Diabetic retinopathy early detection method based on OCTA image texture analysis

A technology for early detection of diabetic retina, applied in the field of biomedical engineering

Inactive Publication Date: 2021-01-19
NINGBO UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Furthermore, in DR research, no studies have compared the features of texture features on OCT and OCTA images

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
  • Diabetic retinopathy early detection method based on OCTA image texture analysis
  • Diabetic retinopathy early detection method based on OCTA image texture analysis
  • Diabetic retinopathy early detection method based on OCTA image texture analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] Such as figure 1 , a method for early detection of diabetic retinopathy based on OCTA image texture analysis, the method is as follows:

[0041] (1) OCTA equipment was used to image the retinal blood vessels of the subjects, and OCTA images of 6 layers of structure were obtained for each study. The six-layer structure is NFLVP (nerve fiber layer vascular plexus, nerve fiber layer vascular layer), SVP (superficial vascular plexus, superficial retinal vascular layer), ICP (intermediate capillary plexus, intermediate capillary plexus), DCP (deep capillary plexus , deep capillary layer), SVC (superficial vascular complex, superficial vascular complex layer) and DVC (deep vascular complex, deep vascular complex layer). SVC consists of NFLVP and SVP. DVC consists of ICP and DCP.

[0042] (2) For each OCTA image, the image is normalized, ...

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 a diabetic retinopathy early detection method based on OCTA image texture analysis. The diabetic retinopathy early detection method comprises the following steps that (1) retinal vessels of a subject are imaged by using OCTA equipment to obtain an OCTA image; (2) normalization processing is carried out on each OCTA image, and each point value of the images are normalized toan interval [0, 1]; (3) noise reduction is carried out on the OCTA images through noise reduction processing; (4) texture characteristic parameters of the OCTA images are extracted; (5) characteristic parameters of a known sample are obtained through the step (4), and then difference and ROC analysis of the characteristic parameters in a control group are obtained through a mathematical statistics method to obtain a boundary value; and (6) characteristic parameters of unknown samples are obtained through the step (4) and compared with the boundary value in the step (5), and the unknown samples are classified according to comparison results. According to the diabetic retinopathy early detection method, the retinopathy condition of a diabetic patient can be quickly and accurately judged, and discomfort and trauma cannot be brought to the patient through a non-invasive method.

Description

technical field [0001] The invention relates to an early detection method for diabetic retinopathy based on OCTA image texture analysis, belonging to the field of biomedical engineering. Background technique [0002] Diabetic retinopathy (DR) is a common microvascular complication of diabetes and the leading cause of vision loss in patients. Since the invention of optical coherence tomography (OCT) at MIT in 1991, OCT has been widely used to diagnose eye diseases, including early DR diagnosis. However, OCT images cannot reveal the microvascular morphology of the eye. As a new OCT-based technique, optical coherence tomography angiography (OCTA) can image the microvasculature of the retina and choroid. OCTA works by detecting the laser reflectivity of red blood cells in motion to image blood flow to delineate blood vessels passing through different regions of the eye. Compared with the traditional gold standard method - fluorescein angiography, OCTA is a non-invasive and ra...

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 Applications(China)
IPC IPC(8): A61B3/10G06T5/00G06T7/00G06T7/41G06T7/90
CPCA61B3/102G06T7/0012G06T7/41G06T7/90G06T2207/10101G06T2207/30041G06T5/70
Inventor 高巍
Owner NINGBO UNIVERSITY OF TECHNOLOGY
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