Grating phase contrast imaging signal extraction method and device, storage medium and electronic equipment

A signal extraction and phase-contrast imaging technology, applied in the field of deep learning, can solve the problems of inability to guarantee displacement accuracy, reduce the radiation dose utilization efficiency of X-ray grating phase-contrast imaging technology, consume a lot of time, etc., and achieve the effect of automatic and fast acquisition

Pending Publication Date: 2021-03-30
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the inaccuracy and time-consuming of the grating step displacement, the traditional signal extraction method cannot guarantee the displacement accuracy to obtain the ideal phase step image, and the acquisition of multiple images will consume a lot of time, which indirectly reduces the quality of the X-ray grating. Radiation Dose Utilization Efficiency of Phase Contrast Imaging Technology
In order to improve the imaging efficiency of the system and reduce the imaging time of the system, it is usually hoped to use a collected phase-stepping image for signal extraction, but the traditional method easily leads to the loss of spatial resolution

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
  • Grating phase contrast imaging signal extraction method and device, storage medium and electronic equipment
  • Grating phase contrast imaging signal extraction method and device, storage medium and electronic equipment
  • Grating phase contrast imaging signal extraction method and device, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] figure 1 It is a schematic flowchart of a grating phase contrast imaging signal extraction method provided in Embodiment 1 of the present invention. This embodiment is applicable to quickly obtain a signal image of a phase-stepping image with a higher spatial resolution based on a pre-trained signal extraction model. Wherein the device can be realized by software and / or hardware, and generally integrated in electronic equipment. For details, see figure 1 As shown, the method may include the following steps:

[0045] S110. Acquire at least one X-ray phase stepping image.

[0046] S120. Input at least one X-ray phase-stepping image into a pre-trained signal extraction model, and obtain a signal image of at least one X-ray phase-stepping image according to an output result of the signal extraction model.

[0047] Wherein, the signal extraction model is trained according to the standard signal image of the sample image and the simulated phase stepping image of the sample...

Embodiment 2

[0053] figure 2 It is a schematic flowchart of a grating phase contrast imaging signal extraction method provided in Embodiment 2 of the present invention. The technical solution of this embodiment introduces the training process of the signal extraction model in detail on the basis of the above embodiments. Optionally, the training method of the signal extraction model includes: acquiring an original object image, and determining the original object based on preset rules The simulated phase step image of the image; the simulated phase step image of the original object image is input into the initial signal extraction model to obtain a predicted signal image, and the initial signal is adjusted according to the predicted signal image and the standard signal image The network parameters of the model are extracted to obtain the signal extraction model.

[0054] On the basis of the above technical solutions, optionally, the simulated phase stepping images are N phase stepping im...

Embodiment 3

[0073] Figure 6 It is a schematic flowchart of a grating phase contrast imaging signal extraction method provided in Embodiment 2 of the present invention. The technical solution of this embodiment introduces training another initial signal extraction model. Optionally, the training method of the signal extraction model includes: acquiring an original object image, and determining the simulated phase of the original object image based on preset rules stepping image: input the simulated phase stepping image of the original object image into the initial signal extraction model to obtain a predicted signal image, and adjust the network of the initial signal extraction model according to the predicted signal image and the standard signal image parameters to get the signal extraction model.

[0074] On the basis of the above technical solutions, optionally, the simulated phase stepping image is a single phase stepping image, the signal extraction model includes a downsampling sub...

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 grating phase contrast imaging signal extraction method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining at least one X-ray phase stepping image, and inputting a plurality of or a single phase stepping image into a pre-trained signal extraction model; using the output result of the signal extraction model as different contrast information images corresponding to the object, and obtaining the signal extraction model by training according to the standard signal image of the sample image and the analog phase stepping image of the sample image. Therefore, the signal image of the phase stepping image can be obtained by directly inputting the phase stepping image into the signal extraction model. Particularly, by corresponding to a signal extraction process corresponding to a single phase stepping image, the method effectively solves the problem that an existing method is prone to causing reduction of image resolution, and the purpose of automatically and rapidly obtaining high-resolution phase contrast imaging is achieved.

Description

technical field [0001] Embodiments of the present invention relate to deep learning technology, and in particular to a method, device, storage medium, and electronic equipment for extracting grating phase-contrast imaging signals. Background technique [0002] X-ray grating phase contrast imaging technology is a grating imaging method based on Talbot effect and Lau effect. Through this technology, the object to be inspected can be effectively exposed to X-rays, so as to obtain the absorption signal, scattering signal and phase contrast signal inside the object. Studies have shown that phase contrast signals can effectively improve the contrast of soft tissue detection, while scattering signals can greatly improve the detection sensitivity of internal particles or void structures in objects. [0003] At present, the extraction of the above-mentioned absorption, scattering, and phase contrast signals is obtained through mathematical calculations based on multiple phase-step p...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01N23/041G01N23/046G01N23/083G06N3/04G06N3/08
CPCG01N23/046G01N23/041G01N23/083G06N3/084G01N2223/04G01N2223/1016G01N2223/401G06N3/045
Inventor 葛永帅梁栋倪一帆朱炯滔刘新郑海荣
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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