Patents by Inventor Xinjie SHEN

Xinjie SHEN has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12131474
    Abstract: The present disclosure is a three-way U-Net method for accurately segmenting an uncertain boundary of a retinal blood vessel, includes: describing an uncertainty of a blood vessel boundary label, constructing an upper bound and a lower bound of the uncertain boundary based on the dilation operator and the erosion operator respectively to obtain a maximum value and a minimum value for the blood vessel boundary, and mapping the boundary with uncertain information into one range; combining an uncertainty representation of the boundary with a loss function, and designing a three-way loss function; training network parameters by adopting a stochastic gradient descent algorithm and utilizing a total loss of the three-way loss function; and designing and implements an auxiliary diagnosis application system for intelligently segmenting the retinal blood vessel with functions of the fundus data acquisition, the intelligent accurate segmentation and the auxiliary diagnosis for the retinal blood vessel.
    Type: Grant
    Filed: May 24, 2023
    Date of Patent: October 29, 2024
    Assignee: NANTONG UNIVERSITY
    Inventors: Weiping Ding, Ying Sun, Tao Hou, Xinjie Shen, Hengrong Ju, Jiashuang Huang, Haipeng Wang, Tingzhen Qin, Yu Geng, Ming Li, Haowen Xue, Zhongyi Wang
  • Publication number: 20240289952
    Abstract: The present disclosure is a three-way U-Net method for accurately segmenting an uncertain boundary of a retinal blood vessel, includes: describing an uncertainty of a blood vessel boundary label, constructing an upper bound and a lower bound of the uncertain boundary based on the dilation operator and the erosion operator respectively to obtain a maximum value and a minimum value for the blood vessel boundary, and mapping the boundary with uncertain information into one range; combining an uncertainty representation of the boundary with a loss function, and designing a three-way loss function; training network parameters by adopting a stochastic gradient descent algorithm and utilizing a total loss of the three-way loss function; and designing and implements an auxiliary diagnosis application system for intelligently segmenting the retinal blood vessel with functions of the fundus data acquisition, the intelligent accurate segmentation and the auxiliary diagnosis for the retinal blood vessel.
    Type: Application
    Filed: May 24, 2023
    Publication date: August 29, 2024
    Applicant: NANTONG UNIVERSITY
    Inventors: Weiping DING, Ying SUN, Tao HOU, Xinjie SHEN, Hengrong JU, Jiashuang HUANG, Haipeng WANG, Tingzhen QIN, Yu GENG, Ming LI, Haowen XUE, Zhongyi WANG
  • Patent number: 11837329
    Abstract: A method for classifying multi-granularity breast cancer genes based on a double self-adaptive neighborhood radius includes large-scale gene locus data are read and normalized, and a data analysis is performed on the large-scale gene loci. An optimum value K is selected by adopting a combination of contour coefficients and a PCA dimensionality reduction visualization, and a model of information granulation is adjusted. A heuristic reduction algorithm is used to implement a multi-granularity attribute reduction of a self-adaptive neighborhood radius based on a cluster center distance and a multi-granularity attribute reduction of a neighborhood radius based on an attribute inclusion degree, and big data for breast cancer genes are classified and predicted by adopting a machine learning classification algorithm based on a SVM support vector machine.
    Type: Grant
    Filed: February 22, 2022
    Date of Patent: December 5, 2023
    Assignee: NANTONG UNIVERSITY
    Inventors: Weiping Ding, Yu Geng, Jialu Ding, Hengrong Ju, Jiashuang Huang, Chun Cheng, Ying Sun, Yi Zhang, Ming Li, Tingzhen Qin, Xinjie Shen, Haipeng Wang
  • Publication number: 20230197203
    Abstract: A method for classifying multi-granularity breast cancer genes based on a double self-adaptive neighborhood radius includes large-scale gene locus data are read and normalized, and a data analysis is performed on the large-scale gene loci. An optimum value K is selected by adopting a combination of contour coefficients and a PCA dimensionality reduction visualization, and a model of information granulation is adjusted. A heuristic reduction algorithm is used to implement a multi-granularity attribute reduction of a self-adaptive neighborhood radius based on a cluster center distance and a multi-granularity attribute reduction of a neighborhood radius based on an attribute inclusion degree, and big data for breast cancer genes are classified and predicted by adopting a machine learning classification algorithm based on a SVM support vector machine.
    Type: Application
    Filed: February 22, 2022
    Publication date: June 22, 2023
    Inventors: Weiping DING, Yu GENG, Hengrong JU, Jiashuang HUANG, Chun CHENG, Ying SUN, Yi ZHANG, Ming LI, Tingzhen QIN, Xinjie SHEN, Haipeng WANG
  • Patent number: 10795942
    Abstract: Provided are a method and device for residing a short message verification code. This method includes: conducting keyword matching on a short message content using a regular expression; when the short message content contains a keyword, matching a verification code for the short message content using the regular expression, to acquire a matched verification code; and displaying the verification code on a current interface and displaying a pre-set time. This method can automatically extract a verification code in a short message and display a pre-set time on a current interface. Within this pre-set time, a user can fill in a verification code on a verification code interface according to the displayed verification code without the need for the user to remember the verification code and to frequently switch between a short message application and a current application as well.
    Type: Grant
    Filed: April 20, 2015
    Date of Patent: October 6, 2020
    Assignee: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO LTD.
    Inventors: Dawei Geng, Xinji Shen
  • Publication number: 20170199941
    Abstract: Provided are a method and device for residing a short message verification code. This method includes: conducting keyword matching on a short message content using a regular expression; when the short message content contains a keyword, matching a verification code for the short message content using the regular expression, to acquire a matched verification code; and displaying the verification code on a current interface and displaying a pre-set time. This method can automatically extract a verification code in a short message and display a pre-set time on a current interface. Within this pre-set time, a user can fill in a verification code on a verification code interface according to the displayed verification code without the need for the user to remember the verification code and to frequently switch between a short message application and a current application as well.
    Type: Application
    Filed: April 20, 2015
    Publication date: July 13, 2017
    Inventors: Dawei Geng, Xinji Shen