Cardiovascular surgery index risk classification method and system based on retina image

A classification method and retinal technology, applied in blood vessel patterns, biological neural network models, instruments, etc., can solve the problems of retinal image feature interference, uneven light, and limit the number of potential participants, etc., to achieve high efficiency and scalability, The effect of improving generalization ability and good interpretability
CN113011340APending Publication Date: 2021-06-22SOUTH CHINA UNIV OF TECH +1
4 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SOUTH CHINA UNIV OF TECH
Publication Date
2021-06-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a cardiovascular surgery index risk classification method and system based on a retina image, and aims to solve the problems that an actual retina image is not clear and is inconsistent in exposure, and the like. The method comprises the steps: firstly, carrying out the preprocessing of contrast enhancement and blood vessel extraction on the retina image; data enhancement such as random rotation and translation is carried out on the extracted blood vessel map to increase the training amount of the data, so that the generalization ability of the model is improved; a two-stage supervised convolutional neural network model is designed for a classification task of a vascular map, so that not only can the features of retina images be learned, but also the correlation between the retina images is considered; a proper hidden layer node number is selected by adopting a localized generalization error, so that the generalization ability of the model is improved; in addition, the model also has the capability of generating a pixel-level fine-grained pixel-level saliency heat map, and has good interpretability.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical fields of image processing and image analysis, in particular to a method and system for risk classification of cardiovascular surgery indicators based on retinal images. Background technique

[0002] The number of people suffering from complex cardiovascular diseases is increasing every year. The evaluation of surgical indicators in patients with complex coronary heart disease is crucial for selecting the appropriate surgical approach, but there is still a lack of an accurate and interpretable method for preoperative assessment of surgical risk and prognosis. Vascular patterns in retinal images of patients with complex coronary artery disease can reflect cardiovascular severity, so retinal images can be used to predict risk classification for cardiovascular surgery indicators. Surgical index risk classification from retinal images is challenging due to limited retinal image data available to patients and ...

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