CN114463259A - Calculation method, device and equipment of dual-energy subtraction parameters and storage medium - Google Patents

Abstract

The application provides a method for calculating dual-energy subtraction parameters, which is applied to calculating soft tissue subtraction parameters and bone subtraction parameters of shadow areas in dual-energy X-ray medical images, wherein the dual-energy X-ray medical images comprise high-energy images and low-energy images, and the method comprises the following steps: acquiring a target dual-energy X-ray medical image for registration processing; determining a region to be detected according to the position of the maximum value of the gradient amplitude image of a preset region, determining a subtraction image according to the high-energy and low-energy sub-image blocks, and generating a relative standard deviation corresponding to each pixel in the region to be detected according to the standard deviation and the mean value of the subtraction image; and determining the soft tissue subtraction parameters and the bone subtraction parameters according to the minimum value of the relative standard deviation. The method has the advantages that the size of the region of interest, namely the region to be detected, is far smaller than the size of the image, the algorithm efficiency is high, the relative standard deviation is used as the judgment criterion based on the skeleton edge visibility, the effect is good, and the clinical requirements can be basically met at one time without manual fine adjustment.

Description

Method, device, device and storage medium for calculating dual-energy subtraction parameters

technical field

The present application relates to the technical field of image processing, and in particular, to a method, device, device and storage medium for calculating dual-energy subtraction parameters.

Background technique

Nowadays, with the development and popularization of medical imaging technology, dual-energy X-ray photography technology has been widely used. Dual-Energy Subtraction is based on the different attenuation characteristics of high and low energy X-rays by human tissue , based on the physical model of X-ray attenuation, with the help of digital image processing technology, to achieve image separation of human soft tissue and bone. Compared with conventional X-rays, dual-energy X-rays take longer, and at the same time, the subtraction results are often disturbed by various factors, resulting in the inability to guarantee the subtraction accuracy, which limits the technology to a certain extent. clinical popularity. In dual-energy X-ray radiography, image post-processing is a major time-consuming process, and the search for subtraction parameters is an important reason for low processing efficiency.

However, the searched closely related patent, "Method and Apparatus to Automatically Determine Tissue Cancellation Parameters in X-Ray Dual Energy Imaging", applicant: GE Medical Systems Global Technology Company. The main idea of the patented solution is to minimize the gradient of the subtracted image within the preset subtraction parameter range to obtain the soft tissue subtraction parameters, and then determine the bone subtraction parameters according to the empirical relationship between the soft tissue and the bone subtraction parameters. This scheme does not eliminate unorganized regions in the gradient calculation, which leads to the interference of information in these regions and affects the accuracy of the calculation results. In addition, although the image has been reduced several times in this scheme, the efficiency is low due to the need to perform optimal subtraction parameter statistics for each pixel point. "Estimation method of dual-energy subtraction parameters and computer-readable storage medium", applicant: Shenzhen Anjian Technology Co., Ltd. The main idea of the patented solution is to minimize the variance of the soft tissue point set to determine the bone subtraction parameters by changing the subtraction parameters, and at the same time minimize the grayscale difference between the soft tissue point set and the bone tissue point set to determine the soft tissue subtraction parameters. This method uses the absolute gray value in both the calculation of variance and gray difference. However, the gray value of the dual-energy subtraction image has a normalization problem, and the use of absolute gray value has a large error risk. In addition, the optimal soft tissue subtraction parameters are determined based on the minimization of the grayscale difference between the skeleton point set and the soft tissue point set. From the experimental results, the effect is not very satisfactory, and there are obvious differences between the numerical calculation results and the visual intuitive results.

At present, the parameters of dual-energy subtraction mainly include manual search and computer automatic search. One is manual search, that is, the user manually adjusts the subtraction parameters, reads the film in real time until the best subtraction effect is obtained, and at the same time determines the best subtraction parameters. The manual search method is simple to implement and has high precision, but the operation is cumbersome and time-consuming. Laborious, poor clinical experience. The other is the computer automatic search, which is completely automatically carried out by the computer according to certain criteria, and continues to search until the optimal subtraction parameters are obtained. However, the current commonly used search methods generally have the problem of insufficient precision. There are obvious differences between the numerical calculation results and the visual intuitive results. The search results are often not very ideal, and manual fine-tuning is often required to obtain the final accurate results.

SUMMARY OF THE INVENTION

In view of the problems, the present application is proposed to provide a method, apparatus, device and storage medium for calculating dual energy subtraction parameters that overcome the problems or at least partially solve the problems.

In order to solve the above problems, the present application discloses a method for calculating dual energy subtraction parameters, which is applied to calculate the soft tissue subtraction parameters and bone subtraction parameters of the shadow area in dual energy X-ray medical images, wherein the dual energy X-ray Line medical images include high-energy images and low-energy images, including steps:

Obtain the target dual-energy X-ray medical image, and perform registration processing on the target high-energy image and the target low-energy image;

Determine the area to be measured according to the position of the maximum value of the gradient amplitude image of the preset area in the target low-energy image after registration processing, and determine the high-energy sub-image block corresponding to the area to be measured in the target high-energy image and a low-energy sub-image block corresponding to the region to be measured in the target low-energy image;

According to the high-energy sub-image block and the low-energy sub-image block, determine the subtraction image corresponding to each pixel in the area to be measured, and determine the standard deviation and mean value of the subtraction image, according to the subtraction image The standard deviation and mean value of generating the relative standard deviation corresponding to each pixel in the area to be tested;

The soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation.

Further, the region to be measured is determined according to the position of the maximum value of the gradient amplitude image of the preset region in the low-energy image of the target after the registration process, and it is determined that the high-energy image of the target corresponds to the region to be measured. The step of the high-energy sub-image block and the low-energy sub-image block corresponding to the area to be measured in the target low-energy image, including:

determining the position of the preset area in the target low-energy image after registration processing, and generating the gradient magnitude image according to the pixels in the preset area;

Obtain the position of the maximum value of the gradient amplitude image, and convert the position of the maximum value of the gradient amplitude image according to the position of the preset area in the target low-energy image to determine the target position, and use the target position The neighborhood position of is set as the area to be tested;

According to the position of the area to be measured, a high-energy sub-image block corresponding to the area to be measured in the target high-energy image and a low-energy sub-image block corresponding to the area to be measured in the low-energy image of the target are determined.

Further, the step of determining the position of a preset area in the target low-energy image after registration processing, and generating the gradient magnitude image according to the pixels in the preset area, includes:

determining the position of the preset area in the target low-energy image after registration processing;

Perform low-pass filtering processing on the pixels of the preset area in the target low-energy image;

The gradient magnitude image is generated according to the pixels in the preset area after low-pass filtering.

Further, the step of generating the gradient magnitude image according to the pixels in the preset area after low-pass filtering processing includes:

determining the x-component and the y-component of the pixel gradient in the preset region after the low-pass filtering process;

The gradient magnitude image is generated according to the x-component and the y-component of the pixel gradient in the preset area.

Further, the subtraction image corresponding to each pixel in the area to be measured is determined according to the high-energy sub-image block and the low-energy sub-image block, and the standard deviation and mean value of the subtraction image are determined, according to The step of generating the relative standard deviation corresponding to each pixel in the region to be measured from the standard deviation and mean of the subtracted image includes:

According to the difference in the energy attenuation mode and photoelectric absorption effect of bone and soft tissue on X-ray photons, and combined with the ratio of the high-energy sub-image block and the low-energy sub-image block corresponding to each pixel in the to-be-measured area to determine the area to be measured. The subtraction image corresponding to each pixel;

determining the standard deviation and mean of the subtracted image corresponding to each pixel in the region to be tested;

The relative standard deviation corresponding to each pixel in the to-be-measured area is generated according to the ratio of the standard deviation of the subtracted image corresponding to each pixel in the to-be-measured area to the mean value.

Further, the steps of determining soft tissue subtraction parameters according to the minimum value of the relative standard deviation, and determining bone subtraction parameters according to the soft tissue subtraction parameters, include:

Determining the subtraction parameter corresponding to the minimum value of the relative standard deviation as the soft tissue subtraction parameter;

The bone subtraction parameter is determined according to the soft tissue subtraction parameter and the preset weight.

Further, the step of determining the bone subtraction parameters according to the soft tissue subtraction parameters and the preset weights includes:

The bone subtraction parameter is determined according to the sum of the soft tissue subtraction parameter and the preset weight; wherein the value of the preset weight is 0.25.

A computing device for dual energy subtraction parameters, which is applied to calculate soft tissue subtraction parameters and bone subtraction parameters in shadow areas in dual energy X-ray medical images, wherein the dual energy X-ray medical images include high-energy images and low-energy images ,include:

The registration module is used to obtain the target dual-energy X-ray medical image, and perform registration processing on the target high-energy image and the target low-energy image;

A determination module, configured to determine the area to be measured according to the position of the maximum value of the gradient amplitude image of the preset area in the low-energy image of the target after registration processing, and determine the area to be measured in the high-energy image of the target corresponding to the area to be measured The high-energy sub-image block and the low-energy sub-image block corresponding to the area to be measured in the target low-energy image;

A calculation module, configured to determine the subtraction image corresponding to each pixel in the area to be measured according to the high-energy sub-image block and the low-energy sub-image block, and determine the standard deviation and mean value of the subtraction image, according to The standard deviation and mean of the subtracted image generate the relative standard deviation corresponding to each pixel in the area to be measured;

An output module, configured to determine the soft tissue subtraction parameter and the bone subtraction parameter according to the minimum value of the relative standard deviation.

A computer device, comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program being executed by the processor to achieve the above-mentioned dual-energy The steps of the calculation method of the subtraction parameters.

A computer-readable storage medium stores a computer program on the computer-readable storage medium, and when the computer program is executed by a processor, implements the steps of the above-mentioned method for calculating a dual-energy subtraction parameter.

This application has the following advantages:

In the embodiment of the present application, by acquiring the target dual-energy X-ray medical image, and performing registration processing on the target high-energy image and the target low-energy image; The position of the maximum value of the value image determines the area to be measured, and determines the high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and the low-energy sub-image corresponding to the area to be measured in the low-energy image of the target block; determine the subtraction image corresponding to each pixel in the area to be measured according to the high-energy sub-image block and the low-energy sub-image block, and determine the standard deviation and mean value of the subtraction image, according to the subtraction image The relative standard deviation corresponding to each pixel in the region to be measured is generated by the standard deviation and mean value of the shadow image; the soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation. In the present application, by extracting a rectangular area with a preset size including the edge of the bone from the low-energy image, and using this as a region of interest (ROI), that is, the area to be measured, the relative standard deviation of the ROI area in the subtraction image under different pixels is calculated, Take the subtraction parameter corresponding to the minimum relative standard deviation as the soft tissue subtraction parameter, and then determine the bone subtraction parameter according to the empirical relationship between the bone and the soft tissue subtraction parameter; the determination of the ROI in this application does not involve complex feature extraction, and is actually used for calculation. The ROI of the image is much smaller than the image size, which greatly improves the efficiency of the algorithm. In principle, the algorithm has better robustness and lower computational overhead, which is easy to implement and provides a guarantee for the clinical rapid acquisition of accurate dual-energy subtraction results. , to lay a foundation for further imaging diagnosis; in addition, the relative standard deviation curve usually has a good convexity, which ensures that the search algorithm can obtain a relatively stable optimal value. It is more in line with the intuitive results of the human eye, and the effect is relatively good, and it can basically meet the clinical requirements at one time without manual fine-tuning.

Description of drawings

In order to illustrate the technical solutions of the present application more clearly, the following briefly introduces the drawings used in the description of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, which are of great significance to the art. For those of ordinary skill, other drawings can also be obtained from these drawings without creative labor.

1 is a flow chart of steps of a method for calculating dual-energy subtraction parameters provided by an embodiment of the present application;

2 is a flowchart of steps of a method for calculating dual-energy subtraction parameters provided by an embodiment of the present application;

3 is a schematic diagram of a relative standard deviation curve of a method for calculating a dual-energy subtraction parameter provided by an embodiment of the present application;

4 is an effect diagram of a method for calculating a dual-energy subtraction parameter provided by an embodiment of the present application;

5 is a structural block diagram of a device for calculating dual-energy subtraction parameters provided by an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a computer device for a method for calculating dual-energy subtraction parameters provided by an embodiment of the present application.

Detailed ways

In order to make the objects, features and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are some, but not all, embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

The core idea of the present application is that, by acquiring the target dual-energy X-ray medical image, the target high-energy image and the target low-energy image are registered; The position of the maximum value of the amplitude image determines the area to be measured, and determines the high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and the low-energy sub-image block corresponding to the area to be measured in the low-energy image of the target Image block; determine the subtraction image corresponding to each pixel in the area to be measured according to the high-energy sub-image block and the low-energy sub-image block, and determine the standard deviation and mean value of the subtraction image, according to the The standard deviation and mean of the subtracted images generate the relative standard deviation corresponding to each pixel in the area to be measured; the soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation.

It should be noted that, in any embodiment of the present application, the digital image is composed of two-dimensional elements, each element has a specific position (x, y) and amplitude f (x, y), these elements are called for pixels. The edge refers to a set of connected pixels, and the gray scale around these pixels has a significant change. If it changes sharply to another gray value with a large difference in gray level, the edge part of the image concentrates most of the information of the image, and the edge is the place where the pixel value changes rapidly, which contains the main information of the target object on the image.

1-2, a flowchart of steps of a method for calculating dual energy subtraction parameters provided by an embodiment of the present application is shown, which is applied to the calculation of soft tissue subtraction parameters and bones in shadow areas in dual energy X-ray medical images. Subtraction parameters, wherein the dual-energy X-ray medical image includes a high-energy image and a low-energy image; including the steps:

S110, acquiring the target dual-energy X-ray medical image, and performing registration processing on the target high-energy image and the target low-energy image;

S120. Determine a region to be measured according to the position of the maximum value of the gradient amplitude image of a preset region in the low-energy image of the target after registration processing, and determine the high-energy quantum corresponding to the region to be measured in the high-energy image of the target an image block and a low-energy sub-image block corresponding to the region to be measured in the target low-energy image;

S130. Determine a subtraction image corresponding to each pixel in the to-be-measured area according to the high-energy sub-image block and the low-energy sub-image block, and determine the standard deviation and mean of the subtraction image, and determine the subtraction image according to the subtraction image. The standard deviation and mean of the shadow image generate the relative standard deviation corresponding to each pixel in the area to be measured;

S140. Determine a soft tissue subtraction parameter and a bone subtraction parameter according to the minimum value of the relative standard deviation.

In the embodiment of the present application, by acquiring the target dual-energy X-ray medical image, and performing registration processing on the target high-energy image and the target low-energy image; The position of the maximum value of the value image determines the area to be measured, and determines the high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and the low-energy sub-image corresponding to the area to be measured in the low-energy image of the target block; determine the subtraction image corresponding to each pixel in the area to be measured according to the high-energy sub-image block and the low-energy sub-image block, and determine the standard deviation and mean value of the subtraction image, according to the subtraction image The relative standard deviation corresponding to each pixel in the region to be measured is generated by the standard deviation and mean value of the shadow image; the soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation. In the present application, by extracting a rectangular area with a preset size including the edge of the bone from the low-energy image, and using this as a region of interest (ROI), that is, the area to be measured, the relative standard deviation of the ROI area in the subtraction image under different pixels is calculated, Take the subtraction parameter corresponding to the minimum relative standard deviation as the soft tissue subtraction parameter, and then determine the bone subtraction parameter according to the empirical relationship between the bone and the soft tissue subtraction parameter; the determination of the ROI in this application does not involve complex feature extraction, and is actually used for calculation. The ROI of the image is much smaller than the image size, which greatly improves the efficiency of the algorithm. In principle, the algorithm has better robustness and lower computational overhead, which is easy to implement and provides a guarantee for the clinical rapid acquisition of accurate dual-energy subtraction results. , to lay the foundation for further imaging diagnosis; in addition, the relative standard deviation curve usually has a good convexity, which ensures that the search algorithm can obtain a more stable optimal value. It is more in line with the intuitive results of the human eye, and the effect is relatively good, and it can basically meet the clinical requirements at one time without manual fine-tuning.

Next, a method for calculating a dual-energy subtraction parameter in this exemplary embodiment will be further described.

As described in step S110, the target dual-energy X-ray medical image is acquired, and the target high-energy image and the target low-energy image are registered.

In an embodiment of the present invention, the specific process of "acquiring a target dual-energy X-ray medical image and registering a target high-energy image and a target low-energy image" described in step S110 can be further described with reference to the following description.

In an embodiment of the present application, the target dual-energy X-ray medical image is acquired, and the target high-energy image and the target low-energy image are registered to ensure that the same coordinates in the two images correspond to the same point in the tissue.

It should be noted that registration refers to the matching of geographic coordinates of different images obtained by different imaging methods in the same area. The process of matching and superimposing multiple images; the process of registration is as follows: first, extract feature points from two images to obtain feature points; find matching feature point pairs by similarity measurement; then obtain an image by matching feature point pairs Spatial coordinate transformation parameters; finally, the image registration is performed by the coordinate transformation parameters.

As described in step S120, the region to be tested is determined according to the position of the maximum value of the gradient amplitude image of the preset region in the target low-energy image after registration processing, and the difference between the target high-energy image and the to-be-measured image is determined. A high-energy sub-image block corresponding to the measurement area and a low-energy sub-image block corresponding to the to-be-measured area in the target low-energy image.

In an embodiment of the present application, the step S120 may be further described in conjunction with the following description: “determine the region to be tested according to the position of the maximum value of the gradient amplitude image of the preset region in the target low-energy image after registration processing, and determine The specific process of generating high-energy sub-image blocks corresponding to the area to be measured in the target high-energy image and low-energy sub-image blocks corresponding to the area to be measured in the target low-energy image”.

As described in the following steps, the position of the preset area in the target low-energy image after registration processing is determined, and the gradient magnitude image is generated according to the pixels in the preset area;

As described in the following steps, the position of the maximum value of the gradient magnitude image is obtained, and the position of the maximum value of the gradient magnitude image is converted according to the position of the preset region in the target low-energy image to determine the target position , the neighborhood position of the target position is set as the area to be measured;

As described in the following steps, according to the position of the area to be measured, a high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and a sub-image block corresponding to the area to be measured in the low-energy image of the target are determined. Low energy sub-image blocks.

In an embodiment of the present application, the position of the preset area in the target low-energy image after registration processing is determined; the pixels of the preset area in the target low-energy image are subjected to low-pass filtering processing to eliminate the influence of noise; The x-component and the y-component of the pixel gradient in the preset area after filtering; the gradient magnitude image is generated according to the x-component and the y-component of the pixel gradient in the preset area.

It should be noted that low-pass filtering is a filtering method. The rule is that low-frequency signals can pass normally, while high-frequency signals that exceed the set threshold are blocked and weakened; however, the magnitude of the blocking and weakening will depend on different frequencies. As well as different filtering purposes, in the field of digital image processing, from the frequency domain, low-pass filtering can smooth and denoise images.

In a specific implementation, according to the location of the film, a sub-region is extracted from the diagnostic region of the target low-energy image after registration processing and determined as a preset region R1 (the size of the preset region can be 300*300), The pixels of the region R1 are subjected to low-pass filtering to eliminate the influence of noise; the x-component and the y-component of the pixel gradient in the preset region after the low-pass filtering process are determined; and the x-component and the y-component of the pixel gradient in the preset region are generated. the gradient amplitude image g; obtain the position coordinate p1 of the maximum value of the gradient amplitude image, and convert the position coordinate p1 of the maximum value of the gradient amplitude image according to the position of the preset region R1 in the target low-energy image is the coordinate p2 of the target position in the low-energy image of the target, and then takes the coordinate p2 of the target position as the center, and takes its 50*50 neighborhood position as the region of interest R2, and the region of interest R2 is the area to be measured; According to the position of the area to be measured, the high-energy sub-image block R _2H and the low-energy sub-image block R _2L corresponding to the area to be measured are extracted from the target high-energy image and the target low-energy image respectively. The calculation formula of the gradient magnitude image g is as follows:

g=|g _x |+|g _y |

where g _x and g _y are the x and y components of the gradient, respectively.

It should be noted that the bone contrast of low-energy images is usually better than that of high-energy images, which is more conducive to edge extraction. Therefore, a sub-area is extracted from the diagnostic area of the target low-energy image after registration processing and determined as the preset area R1. The position of R1 can be determined according to the imaging site and based on the experience of clinical radiologists; taking the most frequently photographed chest radiograph as an example, a sub-region is usually extracted from the upper position of the two lung lobes to determine the preset region R1. The original meaning of the gradient is a vector (vector), indicating that the directional derivative of a function at this point obtains the maximum value along the direction; the gradient magnitude is the modulus of the gradient, and the image gradient represents the speed of image change, reflecting the the edge information of the image. For the edge part of the image, the gray value changes greatly, and the gradient value is also large; for the smoother part of the image, the gray value changes less, and the gradient value is also small. In order to detect edges, it is necessary to detect discontinuities in the image, and image gradients can be used to detect discontinuities.

As described in step S130, a subtraction image corresponding to each pixel in the area to be measured is determined according to the high-energy sub-image block and the low-energy sub-image block, and the standard deviation sum of the subtraction image is determined The mean value, the relative standard deviation corresponding to each pixel in the area to be measured is generated according to the standard deviation and mean value of the subtracted image.

In an embodiment of the present application, the step S130 of “determining the subtraction image corresponding to each pixel in the region to be measured according to the high-energy sub-image block and the low-energy sub-image block, and The specific process of determining the standard deviation and mean value of the subtraction image, and generating the relative standard deviation corresponding to each pixel in the area to be measured according to the standard deviation and mean value of the subtraction image.

As described in the following steps, according to the difference in the energy attenuation mode and photoelectric absorption effect of bone and soft tissue on X-ray photons, and in combination with the ratio of the high-energy sub-image block to the low-energy sub-image block corresponding to each pixel in the region to be measured the subtraction image corresponding to each pixel in the area to be tested;

As described in the following steps, determine the standard deviation and mean value of the subtraction image corresponding to each pixel in the to-be-measured area;

As described in the following steps, the relative standard deviation corresponding to each pixel in the to-be-measured area is generated according to the ratio of the standard deviation of the subtracted image corresponding to each pixel in the to-be-measured area to the mean value.

In a specific implementation, according to the difference in the energy attenuation mode and photoelectric absorption effect of bone and soft tissue on X-ray photons, combined with the high-energy sub-image block R _2H and the low-energy sub-image block R corresponding to each pixel in the region to be measured The ratio of _2L determines the subtraction image R _DES corresponding to each pixel in the area to be measured, and determines the standard deviation STD and mean AVG of the subtraction image R _DES corresponding to each pixel in the area to be measured, according to The ratio of the standard deviation STD of the subtraction image R _DES corresponding to each pixel in the area to be measured to the mean AVG generates the relative standard deviation relative-std corresponding to each pixel in the area to be measured.

In an embodiment of the present application, the calculation formula of the subtracted image R _DES is as follows:

where x and y are the pixel coordinates, and w is the subtraction parameter. Let w vary in the interval [0.2, 0.7] with a step size of 0.01, and a subtraction image sequence can be obtained.

Referring to FIG. 3 , a schematic diagram of a relative standard deviation curve of a method for calculating dual-energy subtraction parameters provided by an embodiment of the present application is shown. A subtraction image R _DES is calculated, and each subtraction parameter corresponds to a subtraction image, and thus corresponds to a relative standard deviation, thereby obtaining a relative standard deviation curve. Its relative standard deviation curve usually has good convex properties, which ensures that the search algorithm can obtain a relatively stable optimal value. The formula for calculating the relative standard deviation relative-std is as follows:

As described in step S140, the soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation.

In an embodiment of the present application, the specific process of "determining soft tissue subtraction parameters and bone subtraction parameters according to the minimum value of the relative standard deviation" in step S140 may be further described with reference to the following description.

As described in the following steps, the subtraction parameter corresponding to the minimum value of the relative standard deviation is determined as the soft tissue subtraction parameter;

As described in the following steps, bone subtraction parameters are determined according to the soft tissue subtraction parameters and preset weights.

In a specific implementation, according to the relative standard deviation calculated above, the subtraction parameter corresponding to the minimum relative standard deviation is used as the soft tissue subtraction parameter w _S , and then the preset weight is determined according to the statistical data of a large number of experiments. is 0.25, and the bone subtraction parameter w _B is determined according to the sum of the soft tissue subtraction parameter w _S and the preset weight.

It should be noted that the minimum relative standard deviation reflects the bone edge with the weakest visibility, and the corresponding subtraction result is visually intuitive as a soft tissue image, so the soft tissue subtraction parameter is determined according to the minimum relative standard deviation. The relationship between the soft tissue subtraction parameter w _S and the bone subtraction parameter w _B calculated according to a large number of experiments is as follows:

w _B = w _S +0.25

According to the relationship between the soft tissue subtraction parameter w _S and the bone subtraction parameter w _B , and in combination with the determined soft tissue subtraction parameters, the bone subtraction parameter can be determined.

Referring to FIG. 4 , an effect diagram of a method for calculating a dual-energy subtraction parameter provided by an embodiment of the present application is shown. From left to right are standard images, soft tissue images, and bone images.

In an embodiment of the present application, the taken chest anteroposterior film is processed according to the above-mentioned method, the dual-energy X-ray medical image of the chest anteroposterior film is obtained, and the high-energy image and the low-energy image are registered to ensure that the two The same coordinates in the images correspond to the same point in the tissue; a sub-region is extracted from the diagnostic region of the low-energy image after registration processing and determined as the preset region R1 (the size of the preset region is 300*300). The pixels of the region R1 are subjected to low-pass filtering to eliminate the influence of noise, and the x-component and the y-component of the pixel gradient in the preset region after the low-pass filtering process are determined; the gradient magnitude image g; obtain the position coordinate p1 of the maximum value of the gradient magnitude image, and convert the position coordinate p1 of the maximum value of the gradient magnitude image into The coordinate p2 of the target position in the low-energy image, and then taking the coordinate p2 of the target position as the center, the 50*50 neighborhood position is set as the region of interest R2, and the region of interest R2 is the region to be measured; The position of the measurement area, respectively extract the high-energy sub-image block R _2H and the low-energy sub-image block R _2L corresponding to the area to be measured in the target high-energy image and the target low-energy image; and photoelectric absorption effect, and combine the ratio of the high-energy sub-image block R _2H and the low-energy sub-image block R _2L corresponding to each pixel in the area to be measured to determine the subtraction image corresponding to each pixel in the area to be measured R _DES , determine the standard deviation STD and mean AVG of the subtraction image R _DES corresponding to each pixel in the area to be measured, according to the standard of the subtraction image R _DES corresponding to each pixel in the area to be measured The ratio of the difference STD to the mean AVG generates the relative standard deviation relative-std corresponding to each pixel in the area to be measured; the subtraction parameter corresponding to the minimum relative standard deviation is 0.43, so the soft tissue subtraction parameter w _S is 0.43, and the bone subtraction parameter is 0.43. The shadow parameter w _B is 0.68.

As for the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for related parts.

Referring to FIG. 5 , a structural block diagram of a dual-energy subtraction parameter calculation device provided by an embodiment of the present application is shown; the above-mentioned dual-energy subtraction parameter calculation device is applied to calculate the shadow area in dual-energy X-ray medical images The soft tissue subtraction parameters and bone subtraction parameters, wherein, the dual-energy X-ray medical images include high-energy images and low-energy images, specifically including:

The registration module 510 is used for acquiring the target dual-energy X-ray medical image, and performing registration processing on the target high-energy image and the target low-energy image;

The determination module 520 is used to determine the area to be measured according to the position of the maximum value of the gradient amplitude image of the preset area in the target low-energy image after registration processing, and determine the area to be measured in the target high-energy image and the area to be measured. Corresponding high-energy sub-image blocks and low-energy sub-image blocks corresponding to the area to be measured in the target low-energy image;

The calculation module 530 is configured to determine the subtraction image corresponding to each pixel in the area to be measured according to the high-energy sub-image block and the low-energy sub-image block, and determine the standard deviation and mean of the subtraction image, generating a relative standard deviation corresponding to each pixel in the region to be measured according to the standard deviation and mean of the subtracted image;

The output module 540 is configured to determine the soft tissue subtraction parameter and the bone subtraction parameter according to the minimum value of the relative standard deviation.

In an embodiment of the present application, the determining module 520 includes:

a gradient amplitude calculation submodule, used for determining the position of a preset area in the target low-energy image after registration processing, and generating the gradient amplitude image according to the pixels in the preset area;

Determine the area to be measured sub-module, obtain the position of the maximum value of the gradient amplitude image, and convert the position of the maximum value of the gradient amplitude image according to the position of the preset area in the target low-energy image to determine the target position, and the neighborhood position of the target position is set as the area to be measured;

Determine sub-image block sub-module, according to the position of the area to be measured, determine the high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and the low-energy image of the target corresponding to the area to be measured. of low-energy sub-image blocks.

In an embodiment of the present application, the gradient magnitude calculation submodule includes:

a sub-module for determining a preset area, which is used to determine the position of the preset area in the low-energy image of the target after registration processing;

a low-pass filtering sub-module, configured to perform low-pass filtering processing on the pixels of the preset area in the target low-energy image;

The generating sub-module is configured to generate the gradient magnitude image according to the pixels in the preset area after the low-pass filtering process.

In an embodiment of the present application, the generating submodule includes:

The first generation submodule is used to determine the x-component and the y-component of the pixel gradient in the preset area after the low-pass filtering process;

The second generating sub-module is configured to generate the gradient magnitude image according to the x component and the y component of the pixel gradient in the preset area.

In an embodiment of the present application, the computing module 530 includes:

The first calculation sub-module is used for combining the high-energy sub-image block and the low-energy sub-image block corresponding to each pixel in the region to be measured according to the difference of the energy attenuation mode and photoelectric absorption effect of bone and soft tissue on X-ray photons. The ratio determines the subtraction image corresponding to each pixel in the to-be-measured area;

a second calculation submodule, configured to determine the standard deviation and mean of the subtracted image corresponding to each pixel in the region to be measured;

The third calculation sub-module is configured to generate the relative standard deviation corresponding to each pixel in the area to be measured according to the ratio of the standard deviation of the subtracted image corresponding to each pixel in the area to be measured to the mean value.

In an embodiment of the present application, the output module 540 includes:

a first output submodule, configured to determine a soft tissue subtraction parameter according to the subtraction parameter corresponding to the minimum value of the relative standard deviation;

The second output sub-module is configured to determine the bone subtraction parameter according to the soft tissue subtraction parameter and the preset weight.

In an embodiment of the present application, the second output sub-module includes:

A submodule for determining bone subtraction parameters, configured to determine the bone subtraction parameters according to the sum of the soft tissue subtraction parameters and a preset weight; wherein the value of the preset weight is 0.25.

Referring to FIG. 6 , a schematic structural diagram of a computer device for a method for calculating dual-energy subtraction parameters provided by an embodiment of the present application is shown, which may specifically include the following:

The computer device 12 described above is in the form of a general-purpose computing device, and the components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, connecting various system components (including the system memory 28 and the processing unit) 16) of the bus 18.

The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or a memory controller, a peripheral bus 18, a graphics acceleration port, a processor, or an office using any of a variety of bus 18 structures. Domain bus 18. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus 18, Micro Channel Architecture (MAC) bus 18, Enhanced ISA bus 18, Audio Video Electronics Standards Association (VESA) local bus 18, and Peripheral Component Interconnect (PCI) bus 18 .

Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including both volatile and nonvolatile media, removable and non-removable media.

System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 . Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as "hard drives"). Although not shown in Figure 4, a magnetic disk drive may be provided for reading and writing to removable non-volatile magnetic disks (eg "floppy disks"), as well as removable non-volatile optical disks (eg CD-ROM, DVD-ROM) or other optical media) to read and write optical drives. In these cases, each drive may be connected to bus 18 through one or more data media interfaces. The memory may include at least one program product having a set (eg, at least one) of program modules 42 configured to perform the functions of various embodiments of the present invention.

A program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42 and program data, each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the described embodiments of the present invention.

The computer device 12 may also communicate with one or more external devices 14 (eg, a keyboard, pointing device, display 24, camera, etc.) and also with one or more devices that enable an operator to interact with the computer device 12, and Communicate with any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. Such communication may take place through an input/output (I/O) interface 22 . Also, the computer device 12 may communicate with one or more networks (eg, a local area network (LAN)), a wide area network (WAN), and/or a public network (eg, the Internet) through a network adapter 20 . As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18 . It should be understood that, although not shown in FIG. 3, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, Tape drives and data backup storage systems 34 and the like.

The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , for example, implementing a method for adaptively identifying a rectangular frame of a beamer provided by an embodiment of the present invention.

That is, when the above-mentioned processing unit 16 executes the above-mentioned program, it realizes the following steps: acquiring the target dual-energy X-ray medical image, and performing registration processing on the target high-energy image and the target low-energy image; according to the target low-energy image after registration processing The position of the maximum value of the gradient amplitude image in the preset area in the target area determines the area to be measured, and determines the high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and the low-energy image of the target that is similar to the area to be measured. The low-energy sub-image block corresponding to the measurement area is determined; the subtraction image corresponding to each pixel in the to-be-measured area is determined according to the high-energy sub-image block and the low-energy sub-image block, and the standard deviation of the subtraction image is determined and the mean value, the relative standard deviation corresponding to each pixel in the area to be measured is generated according to the standard deviation and mean value of the subtracted image; the soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation. In the present application, by extracting a rectangular area with a preset size including the edge of the bone from the low-energy image, and using this as a region of interest (ROI), that is, the area to be measured, the relative standard deviation of the ROI area in the subtraction image under different pixels is calculated, Take the subtraction parameter corresponding to the minimum relative standard deviation as the soft tissue subtraction parameter, and then determine the bone subtraction parameter according to the empirical relationship between the bone and the soft tissue subtraction parameter; the determination of the ROI in this application does not involve complex feature extraction, and is actually used for calculation. The ROI of the image is much smaller than the image size, which greatly improves the efficiency of the algorithm. In principle, the algorithm has better robustness and lower computational overhead, which is easy to implement and provides a guarantee for the clinical rapid acquisition of accurate dual-energy subtraction results. , to lay a foundation for further imaging diagnosis; in addition, the relative standard deviation curve usually has a good convexity, which ensures that the search algorithm can obtain a relatively stable optimal value. It is more in line with the intuitive results of the human eye, and the effect is relatively good, and it can basically meet the clinical requirements at one time without manual fine-tuning.

In the embodiments of the present application, the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, realizes a dual-energy subtraction parameter as provided by all the embodiments of the present application. Calculation method:

That is to say, when the program is executed by the processor, it is realized: including the steps of: acquiring the target dual-energy X-ray medical image, and performing registration processing on the target high-energy image and the target low-energy image; The position of the maximum value of the gradient amplitude image in the preset area determines the area to be measured, and determines the high-energy sub-image block corresponding to the area to be measured in the high-energy image of the target and the low-energy image of the target that is the same as the area to be measured. The low-energy sub-image block corresponding to the area; according to the high-energy sub-image block and the low-energy sub-image block, the subtraction image corresponding to each pixel in the area to be measured is determined, and the standard deviation sum of the subtraction image is determined. The mean value, the relative standard deviation corresponding to each pixel in the area to be measured is generated according to the standard deviation and mean value of the subtracted image; the soft tissue subtraction parameter and the bone subtraction parameter are determined according to the minimum value of the relative standard deviation. In the present application, by extracting a rectangular area with a preset size including the edge of the bone from the low-energy image, and using this as a region of interest (ROI), that is, the area to be measured, the relative standard deviation of the ROI area in the subtraction image under different pixels is calculated, Take the subtraction parameter corresponding to the minimum relative standard deviation as the soft tissue subtraction parameter, and then determine the bone subtraction parameter according to the empirical relationship between the bone and the soft tissue subtraction parameter; the determination of the ROI in this application does not involve complex feature extraction, and is actually used for calculation. The ROI of the image is much smaller than the image size, which greatly improves the efficiency of the algorithm. In principle, the algorithm has better robustness and lower computational overhead, which is easy to implement and provides a guarantee for the clinical rapid acquisition of accurate dual-energy subtraction results. , to lay a foundation for further imaging diagnosis; in addition, the relative standard deviation curve usually has a good convexity, which ensures that the search algorithm can obtain a relatively stable optimal value. It is more in line with the intuitive results of the human eye, and the effect is relatively good, and it can basically meet the clinical requirements at one time without manual fine-tuning.

Any combination of one or more computer-readable media may be employed. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (a non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable Programmable Read Only Memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural programming language - such as the "C" language or similar programming language. The program code may execute entirely on the operator's computer, partly on the operator's computer, as a stand-alone software package, partly on the operator's computer and partly on a remote computer or entirely on the remote computer or server . In the case of a remote computer, the remote computer may be connected to the operator's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider) to connect via the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments may be referred to each other.

Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present application.

Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article or terminal device that includes a list of elements includes not only those elements, but also a non-exclusive list of elements. other elements, or also include elements inherent to such a process, method, article or terminal equipment. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

A method, device, device and storage medium for calculating dual-energy subtraction parameters provided by the present application have been described above in detail. In this paper, specific examples are used to illustrate the principles and implementations of the present application. The above embodiments The description is only used to help understand the method of the present application and its core idea; meanwhile, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific embodiments and application scope. The contents of this specification should not be construed as limiting the application.

Claims (10)

1. A method for calculating dual-energy subtraction parameters is applied to calculating soft tissue subtraction parameters and bone subtraction parameters of shadow areas in dual-energy X-ray medical images, wherein the dual-energy X-ray medical images comprise high-energy images and low-energy images, and the method is characterized by comprising the following steps of:

acquiring a target dual-energy X-ray medical image, and performing registration processing on a target high-energy image and a target low-energy image;

determining a region to be detected according to the position of the maximum value of the gradient amplitude image of a preset region in the target low-energy image after registration processing, and determining a high-energy sub-image block corresponding to the region to be detected in the target high-energy image and a low-energy sub-image block corresponding to the region to be detected in the target low-energy image;

determining a subtraction image corresponding to each pixel in the region to be detected according to the high-energy sub image blocks and the low-energy sub image blocks, determining a standard deviation and a mean value of the subtraction image, and generating a relative standard deviation corresponding to each pixel in the region to be detected according to the standard deviation and the mean value of the subtraction image;

and determining soft tissue subtraction parameters and bone subtraction parameters according to the minimum value of the relative standard deviation.

2. The method for calculating the dual-energy subtraction parameter according to claim 1, wherein the step of determining a region to be measured according to a position of a maximum value of a gradient amplitude image of a preset region in the target low-energy image after the registration processing, and determining a high-energy sub-image block corresponding to the region to be measured in the target high-energy image and a low-energy sub-image block corresponding to the region to be measured in the target low-energy image comprises:

determining the position of a preset region in the target low-energy image after registration processing, and generating the gradient amplitude image according to pixels in the preset region;

acquiring the position of the maximum value of the gradient amplitude image, converting the position of the maximum value of the gradient amplitude image according to the position of the preset area in the target low-energy image to determine a target position, and setting the neighborhood position of the target position as an area to be detected;

and determining a high-energy sub image block corresponding to the area to be detected in the target high-energy image and a low-energy sub image block corresponding to the area to be detected in the target low-energy image according to the position of the area to be detected.

3. The method for calculating the dual-energy subtraction parameter according to claim 2, wherein the step of determining the position of a preset region in the target low-energy image after the registration processing and generating the gradient magnitude image according to pixels in the preset region comprises:

determining the position of a preset region in the target low-energy image after registration processing;

carrying out low-pass filtering processing on pixels in a preset area in the target low-energy image;

and generating the gradient amplitude image according to the pixels in the preset area after the low-pass filtering processing.

4. The method for calculating the dual energy subtraction parameter according to claim 3, wherein the step of generating the gradient magnitude image according to the pixels in the preset region after the low pass filtering process comprises:

determining an x component and a y component of a pixel gradient in a preset area after low-pass filtering;

and generating the gradient amplitude image according to the x component and the y component of the pixel gradient in the preset area.

5. The method for calculating dual-energy subtraction parameters according to claim 1, wherein the step of determining a subtraction image corresponding to each pixel in the region to be measured according to the high-energy sub-image blocks and the low-energy sub-image blocks, determining a standard deviation and a mean value of the subtraction image, and generating a relative standard deviation corresponding to each pixel in the region to be measured according to the standard deviation and the mean value of the subtraction image comprises:

determining a subtraction image corresponding to each pixel in the region to be detected by combining the ratio of a high-energy sub image block and a low-energy sub image block corresponding to each pixel in the region to be detected according to the difference between the energy attenuation mode and the photoelectric absorption effect of bones and soft tissues on X-ray photons;

determining the standard deviation and the mean value of the subtraction image corresponding to each pixel in the region to be detected;

and generating a relative standard deviation corresponding to each pixel in the region to be detected according to the ratio of the standard deviation of the subtraction image corresponding to each pixel in the region to be detected to the mean value.

6. The method of claim 1, wherein the step of determining soft tissue subtraction parameters according to the minimum of the relative standard deviations and bone subtraction parameters according to the soft tissue subtraction parameters comprises:

determining the subtraction parameters corresponding to the minimum value of the relative standard deviation as soft tissue subtraction parameters;

and determining the skeleton subtraction parameters according to the soft tissue subtraction parameters and preset weights.

7. The method of claim 6, wherein the step of determining bone subtraction parameters according to the soft tissue subtraction parameters and preset weights comprises:

determining a skeleton subtraction parameter according to the sum of the soft tissue subtraction parameter and a preset weight; wherein the preset weight has a value of 0.25.

8. A dual-energy subtraction parameter calculation apparatus for calculating soft tissue subtraction parameters and bone subtraction parameters of a shadow region in a dual-energy X-ray medical image, wherein the dual-energy X-ray medical image comprises a high-energy image and a low-energy image, the dual-energy X-ray medical image comprising:

the registration module is used for acquiring a target dual-energy X-ray medical image and registering the target high-energy image and the target low-energy image;

the determining module is used for determining a region to be detected according to the position of the maximum value of the gradient amplitude image of a preset region in the target low-energy image after registration processing, and determining a high-energy sub image block corresponding to the region to be detected in the target high-energy image and a low-energy sub image block corresponding to the region to be detected in the target low-energy image;

the calculation module is used for determining a subtraction image corresponding to each pixel in the region to be detected according to the high-energy sub-image blocks and the low-energy sub-image blocks, determining a standard deviation and a mean value of the subtraction image, and generating a relative standard deviation corresponding to each pixel in the region to be detected according to the standard deviation and the mean value of the subtraction image;

and the output module is used for determining the soft tissue subtraction parameters and the bone subtraction parameters according to the minimum value of the relative standard deviation.

9. A computer device comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing the method of any one of claims 1 to 7.

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

Images