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

U-shaped network and segmentation method of nerve fibers in cornea image

A nerve fiber and network technology, applied in the field of image processing, can solve problems such as inability to segment nerve fibers, reduce segmentation accuracy, interference, etc., achieve low contrast, reduce the amount of parameters, and output reliable results

Pending Publication Date: 2020-06-23
SUZHOU UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional corneal nerve image segmentation methods cannot segment nerve fibers well
For example, the presence of corneal cells in nerve fiber images may be a disturbance; in addition, for diseased corneas, abnormal areas in corneal nerve images may reduce its segmentation accuracy, and the segmentation of thin nerve fibers is also a great challenge

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
  • U-shaped network and segmentation method of nerve fibers in cornea image
  • U-shaped network and segmentation method of nerve fibers in cornea image
  • U-shaped network and segmentation method of nerve fibers in cornea image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0027] In the description of the present invention, it should be understood that the terms "first", "second" and so on are only used for descriptive purposes, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features . Thus, a feature defined as "first", "second", etc. may expressly or implicitly include one or more of that feature.

[0028] Such as figure 1 As shown, the U-shaped network provided by the embodiment of the present invention is an encoder-decoder structure with a symmetrical cross-layer connection. From the image data input end, the encoder has 4 layers in total, and each layer of the first 3 lay...

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 U-shaped network and a segmentation method of nerve fibers in a cornea image, the U-shaped network comprises four layers of encoders and decoders, and the encoders and the decoders are symmetrically connected in a cross-layer manner; a multi-scale separation and fusion module is added after the upsampling operation of the decoder part; according to the U-shaped network, the parameter quantity is reduced, the receptive field is increased, and the segmentation performance is improved; the segmentation method adopts the trained U-shaped network, and the loss function adopts the combination of the fiber length difference between the prediction graph and the gold standard and the Dice loss to jointly constrain the U-shaped network. According to the method, fine cornealnerve fibers can be accurately segmented, and the segmentation precision of the corneal nerve fibers is improved.

Description

technical field [0001] The invention relates to a U-shaped network and a method for segmenting nerve fibers in corneal images, belonging to the technical field of image processing. Background technique [0002] The segmentation and analysis of corneal nerve images has attracted more and more attention. These images obtained by confocal microscopy of the cornea can document changes in the corneal nerves. Corneal injury and corneal disease are often associated with changes in corneal nerve fibers. Segmentation of nerve fibers provides useful information for the quantitative analysis of postoperative regeneration and repair of corneal injury, the effects of long-term wearing of contact lenses, and different degrees of diabetic peripheral neuropathy. [0003] Traditional corneal nerve image segmentation methods cannot segment nerve fibers well. For example, the existence of corneal cells in nerve fiber images may be a disturbance; in addition, for diseased corneas, abnormal a...

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): G06T7/11G06T7/136G06T5/00G06T3/00G06N3/08G06N3/04
CPCG06T7/11G06T7/136G06N3/08G06T2207/30041G06N3/045G06T3/02G06T5/70Y02P90/30
Inventor 陈新建石霏周鑫鑫朱伟芳
Owner SUZHOU UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com