Fundus image focus segmentation and quantitative analysis method based on data enhancement

A fundus image and quantitative analysis technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of inability to match and verify images and results, unfavorable lesion area and distribution state, low precision, etc., to avoid deviation from the boundary, Improved operational stability and improved accuracy

Pending Publication Date: 2021-03-09
山东承势电子科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in some image lesion segmentation and analysis methods, most of them are directly viewed and compared through ultrasound images, which is not conducive to controlling the area a

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0034] A method for segmentation and quantitative analysis of fundus image lesions based on data enhancement, the method includes the following steps:

[0035] P1. Obtain medical image data and perform preprocessing;

[0036] P2. Extract the preprocessed image data to obtain fundus lesion images;

[0037] P3. Establish a calculation model based on the lesion image;

[0038] P4. Predict the lesion area on the medical imaging data based on the computational model;

[0039] P5. Count the boundaries of the lesion area at each parallel level, calculate the area of ​​the lesion, and combine to obtain the volume of the les...

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 fundus image focus segmentation and quantitative analysis method based on data enhancement, and the method comprises the steps: P1, obtaining medical image data, and carryingout the preprocessing; P2, extracting the preprocessed image data to obtain a fundus focus image; P3, establishing a calculation model based on the focus image; P4, predicting a focus area on the medical image data based on the calculation model; P5, counting the boundary of the lesion area of each parallel layer, calculating the lesion area, and combining to obtain the lesion volume; P6, substituting the focus volume into the fundus image, inputting the fundus image into the training model, and training to obtain a focus segmentation model; P7, performing manual segmentation on the segmentation model, and meanwhile, performing automatic segmentation through a model contour to obtain two true value tags; and P8, performing quantitative analysis through true value label comparison results,boundary deviation is avoided, side effects are reduced, cross validation is carried out finally, safety and accuracy are guaranteed, operation stability is improved, and application and popularization are facilitated.

Description

technical field [0001] The present invention relates to the technical field of lesion segmentation and analysis, in particular to a data enhancement-based fundus image lesion segmentation and quantitative analysis method. Background technique [0002] In the medical system, the use of computers and imaging equipment for image acquisition and segmentation can effectively control the results of lesion judgment and improve treatment effects. [0003] However, in some image lesion segmentation and analysis methods, most of them are directly viewed and compared through ultrasound images, which is not conducive to controlling the area and distribution of lesions, and the accuracy is low, and it is not possible to verify the matching of images and results. Image quantitative analysis accuracy, to be proposed a new method. Contents of the invention [0004] The purpose of the present invention is to solve the shortcomings in the prior art, and propose a method for segmentation an...

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): G06T7/11G06T7/194G06T7/00G06T7/62G06K9/62G06N3/04G06N3/08
CPCG06T7/11G06T7/194G06T7/0012G06T7/62G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30041G06V10/751G06N3/045G06F18/241
Inventor 齐泽荣付树军胡迈胡明征张辂刘振王红李卫国廖胜海张波
Owner 山东承势电子科技有限公司
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