A Quantitative Analysis Method of New Coronary Pneumonia Based on CT Image

A CT image and quantitative analysis technology, applied in the field of image processing, can solve problems such as inability to accurately and effectively judge, doctors unable to intuitively observe the location, size and changes of lesions, and insufficient analysis of lesions

Active Publication Date: 2022-08-09
JIAXING NO 1 HOSPITAL +1
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, the above method still has the following disadvantages: two-dimensional CT images are still used for identification, and the data processing of lesions is unreasonable, resulting in insufficient analysis of lesions. Judging whether it is new coronary pneumonia, let alone the condition trend of new crown patients

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Quantitative Analysis Method of New Coronary Pneumonia Based on CT Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] Example: as figure 1 As shown, it is only one of the embodiments of the present invention, a method for quantitative analysis of new coronary pneumonia based on CT images, comprising the following steps:

[0033] A method for quantitative analysis of new coronary pneumonia based on CT images, comprising the following steps:

[0034] S1: Build a machine learning model;

[0035] When step S1 is performed, a CT image database is established, and a machine learning model is established by keeping the boundary points of the preselected frame as floating-point numbers through ROI Align, and using bilinear interpolation during pooling.

[0036] The RoI Align proposed by Mask R-CNN makes pixel-level target segmentation possible. Compared with the traditional RoIPooling, the nearest neighbor sampling method is used for the pre-selection box and the boundary points are converted into integer values ​​during pooling. This method will cause misalignment problems. The ROI Align in...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention provides a quantitative analysis method based on CT image, involving the field of image processing technology, including the following steps: S1: Create a machine learning model; S2: Enter CT images for processing; S3: generate 3D lesion data, calculate new crown pneumoniaQuantitative factor; S4: Determine whether the quantification factor score is higher than the critical threshold; if it is a new crown patient, and execute the S5; otherwise, the patient does not suffer from new crown pneumonia; S5: Repeat S2 to S4, accumulating patients with CT image quantitative factor multiple times many times, Get the trend of the patient's condition.The quantitative analysis method based on CT image based on CT image is simple and convenient. The CT image is generated to generate 3D lesion data. By calculating and quantifying the lesion, doctors can intuitively observe information such as lesions, size, and changes.It can effectively judge whether the patient suffers from new crown pneumonia, and can further judge the trend system of new crown patients.

Description

technical field [0001] The invention relates to the technical field of image processing, [0002] In particular, the present invention relates to a method for quantitative analysis of new coronary pneumonia based on CT images. Background technique [0003] The novel coronavirus pneumonia virus is highly transmissible, has a long incubation period, and its performance on CT images is very similar to that of other common viral pneumonia. The screening of the new coronavirus in the population is under great pressure, so effective and rapid screening techniques are very necessary. [0004] Existing target detection methods for 2019-nCoV are usually based on two-dimensional images. Therefore, the input used for target detection in the field of medical images is generally two-dimensional slices of three-dimensional CT images. target (lesion area) for detection. As a result, only the two-dimensional features of the lesion area are used in the detection process, and its three-dime...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/13G06T7/181G06T7/62G06F16/51G06N20/00G16H30/20G16H50/20
CPCG06T7/0014G06T7/13G06T7/181G06T7/62G06F16/51G06N20/00G16H30/20G16H50/20G06T2207/10081G06T2207/30061
Inventor 姚明孙延豹陈文宇朱震宇李红文韩秀萍吴凡
Owner JIAXING NO 1 HOSPITAL
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap