Eye ground hard exudate segmentation method based on deep learning

A deep learning and exudate technology, applied in neural learning methods, image analysis, biological neural network models, etc., can solve problems such as time-consuming, labor-intensive, misdiagnosis and missed diagnosis, and achieve improved segmentation ability, improved detection ability, and improved The effect of recall

Pending Publication Date: 2022-03-04
HANGZHOU DIANZI UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large number of people who need to be tested, it is time-consuming and labor-intensive for doctors to

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
  • Eye ground hard exudate segmentation method based on deep learning
  • Eye ground hard exudate segmentation method based on deep learning
  • Eye ground hard exudate segmentation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Below, the present invention will be described in more detail according to the accompanying drawings and data sets. Whole flow chart of the present invention sees accompanying drawing figure 1 , including the following steps:

[0040] The fundus lesion detection method based on improved U-NET shown in the present invention can be realized by the following technical solutions:

[0041] Step 1. Take the dataset image containing fundus lesions as the original data sample, and perform data preprocessing on it;

[0042] Step 2. Professionals then manually mark the hard exudate lesions in the fundus image, so as to obtain the data set with annotation information required for training the network model, and divide the obtained data set into a training set and a test set ;

[0043] Step 3, input the training set obtained above into the improved Unet model, train the network parameters of the model, and obtain the hard exudate lesion detection model

[0044] Step 4. Input the ...

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 hard exudate segmentation method based on deep learning, which is characterized in that a double attention module is added on the basis of a traditional Unet model, so that important lesion areas can be concerned; more multi-scale fusion is added, and more feature and semantic information is extracted; finally, a pyramid type fusion mode is used, so that the improved model can effectively improve the detection capability on hard exudate; the invention provides a loss function based on Dice Loss improvement for the class imbalance problem of fundus hard exudate, and the loss function can improve the recall rate of target segmentation and the weight of error segmentation. The loss function is applied to the improved Unet model, so that the segmentation effect can be improved.

Description

technical field [0001] The invention relates to the field of deep learning image segmentation, in particular to a method for segmenting hard fundus exudates based on a multi-scale convolutional neural network. Background technique [0002] Diabetes is a common disease characterized by hyperglycemia, and retinopathy is a complication that is prone to occur after diabetes, and it is also one of the main lesions leading to blindness. Diabetic retinopathy presents clinically with microangiomas, exudates, and hemorrhagic areas. In order to prevent further development of fundus lesions, it is of great significance to detect retinopathy in advance. As a lesion of fundus hemorrhage, the detection of hard exudate is an important step in the detection of retinopathy. Due to the large number of people who need to be tested, it is time-consuming and labor-intensive for doctors to go through manual testing, and due to subjective factors, it is easy to lead to misdiagnosis and missed di...

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): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/08G06T2207/20081G06T2207/20084G06T2207/30041G06N3/045
Inventor 魏丹段梦杨方景龙王兴起
Owner HANGZHOU DIANZI UNIV
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