Cerebrovascular image segmentation method based on semi-supervised learning

A semi-supervised learning and image segmentation technology, applied in the fields of artificial intelligence and medical image processing, it can solve the problems of relying on professional knowledge and experience, the structure of cerebrovascular vessels is delicate and complex, and the cost of segmenting cerebrovascular vessels is high, and achieves the effect of improving segmentation performance.

Pending Publication Date: 2021-08-13
ZHEJIANG UNIV OF TECH
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, due to the special location and complex structure of the cerebral blood vessels, it takes a lot of time and energy for professional doctors to obtain well-labeled training data, and it relies heavily on professional knowledge and experience, so there are a lot of subjective differences.
Therefore, it is expensive to obtain a large amount of labeled data to carry out deep learning research to segment cerebrovascular, and a large amount of unlabeled data has not been well applied, which does not meet the urgent needs of actual clinical applications.

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
  • Cerebrovascular image segmentation method based on semi-supervised learning
  • Cerebrovascular image segmentation method based on semi-supervised learning
  • Cerebrovascular image segmentation method based on semi-supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further explained below in conjunction with specific implementation and accompanying drawings.

[0039] refer to figure 1 and figure 2 , a cerebrovascular image segmentation method based on semi-supervised learning, can solve the difficulty of network training requiring a large number of manual annotations, and effectively utilize unlabeled data.

[0040] The cerebrovascular image segmentation method based on semi-supervised learning comprises the following steps:

[0041] Step 1 data preparation, the process is as follows:

[0042] The cerebrovascular system accounts for a small proportion in the intracranial volume. In order to eliminate the interference of irrelevant background areas (non-vascular areas), the present invention reduces the calculation burden caused by invalid areas in the data and speeds up the processing speed of the model...

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 cerebrovascular image segmentation method based on semi-supervised learning, which adjusts the weight of unlabeled data consistency loss through a region connectivity model, and reduces the unreliability and noise effect of a teacher model, on the basis of the regional connectivity, a student model can more reliably learn from the teacher model step by step. According to the method, the difficulty that network training needs a large amount of manual annotation is solved, the unannotated data is effectively utilized, and the segmentation performance is well improved.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and medical image processing, and is a method for segmenting cerebrovascular images based on semi-supervised learning. Background technique [0002] In recent years, cerebrovascular disease has seriously threatened human life and health, and it has become one of the diseases with a very high fatality rate in neurosurgery. In the actual clinical environment, it is very important to quickly and accurately grasp the spatial structure information of the patient's cerebral blood vessels for the diagnosis and treatment of the disease. The existing methods for segmenting and reconstructing cerebral vessels can be divided into two categories, one is the traditional semi-automatic segmentation methods, such as threshold method, tracking-based method, cluster-based method and model-based segmentation method, etc. Learning is a representative, artificial intelligence-based segmentation algorithm. Du...

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): G06T7/11G06N3/04G06N3/08G06T7/187
CPCG06T7/11G06T7/187G06N3/08G06N3/04G06T2207/30016G06T2207/30101
Inventor 谢雷冯远静罗康黄家浩袁少楠陆星州曾庆润
Owner ZHEJIANG UNIV OF TECH
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