Unlock instant, AI-driven research and patent intelligence for your innovation.

Adversarial network generation method and fundus fluorescence contrast image non-perfusion area segmentation method

An angiographic image and network generation technology, which is applied in the field of image processing and can solve the problems of impaired retinal perfusion, blindness, and unstable permeability.

Pending Publication Date: 2021-05-28
SUZHOU UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the non-perfused area of ​​the retina, the fundus macula is in a state of ischemia and insufficient oxygen, and new blood vessels are prone to form near the non-perfused area. Because the permeability of the tube wall of the new blood vessels is extremely unstable, exudation and bleeding are prone to occur, resulting in the entire Vitreous hemorrhage, which can lead to blindness in severe cases
CNP is also present in cerebral malaria, causing impaired retinal perfusion due to sequestration of parasitic erythrocytes in retinal vessels

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
  • Adversarial network generation method and fundus fluorescence contrast image non-perfusion area segmentation method
  • Adversarial network generation method and fundus fluorescence contrast image non-perfusion area segmentation method
  • Adversarial network generation method and fundus fluorescence contrast image non-perfusion area segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0045] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" etc. The indicated orientation or positional relationship is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, ...

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 invention discloses an adversarial network generation method and a fundus fluorescence contrast image non-perfusion area segmentation method, and relates to the technical field of image processing, and the method comprises: obtaining a sample fundus fluorescence contrast image; inputting the sample fundus fluorescence contrast image into a generator to obtain an output segmentation result; inputting the output segmentation result and a real segmentation result corresponding to the sample fundus fluorescence contrast image into a discriminator to obtain a discrimination result, and forming an adversarial network by the generator and the discriminator; and training the generator and the discriminator according to the output segmentation result, the real segmentation result and the discrimination result, wherein the trained generator is used for segmenting the target fundus fluorescence contrast image. The effect of quickly and accurately segmenting the non-perfusion area of the fundus fluorescence contrast image through the neural network is achieved.

Description

technical field [0001] The invention relates to a method for generating an adversarial network and a method for segmenting non-perfusion areas of fundus fluorescein contrast images, and belongs to the technical field of image processing. Background technique [0002] Retinal capillary non-perfusion (Capillary Non-Perfusion, CNP) is one of diabetic retinal vascular lesions. Due to the complete occlusion of capillaries, blood stops flowing to certain areas of the retina, resulting in the generation of non-perfusion areas. In the non-perfused area of ​​the retina, the fundus macula is in a state of ischemia and insufficient oxygen, and new blood vessels are prone to form near the non-perfused area. Because the permeability of the tube wall of the new blood vessels is extremely unstable, exudation and bleeding are prone to occur, resulting in the entire Vitreous hemorrhage can lead to blindness in severe cases. CNP is also present in cerebral malaria, causing impaired retinal p...

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
IPC IPC(8): G06T7/10A61B3/12A61B3/14
CPCG06T7/10A61B3/12A61B3/14G06T2207/10064G06T2207/20081G06T2207/20084G06T2207/30041
Inventor 向德辉蔡木林田蓓
Owner SUZHOU UNIV