Patents
Literature
Eureka-AI is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Eureka AI

1260 results about "Computed tomography" patented technology

<ul><li>Normal results are when no abnormalities are found.</li><li>Abnormalities reported may include presence of tumors, fractures, blood clots etc.</li></ul>

Liver tumor segmentation method and device based on CT (Computed Tomography) image

The invention provides a liver tumor segmentation method and device based on a CT (Computed Tomography) image. The method comprises the following steps: performing Gaussian denoising on CT image data of a liver, converting the denoised CT image data into standardized data of which a gray average is 0 and a variance is 1, and performing down-sampling operation; extracting a lesion slice and a normal tissue slice from a gold standard image of the CT image of the liver, and classifying the lesion slice and the normal tissue slice into a positive sample and a negative sample; constructing a multi-level depth convolutional neural network, training a model through a stochastic gradient descent to obtain a network model, and acquiring a coarse segmentation binary image of a tumor and a pixel-classification probability image through a classifier; performing morphological erosion operation on the coarse segmentation binary image of the tumor to obtain a foreground image needed by graph cut, performing subtraction operation on the binary image of a liver and the coarse segmentation binary image of the tumor, and performing the morphological erosion operation to obtain a background image corresponding to normal tissues of the liver; and constructing an undirected graph, and obtaining a finial segmentation region of the tumor through a graph cut optimization algorithm.
Owner:SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI +1

High-resolution three-dimensional digital rock core modeling method

The invention discloses a high-resolution digital rock core modeling method. The high-resolution digital rock core modeling method comprises the following steps: firstly, scanning a rock core by X-ray CT (computed tomography); then acquiring the rock throat radius distribution from rock core mercury data, acquiring the rock core porosity radius distribution from rock core nuclear magnetism data, intercepting the part the pore throat radius of which is less than the CT scanning resolution as an input parameter of a random network method, wherein the selected intercepted value is relevant to the CT scanning resolution; comparing the digital rock core porosity obtained by CT scanning with the experiment measurement porosity, calculating the size of the lost porosity of the digital rock core by CT scanning, and constructing a porosity network model by utilizing the intercepted pore throat radius distribution by adopting the random network method, wherein the porosity of the generated network model is consistent with the porosity lost in CT scanning; and converting the porosity network model into the micro porosity digital rock core by applying gridding method, and overlapping the digital rock core constructed by a mercury injection nuclear magnetism method to the digital rock core scanned by CT by adopting a multi-scale integration method. The method breaks through the restriction of CT scanning resolution.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA) +1

Analysis method of corrosion action and corrosion effect of carbonate rock

The invention provides an analysis method of the corrosion action and the corrosion effect of a carbonate rock. The method comprises the following steps: detecting petrologic parameters, geological fluid characteristics and geological background parameters of a reservoir stratum of the carbonate rock; selecting a plunger sample, and preparing the plunger sample into a diagenetic fluid; performing weighing, physical property analysis, CT scan analysis and microscopic property analysis on the sample before experiment; performing a corrosion simulated experiment on the carbonate rock, and collecting the reaction generated liquid; performing the physical property analysis, the CT scan analysis and the microscopic property analysis on the sample after experiment; analyzing the content of Ca<2+> and Mg<2+> of the generated liquid; analyzing the corrosion action of the carbonate rock under different controlling factors, determining a three-dimensional structure and a microcosmic pattern of representation of a corrosion hole of the carbonate rock, and quantitatively assessing the corrosion hole of the carbonate rock and the communicated property evolution. By the method, the corrosion action and the corrosion benefits of the carbonate rock from an earth surface to the deep burying environment can be analyzed, and more accurate analytical data is provided for assessing and forecasting the favorable reservoir stratum of the carbonate rock.
Owner:PETROCHINA CO LTD

Nasopharyngeal-carcinoma (NPC) lesion automatic-segmentation method and nasopharyngeal-carcinoma lesion automatic-segmentation systems based on deep learning

The invention discloses a nasopharyngeal-carcinoma (NPC) lesion automatic-segmentation method and nasopharyngeal-carcinoma lesion automatic-segmentation systems based on deep learning. The method comprises: carrying out registration on a PET (Positron Emission Tomography) image and a CT (Computed Tomography) image of nasopharyngeal carcinoma to obtain a PET image and a CT image after registration;and inputting the PET image and the CT image after registration into a convolutional neural network to carry out feature representation and scores map reconstruction to obtain a nasopharyngeal-carcinoma lesion segmentation result graph. The method carries out registration on the PET image and the CT image of the nasopharyngeal carcinoma, obtains a nasopharyngeal-carcinoma lesion by automatic segmentation through the convolutional neural network, and is more objective and accurate as compared with manual segmentation manners of doctors; and the convolutional neural network in deep learning isadopted, consistency is better, feature learning ability is higher, the problems of dimension disasters, easy falling into a local optimum and the like are solved, lesion segmentation can be carried out on multi-modal images of the PET-CT images, and an application range is wider. The method can be widely applied to the field of medical image processing.
Owner:SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products