知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

720 records (took 0.018 seconds)

    Optical Imaging System for Elliptical Polarization Discrimination Utilizing Multi-Spectral Pixelated Statistical Parametric Mapping
    331.
    发明公开
    Optical Imaging System for Elliptical Polarization Discrimination Utilizing Multi-Spectral Pixelated Statistical Parametric Mapping 审中-公开

    公开(公告)号：US20240127580A1

    公开(公告)日：2024-04-18

    申请号：US18137814

    申请日：2023-04-21

    Applicant: Ronald B. LaComb ,  Lanette Rachel Marie LaComb

    Inventor： Ronald B. LaComb ,  Lanette Rachel Marie LaComb

    IPC: G06V10/764 ,  G01N21/47 ,  G01N33/483 ,  G06T7/00 ,  G06T11/00 ,  G06V10/143

    CPC classification number: G06V10/764 ,  G01N21/47 ,  G01N33/4833 ,  G06T7/0012 ,  G06T11/00 ,  G06V10/143 ,  G01N2021/4709 ,  G06T2207/10024 ,  G06T2207/30024 ,  G06V2201/03

    Abstract: The present disclosure relates to a methodology and apparatus to measure the Stokes parameters pertaining to back scattered light resulting from an array of incident light beams mapping out the possible polarization states represented by the Point Care' sphere creating a multi-dimensional pixelated grayscale parametric data set which is used for algorithm development to classify or characterize substrates for structural signatures expressible by multi-wavelength back-scattered polarized light, caused by changes to tissue or material morphology, structural anomalies, material grains, disease, stress, pressure or temperature gradients, or other phenomena affecting signatures of back-scattered polarized light which may be regionally or locationally dependent. The optical polarization imaging apparatus features spinning optical elements consisting of linear polarizers and optical retarders to sequentially produce an array of illumination polarization beams at various wavelengths which are directed onto a target, the back scattered light is filtered by an analyzing optical circuit, containing spinning and stationary polarizers and retarders, a digital camera captures a series of filtered images which can be used to calculate the four Stokes parameters on a pixel by pixel basis for each of the incident polarizations mapping out the Point Care' Sphere, forming a data set consisting of normalized gray scale images pertaining to the four Stokes Vectors for each incident polarization, with one complete data set per input wavelength. The data set can be used to express depth and regionally dependent polarization descriptors (degree of circular polarization, degree of linear polarization, degree of polarization, polarization visibility) or used as an input to a machine learning based algorithm for classification on a pixel or pixel bin basis which can be used for cancer diagnostics, tumor demarcation or structural characterization of materials. The classified data can be overlayed with pictorial data creating a classification mask registered to physical coordinates of the target. Illumination of the target with an array of incident polarizations at various wavelengths optimizes regional structural alignment with one or more incident polarizations maximizing optical signatures for that region, analysis based upon the complete data set enables assemblies of regionally and polarization dependent description which can lead to more accurate regional and global classification of the target.

    COMPUTER SUPPORTED REVIEW OF TUMORS IN HISTOLOGY IMAGES AND POST OPERATIVE TUMOR MARGIN ASSESSMENT
    334.
    发明公开
    COMPUTER SUPPORTED REVIEW OF TUMORS IN HISTOLOGY IMAGES AND POST OPERATIVE TUMOR MARGIN ASSESSMENT 审中-公开

    公开(公告)号：US20240119595A1

    公开(公告)日：2024-04-11

    申请号：US18543461

    申请日：2023-12-18

    Applicant: Leica Biosystems Imaging, Inc.

    Inventor： Walter Georgescu

    IPC: G06T7/00 ,  G06F18/214 ,  G06F18/24 ,  G06N3/08 ,  G06V10/94 ,  G06V20/69 ,  G16H30/40

    CPC classification number: G06T7/0012 ,  G06F18/2148 ,  G06F18/24 ,  G06N3/08 ,  G06V10/95 ,  G06V20/693 ,  G06V20/695 ,  G06V20/698 ,  G16H30/40 ,  G06F3/04842 ,  G06V2201/03

    Abstract: A computer apparatus and method for identifying and visualizing tumors in a histological image and measuring a tumor margin are provided. A CNN is used to classify pixels in the image according to whether they are determined to relate to nontumorous tissue, or one or more classes for tumorous tissue. Segmentation is carried out based on the CNN results to generate a mask that marks areas occupied by individual tumors. Summary statistics for each tumor are computed and supplied to a filter which edits the segmentation mask by filtering out tumors deemed to be insignificant. Optionally, the tumors that pass the filter may be ranked according to the summary statistics, for example in order of clinical relevance or by a sensible order of review for a pathologist. A visualization application can then display the histological image having regard to the segmentation mask, summary statistics and/or ranking. Tumor masses extracted by resection are painted with an ink to highlight its surface region. The CNN is trained to distinguish ink and no-ink tissue as well as tumor and no-tumor tissue. The CNN is applied to the histological image to generate an output image whose pixels are assigned to the tissue classes. Tumor margin status of the tissue section is determined by the presence or absence of tumor-and-ink classified pixels. Tumor margin involvement and tumor margin distance are determined by computing additional parameters based on classification-specified inter-pixel distance parameters.

Patent Agency Ranking