A retinal fundus image segmentation method based on a deep full convolutional neural network
A convolutional neural network and fundus image technology, applied in the field of medical image processing, can solve the problems of long time required, relatively sensitive selection, complex processing process, etc., and achieve the effect of ensuring segmentation accuracy, fast segmentation speed, and high processing effect.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0024] Embodiment 1: The present invention provides a method for segmenting retinal fundus images based on a deep full convolutional neural network. First, based on an existing algorithm, the optic disc region of the fundus image is located and extracted, and then the optic disc positioning region image is used as a deep full convolutional neural network. The input of the network is then used to predict the pixels in the input image using a deep fully convolutional neural network, and finally the corresponding cup-to-disk ratio is calculated through the obtained optic disc and optic cup segmentation results, such as figure 1 shown.
[0025] The method and technical effect of the present invention will be described below through specific examples.
[0026] Step 1: Use the fundus map dataset ORIGA as the training and test retinal fundus image set, which has a total of 650 left and right eye images of different objects. Among them, 325 images are used as training samples, and th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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