A Method of Optic Cup and Disc Segmentation Based on Fundus Map Dataset Transfer Learning

A technology of transfer learning and graph data, applied in image data processing, ophthalmoscopy, image analysis, etc., can solve the problem of inability to accurately segment the optic cup and disc, and achieve the effect of improving the segmentation accuracy

Active Publication Date: 2022-04-08
NANKAI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that the existing automatic glaucoma screening algorithm cannot accurately segment the optic cup and optic disc during the migration process of the fundus map data set

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
  • A Method of Optic Cup and Disc Segmentation Based on Fundus Map Dataset Transfer Learning
  • A Method of Optic Cup and Disc Segmentation Based on Fundus Map Dataset Transfer Learning
  • A Method of Optic Cup and Disc Segmentation Based on Fundus Map Dataset Transfer Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] In order to explain in detail the technical content, structural features, achieved goals and effects of the technical solution, the following will be described in detail in conjunction with specific embodiments and accompanying drawings.

[0077] see figure 1 As shown, it is a flow chart of the cup-optic-disc segmentation method based on the transfer learning of the fundus image dataset. The specific implementation process of this embodiment is divided into 3 steps, and the specific steps are as follows.

[0078] Step 1. Fundus image data collection and data preprocessing

[0079] Collect public fundus map datasets as research datasets. Common ones are DRISHTI-GS, RIM-ONE v3 and REFUGE datasets.

[0080] DRISHTI-GS Fundus Map Dataset. The dataset was collected and labeled by Arvind Eye Hospital in India. It contains 101 color fundus images centered on the optic disc, with a viewing angle of 30° and a resolution of approximately 2047x1760. Among them, 50 fundus maps ...

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 belongs to the technical field of artificial intelligence, and in particular relates to a medical fundus map data set, in particular to an optic cup and optic disc segmentation method for transfer learning of the fundus map data set. Through the backbone segmentation network and the confrontation training of two domain discriminators, the method extracts the common features between the fundus image datasets, and uses the attention module to weight the features, which solves the problem of blurring the boundaries of the optic cup and disc, and excludes the rest. The interference of fundus lesions on segmentation tasks. On the premise of not using the labeling information of the target dataset, the algorithm maintains a high cup-optic disc segmentation accuracy during the transfer of the fundus map dataset, which effectively solves the limitation of the performance of traditional automatic glaucoma screening methods caused by insufficient fundus labeling data.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a medical fundus map data set, in particular to an optic cup and optic disc segmentation method for transfer learning of the fundus map data set. Background technique [0002] Glaucoma is the leading cause of blindness worldwide. The disease causes a defect in the fibers of the optic nerve, which can lead to irreversible visual damage. Therefore, early diagnosis and treatment are extremely critical for glaucoma patients. [0003] In clinical practice, the Cup-to-Disc Ratio (CDR), that is, the ratio of the vertical diameter (vertical diameter) of the optic cup (OC) to the optic disc (OD), is an important criterion for glaucoma screening. Important indicators. Glaucoma often results in a markedly increased cup-to-disk ratio due to damage to the optic nerve fibers. By analyzing the eye fundus image, doctors can accurately track the morphological chang...

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 Patents(China)
IPC IPC(8): G06T7/11G06T7/12A61B3/00A61B3/12A61B3/14
CPCG06T7/11G06T7/12A61B3/0025A61B3/12A61B3/14G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/30041
Inventor 袁晓洁张宇豪欧阳嘉伟蔡祥睿康宏张莹
Owner NANKAI 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