-
公开(公告)号：US20230031910A1
公开(公告)日：2023-02-02
申请号：US17284794
申请日：2020-12-09
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Dong LIANG , Zhanli HU , Hairong ZHENG , Xin LIU , Qingneng LI , Yongfeng YANG
Abstract: An apriori guidance network for multitask medical image synthesis is provided. The apriori guidance network includes a generator and a discriminator, wherein the generator includes an apriori guidance module configured to convert an input feature map into a target modal image pointing to a target domain according to an apriori feature, and the apriori feature is a deep feature of the target modal image. The generator is configured to generate a corresponding target domain image by taking the apriori feature of the target modal image and source modal image data as an input. The discriminator is configured to discriminate an authenticity of the target domain image outputted by the generator.
-
公开(公告)号：US20220283325A1
公开(公告)日：2022-09-08
申请号：US17824453
申请日：2022-05-25
Inventor： Zhanli HU , Yongfeng YANG , Chunhui ZHANG , Zhonghua KUANG , Xiaohui WANG , San WU , Dong LIANG , Xin LIU , Hairong ZHENG
Abstract: A method for processing positron emission tomography data is provided, this method includes: obtaining a first coordinate and a second coordinate respectively corresponding to two ends of a response line to be processed; determining corresponding dimensional coordinates of the response line to be processed in a sinogram based on the first coordinate and the second coordinate; and generating the sinogram corresponding to the response line to be processed based on the dimensional coordinates. According to this method, the amount of calculation of system matrix is reduced, the accuracy of position information of the generated response line is improved, and the accuracy of generated sinogram is improved accordingly.
-
公开(公告)号：US20210333344A1
公开(公告)日：2021-10-28
申请号：US16624478
申请日：2019-09-17
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Dong LIANG , Jing CHENG , Haifeng WANG , Hairong ZHENG , Xin LIU
Abstract: Disclosed are a magnetic-resonance imaging method, apparatus and system, and a storage medium. The method includes acquiring an initial model of magnetic-resonance imaging and establishing an initial imaging model according to an iterative algorithm used for solving the initial model, where the iterative algorithm includes at least one of an undetermined parameter, an undetermined solving operator or an undetermined structural relationship; training the initial imaging model on the basis of sample data to generate a magnetic-resonance imaging model, where training of the initial imaging model is used for learning the at least one of the undetermined parameter, the undetermined solving operator or the undetermined structural relationship in the iterative algorithm; and acquiring under-sampled K-space data to be processed, inputting the under-sampled K-space data into the magnetic-resonance imaging model, and generating a magnetic-resonance image.
-
4.发明申请公开(公告)号：US20210192806A1
公开(公告)日：2021-06-24
申请号：US16878633
申请日：2020-05-20
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Zhan Li HU , Dong LIANG , Hai Rong ZHENG , Xin LIU , Yong Feng YANG , Zhen Xing HUANG
IPC: G06T11/00
Abstract: The disclosure provides a low-dose image reconstruction method and system based on prior anatomical structure difference. The method includes: determining the weights of different parts in the low-dose image based on prior information of anatomical structure differences; constructing a generative network being taking the low-dose image as input extract features, and integrating the weights of the different parts in the feature extraction process, outputting a predicted image; constructing a determining network being taking the predicted image and standard-dose image as input, to distinguish the authenticity of the predicted image and standard-dose image as the first optimization goal, and identifying different parts of the predicted image as the second optimization goal, collaboratively training the generative network and the determining network to obtain the mapping relationship between the low-dose image and the standard-dose image; and reconstructing the low-dose image by using the obtained mapping relationship. The disclosure can obtain more accurate high-definition images.
-
5.发明申请公开(公告)号：US20200320704A1
公开(公告)日：2020-10-08
申请号：US16910074
申请日：2020-06-24
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Hairong ZHENG , Xin LIU , Na ZHANG , Zhanli HU , Dong LIANG , Yongfeng YANG
Abstract: A method of processing plaques in magnetic resonance imaging of vessel wall include: step S101, training a generative adversarial network and a capsule neural network to obtain a trained generator network and a trained capsule neural network; and step S102, cascade-connecting the trained generator network with the capsule neural network into a system to recognize and classify plaques in magnetic resonance imaging of vessel wall. In one aspect, the capsule neural network has more abundant vascular plaques characteristic information represented by vector; in another aspect, when the trained generator network and the capsule neural network are cascaded into the system to recognize and classify the plaques in magnetic resonance imaging of vessel wall, an accuracy of recognition and classification may be greatly improved. A device for processing the method as well as a computer for implementing are also disclosed.
-
Patent Agency Ranking
公开(公告)号：US20220188978A1
公开(公告)日：2022-06-16
申请号：US17340117
申请日：2021-06-07
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Zhanli HU , Hairong ZHENG , Na ZHANG , Xin LIU , Dong LIANG , Yongfeng YANG , Hanyu SUN
Abstract: The present application relates to a method and system for generating multi-task learning-type generative adversarial network for low-dose PET reconstruction, and relates to the field of deep learning. The method includes connecting layers of the encoder with layers of the decoder by skip connection to provide a U-Net type picture generator; generating a group of generative adversarial networks by matching a plurality of picture generators with a plurality of discriminators in one-to-one manner; obtaining a first multi-task learning-type generative adversarial network; designing a joint loss function 1 for improving image quality; and training the first multi-task learning-type generative adversarial network according to the joint loss function 1 in combination with an optimizer to provide a second multi-task learning-type generative adversarial network.
-
公开(公告)号：US20210088611A1
公开(公告)日：2021-03-25
申请号：US17032588
申请日：2020-09-25
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Ye LI , Qiaoyan CHEN , Jo LEE , Chao LUO , Jianhong WEN , Chao ZOU , Xin LIU
IPC: G01R33/3875 , G01R33/44 , G01R33/54 , A61B5/055 , G01R33/48
Abstract: A local shimming system for magnetic resonance imaging and the method thereof, wherein the shimming method comprises the following steps: collecting B0 field map information using two-dimensional gradient echo (301); calculating and evaluating the homogeneity of B0 (302); optimizing the current of each channel shim coil (303); determining whether the minimum standard deviation value of Δf is obtained (304); outputting an optimal current combination values and setting an optimum current value corresponding to each channel of the shim coil on the current control software (305); and testing and evaluating the homogeneity of B0 to achieve the shimming goal (306).
-
8.发明申请公开(公告)号：US20170363702A1
公开(公告)日：2017-12-21
申请号：US15618979
申请日：2017-06-09
Inventor： Xi PENG , Dong LIANG , Xin LIU , Hairong ZHENG
IPC: G01R33/563 , G01R33/56
CPC classification number: G01R33/56341 , A61B5/055 , A61B5/7203 , G01R33/5602 , G06T5/002 , G06T2207/10092
Abstract: The application provides a method, apparatus and computer program product for denoising a magnetic resonance diffusion tensor, wherein the method comprises: collecting data of K space; calculating a maximum likelihood estimator of a diffusion tensor according to the collected data of K space; calculating a maximum posterior probability estimator of the diffusion tensor by using sparsity of the diffusion tensor and sparsity of a diffusion parameter and taking the calculating maximum likelihood estimator as an initial value; and calculating the diffusion parameter according to the calculated maximum posterior probability estimator. The application solves the technical problem in the prior art of how to realize high precision denoising of diffusion tensor while not increasing scanning time and affecting spatial resolution, achieves the technical effects of effectively suppressing noises in the diffusion tensor and improving the estimation accuracy of the diffusion tensor.
-
公开(公告)号：US20160370444A1
公开(公告)日：2016-12-22
申请号：US15103845
申请日：2014-12-05
Inventor： Xi PENG , Dong LIANG , Xin LIU , Hairong ZHENG
IPC: G01R33/50 , G01R33/561 , G01R33/56
CPC classification number: G01R33/561 , G01R33/50 , G01R33/5608 , G01R33/5611
Abstract: Disclosed is a magnetic resonance rapid parameter imaging method and system. The method comprises: obtaining a target undersampled magnetic resonance signal (S10); obtaining prior information of a parameter model (S20); performing sequence reconstruction of a target image according to the undersampled magnetic resonance signal and the prior information to obtain a target image sequence (S30); and substituting the target image sequence into the parameter estimation model to obtain object parameters and to generate parametric images (S40).
Abstract translation: 公开了一种磁共振快速参数成像方法和系统。 该方法包括：获得目标欠采样磁共振信号（S10）; 获取参数模型的先验信息（S20）; 根据欠采样的磁共振信号和先验信息执行目标图像的序列重构以获得目标图像序列（S30）; 并且将目标图像序列代入参数估计模型以获得对象参数并生成参数图像（S40）。
-
公开(公告)号：US20240202873A1
公开(公告)日：2024-06-20
申请号：US18555723
申请日：2021-04-19
Inventor： Shanshan WANG , Haoyun LIANG , Hairong ZHENG , Xin LIU
CPC classification number: G06T5/20 , G06T5/50 , G06T5/60 , G06T2207/20084 , G06T2207/20221
Abstract: The present application relates to image processing technical field, and provides a method for image reconstruction, an apparatus, a terminal device, and a storage medium. The method first extracts an initial feature map of an original image, then calculates an average value of each column pixel in the initial feature map, and constructs a target row vector and duplicates the target row vector in the column direction after convolution processing, to obtain a feature map. In addition, an average value of the element of each row of pixels in the initial feature map is calculated respectively, and a target column vector is constructed. It is duplicated in a row direction to obtain another feature map, and then the two feature maps are fused. Finally, two-dimensional convolution processing is performed on a fused feature map, and a reconstructed image is generated, thereby the long-distance dependencies of the image can be captured.
-
-
-
-
-
-
-
-
-
Search Results
26
records
(took 0.028 seconds)
