-
91.发明公开公开(公告)号：US20230386048A1
公开(公告)日：2023-11-30
申请号：US18366706
申请日：2023-08-08
Inventor： Yuxin SONG , Baoliang ZHAO , Ying HU , LONG LEI
IPC: G06T7/149
CPC classification number: G06T7/149 , G06T2207/10132 , G06T2207/20081 , G06T2207/10072
Abstract: The present disclosure relates to the field of image processing technologies, and provides an ultrasound image segmentation method and apparatus, a terminal device, and a storage medium. With the method, simulated ultrasound images are synthesized based on Computed Tomography (CT) images. An image segmentation model is pre-trained using the synthesized simulated ultrasound images. The pre-trained image segmentation model is migrated, by employing a transfer learning method, to real sample ultrasound images for further training to obtain a final image segmentation model. A segmentation processing on an ultrasound image to be segmented is completed by the final image segmentation model. In this way, the ultrasound images synthesized based on the CT images can be used to replace a part of training data, thereby solving a problem of lack of training data when training the image segmentation model.
-
92.发明公开公开(公告)号：US20230377758A1
公开(公告)日：2023-11-23
申请号：US18366704
申请日：2023-08-08
Inventor： Ying HU , Baoliang ZHAO , Long LEI , Huajie TANG
CPC classification number: G16H50/50 , G06T7/73 , G06T7/246 , G06T7/0012 , G06T2207/30096 , G06T2207/30241 , G06T2207/30204 , G06T2207/20081
Abstract: The present disclosure relates to the technical field of image processing and provides a motion estimation method and apparatus for a tumor, a terminal device, and a storage medium. The method includes: obtaining a current value of a respiratory correlation signal of a patient, the respiratory correlation signal reflecting a motion trajectory feature of a designated organ with the tumor of the patient in each of different respiratory states; inputting the current value of the respiratory correlation signal into a tumor motion estimation model to obtain an estimated current position of the tumor; and inputting the estimated current position of the tumor into an organ motion estimation model to obtain an estimated current velocity vector field of the designated organ. By adopting the motion estimation method, it realizes a respiratory motion estimation for the whole organ and enhance accuracy of positioning the tumor and vital anatomical structures around the tumor.
-
93.发明公开公开(公告)号：US20230343026A1
公开(公告)日：2023-10-26
申请号：US18026498
申请日：2021-01-08
Inventor： Shuqiang WANG , Bowen HU , Yanyan SHEN
CPC classification number: G06T17/00 , G06T9/002 , G06T19/20 , G06T2210/41 , G06T2219/2004
Abstract: A method and a device for a three-dimensional reconstruction of brain structure, and terminal equipment. The method includes steps of: obtaining a 2D image of a brain, inputting the 2D image of the brain into a 3D brain point-cloud reconstruction model that has been trained to be processed, and outputting a 3D point-cloud of the brain. The 3D brain point-cloud reconstruction model includes a ResNet encoder and a graphic convolutional neural network. The ResNet encoder is configured to extract a coding feature vector of the 2D image of the brain, and the graphic convolutional neural network is configured to construct the 3D point-cloud of the brain according to the coding feature vector.
-
94.发明公开公开(公告)号：US20230314377A1
公开(公告)日：2023-10-05
申请号：US18332697
申请日：2023-06-09
Inventor： Long MENG , Wei ZHOU , Hairong ZHENG , Lili NIU , Zhengrong LIN , Benxian PENG , Farooq UMAR , Yingjian CUI
CPC classification number: G01N29/022 , H03H9/25 , H03H9/02574 , H03H3/10
Abstract: The present invention discloses a real-time ultrasonic stimulation electric signal recording chip and a preparation method thereof, where the preparation method includes the following steps: S1 manufacturing an interdigital electrode on a piezoelectric substrate to obtain a surface acoustic wave chip, and manufacturing a recording electrode and an electrode lead; S2, manufacturing an insulation protection layer on the chip obtained in the S1, and processing the insulation protection layer to form the recording electrode, so as to obtain a chip combining the interdigital electrode and the recording electrode; S3, preparing a PDMS cavity; and S4, bonding the PDMS cavity prepared in the S3 and the chip obtained in the S2. In the present invention, combining the interdigital electrode generating a surface acoustic wave ultrasound with a multi-channel recording electrode, such that real-time recording of a multi-channel electric signal under ultrasonic stimulation is achieved.
-
公开(公告)号：US20230238857A1
公开(公告)日：2023-07-27
申请号：US17611808
申请日：2021-03-23
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY CHINESE ACADEMY OF SCIENCES , NATIONAL INSTITUTE OF ADVANCED MEDICAL DEVICES, SHENZHEN
Inventor： Tianfu SUN , Hairong ZHENG , Jianing LIANG , Linghui LONG , Fucheng JIANG , Huiyun LI , Liwen WAN , Long LI
Abstract: The present application disclosed a magnetic levitation system, and the magnetic levitation system includes a stator, a rotor, and a magnetic coupling mechanism; the stator includes a stator winding mechanism for controlling the rotor to move away from or close to the axis direction of the stator. The magnetic coupling mechanism includes magnetic sources, and the magnetic coupling mechanism is magnetically coupled with the rotor through the magnetic sources to drive the rotor to rotate around the axis direction of the stator. The magnetic levitation system decouples the magnetic circuit that drives the rotor to move from the magnetic circuit that drives the rotor to rotate, so as to reduce control difficulty, enhance stability, and reduce torque fluctuations.
-
Patent Agency Ranking
公开(公告)号：US20230100638A1
公开(公告)日：2023-03-30
申请号：US17277301
申请日：2021-02-05
Inventor： Zeyang XIA , Yangzhou GAN , Hao DENG , Jing XIONG
Abstract: A soft-bodied apparatus and a method for opening an eyelid are provided. The apparatus includes: a head support module, a real-time eyelid positioning module, a robot end-effector real-time positioning module, and an automatic eyelid opening operation module. The automatic eyelid opening operation module includes a robot body and a robot control system. The robot body is provided with a multi-axis rigid body mechanical arm and a soft-bodied end-effector. The robot control system takes the real-time poses of the upper and lower eyelids of the user as a motion target, and takes the real-time shape and the pose of the soft-bodied end-effector as feedback information to control motion of the robot body to automatically open the eyelid.
-
公开(公告)号：US20220414849A1
公开(公告)日：2022-12-29
申请号：US17779718
申请日：2019-11-25
Inventor： Shuqiang WANG , Senrong YOU , Yiqian LU , Shengye HU
Abstract: Disclosed by the present application are an image enhancement method and apparatus, a terminal device and a computer-readable storage medium. The image enhancement method comprises: obtaining an image to be processed; performing a wavelet transform operation on the image to obtain raw feature information of the image, the raw feature information comprising global contour feature information, transversal detail feature information, longitudinal detail feature information, and contrast detail feature information; inputting the raw feature information into a trained target network for processing to obtain corresponding reconstruction feature information, the reconstruction feature information comprising global contour reconstruction information, transversal detail reconstruction information, longitudinal detail reconstruction information, and contrast detail reconstruction information; performing an inverse wavelet transform operation on the reconstruction feature information to obtain a reconstructed image; the resolution of the reconstructed image is higher than the resolution of the image to be processed.
-
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：US20210342551A1
公开(公告)日：2021-11-04
申请号：US17367883
申请日：2021-07-06
Applicant: Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , Tencent Technology (Shenzhen) Company Limited
Inventor： Min Yang , Wei Bi , Xiao Jiang Liu , Lei Chen , Ting Ting Huang
Abstract: A method for training a dialog generation model includes: acquiring a dialog data set, and encoding a post in the dialog data set by using an encoder in the dialog generation model to obtain an encoded representation of the post; fusing, by using a decoder in the dialog generation model, the encoded representation of the post and knowledge information corresponding to the post that is obtained from a knowledge base question answering model through transfer learning to obtain a predicted response corresponding to the post; determining a value of a loss function of the dialog generation model based on the predicted response and the annotated response that correspond to the post; and updating a model parameter of the dialog generation model based on the value of the loss function. A method, an apparatus, a device, and a computer storage medium for generating a dialog are also provided.
-
公开(公告)号：US11004206B2
公开(公告)日：2021-05-11
申请号：US16490082
申请日：2017-03-21
Inventor： Wenchao Li , Ruizhen Hu , Hui Huang
Abstract: The present disclosure provides a three-dimensional shape expression method and device thereof. The method includes following steps: extracting a hybrid type framework of a three-dimensional shape; obtaining a segmentation of the three-dimensional shape by segmenting the hybrid type framework; obtaining a sub-structure of the three-dimensional shape according to the segmentation of the three-dimensional shape; and establishing an expression of the three-dimensional shape by using a bag-of-words model according to the sub-structure of the three-dimensional shape. The embodiments of the present disclosure are capable to express a three-dimensional shape with an easy and high-efficient method.
-
-
-
-
-
-
-
-
-
Search Results
147
records
(took 0.026 seconds)
