中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

22 records (took 0.021 seconds)

    IMAGE QUALITY IMPROVEMENT METHODS FOR OPTICAL COHERENCE TOMOGRAPHY
    11.
    发明申请
    IMAGE QUALITY IMPROVEMENT METHODS FOR OPTICAL COHERENCE TOMOGRAPHY 有权

    公开(公告)号：US20220130021A1

    公开(公告)日：2022-04-28

    申请号：US17647527

    申请日：2022-01-10

    Applicant: Topcon Corporation

    Inventor： Zaixing Mao ,  Zhenguo Wang ,  Kinpui Chan

    IPC: G06T5/00 ,  G06T5/50

    Abstract: Ophthalmological images generated by coherent imaging modalities have multiple types of noise, including random noise caused by the imaging system and speckle noise caused by turbid objects such as living tissues. These noises can occur at different levels in different locations. A noise-reduction method and system of the present disclosure thus relates to applying different filters for different types of noise and/or different locations of images, sequentially or in parallel and combined, to produce a final noise-reduced image.

    3D quantitative analysis with deep learning
    12.
    发明授权
    3D quantitative analysis with deep learning 有权

    公开(公告)号：US11302006B2

    公开(公告)日：2022-04-12

    申请号：US17103058

    申请日：2020-11-24

    Applicant: Topcon Corporation

    Inventor： Zaixing Mao ,  Zhenguo Wang ,  Kinpui Chan ,  Yasufumi Fukuma

    IPC: G06T7/00 ,  G06N20/00 ,  G06N7/00

    Abstract: A machine learning model is trained to identify the texture difference between the different layers of a multilayer object. By training with data in full 3D space, the resulting model is capable of predicting the probability that each pixel in a 3D image belongs to a certain layer. With the resulting probability map, comparing probabilities allows one to determine boundaries between layers, and/or other properties and useful information such as volume data.

    Image quality improvement methods for optical coherence tomography
    13.
    发明授权
    Image quality improvement methods for optical coherence tomography 有权

    公开(公告)号：US11257190B2

    公开(公告)日：2022-02-22

    申请号：US16797848

    申请日：2020-02-21

    Applicant: Topcon Corporation

    Inventor： Zaixing Mao ,  Zhenguo Wang ,  Kinpui Chan

    IPC: G06T5/00 ,  G06T5/50

    Abstract: Ophthalmological images generated by coherent imaging modalities have multiple types of noise, including random noise caused by the imaging system and speckle noise caused by turbid objects such as living tissues. These noises can occur at different levels in different locations. A noise-reduction method and system of the present disclosure thus relates to applying different filters for different types of noise and/or different locations of images, sequentially or in parallel and combined, to produce a final noise-reduced image.

    Method and apparatus for low coherence interferometry
    17.
    发明授权
    Method and apparatus for low coherence interferometry 有权

    公开(公告)号：US11751762B2

    公开(公告)日：2023-09-12

    申请号：US16719305

    申请日：2019-12-18

    Applicant: Topcon Corporation

    Inventor： Jongsik Kim ,  Ying Dong ,  Song Mei ,  Kinpui Chan ,  Zhenguo Wang ,  Zaixing Mao

    IPC: A61B3/10 ,  A61B3/14 ,  A61B3/12 ,  G01N21/17

    CPC classification number: A61B3/102 ,  A61B3/1225 ,  A61B3/14 ,  G01N21/17 ,  G01N2021/1787

    Abstract: A low coherence imaging method comprises acquiring image data of an object with an interferometric imaging system, where the image data is from a location of the object at first and second times; determining a first depth profile from the image data from the location at the first time and a second depth profile from the image data of the location at the second time; determining a change with respect to depth between the first and second depth profiles; and determining a property, or identifying a location, of at least one dynamic particle in the object based on the change between the first and second depth profiles. The method is able to identify, analyze, and/or visualize dynamic particles with features comparable to at least fluorescein angiography, indocyanine green angiography, confocal scanning laser fluorescein angiography, confocal scanning laser indocyanine green angiography, and fluorescence microscopy images, without the use of a dye.

    3D QUANTITATIVE ANALYSIS WITH DEEP LEARNING
    20.
    发明申请
    3D QUANTITATIVE ANALYSIS WITH DEEP LEARNING 有权

    公开(公告)号：US20210082116A1

    公开(公告)日：2021-03-18

    申请号：US17103058

    申请日：2020-11-24

    Applicant: Topcon Corporation

    Inventor： Zaixing Mao ,  Zhenguo Wang ,  Kinpui Chan ,  Yasufumi Fukuma

    IPC: G06T7/00 ,  G06N20/00 ,  G06N7/00

    Abstract: A machine learning model is trained to identify the texture difference between the different layers of a multilayer object. By training with data in full 3D space, the resulting model is capable of predicting the probability that each pixel in a 3D image belongs to a certain layer. With the resulting probability map, comparing probabilities allows one to determine boundaries between layers, and/or other properties and useful information such as volume data.

Patent Agency Ranking