Automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images

A technology of optical coherence tomography and vulnerable plaque, which is applied in the field of image analysis and machine learning, can solve the problem of limited number of labeled samples, and achieve the effect of overcoming the limited number of samples and high recognition accuracy

Active Publication Date: 2021-11-02
UNIV OF JINAN
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the field of medical image analysis, the number of labeled samples is limited, which brings great challenges to the application of deep learning in medical image analysis.
[0005] At present, through investigation and research, it is found that there is no automatic recognition technology for vulnerable plaques in cardiovascular OCT images using artificial intelligence technology at home and abroad.

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
  • Automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images
  • Automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images
  • Automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Attached below figure 1 , attached figure 2 The present invention will be further described.

[0034] A method for automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images, comprising the steps of:

[0035] a) collecting cardiovascular OCT images;

[0036] b) standardize the cardiovascular OCT images;

[0037] c) Perform vulnerable plaque identification processing on the normalized image, and convert the OCT image (I∈R M×W ) is divided into vulnerable plaques and non-vulnerable plaques, and each column of OCT images (x∈R M ) is defined as a sample, thus forming a data set as:

[0038] S={(x i ,y i )|x i ∈R M ,y i ∈Y,i=1,...,N}

[0039] where K is the vector x i The corresponding class label, M is the height of the image, W is the width of the image, and the sample set is X={x i |i=1,...,N}, label set Y={y i |i=1,...,N,y i =1,...,K}, N is the total number of samples;

[0040] d) Construct a deep learning mo...

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

A method for automatically identifying vulnerable plaques in cardiovascular optical coherence tomography OCT images, comprising the following steps: a) collecting cardiovascular OCT images; b) performing standardized processing on cardiovascular OCT images; c) performing easy processing on the standardized processed images Lesion plaque recognition processing, d) using the stacked self-encoding method to construct a deep learning model for the sample set: e) classify and identify; f) use the bilinear interpolation method to convert the Cartesian coordinate system; g) convert the coordinate system The image is divided into quadrants; h) judging whether there are two or more connected regions in the same quadrant in the quadranted image. Combined with the characteristics of cardiovascular OCT images, the sample data set is reconstructed to overcome the problem of limited sample number. In addition, the learning model is often affected by the training set. The present invention randomly selects samples from the data set multiple times to train the learning model, and forms an integrated learning model through a voting strategy. A large number of experiments have proved that this technology can achieve high recognition accuracy.

Description

technical field [0001] The invention relates to the technical fields of image analysis and machine learning, in particular to a method for automatic identification of vulnerable plaques in cardiovascular optical coherence tomography OCT images. Background technique [0002] Cardiovascular disease is the main cause of morbidity and death. With the advancement of image analysis and machine learning technology, the diagnosis and treatment of cardiovascular disease have developed rapidly. Optical coherence tomography (Optical Coherence Tomography, OCT) is a new medical imaging technology, which has been widely used in clinic. This technology has also been applied in cardiovascular imaging. It can distinguish the structure of blood vessel walls, accurately display the characteristics of atherosclerotic plaques, and identify vulnerable plaques. It plays a very important role in the diagnosis, identification, treatment and evaluation of cardiovascular lesions. . [0003] Before i...

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): G06T7/00G06T7/136G06N20/20A61B5/00A61B5/02
CPCA61B5/0066A61B5/02007G06N3/084G06T7/0012G06T2207/10101G06T2207/30048G06T2207/30101
Inventor 牛四杰王栋徐荣彬商慧杰高鲲
Owner UNIV OF JINAN
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