-
公开(公告)号：US20190223725A1
公开(公告)日：2019-07-25
申请号：US15879486
申请日：2018-01-25
发明人： Xiaoguang Lu , Monami Banerjee
摘要： For heart segmentation in magnetic resonance or other medical imaging, deep learning trains a neural network. The neural network, such as U-net, includes at least one long-short-term memory (LSTM), such as a convolutional LSTM. The LSTM incorporates the temporal characteristics with the spatial to improve accuracy of the segmentation by the machine-learnt network.
-
公开(公告)号：US10074037B2
公开(公告)日：2018-09-11
申请号：US15172949
申请日：2016-06-03
发明人： Xiaoguang Lu , Vibhas Deshpande , Peter Kollasch , Dingxin Wang , Puneet Sharma
IPC分类号： G06K9/00 , G06K9/62 , A61B5/055 , A61B5/00 , A61B6/03 , A61B8/00 , G06N99/00 , G06T7/00 , G01R33/54
CPC分类号： G06K9/6265 , A61B5/055 , A61B5/4585 , A61B6/032 , A61B6/037 , A61B8/58 , G01R33/543 , G06N20/00 , G06T7/0014 , G06T2207/30048 , G06T2207/30101
摘要： Systems and methods for determining optimized imaging parameters for imaging a patient include learning a model of a relationship between known imaging parameters and a quality measure, the known imaging parameters and the quality measure being determined from training data. Optimized imaging parameters are determined by optimizing the quality measure using the learned model. Images of the patient are acquired using the optimized imaging parameters.
-
公开(公告)号：US20190205606A1
公开(公告)日：2019-07-04
申请号：US16094900
申请日：2017-07-19
发明人： Shaohua Kevin Zhou , Mingqing Chen , Hui Ding , Bogdan Georgescu , Mehmet Akif Gulsun , Tae Soo Kim , Atilla Peter Kiraly , Xiaoguang Lu , Jin-hyeong Park , Puneet Sharma , Shanhui Sun , Daguang Xu , Zhoubing Xu , Yefeng Zheng
CPC分类号： G06K9/0014 , G06K9/4628 , G06K9/6209 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T7/11 , G16H30/40
摘要： Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.
-
公开(公告)号：US20170351937A1
公开(公告)日：2017-12-07
申请号：US15172949
申请日：2016-06-03
发明人： Xiaoguang Lu , Vibhas Deshpande , Peter Kollasch , Dingxin Wang , Puneet Sharma
CPC分类号： G06K9/6265 , A61B5/055 , A61B5/4585 , A61B6/032 , A61B6/037 , A61B8/58 , G01R33/543 , G06N99/005 , G06T7/0014 , G06T2207/30048 , G06T2207/30101
摘要： Systems and methods for determining optimized imaging parameters for imaging a patient include learning a model of a relationship between known imaging parameters and a quality measure, the known imaging parameters and the quality measure being determined from training data. Optimized imaging parameters are determined by optimizing the quality measure using the learned model. Images of the patient are acquired using the optimized imaging parameters.
-
公开(公告)号：US09684982B2
公开(公告)日：2017-06-20
申请号：US14842157
申请日：2015-09-01
发明人： Ti-chiun Chang , Xiaoguang Lu , Peter Speier
CPC分类号： G06T11/005 , G01R33/4835 , G01R33/5608 , G06K9/522 , G06T5/20 , G06T7/0012 , G06T2207/10088
摘要： A computer-implemented method for performing isotropic reconstruction of Magnetic Resonance Imaging (MRI) data includes receiving a stack of slices acquired by an MRI device in two or more directions and reslicing the stack of slices into (i) an acquired view stack comprising high-resolution slices acquired in-plane, and (ii) a reslice stack comprising degraded slices acquired out of plane. An estimated slice profile is generated based on the stack of slices and the acquired view stack is convolved with the estimated slice profile to yield a simulated distorted slice stack. The simulated distorted slice stack is subtracted from the acquired view stack to yield a high-frequency band estimate and the high-frequency band estimate is combined with the reslice stack to yield isotropic reconstruction results.
-
公开(公告)号：US20170160363A1
公开(公告)日：2017-06-08
申请号：US15372445
申请日：2016-12-08
发明人： Xiao Chen , Boris Mailhe , Qiu Wang , Shaohua Kevin Zhou , Yefeng Zheng , Xiaoguang Lu , Puneet Sharma , Benjamin L. Odry , Bogdan Georgescu , Mariappan S. Nadar
CPC分类号： G01R33/5608 , G01R33/50 , G06N3/08
摘要： A learning-based magnetic resonance fingerprinting (MRF) reconstruction method for reconstructing an MR image of a tissue space in an MR scan subject for a particular MR sequence is disclosed. The method involves using a machine-learning algorithm that has been trained to generate a set of tissue parameters from acquired MR signal evolution without using a dictionary or dictionary matching.
-
公开(公告)号：US20190117073A1
公开(公告)日：2019-04-25
申请号：US15791680
申请日：2017-10-24
发明人： Marie-Pierre Jolly , Xiaoguang Lu
CPC分类号： A61B5/0044 , A61B5/055 , G06K9/4671 , G06K9/6211 , G06K2209/051 , G06T7/13 , G06T2207/10088 , G06T2207/20164 , G06T2207/30048
摘要： A method for computing global longitudinal strain from cine magnetic resonance (MR) images includes automatically detecting landmark points in each MR long axis image frame included in a cine MR image sequence. A deformation field is determined between every pair of frames based on the landmark points. Myocardial pixels in the frames are labeled using a deep learning framework to yield myocardium masks. These myocardium masks are propagated to each frame using the deformation fields. A polar transformation is performed on each of the masked frames. The contours of the myocardium in each transformed frame are computed using a shortest path algorithm. Next, longitudinal strain is calculated at every pixel in the myocardium for the polar frames using the contours of the myocardium. Then, global longitudinal strain is computed by averaging the longitudinal strain at every pixel in the myocardium of the transformed frames.
-
8.发明申请Isotropic Volume Reconstruction from Multiple 2D Scans Using Super -Resolution Techniques 有权使用超分辨率技术从多个2D扫描的各向同性体重建公开(公告)号：US20170061652A1
公开(公告)日：2017-03-02
申请号：US14842157
申请日：2015-09-01
发明人： Ti-chiun Chang , Xiaoguang Lu , Peter Speier
CPC分类号： G06T11/005 , G01R33/4835 , G01R33/5608 , G06K9/522 , G06T5/20 , G06T7/0012 , G06T2207/10088
摘要： A computer-implemented method for performing isotropic reconstruction of Magnetic Resonance Imaging (MRI) data includes receiving a stack of slices acquired by an MRI device in two or more directions and reslicing the stack of slices into (i) an acquired view stack comprising high-resolution slices acquired in-plane, and (ii) a reslice stack comprising degraded slices acquired out of plane. An estimated slice profile is generated based on the stack of slices and the acquired view stack is convolved with the estimated slice profile to yield a simulated distorted slice stack. The simulated distorted slice stack is subtracted from the acquired view stack to yield a high-frequency band estimate and the high-frequency band estimate is combined with the reslice stack to yield isotropic reconstruction results.
摘要翻译： 用于执行磁共振成像（MRI）数据的各向同性重建的计算机实现的方法包括：在两个或更多个方向上接收由MRI装置获取的切片堆叠，并将所述切片堆叠成（i）获取的视图堆叠， 在平面内获取的分辨率切片，以及（ii）包括从平面获取的退化切片的重叠堆叠。 基于片堆栈生成估计切片轮廓，并且获取的视图堆叠与估计的切片轮廓卷积以产生模拟失真的切片堆叠。 从获取的视图堆栈中减去模拟失真的片层叠，以产生高频带估计，并将高频带估计与重叠堆组合以产生各向同性重建结果。
-
9.发明授权公开(公告)号：US09734573B2
公开(公告)日：2017-08-15
申请号：US14245011
申请日：2014-04-04
申请人： The United States of America, as respresented by the Secretary, Dept. of Health and Human Services , Siemens Healthcare GmbH
发明人： Bruce S. Spottiswoode , Xiaoguang Lu , Xiaoming Bi , Hui Xue , Christopher Glielmi , Peter Kellman , Andreas Greiser
IPC分类号： G06T7/00
CPC分类号： G06T7/0012 , G06T2207/10088 , G06T2207/30048
摘要： A computer-implemented method for determining magnetic field inversion time of a tissue species includes generating a T1-mapping image of a tissue of interest, the T1-mapping image comprising a plurality of T1 values within an expected range of T1 values for the tissue of interest. An image mask is created based on predetermined identification information about the tissue of interest. Next, an updated image mask is created based on a largest connected region in the image mask. The updated image mask is applied to the T1-mapping image to yield a masked image. Then, a mean relaxation time value is determined for the largest connected region. The mean relaxation time value is then used to determine a time point for nulling longitudinal magnetization.
-
公开(公告)号：US11800978B2
公开(公告)日：2023-10-31
申请号：US15641534
申请日：2017-07-05
发明人： Xiaoguang Lu , Carmel Hayes
CPC分类号： A61B5/0044 , A61B5/0037 , A61B5/055 , G06N3/045 , G06N3/08 , G06N20/00
摘要： A computer-implemented method of performing deep learning based isocenter positioning includes acquiring a plurality of slabs covering an anatomical area of interest that comprises a patient's heart. For each slab, one or more deep learning models are used to determine a likelihood score for the slab indicating a probability that the slab includes at least a portion of the patient's heart. A center position of the patient's heart may then be determined based on the likelihood scores determined for the plurality of slabs.
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.029 秒)
