Crystalline lens segmentation method and device and storage medium

A lens and image segmentation technology, applied in the field of image analysis, can solve problems such as large amount of calculation, long algorithm operation time, stability and precision dependence, etc., to avoid poor robustness, improve segmentation efficiency, stability and precision improvement Effect

Active Publication Date: 2020-05-29
CIXI INST OF BIOMEDICAL ENG NINGBO INST OF MATERIALS TECH & ENG CHINESE ACAD OF SCI +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires pre-training to obtain U-shaped fully convolutional neural network models and shape templates. The stability and accuracy depend on the training results, and the calculation load is large and the algorithm operation time is long.

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
  • Crystalline lens segmentation method and device and storage medium
  • Crystalline lens segmentation method and device and storage medium
  • Crystalline lens segmentation method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A lens segmentation method, comprising: acquiring an ROI image including a lens from an original image; judging the difficulty of image segmentation based on the ROI image, and acquiring a lens segmentation result through a real-time segmentation network based on the ROI image. The target area is extracted through the preprocessing algorithm, which greatly reduces the size of the image to be segmented, reduces the interference of redundant information, and reduces the calculation load of the segmentation network algorithm. In the process of judging the difficulty of image segmentation and obtaining the results of lens segmentation, a real-time segmentation network using ShuffleNet for encoding and SkipNet for decoding is used. In actual application scenarios, due to lens structure lesions, or intraocular lens, etc., the captured AS-OCT images may have missing or non-existent lens structures, which will affect the structure segmentation. Therefore, in this embodiment, be...

Embodiment 2

[0058] A lens segmentation system that consists of four parts:

[0059] Whether it can be segmented or not is a judging module, which is used to determine whether the input original image can be segmented or not. Judge whether the input AS-OCT original image can be segmented. This module corresponds to Step 1 of Embodiment 1 and can be used to implement Step 1 of Embodiment 1.

[0060] The ROI image extraction module is used to obtain the ROI image containing the lens from the original image. Find the boundary of the lens area in the original image, and obtain the ROI image containing the lens. This module corresponds to Step 2 of Embodiment 1, and can be used to implement Step 2 of Embodiment 1.

[0061] The segmentation difficulty classification module judges the difficulty of image segmentation based on the input ROI image. The ROI image output by the ROI image extraction module is used as input to judge the segmentation difficulty level of the image. This module corre...

Embodiment 3

[0064] A computer-readable storage medium includes computer-readable instructions. When a processor reads and executes the computer-readable instructions, the processor performs the operations described in Embodiment 1.

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 relates to the technical field of image analysis, in particular to a crystalline lens segmentation method and device and a storage medium. The method comprises the following steps: acquiring an ROI image containing a crystalline lens from an original image; and judging the image segmentation difficulty based on the ROI image, and obtaining a crystalline lens segmentation result through a real-time segmentation network based on the ROI image. The target area is extracted through the preprocessing algorithm, the size of the to-be-segmented image is greatly reduced, interference ofredundant information is reduced, and the calculated amount of the segmentation network algorithm is reduced.

Description

technical field [0001] The invention relates to the technical field of image analysis, in particular to a lens segmentation method, device and storage medium. Background technique [0002] Cataract is a disease that causes vision loss due to the denaturation of the protein in the lens of the eye, resulting in clouding of the lens. [0003] Anterior Segment Optical Coherence Tomography (AS-OCT) is a non-invasive, high-resolution anterior segment imaging technique that is often used to assist in the diagnosis of ophthalmic diseases, such as cataracts and glaucoma. Lens density is an important index to measure the severity of cataract and other diseases, and the segmentation of lens structure is an important basis and prerequisite for the calculation of lens density. At present, the lens opacities classification system (Lens Opacities Classification System III, LOCS III) classification standard is used internationally to classify living cataracts to determine the scope and deg...

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): G06T7/11G06T7/13G16H50/20
CPCG06T7/11G06T7/13G16H50/20G06T2207/30041
Inventor 曹桂平刘江
Owner CIXI INST OF BIOMEDICAL ENG NINGBO INST OF MATERIALS TECH & ENG CHINESE ACAD OF SCI
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