CN115546342A - Dual energy CT image generation method, device, electronic equipment and readable storage medium - Google Patents

Abstract

The invention discloses a dual-energy CT image generation method, device, electronic equipment and readable storage medium, belonging to the technical field of CT image processing. The dual-energy CT image generation method includes: acquiring a first energy scan image and a second energy scan image, the first energy and the second energy are different; acquiring the second energy scan image according to the first energy scan image and a prediction model An energy prediction image, the prediction model is pre-trained according to the first energy history scan image and the second energy history scan image; a second energy composite image is obtained according to the second energy prediction image and the second energy scan image, and the The second energy composite image and the first energy scanning image are determined to be dual-energy CT images.

Description

Dual energy CT image generation method, device, electronic equipment and readable storage medium

technical field

The present invention relates to the technical field of CT image processing, in particular to a dual-energy CT image generation method, device, electronic equipment and readable storage medium.

Background technique

Computer tomography (computer tomography, CT) is a technology that uses X-rays to irradiate the target to be measured, and obtains a tomographic image of the target through computer processing. Dual-energy CT is a way to obtain images of the measured target through two scans with different energies. Based on the specificity of the attenuation coefficients of different substances for different energy X-rays, the composition of different objects can be accurately calculated through dual-energy CT scanning, thereby generating accurate images of the measured target.

However, in the related art, dual-energy CT has an unavoidable time interval between two scans. During this time interval, the contrast agent flows with the blood and the normal movement of organs leads to differences in the images obtained by the two scans, and thus This leads to poor matching of scanning images with different energies, which affects subsequent treatment and diagnosis.

Contents of the invention

The technical problem to be solved by the present invention is to provide a dual-energy CT image generation method, device, electronic equipment and readable storage medium in order to overcome the defect of low matching degree of dual-energy CT scanning images in the prior art.

The present invention solves the above technical problems through the following technical solutions:

In a first aspect, an embodiment of the present invention provides a method for generating a dual-energy CT image, the method comprising:

acquiring a first energy scan image and a second energy scan image, the first energy and the second energy being different;

Acquiring a second energy prediction image according to the first energy scan image and a prediction model, the prediction model being pre-trained according to the first energy history scan image and the second energy history scan image;

Acquiring a second energy composite image according to the second energy prediction image and the second energy scanning image, and determining the second energy composite image and the first energy scanning image as a dual-energy CT image.

In one embodiment, the acquiring a second energy composite image according to the second energy prediction image and the second energy scanning image includes:

Comparing the second energy prediction image and the second energy scan image to obtain non-consistent pixels;

Obtaining a fusion mask based on the non-uniform pixels;

performing image fusion on the second energy scanning image and the second energy prediction image according to the fusion mask to obtain the second energy synthesis image.

In one embodiment, the comparing the second energy prediction image and the second energy scanning image to obtain non-consistent pixels includes:

Taking the pixels whose absolute value of the CT value difference between the second energy prediction image and the second energy scanning image is greater than or equal to a set threshold as the inconsistent pixels.

In one embodiment, the determining the fusion mask based on the non-consistent pixels includes:

dividing the non-consistent pixels into prediction error pixels and scanning error pixels according to the pixels at the same position as the non-consistent pixels in the first energy scanned image;

The mask is generated from the prediction error pixels and the scanning error pixels.

In one embodiment, the method also includes:

filtering training data from the first energy history scan image and the second energy history scan image;

Model training is performed according to the training data to obtain the prediction model.

In one embodiment, the filtering out the training data from the first energy history scan image and the second energy history scan image includes:

performing image matching on the first energy history scan image and the second energy history scan image;

The first energy history scan image and the second energy history scan image that match the standard are used as the training data.

In one embodiment, the filtering out the training data from the first energy history scan image and the second energy history scan image includes:

performing image matching on the first energy history scan image and the second energy history scan image;

Perform registration processing on the first energy history scan image and the second energy history scan image that do not meet the matching requirements, and perform secondary image matching on the registered image;

The first energy history image and the second energy history image whose secondary image matching is satisfactory are used as the training data.

In a second aspect, an embodiment of the present invention provides a dual-energy CT image generation device, the device comprising:

A first acquisition module, configured to acquire a first energy scan image and a second energy scan image, where the first energy is different from the second energy;

The second acquisition module is configured to acquire a second energy prediction image according to the first energy scan image and a prediction model, and the prediction model is pre-trained according to the first energy history scan image and the second energy history scan image;

A determining module, configured to acquire a second energy composite image according to the second energy prediction image and the second energy scan image, and determine the second energy composite image and the first energy scan image as a dual-energy CT image .

In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the above-mentioned first The dual-energy CT image generation method described in the aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for generating a dual-energy CT image provided in the first aspect is implemented.

The positive progress effect of the present invention is:

In the dual-energy CT image generation method provided by the embodiment of the present invention, the second energy prediction image is predicted from the first energy scanning image, so as to avoid the structural difference caused by the time difference between the two scans. The second energy prediction image is corrected by using the second energy scanning image to obtain a second energy synthesis image, so as to ensure the accuracy of the second energy synthesis image. Furthermore, a dual-energy image is formed from the first energy scanning image and the second energy composite image, providing accurate reference for subsequent treatment.

Description of drawings

Fig. 1 is a flowchart of a method for generating a dual-energy CT image according to an exemplary embodiment;

Fig. 2 is a flowchart of step S103 shown according to an exemplary embodiment;

Fig. 3 is a flowchart of step S1032 shown according to an exemplary embodiment;

Fig. 4 is a flow chart of a method for generating a dual-energy CT image according to another exemplary embodiment;

Fig. 5 is a flowchart of step S104 shown according to an exemplary embodiment;

Fig. 6 is a block diagram of a device for generating a dual-energy CT image according to an exemplary embodiment;

Fig. 7 is a block diagram of a determination module shown according to an exemplary embodiment;

Fig. 8 is a block diagram of an acquisition unit shown according to an exemplary embodiment;

Fig. 9 is a block diagram of a dual-energy CT image generating device according to another exemplary embodiment;

Fig. 10 is a block diagram of a screening module shown according to an exemplary embodiment;

Fig. 11 is a schematic structural diagram of an electronic device according to an exemplary embodiment.

detailed description

The present invention is further illustrated below by means of examples, but the present invention is not limited to the scope of the examples.

The terminology used in the present disclosure is for the purpose of describing particular embodiments only, and is not intended to limit the present disclosure. Unless otherwise defined, the technical terms or scientific terms used in the present disclosure shall have the usual meanings understood by those skilled in the art to which the present disclosure belongs. Words such as "a" or "one" used in the present disclosure and the claims do not indicate a limitation of quantity, but mean that there is at least one. Unless otherwise stated, "comprises" or "comprises" and similar terms mean that the elements or items listed before "comprises" or "comprises" include the elements or items listed after "comprises" or "comprises" and their equivalents, and Other elements or items are not excluded. Words such as "connected" or "connected" are not limited to physical or mechanical connections, and may include electrical connections, whether direct or indirect.

As used in this disclosure and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

In related technologies, dual-source scanning, fast kV switching scanning, double-layer detectors and other solutions have limited the clinical implementation of dual-energy CT imaging due to high cost. Schemes such as slow kV switching scans that require two scans not only bring additional doses to the patient, but also the inevitable contrast agent flow and organ movement within the time difference between the two acquisitions cause the low matching degree of the two scan images, greatly Clinical diagnosis after imaging is affected.

Based on the above problems, an embodiment of the present invention provides a method for generating a dual-energy CT image, so as to achieve both a high matching degree of a dual-energy CT image and low hardware cost. The technical solutions provided by the embodiments of the present invention are applicable to various CT geometries, including but not limited to parallel beams and cone beams, and the technical solutions provided by the embodiments of the present invention are applicable to various CT scan modes, including but not limited to tomographic Sweep and helical scan. Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

Example 1

Fig. 1 is a flow chart of a method for generating a dual-energy CT image according to an exemplary embodiment. As shown in Figure 1, the method includes:

Step S101, acquiring a first energy scan image and a second energy scan image, where the first energy and the second energy are different.

The first energy scanning image and the second energy scanning image are scanning images of the same scanned object under different energy spectrum X-rays. X-rays with different energy spectra are realized by adjusting the tube voltage of the X-ray tube. Due to the time difference between the two scans, the contrast agent flow and organ movement within the time difference cause unavoidable structural differences between the first energy scan image and the second scan image.

Optionally, the first energy is lower than the second energy. In such a case, the attenuation of the target area in the first energy scanning image acquired by relatively low-energy X-ray scanning is greater, and it is easier to identify different tissues or parts, so as to provide accurate input for image prediction in subsequent steps.

Optionally, the second energy scanning image is acquired by means of sparse acquisition and low-dose acquisition, so as to reduce the radiation dose borne by the scanned object. Among them, sparse acquisition refers to performing projection scanning at a larger interval angle, which improves the acquisition rate, thereby reducing the radiation dose borne by the scanned object. Moreover, the scanning dose is also related to the tube current of the X-ray tube, and the scanning dose can be changed by adjusting the tube current of the X-ray tube. In step S101, low dose acquisition is realized by reducing the tube current of the X-ray tube.

Step S102. Acquire a second energy prediction image according to the first energy scanning image and a prediction model, the prediction model is pre-trained based on the first energy history scanning image and the second energy history scanning image.

In conjunction with step S101, when the first energy is low, the prediction accuracy of the second energy prediction image acquired according to the first energy scanning image is higher. Optionally, in step S102, the prediction model is obtained through deep learning training according to the first energy history scanning image and the second energy history scanning image, and the specific acquisition method of the prediction model will be described in detail below.

Step S103, acquiring a second energy composite image according to the second energy prediction image and the second energy scan image, and determining the second energy composite image and the first energy scan image as a dual-energy CT image.

Due to limitations of physical principles, the first energy image and the second energy image do not satisfy a perfect mapping relationship, so the second energy prediction image obtained only through the first energy scan image has uncertainty and error risks. In step S103, the second energy scanning image is used to perform auxiliary correction on the second energy prediction image to obtain a second energy composite image, so as to optimize the accuracy and effectiveness of the finally obtained dual-energy CT image.

In summary, the dual-energy CT image generation method provided by the embodiment of the present invention predicts the second energy prediction image through the first energy scanning image, so as to avoid the structural difference caused by the time difference between the two scans. The second energy prediction image is corrected by using the second energy scanning image to obtain a second energy synthesis image, so as to ensure the accuracy of the second energy synthesis image. Furthermore, a dual-energy image is formed from the first energy scanning image and the second energy composite image, providing accurate reference for subsequent treatment.

In an example, step S103 is implemented in the following manner. Fig. 2 is a flowchart of step S103 shown according to an exemplary embodiment. As shown in Figure 2, step S103 includes:

Step S1031, comparing the second energy prediction image and the second energy scanning image to obtain non-consistent pixels.

Optionally, in step S1031, specifically, the pixels whose absolute value of the CT value difference between the second energy prediction image and the second energy scanning image is greater than or equal to the set threshold are regarded as inconsistent pixels. The CT values of the same substance in the second energy prediction image and the second energy scanning image are consistent or have little difference, so the different pixels in the two images are determined by using the CT value as a criterion.

Step S1032, acquiring a fusion mask based on non-consistent pixels.

Further, a fusion mask is determined according to the inconsistent pixels determined in step S1032. Optionally, Fig. 3 is a flow chart of step S1032 shown according to an exemplary embodiment. As shown in Figure 3, step S1032 includes:

Step S301 , according to the pixels at the same position as the non-consistent pixels in the first energy-scanned image, divide the non-consistent pixels into prediction error pixels and scanning error pixels.

Wherein, the prediction error pixels refer to non-consistent pixels due to prediction errors, and the scanning error pixels refer to non-consistent pixels due to organ movement, contrast agent flow and other reasons. Among them, the scanning error pixels are unavoidable pixel differences in the two scanning processes.

The first energy scan image and the second energy scan image are two actual image scans, and scanning errors inevitably exist. The second energy prediction image is predicted based on the first energy scan image, so the second energy prediction image and the first energy scan image have the same tissue structure, but the CT values of the same pixel points are different. In this case, in step S301, according to the first energy scanning image and the second energy scanning image, the scanning error pixels caused by structural differences can be determined, and then the inconsistent pixels are divided into scanning error pixels and prediction error pixels .

Optionally, when determining the scanning error pixel, the geometric structure and anatomical structure information in the first energy scanning image, the second energy scanning image and the second energy prediction image are used as a reference, and image matching (for example, based on the gray gradient is performed) Image matching) and other methods to determine the scanning error pixels.

Step S302, generating a mask according to the prediction error pixels and the scanning error pixels.

The mask is a matrix with the same size as the first energy scan image and the second energy scan image. Regarding the implementation of the mask, for example, the value in the mask is 0 or 1. Specifically, for consistent pixels and non-uniform pixels classified as scanning error pixels, the corresponding value in the mask is 1. At this time, the final second energy composite image adopts the pixel values of the second energy prediction image. For non-consistent pixels that are not classified as prediction errors, the corresponding value in the mask is 0. At this time, the final second energy synthesis image adopts the pixel values of the second energy scanning image. Exemplarily, the values in the mask are greater than or equal to 0 and less than or equal to 1. The image effect of the second energy synthesized image obtained in this way is better, especially the image synthesized effect is more realistic for regions with non-uniform pixels.

Continuing to refer to 2, execute step S1033 after step S1032, specifically as follows:

Step S1033, performing image fusion on the second energy scanning image and the second energy prediction image according to the fusion mask to obtain a second energy composite image.

Combined with the above description of step S302, here the second energy composite image is acquired in the following manner:

Image_synthetic=Image_predict×mask+Image_scan×(1–mask)

Wherein, Image_synthetic is the second energy synthetic image, Image_predict is the second energy prediction image, Image_scan is the second energy scanning image, and mask is the mask.

In summary, a dual-energy CT image is generated through steps S101 to S103. Combined with the complete dual-energy CT image generation method provided by the embodiment of the present invention, the reason for reducing the radiation dose by reducing the X-ray tube current in step S101 is explained again.

Usually, the radiation dose is reduced by reducing the tube current of the X-ray tube during CT scanning. However, the reduction of the tube current will lead to the increase of image noise and affect the image quality. Therefore, in the dual-energy CT image generation method provided by the related art, in order to ensure the image quality, it is necessary to increase the tube voltage of the dual-energy scan, which leads to an increase in radiation dose.

In the embodiment of the present invention, the second energy prediction image is predicted by the first energy scan image, and the second energy prediction image is optimized by the second energy scan image, so as to improve the accuracy of the generated dual-energy CT image. Therefore, for the first energy scanning image and the second energy scanning image acquired in step S101, the requirement on image noise is reduced. In such a case, a lower tube current of the X-ray tube may be used when performing image scanning in step S101, so as to achieve the purpose of reducing the radiation dose.

Fig. 4 is a flow chart of a method for generating a dual-energy CT image according to another exemplary embodiment. As shown in Figure 4, the method also includes:

Step S104, filtering out training data from the first energy history scan image and the second energy history scan image.

The training data is optimized by screening, so that the prediction model trained based on the training data can more accurately predict the second energy scanning image according to the first energy scanning image.

As an example, Fig. 5 is a flowchart of step S104 shown according to an exemplary embodiment. As shown in Figure 5, step S104 includes:

Step S1041 , performing image matching on the first energy history scan image and the second energy history scan image.

Step S1042, using the first energy history scan image and the second energy history scan image that match the standard as training data.

Step S1043 , performing registration processing on the first energy history scanning image and the second energy history scanning image whose matching is not up to standard, and performing secondary image matching on the image after the registration processing.

Step S1044 , using the first energy history image and the second energy history image that have met the secondary image matching standard as training data.

In step S1041, the first energy history scan image and the second energy history scan image are clinical data or phantom data. The acquisition methods include but are not limited to plain tomography and helical scanning. Moreover, the specific method of image matching is not limited, for example, image matching is performed using structural similarity and cross-correlation coefficient as a reference, and/or image matching is performed based on gray gradients.

In step S1042 and step S1043, the standard of matching is determined based on the specific method of image matching adopted. For example, if the structural similarity is greater than or equal to the set threshold, it is determined that the matching is satisfactory, and if the structural similarity is less than the set threshold, it is determined that the matching is not Up to standard.

In step S1042, the matched first energy history scan image and the second energy history scan image are used as training data to optimize the effectiveness of the training data so that the prediction model accurately reflects the matched first energy history scan image and the second energy history scan image. Relationships between energy history scan images.

Steps S1043 and S1044 perform registration processing on the first energy history scan image and the second energy history scan image that do not meet the matching standard, so as to improve the matching degree of the first energy history scan image and the second energy history scan image. In this way, the first energy history scan image and the second energy history scan image that can match the standard after the registration process are also used as training data, which reduces the standard of training data set screening, and on the one hand, it is convenient to collect a sufficient amount of training data , on the other hand, to avoid the trained prediction model from being too idealistic, and to be closer to the data obtained in practical applications.

Continuing to refer to FIG. 4 , step S105 is executed after step S104 , specifically as follows.

Step S105, perform model training according to the training data to obtain a prediction model.

Optionally, the prediction model is obtained by using a deep learning model. For example, the first energy history scan image in the training data is used as the input data for model training, the second energy history scan image in the training data is used as the gold standard for model training, and the loss is constructed by using the gold standard and the image output by the model function. In the process of model training, the prediction model is determined by the convergence of the loss function to the preset threshold. Wherein, the deep learning network used in step S105 includes but not limited to: Transformer, CNN, GAN. In addition, in step S105, other algorithms may also be used to obtain the prediction model based on the training data, which is not specifically limited in this embodiment of the present invention.

In summary, the dual-energy CT image generation method provided by the embodiment of the present invention predicts the second energy prediction image through the first energy scanning image, so as to avoid the structural difference caused by the time difference between the two scans. The second energy prediction image is corrected by using the second energy scanning image to obtain a second energy synthesis image, so as to ensure the accuracy and reliability of the second energy synthesis image. Furthermore, a dual-energy image is formed from the first energy scanning image and the second energy composite image, providing accurate reference for subsequent treatment. For the two scans, the radiation dose lower than that in the related art can be used to scan, reducing the radiation dose of the scanned object. Moreover, the hardware cost of the dual-energy CT image generation method provided by the embodiment of the present invention is low, which is convenient for implementation and popularization of dual-energy CT scanning.

Example 2

Fig. 6 is a block diagram of a device for generating a dual-energy CT image according to an exemplary embodiment. As shown in FIG. 6 , the device includes: a first obtaining module 610 , a second obtaining module 620 and a determining module 630 .

The first acquiring module 610 is configured to acquire a first energy scan image and a second energy scan image, and the first energy is different from the second energy.

The second obtaining module 620 is used for obtaining a second energy prediction image according to the first energy scanning image and a prediction model, and the prediction model is pre-trained according to the first energy history scanning image and the second energy history scanning image.

The determination module 630 is configured to obtain a second energy composite image according to the second energy prediction image and the second energy scan image, and determine the second energy composite image and the first energy scan image as a dual-energy CT image.

In one embodiment, Fig. 7 is a block diagram of a determining module according to an exemplary embodiment. As shown in FIG. 7 , the determination module 630 includes: a comparison unit 631 , an acquisition unit 632 and a fusion unit 633 .

The comparing unit 631 is configured to compare the second energy prediction image and the second energy scanning image to obtain non-consistent pixels.

The acquiring unit 632 is configured to acquire a fusion mask based on non-uniform pixels.

The fusion unit 633 is configured to perform image fusion on the second energy scanning image and the second energy prediction image according to the fusion mask to obtain a second energy synthesis image.

In one embodiment, the comparison unit 631 is specifically configured to regard pixels whose absolute value of the difference between the CT values in the second energy prediction image and the second energy scan image is greater than or equal to a set threshold as inconsistent pixels.

In one embodiment, Fig. 8 is a block diagram of an acquisition unit according to an exemplary embodiment. As shown in FIG. 8 , the obtaining unit 632 includes: a dividing subunit 6321 and a generating subunit 6322 .

Wherein, the division subunit 6321 is used to divide the non-consistent pixels into prediction error pixels and scanning error pixels according to the pixels at the same position as the non-consistent pixels in the first energy scan image.

The generation subunit 6322 is used to generate a mask according to the prediction error pixels and the scanning error pixels.

In one embodiment, Fig. 9 is a block diagram of a device for generating a dual-energy CT image according to another exemplary embodiment. As shown in FIG. 9 , the device further includes: a screening module 640 and a training module 650 .

The filtering module 640 is used to filter out training data from the first energy history scan image and the second energy history scan image.

The training module 650 is used for performing model training according to the training data to obtain a prediction model.

In one embodiment, Fig. 10 is a block diagram of a screening module according to an exemplary embodiment. As shown in FIG. 10 , the screening module 640 includes: an image matching unit 641 and a first determining unit 642 .

The image matching unit 641 is configured to perform image matching on the first energy history scan image and the second energy history scan image.

The first determining unit 642 is configured to use the first energy history scan image and the second energy history scan image that match the standard as training data.

In one embodiment, the screening module 640 further includes: a registration processing unit 643 and a second determination unit 644 .

The registration processing unit 643 is configured to perform registration processing on the first energy history scan image and the second energy history scan image that do not meet the matching requirements, and perform secondary image matching on the image after the registration processing;

The second determination unit 644 is configured to use the first energy history image and the second energy history image that have met the secondary image matching standard as training data.

To sum up, the dual-energy CT image generation device provided by the embodiment of the present invention predicts the second energy prediction image through the first energy scanning image, so as to avoid the structural difference caused by the time difference between the two scans. The second energy prediction image is corrected by using the second energy scanning image to obtain a second energy synthesis image, so as to ensure the accuracy and reliability of the second energy synthesis image. Furthermore, a dual-energy image is formed from the first energy scanning image and the second energy composite image, providing accurate reference for subsequent treatment. For the two scans, the radiation dose lower than that in the related art can be used to scan, reducing the radiation dose of the scanned object. Moreover, the hardware cost of the dual-energy CT image generation method provided by the embodiment of the present invention is low, which is convenient for implementation and popularization of dual-energy CT scanning.

Example 3

An embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the dual-energy CT as provided in Embodiment 1 is realized. image generation method.

Optionally, the electronic device is an electronic device that cooperates with a CT scanning device, and is configured to generate a dual-energy CT image based on an image acquired by the CT scanning device. Optionally, the electronic device is a CT scanning device.

FIG. 11 is a schematic structural diagram of an electronic device provided in this embodiment. The electronic device includes at least one processor and a memory communicatively coupled to the at least one processor. Wherein, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the dual-energy CT of Embodiment 1 image generation method. The electronic device 3 shown in FIG. 11 is only an example, and should not limit the functions and scope of use of the embodiments of the present invention.

Components of the electronic device 3 may include but not limited to: the at least one processor 4 mentioned above, the at least one memory 5 mentioned above, and the bus 6 connecting different system components (including the memory 5 and the processor 4 ).

The bus 6 includes a data bus, an address bus and a control bus.

The memory 5 may include a volatile memory, such as a random access memory (RAM) 51 and/or a cache memory 52 , and may further include a read only memory (ROM) 53 .

Memory 5 may also include a program/utility tool 55 having a set (at least one) of program modules 54 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, which Each or some combination of the examples may include the implementation of a network environment.

The processor 4 executes various functional applications and data processing by running the computer program stored in the memory 5 , such as the above-mentioned dual-energy CT image generation method.

Electronic device 3 may also communicate with one or more external devices 7 (eg, keyboards, pointing devices, etc.). This communication can take place through an input/output (I/O) interface 8 . Moreover, the electronic device 3 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network such as the Internet) through the network adapter 9 . As shown in FIG. 11 , the network adapter 9 communicates with other modules of the electronic device 3 through the bus 6 . It should be appreciated that although not shown in FIG. 11 , other hardware and/or software modules may be used in conjunction with electronic device 3, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array ) systems, tape drives, and data backup storage systems.

It should be noted that although several units/modules or subunits/modules of an electronic device are mentioned in the above detailed description, such division is only exemplary and not mandatory. Actually, according to the embodiment of the present invention, the features and functions of two or more units/modules described above may be embodied in one unit/module. Conversely, the features and functions of one unit/module described above can be further divided to be embodied by a plurality of units/modules.

Example 4

An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, and is characterized in that, when the computer program is executed by a processor, the method for generating a dual-energy CT image as in Embodiment 1 is implemented.

Wherein, the readable storage medium may more specifically include but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device or any of the above-mentioned the right combination.

In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on the terminal device, the program code is used to make the terminal device execute the above-mentioned second aspect. Steps in the pulse ablation region prediction method.

Wherein, the program code for executing the present invention may be written in any combination of one or more programming languages, and the program code may be completely executed on the user equipment, partially executed on the user equipment, or used as an independent software Package execution, partly on the user device and partly on the remote device, or entirely on the remote device.

Although the specific implementation of the present invention has been described above, those skilled in the art should understand that this is only an example, and the protection scope of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principle and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims (10)

1. A dual energy CT image generation method, the method comprising:

acquiring a first energy scanning image and a second energy scanning image, wherein the first energy and the second energy are different;

acquiring a second energy prediction image according to the first energy scanning image and a prediction model, wherein the prediction model is obtained by pre-training according to a first energy history scanning image and a second energy history scanning image;

and acquiring a second energy synthesis image according to the second energy prediction image and the second energy scanning image, and determining the second energy synthesis image and the first energy scanning image as a dual-energy CT image.

2. The method according to claim 1, wherein said obtaining a second energy-combined image from the second energy-predicted image and the second energy-scanned image comprises:

comparing the second energy prediction image with the second energy scanning image to obtain a non-uniform pixel;

acquiring a fusion mask based on the non-uniform pixels;

and carrying out image fusion on the second energy scanning image and the second energy prediction image according to the fusion mask to obtain a second energy synthesis image.

3. The method of claim 2, wherein said comparing the second energy prediction image to the second energy scan image to obtain non-uniform pixels comprises:

and taking the pixels of which the absolute value of the difference between the CT values in the second energy prediction image and the second energy scanning image is greater than or equal to a set threshold value as the non-uniform pixels.

4. The method of claim 2, wherein determining a fusion mask based on the non-uniform pixels comprises:

dividing the non-uniform pixels into prediction error pixels and scanning error pixels according to pixels at the same positions as the non-uniform pixels in the first energy scanning image;

generating the mask from the prediction error pixels and the scan error pixels.

5. The method of claim 1, further comprising:

screening out training data from the first energy historical scanning image and the second energy historical scanning image;

and carrying out model training according to the training data to obtain the prediction model.

6. The method of claim 5, wherein the screening training data from the first energy history scan image and the second energy history scan image comprises:

performing image matching on the first energy history scanned image and the second energy history scanned image;

and taking the first energy history scanning image and the second energy history scanning image which are matched to reach the standard as the training data.

7. The method of claim 5, wherein the screening training data from the first energy history scan image and the second energy history scan image comprises:

performing image matching on the first energy history scanned image and the second energy history scanned image;

registering the first energy history scanning image and the second energy history scanning image which are not matched up to the standard, and performing secondary image matching on the images subjected to registration processing;

and matching the first energy historical image and the second energy historical image which reach the standard with a secondary image to be used as the training data.

8. A dual energy CT image generation apparatus, the apparatus comprising:

a first acquisition module, configured to acquire a first energy scan image and a second energy scan image, where the first energy and the second energy are different;

the second obtaining module is used for obtaining a second energy prediction image according to the first energy scanning image and the prediction model, and the prediction model is obtained by pre-training according to the first energy history scanning image and the second energy history scanning image;

and the determining module is used for acquiring a second energy synthesis image according to the second energy prediction image and the second energy scanning image, and determining the second energy synthesis image and the first energy scanning image as a dual-energy CT image.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the dual energy CT image generation method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the dual energy CT image generation method of any one of claims 1 to 7.

Images