Method and system for segmenting corneal structures from oct corneal images

A corneal structure and image segmentation technology, applied in the field of biomedical images, can solve problems such as being unable to meet clinical real-time and accuracy requirements at the same time, weak signals on both sides of the cornea, and affecting doctors' real-time diagnosis.
CN108269258BActive Publication Date: 2020-07-24SHENZHEN INST OF ADVANCED TECH
4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN INST OF ADVANCED TECH
Publication Date
2020-07-24

Smart Images

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

Abstract

The invention provides a method and system for segmenting a cornea structure from an OCT (Optical Coherence Tomography) cornea image, and relates to the technical field of biomedical images. The method comprises the steps of scaling the OCT cornea image; determining the horizontal coordinate of the vertex of a cornea and the initial longitudinal coordinate of the vertex of each layer of the cornea; determining initial interfaces in a circle fitting mode; performing boundary expansion on the initial interface of each layer of the cornea according to the set neighborhood width to obtain annularregions of interest; obtaining rectangular regions of interest; respectively performing inverse processing of average grayscale difference processing and flattening processing on the rectangular regions of interest to obtain modified interfaces; respectively performing an Hough transform circle fitting operation on each modified interface based on a principle that the perpendicular bisector passesthe center of a circle to obtain the center and radius of each layer of the cornea; and respectively performing Kalman filtering of horizontal projectile motion on the modified interface of each layer of the cornea. The speed and accuracy of OCT cornea image for segmenting each layer of the cornea are improved according to the invention.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of biomedical images, in particular to a method and system for segmenting corneal structures from OCT corneal images. Background technique

[0002] Optical coherence tomography (OCT) is a non-destructive optical signal acquisition and processing method for imaging surface tissue structure. In recent years, OCT has become an important and innovative corneal measurement and diagnostic technique. Quantitative analysis of different layers of the cornea can help diagnose changes in visual function and help doctors diagnose corneal edema, ocular hypertension, and endothelial dysfunction, as well as corneal thickness analysis before and after refractive surgery. Therefore, under the premise of ensuring speed and accuracy, it is of great significance to segment different layers of the cornea to obtain thickness and curvature information.

[0003] However, the existing fully automatic corneal segmentation methods h...

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