Huawei Technologies Co., Limited

Tencent Technology (shenzhen) Company Limited

Shenzhen Institutes of Advanced Technology

Nokia Technologies Oy

Carbon (shenzhen) Medical Device Co, Ltd.

Shanshan Wang

Wenfu Wu

Ying Hu

Yu Yin

Weihua Hu

Zhiyu Di

Xin Liu

Hairong Zheng

Dong Liang

Li Xue

Zongpeng Du

Zhu Liang

Zhiwang Zhao

Lan Zou

Hui Li

Wenjun Yan

Jian Zhu

Xiaojun Huang

Shaofeng Liu

Wenyong Han

Shengyi Qin

Yan Wei

Shi Wang

Ningshen Wang

Yinzhou Guo

Bingli Zhi

Xiongwen Huang

Rui Ju

Guowei Tang

Ruiming Long

Rongliang Zhu

Mengling Wu

Pablo David Burstein

Qinxue Li

Liying Sun

Ningbo Huang

Lina Liu

Sha Tan

Taohui Xiao

An ultrasonic puncture guidance planning system based on a multi-modal medical image registration, which includes: an MRI sequence image rendering unit configured to receive MRI sequence images, and perform three-dimensional rendering and plot puncture points; an ultrasound sequence image reconstruction unit configured to receive ultrasound sequence images and reconstruct ultrasound volume data; a registration unit configured to perform a three-dimensional registration operation to obtain a registration transformation coefficient; and a puncture planning unit configured to receive ultrasound images of a human body acquired by an ultrasound probe, and generate and display a puncture planning image according to a system puncture point and a current ultrasonic image. An electromagnetic coordinate system under ultrasound is unified to a MRI world coordinate system through a multi-modal medical image registration, and it is determined whether the puncture point is on the ultrasound plane to guide the ultrasound for accurate puncture.

Ultrasonic puncture guidance planning system based on multi-modal medical image registration using an iterative closest point algorithm

An alarm analysis method, including determining M alarm pairs in a first alarm set, where each alarm pair of the M alarm pairs includes a first alarm and a second alarm having an association, generating, according to an association rule, a first feature set of N alarm pairs, the first alarm of each alarm pair of the N alarm pairs being an alarm pair root in the first feature set, the first feature set including a first probability that a first subsystem to which each first alarm belongs is a subsystem root and a first alarm object is an alarm object root and a second probability that a second subsystem to which each second alarm belongs is a subsystem root and a second alarm object is an alarm object root, and determining root information of the first alarm set based on the first probability and the second probability.

Alarm analysis method and related device

A method, device and system for creating resources during a user equipment (UE) hands over from a non-3Generation Partnership Project (non-3GPP) system to a 3GPP system are provided. A serving gateway (Serving GW) receives a first resource request message, such as Create Default Bearer Request message, including handover indication information indicating the handover from a mobility management network device, e.g., a MME. As the received resource request message includes the handover indication information, the Serving GW includes the handover indication information in a second resource request message and then sends the second resource request message to a PDN GW. After receiving the second resource request message, the PDN GW policy and charging control (PCC) rules to be used by the UE in the 3GPP access system so as to create the resources used by the UE in the 3GPP system.

Method and network device for creating and deleting resources

A method for implementing a generic routing encapsulation (GRE) tunnel, an access point (AP), and a network system. The method includes establishing a Control And Provisioning of Wireless Access Points (CAPWAP) tunnel with an access controller (AC), receiving addresses of at least two gateways, establishing at least two GRE tunnels coupled to the gateways respectively according to the addresses of the at least two gateways, and selecting one of the at least two GRE tunnels to transmit data.

Method for implementing GRE tunnel, access point and gateway

A method for magnetic resonance imaging and plaque recognition includes: obtaining magnetic resonance undersampled K-space data; transforming the magnetic resonance undersampled K-space data to an image domain through inverse Fourier transform to obtain a preprocessed image; reconstructing the preprocessed image through a pre-established deep learning reconstruction model to obtain a high-resolution imaging image of a blood vessel wall; and recognizing plaques in the high-resolution imaging image of the blood vessel wall through a pre-established deep learning plaque recognition model. A neural network corresponding to the pre-established deep learning reconstruction model is a dense connection network. The magnetic resonance undersampled K-space data is head-and-neck combined magnetic resonance undersampled K-space data of the blood vessel wall.

Method and apparatus for magnetic resonance imaging and plaque recognition

Provided are a parallel magnetic resonance imaging method and apparatus based on adaptive joint sparse codes and a computer-readable medium. The method includes solving an l&#x2212;l&#x2212;lminimization objective, where the lnorm is a data fitting term, the lnorm is a sparse representation error, and the lmixed norm is the joint sparsity constraining across multiple channels; separately updating each of a sparse matrix, a dictionary and K-space data with a corresponding algorithm, and obtaining a reconstructed image by a sum of root mean squares of all the channels. The joint sparsity of the channels is developed using the norm l. In this manner, calibration is not required while information sparsity is developed. Moreover, the method is robust.

Adaptive joint sparse coding-based parallel magnetic resonance imaging method and apparatus and computer readable medium

The present disclosure relates to a 1D partial Fourier parallel magnetic resonance imaging method with a deep convolutional network and belongs to the technical field of magnetic resonance imaging. The method includes steps of: creating a sample set and a sample label set for training; constructing an initial deep convolutional network model; inputting a training sample of the sample set to the initial deep convolutional network model for forward process, comparing an output result of the forward process with an expected result in the sample label set, and performing training with a gradient descent method until a parameter of each layer which enables consistency between the output result and the expected result to be maximum is obtained; creating an optimal deep convolutional network model by using the obtained parameter of the each layer; and inputting a multi-coil undersampled image sampled online to the optimal deep convolutional network model, performing the forward process on the optimal deep convolutional network model, and outputting a reconstructed single-channel full-sampled image. The present disclosure can well remove the noise of the reconstructed image, reconstruct a magnetic resonance image with a better visual effect, and has high practical value.

One-dimensional partial Fourier parallel magnetic resonance imaging method based on deep convolutional network

A method for user detachment when a handover or change occurs in a heterogeneous network is provided. The method includes: a user equipment (UE) is handed over or switched from a source network to a target network; a network element on a network side determines whether to detach the UE from the source network, and if yes, the network element on the network side detaches the UE from the source network. A system and a device for user detachment when a handover or change occurs in a heterogeneous network, and another method for user detachment when a handover or change occurs in a heterogeneous network are also provided.

Method, system, and device for user detachment when a handover or change occurs in heterogeneous network

A method for implementing a GRE tunnel, an access point (AP), and a gateway (GW). The method includes: the AP receives a first packet, where the first packet carries an address of the GW; configures a GRE tunnel to the GW, where a source destination of the GRE tunnel is an address of the AP, and a destination address of the GRE tunnel is the address of the GW; the AP receives a second packet sent by user equipment; performs GRE tunnel encapsulation for the second packet to form a third packet; and the AP sends the third packet to the GW by using the GRE tunnel, where the third packet carries the address of the AP. The embodiments of the present application enable efficient establishment of the GRE tunnel between the AP and the GW if there are a large quantity of APs.

The present disclosure discloses an interactive method and apparatus in a live room. The method includes: receiving, from a live backstage, a live video stream sent by a first client; displaying a live interface on a display screen according to the live video stream; receiving, from the live backstage, an interactive video sent by a second client, the second client and the first client belong to a same live room, and the interactive video being a video whose video duration is less than a preset threshold; and playing, in picture-in-picture mode (PIP), the interactive video on a PIP area of the live interface.

Interactive method, apparatus, and system in live room

Embodiments of the present invention disclose an alarm information processing method, including: acquiring, by an EMS, a first alarm information set reported by a VNFM, where the first alarm information set is generated after the VNFM performs correlation analysis on at least one piece of NFVI alarm information and at least one piece of VIM alarm information; acquiring, by the EMS, a second alarm information set reported by a VNF, where the second alarm information set includes at least one piece of VNF alarm information; and performing, by the EMS, correlation analysis on the first alarm information set and the second alarm information set, and dispatching a configured work order for alarm information that has a correlation relationship. By using the present invention, a cross-layer association between alarm information can be implemented to reduce a quantity of work orders.

Alarm information processing method, related device, and system

A method for establishing data connections on a mobile network, a mobile network, and a policy control entity are disclosed. The method includes: establishing a data channel between a user equipment (UE) and a gateway (GW), and allocating an Internet Protocol (IP) address to the UE according to an address allocation request or a data channel setup request sent from the UE; and triggering the policy control entity to establish or update a policy control session according to the IP address. By using the mobile network and the policy control entity under the present disclosure, after the data channel is established between the UE and the GW, the GW may trigger the policy control entity to establish or update a policy control session.

Method for establishing data connection on mobile network, mobile network, and policy control entity

Growing community of inventors

Shanghai, China

Shanshan Wang