An unsupervised/semi-supervised CT image reconstruction depth network train method

A CT image and deep network technology, applied in the field of image processing, can solve the problems of high computational cost, lack of extraction of common features, influence of network accuracy, etc., to avoid the acquisition process, increase the practicability, and achieve the effects of high imaging quality.

Active Publication Date: 2018-12-18
广州本影医疗科技有限公司
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method based on the maximum a posteriori model has higher accuracy in actual use, but due to the existence of a large number of iterative processes in the algorithm, the calculation cost is high and the time-consuming is long (tens or even hundreds of times the denoising speed of deep learning) , At the same time, since this method can only process one CT image at a time, it lacks the extraction of common features, which also limits the best effect that this method can achieve
[0005] The method based on deep learning is fast and works well in the case of a large amount of accurate labeled data

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
  • An unsupervised/semi-supervised CT image reconstruction depth network train method
  • An unsupervised/semi-supervised CT image reconstruction depth network train method
  • An unsupervised/semi-supervised CT image reconstruction depth network train method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The real patient CT data provided by the "2016Low-dose CT Grand Challenge datasets" website is adopted as the experimental data source of the present invention. Among them, we only use 50 low-dose CT data with a dose of 10mAs as our experimental training data (excluding prediction data). Choose the second-order TV sparsity property of the chord graph (such as Figure 5 shown) is a priori, refer to figure 1 , the present invention comprises the steps in turn:

[0058] Step S1: Obtain unlabeled low-dose projection data under the CT scanning protocol (50 pieces of low-dose CT chord diagram data with a dose of 10mAs are used here), and initialize the network structure and network parameters;

[0059] Step S2: Skip this step due to lack of labeled data;

[0060] Step S3: Determine the loss function corresponding to the unlabeled data, the expression is:

[0061]

[0062] where θ is the network parameter, f θ (x) is the CT chord diagram data output by the network, p i...

Embodiment 2

[0088] The real patient CT data provided by the "2016Low-dose CT Grand Challenge datasets" website is adopted as the experimental data source of the present invention. Among them, we use 50 low-dose CT data with a dose of 10mAs, and 10 pairs of CT chord diagram data pairs with a dose of (10mAs, 200mAs) as our experimental training data (excluding prediction data). Choose the second-order TV sparsity property of the chord graph (such as Figure 5 shown) is a priori, refer to figure 1 , the present invention comprises the steps successively:

[0089] Step S1: Obtain unlabeled low-dose CT chord data under the CT scanning protocol (50 low-dose CT data with a dose of 10mAs, 10 pairs of CT chord data with a dose of (10mAs, 200mAs) are used here), and initialize the network structure and network parameters;

[0090] Step S2: Determine the loss function corresponding to the labeled data, the expression is:

[0091] loss=‖f θ (x)-y true ‖ 2 (1)

[0092] Step S3: Determine the ...

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

An unsupervised/semi-supervised CT image reconstruction depth network train method is provided. Firstly, the CT chord data under the CT scanning protocol and the imaging system parameters of the CT equipment are obtained. The data include low-dose CT chord data without labeling, and a small amount of low-dose CT chord data correspond to labeled CT chord data. The labeled CT chord data refers to the clear CT chord data information of known low dose data corresponding to high dose. The loss functions of unlabeled and labeled data are constructed respectively, and the total loss functions of unsupervised/semi-supervised network are obtained by weighted summation, and the denoising network is trained by this loss function. The method achieves the effect of a CT image denoising network with higher precision and higher speed by using non-annotated data only or only a small amount of annotated data. The invention aims at establishing a method of combining a chord data restoration model and adepth learning model, thereby realizing high-quality CT image reconstruction.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to image processing of medical images, in particular to an unsupervised / semi-supervised CT image reconstruction deep network training method based on fusion of deep learning and error modeling framework. Background technique [0002] CT (Computed Tomography) is currently widely used in clinical medical imaging diagnosis. However, excessive doses of X-rays will cause potential harm to the human body, easily induce malignant tumors, and cause organ damage. Therefore, reducing the dose of X-rays as much as possible has become one of the key technologies in the field of medical CT imaging. However, this It often leads to severe degradation and serious noise in CT chord data. [0003] In order to solve the problem of noise contained in low-dose CT images, two common methods have been proposed, one is the method of modeling the noise and constructing the maximum a posteriori model...

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): G06T5/00G06N3/04G06N3/08
CPCG06T5/002G06T2207/10081G06T2207/20024G06T2207/20081G06T2207/20084
Inventor 孟德宇谢琦赵谦马建华耿明瑞邓芸
Owner 广州本影医疗科技有限公司
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