Intracranial aneurysm area automatic detection system and method for CTA image

A technology for automatic detection of intracranial aneurysms, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of small proportion of CTA area, small area proportion, large background noise, etc., to reduce overfitting the possible effect of

Pending Publication Date: 2020-07-24
JILIN UNIV
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on the above technical problems, the present invention designs and develops an automatic detection system for intracranial aneurysm regions in CTA images. The problem of too little
[0007] The present invention designs and develops a method for automatic detection of intracranial aneurysm regions on CTA images. The ...

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
  • Intracranial aneurysm area automatic detection system and method for CTA image
  • Intracranial aneurysm area automatic detection system and method for CTA image
  • Intracranial aneurysm area automatic detection system and method for CTA image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0103] Using the network model 2D U-net, 3D U-net and the loss function Tversky index loss to realize the detection and segmentation of intracranial aneurysms, in order to reduce the time cost of manual labeling and screening.

[0104] It specifically includes: data enhancement module, used to solve the problem of less initial training sample data; suspected area preselection module, used to segment suspected lesion areas on the original image to solve the problem of excessive sample background noise; fine target detection module, used It is used to locate the position of the intracranial aneurysm and segment the area where the intracranial aneurysm is located; the multi-dimensional fusion module is used to fuse the three-dimensional spatial information of the intracranial aneurysm to achieve more accurate segmentation; the incremental training module is used for the new CTA images are trained to continuously improve the accuracy of automatic detection devices.

[0105] The pr...

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 an intracranial aneurysm area automatic detection system and a detection method for a CTA image. The system comprises: a data enhancement module which is used for carrying outenhancement treatment on collected CTA image data; a suspected area pre-selection module used for carrying out model training on the enhanced CTA image data and determining central coordinates of a suspected area; a fine target detection module used for cutting an original image according to the center coordinates, then carrying out model training, and marking the area where the intracranial aneurysm is located on the original image; a multi-dimensional fusion module used for cutting a three-dimensional image according to the center coordinates, then carrying out model training, marking the area where the intracranial aneurysm is located on the three-dimensional image, and marking the area where the intracranial aneurysm is located on the original image in combination with a fine target detection result; and an incremental training module used for acquiring a newly added CTA image and re-determining the area where the intracranial aneurysm is located.

Description

technical field [0001] The invention relates to the field of auxiliary medical devices, in particular to an automatic detection system and detection method for an intracranial aneurysm region for CTA images. Background technique [0002] Intracranial aneurysm is the main cause of non-traumatic subarachnoid hemorrhage. Brain cell damage and vasospasm caused by rupture and hemorrhage will lead to high disability and high mortality. Intracranial aneurysms are estimated to affect about 3% of adults and are extremely difficult to diagnose when the tumor has not ruptured. Studies have shown that the cause of intracranial aneurysm rupture is closely related to the location and size of the intracranial aneurysm. Therefore, an accurate detection method is an effective means to reduce the risk of intracranial aneurysm rupture at this stage. Traditional intracranial aneurysm detection methods rely on manual screening and manual labeling. This method not only requires high human capi...

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): G06T7/11G06T5/50
CPCG06T7/11G06T5/50G06T2207/20081G06T2207/10081Y02T10/40
Inventor 吴春国白烁彤黄萨梁艳春
Owner JILIN 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