Arterial blood vessel image model train method, segmentation method, device and electronic device

An arterial blood vessel and image segmentation technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of image segmentation interference, large gap in diagnosis results, low blood vessel definition, etc., and achieve the goal of reducing image noise interference Effect

Inactive Publication Date: 2018-12-25
ZHONGAN INFORMATION TECH SERVICES CO LTD +1
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Subtle object segmentation differences may lead to large gaps in diagnostic results
Moreover, the arterial vessels and their structures are complex, especially the brain vessels have many fine capillaries, and the traditional methods cannot extract blood vessel targets well.
[0005] In addition, there is a certain degree of difference in the equipment, data format, and picture quality of different medical imag

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
  • Arterial blood vessel image model train method, segmentation method, device and electronic device
  • Arterial blood vessel image model train method, segmentation method, device and electronic device
  • Arterial blood vessel image model train method, segmentation method, device and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] figure 1 It is a flow chart of the method for training an arterial blood vessel image segmentation model provided in Embodiment 1 of the present invention. The method can be executed by a training device for an arterial blood vessel image segmentation model, and the device can be implemented in a software / hardware manner. Such as figure 1 As shown, the method specifically includes:

[0087] S1. Preprocessing the acquired DSA images to build an arterial image library.

[0088] S2. Label some sample images in the arterial vessel image database to construct a set of labeled sample images. Wherein, the labeled sample image set includes sample images and labeled images corresponding to the sample images.

[0089] S3. Constructing a deep convolutional network and setting parameters of the deep network to generate an initial artery segmentation model.

[0090] S4. Using the labeled sample image set to train an initial arterial vessel segmentation model to generate an arter...

Embodiment 2

[0158] Based on the arterial blood vessel image segmentation model trained in the first embodiment, the embodiment of the present invention also provides an arterial blood vessel image segmentation method, which can implement the subtraction method by using a pre-trained arterial blood vessel image segmentation model. Fast and accurate segmentation and extraction of arteries in angiography (DSA) medical images.

[0159] Figure 12 It is a flow chart of the method for segmenting arterial blood vessel images provided in Embodiment 2 of the present invention. The method may be executed by an apparatus for segmenting arterial blood vessel images, and the apparatus may be implemented in a software / hardware manner. Such as Figure 12 As shown, the method specifically includes:

[0160] A1. Obtain the DSA image to be processed.

[0161] Specifically, for the process of acquiring the DSA image to be processed, reference may be made to step S11 in Embodiment 1, which will not be rep...

Embodiment 3

[0169] As the realization of the arterial blood vessel image segmentation model training method in the first embodiment, the embodiment of the present invention also provides an arterial blood vessel image segmentation model training device, refer to Figure 14 As shown, the device includes:

[0170] A preprocessing unit 141, configured to preprocess the acquired DSA images to construct an arterial image library;

[0171] The first labeling unit 142 is configured to label some sample images in the arterial vessel image library to construct a set of labeled sample images;

[0172] The first training unit 143 is used to construct a convolutional deep network, and set deep network parameters to generate an initial arterial vessel segmentation model;

[0173] The second training unit 144 is configured to use the labeled sample image set to train the initial arterial vessel segmentation model to generate an arterial vessel image segmentation model;

[0174] The second labeling un...

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 artery blood vessel image model training method, a segmentation method, a device and an electronic device, belonging to the technical field of digital image processing. Theartery blood vessel image model training method comprises the following steps: 1, pre-processing the acquired DSA image to construct an artery blood vessel image database; 2, labeling part of the sample images in the arterial blood vessel image library to construct a labeled sample image set; 3, constructing a convolution depth network and setting parameter of that depth network to generate an initial artery blood vessel segmentation model; 4, training an initial artery blood vessel segmentation model by using a label sample image set to generate an artery blood vessel image segmentation model; 5, further labeling the blood vessel target image obtained by using the artery blood vessel image segmentation model to segment other images except part of the sample images in the artery blood vessel image library, so as to carry out iterative training on the artery blood vessel image segmentation model. The embodiment of the invention can extract target blood vessels from DSA images with highaccuracy.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to an arterial blood vessel image model training method, segmentation method, device and electronic equipment. Background technique [0002] With the promulgation of the national "White Paper on Medical Artificial Intelligence Technology and Application" and more than 80 related national bonus policies, the application of the combination of artificial intelligence and medical treatment has good development opportunities. At present, there is a large imbalance between medical resources and demand in China, which is even more serious in second- and third-tier cities. The lack of high-quality doctor resources hinders timely diagnosis and treatment of patients. [0003] In terms of analyzing medical images, most doctors spend most of their time on a single and large number of image reading tasks, which brings obstacles to doctors' in-depth and effective diagnosis and tr...

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): G06T7/11G06T5/00G06N3/04
CPCG06T5/001G06T7/11G06T2207/30101G06T2207/20084G06T2207/20081G06N3/045
Inventor 雷宇毛顺亿苏佳斌张鑫高超顾宇翔倪伟杨恒褚振方胡仲华孙谷飞周建华陆王天宇梅鵾傅致晖
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD
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