Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Dual-energy CT super-resolution image reconstruction method and system based on sparse representation

A super-resolution image, sparse representation technology, applied in image data processing, graphic image conversion, 2D image generation and other directions, can solve the problem of insufficient low-resolution images, non-unique reconstruction constraint solutions, etc., to reduce computational complexity degree, improve resolution, and the effect of good application prospects

Pending Publication Date: 2022-01-11
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The basic constraint of SR reconstruction is that after applying the same generative model to the restored image, the observed low-resolution image should have been regenerated. However, super-resolution image reconstruction itself is a pathological problem. A known low-resolution CT image, which corresponds to more than one possible high-resolution CT image, due to the insufficient number of low-resolution images, pathological registration and unknown fuzzy operators, and non-unique solutions to reconstruction constraints

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
  • Dual-energy CT super-resolution image reconstruction method and system based on sparse representation
  • Dual-energy CT super-resolution image reconstruction method and system based on sparse representation
  • Dual-energy CT super-resolution image reconstruction method and system based on sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the purpose, technical solution and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and technical solutions.

[0030]In dual-energy spectral CT super-resolution, there are low photon counts in the narrow energy bin width of the photon-counting detector, quantum noise and non-uniform response of the detector unit, which lead to low imaging resolution. To this end, an embodiment of the present invention provides a dual-energy CT super-resolution image reconstruction method based on sparse representation, see figure 1 As shown, it contains the following content:

[0031] Collect high-resolution dual-energy images under the low-energy spectrum and high-energy spectrum, and filter and down-sample the high-resolution dual-energy images to obtain low-resolution dual-energy images that match the high-resolution dual-energy images unde...

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 image super-resolution reconstruction, and particularly relates to a dual-energy CT (Computed Tomography) super-resolution image reconstruction method and a dual-energy CT super-resolution image reconstruction system based on sparse representation, which are characterized in that paired high-resolution and low-resolution dual-energy CT images are obtained through de-downsampling operation of an original truth value image fuzzy filter, and paired matched image segmentation blocks are extracted from CT images in a training set; in order to obtain similarity of sparse representation, two pairs of dictionaries are jointly trained for the high-energy-spectrum CT image and the low-energy-spectrum CT image respectively, and each pair of dictionaries comprises dictionaries of low-resolution image blocks and dictionaries of high-resolution image blocks; the sparse representation coefficients extracted from the low-resolution input block are then multiplied by the corresponding high-resolution dictionary for reconstructing the high-resolution output. According to the method, better image quality and clearer visual effect can be obtained by reconstructing the high-resolution image in combination with a proper amount of iterative operation, the resolution of the dual-energy CT image can be effectively improved according to the image quality evaluation index and the peak signal-to-noise ratio, and the method is convenient for actual scene application.

Description

technical field [0001] The invention belongs to the technical field of image super-resolution reconstruction, in particular to a dual-energy CT super-resolution image reconstruction method and system based on sparse representation. Background technique [0002] Computed Tomography (CT) technology can non-destructively and non-contactly obtain the internal structure information of the imaging object, and has played an important role in the fields of medical diagnosis, industrial inspection and safety inspection. CT technology is also one of the key technologies of computer-aided diagnosis based on medical imaging. Efficiently obtaining high-quality medical CT images is very important for the clinical application of computer-aided diagnosis technology. Computed tomography technology obtains material and structural information by collecting projection information of X-rays penetrating objects, but due to the similar attenuation coefficients between materials for X-rays, single...

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): G06T11/00G06T3/40G06K9/62G06V10/74G06V10/26G06V10/774G06V10/77
CPCG06T11/003G06T11/008G06T3/4076G06F18/214
Inventor 李磊仲心怡闫镔蔡爱龙梁宁宁王林元于小缓王毅忠孙艳敏
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
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
Eureka Blog
Learn More
PatSnap group products