Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SD-OCT image macular fovea centralis center positioning method

A center positioning and center position technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as failure and poor retinal robustness, and achieve the effect of improving accuracy and reducing labor.

Active Publication Date: 2019-10-25
NANJING UNIV OF SCI & TECH +2
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing technologies are mainly based on the convergence of the retinal layer structure and the thinning of the retinal thickness. These algorithms need to rely on multi-layer retinal layer segmentation algorithms, and these layer segmentation algorithms are less robust to retinal disease, especially in the In diseases such as retinal edema, the position of the center of the macular fovea will no longer be at the minimum value of retinal thickness, so these foveal algorithms will also fail

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
  • SD-OCT image macular fovea centralis center positioning method
  • SD-OCT image macular fovea centralis center positioning method
  • SD-OCT image macular fovea centralis center positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] The present invention takes SD-OCT retinal three-dimensional data as input, and uses a random forest classifier combined with clinical experience to locate the central fovea of ​​the SD-OCT retinal image.

[0056] In this embodiment, SD-OCT retinal volume data is collected by SD-OCT imaging equipment, and the pixel size of the three-dimensional data is 1024 pixels×512 pixels×128 pixels. In this embodiment, 700 SD-OCT volume data are collected, and 500 individual data are used as a training set to train a random forest model.

[0057] combine figure 2 , manually mark the position of the center of the macular fovea in the training data, as the gold standard, its position is recorded as O, and the avascular area is defined as a circular area with the center of the fovea O as the center and r0 = 0.25mm as the radius; O is the center of the circle, and a circular area with a radius of r1=0.15mm is used as the positive sample area, and the corresponding label value of this ...

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 SD-OCT image macular fovea centralis center positioning method. The method comprises the following steps: segmenting an inner boundary film layer and a Bloom film layer of an SD-OCT image; extracting each column of pixels between the inner boundary film layer and the Bloom film layer as features; training a random forest classifier to segment a fovea centralis non-vascular region, and calculating the geometric center position of the fovea centralis non-vascular region as the rough center position P1 of the macular fovea centralis; a retina thickness image is generated within a certain range with P1 as the center; judging whether the retina in the area is sunken or not, and if yes, taking the position at the minimum thickness value as a new foveal fovea central position P2; if not, the P2 is still the position of the P1; and searching a central concave high-reflection region around the position P2, if the high-reflection region exists, taking the central position of the high-reflection region as a final central concave central position P3, and otherwise, taking the P3 as the position P2. Compared with the conventional method for positioning only accordingto the thickness change of the retina, the robustness and the precision of the method are greatly improved.

Description

technical field [0001] The invention belongs to the field of retinal image analysis, in particular to a method for locating the center of the macular fovea in a frequency-domain optical coherence tomography (SD-OCT) image. Background technique [0002] SD-OCT is a rapid, non-invasive frequency-domain optical coherence tomography technique that has become part of the standard of care in ophthalmology. The macular area of ​​the retina is the main imaging area of ​​SD-OCT, and the center of the macular fovea is the most important marker of the macular area of ​​the retina, and it is the most sensitive area on the retina. Generating a thickness grid map based on the center of the macular fovea is an important tool for early treatment of retinopathy. Therefore, the positioning of the center of the macular fovea is a fundamental work of great significance. [0003] Existing technologies are mainly based on the convergence of the retinal layer structure and the thinning of the re...

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): G06K9/32A61B3/10A61B3/103G06K9/62G06T7/11
CPCA61B3/102A61B3/103G06T7/11G06T2207/10101G06T2207/30041G06V10/25G06F18/2411G06F18/214
Inventor 陈强李鸣超袁松涛李洪刚
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products