Shanghai Neusoft Medical Technology Co., Ltd.

Neusoft Medical Systems Co., Ltd.

Alcatel

Shanghai Microport Cardioflow Medtech Co., Ltd.

Givaudan S.a.

Feng Huang

Yu Meng Li

Jian Li

Chao Wang

Andreas Goeke

Qiyi Luo

Yue Zou

Guoming Chen

Jing Zhao

Andreas Natsch

Yuan Fang

Hongyu Guo

Yu Li

Ming Cheng

Julie Charpentier

Dong Han

Roger Emter

Chengyun Yue

Shaohui Chen

Lijun Zhou

Jianchao Han

Cong Tian

Zhigang Wu

Ruibo Song

Jiaoming Dong

Dakai Chen

Yihao Duan

Mingliang Chen

Yongfa Yang

Ling Mei

Nicolas Cocito Armanino

Chun Chen

Xiaoyi Zhang

The present application discloses an implant loading apparatus comprising a guider and a guide base. The guider is sleeved on the exterior of the guide base. The guide base comprises a guide column, a connecting section, and a base connected in the axial direction. Fixing sections are provided on either end of the connecting section. The guide base is removably connected to the guider via the fixing sections. The guide base is provided with the two fixing sections that fit the guider to implement twice removable fixing, thus favoring a coaxial operation. A valve stent is neither twisted nor tilted during a compression process, thus increasing loading efficiency, greatly reducing the operation difficulty of a surgery, and allowing the implementation of a single person operation.

Implant loading apparatus

Methods, devices, apparatus and systems for magnetic resonance imaging with deep neural networks are provided. In one aspect, a method of magnetic resonance imaging method combines a deep neural network and an accelerated imaging manner. The method includes: scanning a subject with a first undersampling factor and a first sampling trajectory to obtain first imaging information, processing the first imaging information with the deep neural network to obtain second imaging information corresponding to a second undersampling factor that is smaller than the first undersampling factor, and reconstructing a magnetic resonance image of the subject from the second imaging information.

Magnetic resonance imaging with deep neutral networks

Methods, devices, systems and apparatus for medical imaging, e.g., Magnetic Resonance (MR) imaging or Computed Tomography (CT) imaging, using neural networks are provided. In one aspect, an imaging method includes: determining a first neural network and a second neural network corresponding to a target imaging task, the first neural network including a first neural network parameter and a first neural network model, the second neural network including a second neural network parameter and a second neural network model, obtaining a reconstructed image by performing reconstruction for down-sampling data of a tissue under test using the first neural network, the target imaging task corresponding to the tissue under test, and obtaining an image output by a second neural network as a target image of the tissue under test by performing an image processing operation corresponding to the target imaging task for the reconstructed image using the second neural network.

Medical imaging using neural networks

Methods, devices, systems and apparatus for determining emphysema thresholds for controlling magnetic resonance imaging are provided. In one aspect, a magnetic resonance imaging method includes: collecting magnetic resonance imaging data as first k-space data by undersampling a magnetic resonance signal, performing parallel imaging reconstruction on the first k-space data to obtain a first image, performing enhancement processing on the first image to obtain a second image that comprises distributional information of image supporting points, and performing constrained reconstruction on the first k-space data by using the second image as a prior image to obtain a third image as a magnetic resonance image to be displayed.

Magnetc resonance imaging

Methods, devices, systems and apparatus for training image enhancement models and enhancing images are provided. In one aspect, a method of training an image enhancement model includes: for each of one or more constraint features, processing a ground truth image with the constraint feature to obtain a feature image corresponding to the constraint feature, for each of the one or more feature images, using the ground truth image and the feature image to train a convolutional neural network (CNN) structure model corresponding to the feature image, determining a loss function of the image enhancement model based on the one or more CNN structure models corresponding to the one or more feature images, and establishing the image enhancement model based on the loss function. A to-be-enhanced image can be input into the established image enhancement model to obtain an enhanced image.

Training image enhancement model and enhancing image

Methods, devices, systems and apparatus for dynamic imaging based on echo planar imaging (EPI) sequence are provided. In one aspect, a method includes: obtaining first pre-scanned k-space data by performing a pre-scan for a subject based on a first EPI sequence and pre-scanning parameters, obtaining a pre-scanned image and second pre-scanned k-space data according to the first pre-scanned k-space data, performing a dynamic scan for the subject based on a second EPI sequence and dynamic scanning parameters to generate dynamically-scanned k-space data associated with each of a plurality of dynamic periods in the dynamic scan, and for each of the dynamic periods, generating a residual image according to the dynamically-scanned k-space data of the dynamic period and the second pre-scanned k-space data, and adding the pre-scanned image and the residual image to obtain a dynamic image of the dynamic period.

Dynamic imaging based on echo planar imaging sequence

Methods, devices, systems and apparatus for magnetic resonance imaging are provided. In an example, a method includes: obtaining M imaging data sets collected by a receiving coil array including N coil channels under M radio-frequency excitations, determining odd echo phase information and even echo phase information for each of the imaging data sets, mapping M odd echo data sets and M even echo data sets of the imaging data sets as a virtual imaging data set for a virtual coil array that includes N&#xd7;M&#xd7;2 virtual coil channels, and performing parallel magnetic resonance imaging based on the odd echo phase information and the even echo phase information of each of the imaging data sets, the virtual imaging data set and parallel reconstruction reference data.

Magnetic resonance imaging

A stent () used for a heart valve prosthesis and the heart valve prosthesis that includes the stent () and is used for heart valve replacement. The stent is configured to support a heart valve () and includes, along a longitudinal axis, an inflow section (), an outflow section () and a transition section () between the inflow section () and the outflow section (). The stent () has a contracted delivery configuration and an expanded deployed configuration. In the expanded deployed configuration, the inflow section () defines a concave contour that is complementary to a structure of a native valve annulus. The concave contour enables self-deployment and close adherence of the stent (), thereby preventing its displacement and perivalvular leakage after implantation.

Heart valve prosthesis

Methods, devices and apparatus for reconstructing a magnetic resonance image are provided. In one aspect, a method includes: determining array coil images according to first data collected by array coils of an MRI device during a prescan, where each coil of the array coils corresponds to a respective one of channels; determining a quadrature body coil image according to at least one of second data collected by a quadrature body coil of the MRI device during the prescan and the first data collected by the array coils; obtaining a corrected quadrature body coil image by correcting an uniformity of the quadrature body coil image; determining coil sensitivity maps according to the array coil images and the corrected quadrature body coil image; and reconstructing a magnetic resonance image with third data collected by the array coils during a normal scan according to the coil sensitivity maps.

Magnetic resonance image reconstruction

Methods and devices for magnetic resonance imaging are provided. In one aspect, a method includes: obtaining undersampled k-space data as first partial k-space data by scanning a subject in an accelerated scanning manner, generating a first image by performing image reconstruction for the first partial k-space data according to a trained deep neural network and an explicit analytic solution imaging algorithm, obtaining mapped data of complete k-space by mapping the first image to k-space, extracting second partial k-space data from the mapped data of complete k-space, the second partial k-space data being distributed in the k-space at a same position as the first partial k-space data in the k-space, obtaining a residual image by performing image reconstruction according to the first partial k-space data and the second partial k-space data, and finally generating a magnetic resonance image of the subject by adding the first image with the residual image.

Magnetic resonance imaging method and device

Methods and devices for reconstructing a magnetic resonance image, and a non-transitory machine readable storage medium are provided. In an example, the method includes: obtaining a previous image; for each of channels, collecting k-space data of the channel by a partial sampling technology, generating original k-space data of the channel by mapping the previous image into k-space of the channel, and obtaining residue k-space data of the channel by subtracting the original k-space data of the channel from the k-space data of the channel; reconstructing a residue image with the residue k-space data of each of the channels by taking sparsity of the residue image as a constraint term and a difference between virtual residue k-space data of the channel and the residue k-space data of the channel as a data fidelity term; and obtaining a reconstructed magnetic resonance image by adding the residue image to the previous image.

A method and a device for reconstructing magnetic resonance images with different contrasts are provided. According to an example of the method, after collecting magnetic resonance signal data recorded in k-space of N contrasts by N number of magnetic scans, a first image for each of the contrasts may be obtained by performing image reconstruction according to the magnetic resonance signal data corresponding to the contrast; an association coefficient of each of the contrasts may be determined according to the first images for the N contrasts; and a second image shared with the N contrasts may be obtained by performing image reconstruction based on the magnetic resonance signal data of the N contrasts and the association coefficient of each of the N contrasts. In this way, a reconstructed image for each of the contrast may be obtained by combining the association coefficient of the contrast with the second image.

Reconstructing magnetic resonance images with different contrasts

Dynamic magnetic resonance imaging methods and devices are provided. According to an example, a method includes: collecting respective k-space data for each of imaging phases by scanning a part of a subject via an equidistant undersampling manner, determining basic k-space data for the part of the subject, determining respective differential k-space data for each of the imaging phases based on the respective k-space data for each of the imaging phases and the basic k-space data, obtaining a basic image based on the basic k-space data, determining a respective sparse image for each of the imaging phases, reconstructing a respective differential image for each of the imaging phases from the respective differential k-space data for the imaging phase, and obtaining a respective magnetic resonance image for each of the imaging phases based on the respective differential image for the imaging phase and the basic image.

Dynamic magnetic resonance imaging

Methods and devices for reconstructing magnetic resonance images for contrasts are provided. In an example, the method includes: for each channel for each contrast, collecting k-space data of a subject in the channel by scanning the subject in an undersampling manner, collecting central k-space data by scanning a k-space central region of the subject in k-a fullsampling manner, training a convolution kernel of respective phase encoding lines in the channel based on the central k-space data of the contrasts, and obtaining entire k-space data in the channel based on the convolution kernel of respective phase encoding lines in the channel and collected k-space data in the channels, and obtaining a respective magnetic resonance image for each of the contrasts by performing image reconstruction on the entire k-space data in each channel for the contrast.

Reconstructing magnetic resonance images for contrasts

The present invention provides a method for sending and receiving the network management messages and/or the control messages, that is, using GFP protocol in stead of conventional LAPD protocol, predetermining the mapping relationship between the values of UPI field in GFP protocol and the types of the data including the network management messages and/or the control messages, furthermore, filling the UPI field of GFP protocol based on the corresponding mapping relationship, encapsulating the network management messages and/or the control messages via GFP protocol into SDH/SONET, PDH or OTN, and transmitting the encapsulated data. GFP protocol is a universal protocol, allowing for inter-operation of the network management messages and the control messages between the equipments of different manufacturers.

Growing community of inventors

Shanghai, China

Feng Huang