF HEIDELBERG

发明人： Sebastian Weingartner ,  Steen Moeller ,  Mehmet Akcakaya

IPC分类号： G01R33/483 ,  G01R33/561 ,  G01R33/46 ,  G01R33/563

摘要： Methods for fast magnetic resonance imaging (“MRI”) using a combination of outer volume suppression (“OVS”) and accelerated imaging, which may include simultaneous multislice (“SMS”) imaging, data acquisitions amenable to compressed sensing reconstructions, or combinations thereof. The methods described here do not introduce fold-over artifacts that are otherwise common to reduced field-of-view (“FOV”) techniques.

公开(公告)号：US20180292487A1

公开(公告)日：2018-10-11

申请号：US15947167

申请日：2018-04-06

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA ,  RUPRECHT-KARLS UNIVERSITY OF HEIDELBERG

发明人： Sebastian Weingartner ,  Steen Moeller ,  Mehmet Akcakaya

IPC分类号： G01R33/483 ,  G01R33/561 ,  G01R33/46

摘要： Methods for fast magnetic resonance imaging (“MRI”) using a combination of outer volume suppression (“OVS”) and accelerated imaging, which may include simultaneous multislice (“SMS”) imaging, data acquisitions amenable to compressed sensing reconstructions, or combinations thereof. The methods described here do not introduce fold-over artifacts that are otherwise common to reduced field-of-view (“FOV”) techniques.

公开(公告)号：US20180067184A1

公开(公告)日：2018-03-08

申请号：US15695259

申请日：2017-09-05

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Sebastian Weingartner ,  Mehmet Akcakaya

IPC分类号： G01R33/565 ,  G01R33/56 ,  G01R33/561

CPC分类号： G01R33/56545 ,  G01R33/50 ,  G01R33/5602 ,  G01R33/5607 ,  G01R33/5608 ,  G01R33/5614

摘要： A system and method for obtaining magnetic resonance images are provided. The system is programmed to control the RF system to apply a saturation pulse at a reference frequency that saturates a selected labile spin species of the subject. The system is programmed to control the RF system to apply an inversion pulse after a variable delay. The system is programmed to control the RF system and the plurality of gradient coils to apply a motion sensitized driven equilibrium (MSDE) preparation pulse. The system is programmed to control the plurality of gradient coils to read imaging data during an acquisition time period. The system is programmed to reconstruct a T1 mapping image of the subject with black-blood contrast.

公开(公告)号：US11009576B2

公开(公告)日：2021-05-18

申请号：US15947001

申请日：2018-04-06

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Steen Moeller ,  Mehmet Akcakaya

IPC分类号： G01V3/00 ,  G01R33/483 ,  G01R33/46 ,  G01R33/561

摘要： Described here are systems and methods for volumetric excitation in magnetic resonance imaging (“MRI”) using frequency modulated radio frequency (“RF”) pulses. In general, quadratic phase modulation along the slice encoding direction is implemented for additional spatiotemporal encoding, which better distributes signal content in the slice direction and enables higher acceleration rates that are robust to slice-undersampling.

公开(公告)号：US20210118200A1

公开(公告)日：2021-04-22

申请号：US17075411

申请日：2020-10-20

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Mehmet Akcakaya ,  Burhaneddin Yaman ,  Seyed Amir Hossein Hosseini

IPC分类号： G06T11/00 ,  G16H30/40 ,  G06N3/04 ,  G06N3/08

摘要： Self-supervised training of machine learning (“ML”) algorithms for reconstruction in inverse problems are described. These techniques do not require fully sampled training data. As an example, a physics-based ML reconstruction can be trained without requiring fully-sampled training data. In this way, such ML-based reconstruction algorithms can be trained on existing databases of undersampled images or in a scan-specific manner.

公开(公告)号：US10451700B2

公开(公告)日：2019-10-22

申请号：US15695259

申请日：2017-09-05

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Sebastian Weingartner ,  Mehmet Akcakaya

IPC分类号： G01R33/565 ,  G01R33/56 ,  G01R33/561

摘要： A system and method for obtaining magnetic resonance images are provided. The system is programmed to control the RF system to apply a saturation pulse at a reference frequency that saturates a selected labile spin species of the subject. The system is programmed to control the RF system to apply an inversion pulse after a variable delay. The system is programmed to control the RF system and the plurality of gradient coils to apply a motion sensitized driven equilibrium (MSDE) preparation pulse. The system is programmed to control the plurality of gradient coils to read imaging data during an acquisition time period. The system is programmed to reconstruct a T1 mapping image of the subject with black-blood contrast.

公开(公告)号：US20180217217A1

公开(公告)日：2018-08-02

申请号：US15885158

申请日：2018-01-31

申请人： REGENTS OF THE UNIVERSITY OF MINNESOTA

发明人： Sebastian Weingartner ,  Mehmet Akcakaya

IPC分类号： G01R33/56 ,  G01R33/50 ,  A61B5/00 ,  G01R33/561

CPC分类号： G01R33/5602 ,  A61B5/0044 ,  A61B5/055 ,  G01R33/246 ,  G01R33/4828 ,  G01R33/50 ,  G01R33/5601 ,  G01R33/5613 ,  G01R33/56509 ,  G01R33/5673

摘要： Systems and methods for producing quantitative maps of a longitudinal relaxation parameter, such as a longitudinal relaxation time (“T1”), using magnetic resonance imaging (“MRI”) are described. More particularly, a pulse sequence and imaging method for cardiac phase-resolved myocardial T1 mapping are provided.