WO2022032456A1 - Image reconstruction method and apparatus, and computer storage medium - Google Patents

Abstract

An image reconstruction method and apparatus, and a computer storage medium. The image reconstruction method comprises: acquiring a first image and a second image, which are obtained by scanning a target area (101); according to the first image and the second image, determining a first decomposed image of a first element and a second decomposed image of a second element in the target area (102); and respectively performing weighted summation on the first decomposed image and the second decomposed image by means of a first weight set corresponding to the first element and a second weight set corresponding to the second element, so as to obtain a reconstructed image (103). Different elements are decomposed according to images obtained under two energies, and weighted summation is performed on the decomposed image of each element, so that different elements are displayed more clearly, and the image quality is improved.

Description

Image reconstruction method, device and computer storage medium technical field

The embodiments of the present application relate to the technical field of image processing, and in particular, to an image reconstruction method, an apparatus, and a computer storage medium.

Background technique

Computed Tomography (CT) equipment scans the body so that doctors can observe it. In order to improve the efficiency of doctors' reading and diagnosis, the same object can be scanned under different energies. The CT reconstruction images under two groups of energies are usually fused into one image by a certain proportion of mixing method, which makes the display clearer and facilitates observation.

In the related art, linear mixing, nonlinear mixing, Gaussian mixing, etc. are performed on images obtained under two energies. However, in the process of realizing the above image reconstruction, because the images obtained under the two energies are directly mixed, the images usually contain beam hardening artifacts, which affect the image quality.

SUMMARY OF THE INVENTION

In view of this, one of the technical problems solved by the embodiments of the present invention is to provide an image reconstruction method, device and computer storage medium to overcome the poor image quality caused by the beam hardening artifacts contained in the image in the prior art Defects.

In a first aspect, an embodiment of the present application provides an image reconstruction method, which includes:

Obtain a first image and a second image obtained by scanning the target area, the first image and the second image are generated based on different ray energies; determine the first decomposition of the first element in the target area according to the first image and the second image The second decomposed image of the image and the second element; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, the first decomposed image and the second decomposed image are respectively weighted and summed to obtain Rebuild the image.

Optionally, in an embodiment of the present application, determining the first decomposed image of the first element and the second decomposed image of the second element in the target area according to the first image and the second image includes:

According to the first image and the second image, in the target area, calculate the decomposed pixel value of the first element and the decomposed pixel value of the second element contained in each pixel; The decomposed pixel values of the two elements obtain the first decomposed image and the second decomposed image.

Optionally, in an embodiment of the present application, the method further includes: determining at least two distribution bands according to the distribution of the decomposed pixel values of the first element; determining the weight of each distribution band, and obtaining the first A set of weights.

Optionally, in an embodiment of the present application, the smaller the decomposed pixel value of the first element, the smaller the weight of the corresponding distribution band, the larger the decomposed pixel value of the first element, the smaller the weight of the corresponding distribution band. the larger the value.

Optionally, in an embodiment of the present application, the first decomposed image and the second decomposed image are weighted respectively by using the first weight set corresponding to the first element and the second weight set corresponding to the second element. Summed to get the reconstructed image, including:

In the first decomposed image, the decomposed pixel value of the first element of each pixel is multiplied by the corresponding weight in the first weight set to obtain the first image to be fused of the first element; in the second decomposed image, The decomposed pixel value of the second element of each pixel is multiplied by the corresponding weight in the second weight set to obtain the second image to be fused of the second element; the corresponding position of the first image to be fused and the second image to be fused The pixel values of , are added to obtain the reconstructed image.

Optionally, in an embodiment of the present application, acquiring the first image and the second image obtained by scanning the target area, including:

The first image is obtained by scanning the target area with a first ray source at a first energy, and a second image is obtained by scanning the target area with a second ray source at a second energy. The first energy is different from the second energy.

Optionally, in an embodiment of the present application, acquiring the first image and the second image obtained by scanning the target area, including:

The first detector is used to receive rays for scanning the target area to obtain a first image, and the second detector is used to receive rays for scanning the target area to obtain a second image.

Optionally, in an embodiment of the present application, acquiring the first image and the second image obtained by scanning the target area includes: using a multi-layer flat-panel detector to receive rays that scan the target area, passing through two layers of the The tablet obtains the first image and the second image, respectively.

Optionally, in an embodiment of the present application, the first element is a water material, and the second element is a bone material.

In a second aspect, an embodiment of the present application provides an image reconstruction apparatus, including: an acquisition module, a decomposition module, and a reconstruction module;

Wherein, the acquisition module is used to acquire the first image and the second image obtained by scanning the target area, and the first image and the second image are generated based on different ray energies;

A decomposition module for determining the first decomposed image of the first element and the second decomposed image of the second element in the target area according to the first image and the second image;

The reconstruction module is configured to use the first weight set corresponding to the first element and the second weight set corresponding to the second element to perform weighted summation on the first decomposed image and the second decomposed image respectively to obtain a reconstructed image.

In a third aspect, an embodiment of the present application provides a computer storage medium, where a computer program is stored on the computer storage medium, and when the processor executes the computer program, the image reconstruction method described in the first aspect is implemented.

In a fourth aspect, an embodiment of the present application provides an image reconstruction device, including: a processor, an imaging source, a multi-layer flat panel detector, and a frame; the imaging source and the multi-layer flat panel detector are arranged on the frame; the processor is configured to execute The pre-stored computer program implements the image reconstruction method described in the first aspect.

In a fifth aspect, an embodiment of the present application provides a radiotherapy apparatus, including: a processor, an imaging source, a multi-layer flat panel detector, a rack, a treatment source, and a treatment couch; the imaging source, the multi-layer flat panel detector and the treatment source are arranged in on the rack; the processor is used for executing a pre-stored computer program to implement the image reconstruction method according to any one of claims 1-9.

The image reconstruction method, device, and computer storage medium provided by the embodiments of the present application acquire a first image and a second image obtained by scanning a target area; determine the first decomposition of the first element in the target area according to the first image and the second image The second decomposed image of the image and the second element; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, the first decomposed image and the second decomposed image are respectively weighted and summed to obtain Rebuild the image. Because different elements are decomposed according to the images obtained under the two energies, and the decomposed images of each element are weighted and summed, the different elements are displayed more clearly and the image quality is improved.

Description of drawings

Hereinafter, some specific embodiments of the embodiments of the present application will be described in detail by way of example and not limitation with reference to the accompanying drawings. The same reference numbers in the figures designate the same or similar parts or parts. It will be understood by those skilled in the art that the drawings are not necessarily to scale. In the attached picture:

1 is a flowchart of an image reconstruction method provided in Embodiment 1 of the present application;

2 is a flowchart of an image reconstruction method according to Embodiment 2 of the present application;

FIG. 3 is a schematic diagram of a reconstructed image effect according to Embodiment 2 of the present application;

FIG. 4 is a structural diagram of an image reconstruction apparatus according to Embodiment 3 of the present application;

FIG. 5 is a structural diagram of another image reconstruction apparatus provided in Embodiment 3 of the present application;

FIG. 6 is a structural diagram of an image reconstruction apparatus according to Embodiment 4 of the present application;

FIG. 7 is a structural diagram of a radiotherapy apparatus according to Embodiment 5 of the present application.

detailed description

The specific implementation of the embodiments of the present invention is further described below with reference to the accompanying drawings of the embodiments of the present invention.

Embodiment 1.

Embodiment 1 of the present application provides an image reconstruction method. As shown in FIG. 1 , FIG. 1 is a flowchart of an image reconstruction method provided by an embodiment of the present application. The image reconstruction method includes the following steps:

101. Acquire a first image and a second image obtained by scanning a target area.

It should be noted that the first image and the second image are generated based on different ray energies. The image reconstruction method provided in this embodiment of the present application can be applied to radiographic imaging, where the rays may be X-rays or mixed light rays (for example, white light rays). The target area is the area where the target object is imaged and displayed. For example, if the target object is the human body, and X-rays are used to image the human chest, the target area is the human chest; for another example, the target object is the human body, and the face is imaged with natural light , then the target area is a human face. Of course, this is just an exemplary description, which does not mean that the present application is limited to this.

Here, four specific examples of the imaging methods of the first image and the second image are described respectively:

Optionally, in the first example, different ray sources are used to generate rays of different energies, and the first image and the second image obtained by scanning the target area are obtained, including:

The first image is obtained by scanning the target area with a first ray source at a first energy, and a second image is obtained by scanning the target area with a second ray source at a second energy. The first energy is different from the second energy. In the first example, there are two ray sources that emit rays of different energy. The first ray source emits rays of the first energy, and the second ray source emits rays of the second energy. A first image and a second image are obtained by scanning.

Optionally, in the second example, different detectors are used to receive rays of different energies to obtain the first image and the second image obtained by scanning the target area, including:

The first detector is used to receive rays for scanning the target area to obtain a first image, and the second detector is used to receive rays for scanning the target area to obtain a second image. In the second example, the target area can be imaged by different detectors using the same ray source, and the ray energy received by the two detectors (ie, the first detector and the second detector) is different, thereby forming different energies The first and second images below.

Optionally, in a third example, using a multi-layer flat panel detector to receive rays for imaging, and acquiring the first image and the second image obtained by scanning the target area, includes: using the multi-layer flat panel detector to receive and perform imaging on the target area. The scanned rays pass through the two layers of the flat plate to obtain the first image and the second image, respectively. Exemplarily, the multi-layer flat panel detector may be a double-layer flat panel detector, the radiation source emits rays from top to bottom, the first detector may be arranged above the second detector, and after the rays pass through the target area, the first detector emits rays. Imaging, the first detector absorbs a part of the ray, and the unabsorbed ray continues downward. After reaching the second detector, the second detector is used for imaging. In the process of emitting rays from the ray source, the two layers of the double-layer flat-panel detector are used. The tablet can generate the first image and the second image simultaneously. The flat plate of the first layer may be an 80KV flat plate, and the flat plate of the second layer may be a flat plate of 140 KV. Of course, this is just an exemplary illustration.

Optionally, in a fourth example, acquiring the first image and the second image obtained by scanning the target area includes: setting a first voltage to the ray source, and using the rays emitted by the ray source under the first voltage to perform a ray on the target area. The first image is obtained by imaging; the second voltage is set on the radiation source, and the target area is imaged by using the radiation emitted by the radiation source under the second voltage to obtain the second image. Different voltages can make the ray source emit rays of different energies, and there is no need to set up two ray sources or two detectors, and the device structure is simpler.

102. Determine a first decomposed image of the first element and a second decomposed image of the second element in the target area according to the first image and the second image.

Optionally, in an embodiment of the present application, determining the first decomposed image of the first element and the second decomposed image of the second element in the target area according to the first image and the second image includes:

According to the first image and the second image, in the target area, calculate the decomposed pixel value of the first element and the decomposed pixel value of the second element contained in each pixel; The decomposed pixel values of the two elements obtain the first decomposed image and the second decomposed image.

It should be noted that the first decomposed image and the second decomposed image may be obtained by using a statistical iterative reconstruction algorithm. The first decomposed image may include the decomposed pixel value of the first element in each pixel, or it can be said to be the decomposition coefficient of the first element in each pixel or the energy density or image density of the first element. The name of the decomposed pixel value is not limited. The decomposed pixel value of the first element in a pixel is used to indicate the pixel component of the decomposed first element in the pixel. Similarly, the decomposed pixel value of the second element is used to indicate the pixel in the pixel. The pixel component of the decomposed second element. Exemplarily, in an embodiment of the present application, the first element may be a water material, the second element may be a bone material, and both the first image and the second image may be regarded as pixels and/or bone materials of the water material. The result of the pixel composition of the material, that is, each pixel in the first image and the second image is the result of the pixel composition of the water material and/or the pixel composition of the bone material, and each pixel is decomposed to obtain the pixel composition of the water material respectively. and the pixel composition of the bone material. Of course, this is just an exemplary description, which does not mean that the present application is limited thereto.

103. Using the first weight set corresponding to the first element and the second weight set corresponding to the second element, respectively perform weighted summation on the first decomposed image and the second decomposed image to obtain a reconstructed image.

Optionally, in an embodiment of the present application, the first decomposed image and the second decomposed image are weighted respectively by using the first weight set corresponding to the first element and the second weight set corresponding to the second element. Summed to get the reconstructed image, including:

In the first decomposed image, the decomposed pixel value of the first element of each pixel is multiplied by the corresponding weight in the first weight set to obtain the first image to be fused of the first element; in the second decomposed image, The decomposed pixel value of the second element of each pixel is multiplied by the corresponding weight in the second weight set to obtain the second image to be fused of the second element; the corresponding position of the first image to be fused and the second image to be fused The pixel values of , are added to obtain the reconstructed image.

The first weight set may include at least one weight, and the second weight set may include at least one weight. It should be noted that each pixel in the first decomposed image corresponds to one weight in the first weight set, and the first Each pixel in the binary decomposition image corresponds to a weight in the second weight set. According to the correspondence between the weight and the pixel, the pixel value of each pixel in the first decomposed image can be multiplied by the corresponding weight to obtain the first image to be fused and the second image to be fused, and the first image to be fused and the second image to be fused can be obtained by multiplying the pixel value of each pixel in the first decomposed image by the corresponding weight value. The pixel values of the corresponding positions of the images to be fused are added to obtain a reconstructed image.

It should be noted that, in the first weight set and the second weight set, the weights may be set according to the decomposed pixel value of the first element and the decomposed pixel value of the second element. Exemplarily, in an embodiment of the present application, the method further includes: determining at least two distribution bands according to the distribution of the decomposed pixel values of the first element; determining the weight of each distribution band, and obtaining the first A set of weights. A histogram may be generated according to the decomposed pixel values of the first element, and at least one distribution band may be determined according to the distribution of the decomposed pixel values of the first element in the histogram. Optionally, the smaller the decomposed pixel value of the first element is, the smaller the weight of the corresponding distribution band is, and the larger the decomposed pixel value of the first element is, the larger the weight of the corresponding distribution band is. After weighting, the comparison of the decomposed pixel values of the first element can be made more obvious, which is convenient for observation. Of course, the second weight set corresponding to the second element may also set the weight in the manner of the first weight set, which is only an exemplary description here, and does not mean that the present application is limited thereto.

Combining steps 101-103, because according to the first image and the second image, the pixel components of different elements are decomposed, and the weighted summation of different elements and different pixels in the same element can make the contrast of different pixels in the image more obvious. , for easy observation.

The image reconstruction method, device, and computer storage medium provided by the embodiments of the present application acquire a first image and a second image obtained by scanning a target area; determine the first decomposition of the first element in the target area according to the first image and the second image The second decomposed image of the image and the second element; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, the first decomposed image and the second decomposed image are respectively weighted and summed to obtain Rebuild the image. Because different elements are decomposed according to the images obtained under the two energies, and the decomposed images of each element are weighted and summed, the different elements are displayed more clearly and the image quality is improved.

Embodiment two,

Based on the image reconstruction method provided in the first embodiment of the present application, the second embodiment of the present application provides an image reconstruction method, and further describes the image reconstruction method described in the first embodiment. This embodiment takes CT image reconstruction as an example. The image reconstruction method provided by this embodiment includes the following steps:

Step 201: Scan the target area under the first energy and the second energy respectively to obtain a first image and a second image.

In this embodiment, the first image and the second image are CT projection images obtained by scanning the target area of the target at the first energy and the second energy, respectively.

Step 202 , according to the first image and the second image, use a statistical iterative reconstruction algorithm to obtain the decomposition image of the water material and the decomposition image of the bone material.

In this embodiment, the first element is a water material, the second element is a bone material, the first decomposition image is a water material decomposition image, and the second decomposition image is a bone material decomposition image.

Step 203: Perform histogram statistics on the water material decomposition image to obtain at least one distribution band of the water material decomposition image.

Step 204: Multiply the decomposed pixel value of the first element of each pixel in the first decomposed image by the corresponding weight in the first weight set to obtain the first image to be fused of the first element.

Exemplarily, f _w represents the water material decomposition image, f _b represents the bone material decomposition image, the number of distribution bands can be 3, the decomposition pixel value of the water material in the water material decomposition image (that is, the decomposition pixel value of the first element). ) is between [B _min , B _max ], where B _min represents the minimum value of the decomposition pixel value of the water material in the water material decomposition image, B _max represents the maximum value of the decomposition pixel value of the water material in the water material decomposition image, The 3 distribution bands may include: a first distribution band [B _min , B _min +(B _max -B _min )/3), a second distribution band [B _min +(B _max -B _min )/3, B _min + 2(B _max -B _min )/3), the third distribution band [B _min +2(B _max -B _min )/3,B _max ], that is, [B _min ,B _max ] is evenly divided into 3 distribution bands . The weight of the first distribution band is μ _w (ε _high ), which represents the linear attenuation coefficient at higher energy, and the value of the attenuation coefficient is lower, and the weight of the first distribution band is μ _w (ε _mid ), which represents the intermediate energy The linear attenuation coefficient under , the weight of the third distribution band is μ _w (ε _low ), which represents the linear attenuation coefficient at lower energies, and the numerical value of the attenuation coefficient is higher, where μ _w (ε _low )>μ _w ( ε _mid )>μ _w (ε _high ). The pixel value in the first image to be fused can be calculated by formula one, and formula one is as follows:

表示第一待融合图像中第j个像素的像素值，f _wj表示水材料分解图像中第j个像素的像素值，μ _w(ε)表示第一权值集合中能量ε下的权值，也可以说是能量ε下的线性衰减系数。 in,

represents the pixel value of the j-th pixel in the first image to be fused, f _wj represents the pixel value of the j-th pixel in the water material decomposition image, μ _w (ε) represents the weight under the energy ε in the first weight set, It can also be said to be the linear decay coefficient at the energy ε.

After step 202, the method further includes step 205:

Step 205: Multiply the decomposed pixel value of the second element of each pixel in the second decomposed image by the corresponding weight in the second weight set to obtain the second image to be fused of the second element.

In this embodiment, the second decomposed image is the decomposed image of the bone material, and the pixel value in the second image to be fused can be calculated by using the formula 2, and the formula 2 is as follows:

表示第二待融合图像中第j个像素的像素值，f _bj表示骨材料分解图像中第j个像素的像素值，μ _b(ε)表示第二权值集合中能量ε下的权值，也可以说是能量ε下的线性衰减系数，在本实施例中，第二权值集合可以包含一个权值，即骨材料分解图像中每个像素的像素值均乘以相同的权值。 in,

represents the pixel value of the jth pixel in the second image to be fused, f _bj represents the pixel value of the jth pixel in the bone material decomposition image, μ _b (ε) represents the weight under the energy ε in the second weight set, It can also be said to be a linear attenuation coefficient under the energy ε. In this embodiment, the second weight set may include one weight, that is, the pixel value of each pixel in the bone material decomposition image is multiplied by the same weight.

After step 204 and step 205, the method further includes step 206:

Step 206: Add the pixel values of the corresponding positions of the first image to be fused and the second image to be fused to obtain a reconstructed image.

Exemplarily, in combination with the descriptions in step 204 and step 205, the pixel value of each pixel in the reconstructed image can be calculated according to formula 3, where formula 3 is as follows:

表示重建图像中第j个像素的像素值。 in,

represents the pixel value of the jth pixel in the reconstructed image.

With reference to the descriptions of steps 201 to 206, referring to FIG. 3, FIG. 3 is a schematic diagram of a reconstructed image effect provided by Embodiment 2 of the present application. In FIG. 3, picture a represents the first image obtained at 80KV, and picture b represents The second image obtained under 140KV, the image c represents the mixed image obtained by linearly mixing the first image and the second image, the image d represents the decomposition image of the water material, the image e represents the decomposition image of the bone material, and the image f represents the image according to step 203 -206 Reconstructed image after weighted summation. Comparing the f image with the c image, it can be observed that the f image is weighted according to different elements due to the material decomposition, which makes the reconstructed image clearer.

In the image reconstruction method provided by the embodiment of the present application, a first image and a second image obtained by scanning a target area are obtained; The second decomposed image; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, respectively, performing weighted summation on the first decomposed image and the second decomposed image to obtain a reconstructed image. Because different elements are decomposed according to the images obtained under the two energies, and the decomposed images of each element are weighted and summed, the different elements are displayed more clearly and the image quality is improved.

Embodiment three,

Based on the image reconstruction methods provided in Embodiment 1 and Embodiment 2 of the present application, an embodiment of the present application provides an image reconstruction apparatus for executing the image reconstruction methods described in Embodiment 1 and Embodiment 2 above. Referring to FIG. 4 , the image reconstruction device 40 includes: an acquisition module 401, a decomposition module 402 and a reconstruction module 403;

Wherein, the acquisition module 401 is used to acquire the first image and the second image obtained by scanning the target area, and the first image and the second image are generated based on different ray energies;

A decomposition module 402, configured to determine the first decomposed image of the first element and the second decomposed image of the second element in the target area according to the first image and the second image;

The reconstruction module 403 is configured to use the first weight set corresponding to the first element and the second weight set corresponding to the second element to perform weighted summation on the first decomposed image and the second decomposed image respectively to obtain a reconstructed image.

Optionally, in an embodiment of the present application, the decomposition module 402 is configured to, according to the first image and the second image, in the target area, calculate the decomposed pixel value of the first element contained in each pixel and the second The decomposed pixel value of the element; the first decomposed image and the second decomposed image are obtained according to the decomposed pixel value of the first element and the decomposed pixel value of the second element of each pixel.

Optionally, in an embodiment of the present application, as shown in FIG. 5 , the image reconstruction apparatus 40 further includes a weight module 404, and the weight module 404 is configured to decompose the distribution of pixel values according to the first element The condition determines at least two distribution bands; determines the weight of each distribution band, and obtains a first set of weights.

Optionally, in an embodiment of the present application, the smaller the decomposed pixel value of the first element, the smaller the weight of the corresponding distribution band, the larger the decomposed pixel value of the first element, the smaller the weight of the corresponding distribution band. the larger the value.

Optionally, in an embodiment of the present application, the reconstruction module 403 is configured to compare the decomposed pixel value of the first element of each pixel in the first decomposed image with the corresponding weight in the first weight set. Multiply to obtain the first image to be fused of the first element; multiply the decomposed pixel value of the second element of each pixel in the second decomposed image with the corresponding weight in the second weight set to obtain the second element’s decomposed pixel value The second image to be fused; the reconstructed image is obtained by adding the pixel values of the corresponding positions of the first image to be fused and the second image to be fused.

Optionally, in an embodiment of the present application, the acquisition module 401 is configured to scan the target area with a first ray source at a first energy to obtain a first image, and use a second ray source under a second energy A second image is obtained by scanning the target area, and the first energy is different from the second energy.

Optionally, in an embodiment of the present application, the acquisition module 401 is configured to use a first detector to receive rays that scan the target area to obtain a first image, and use a second detector to receive rays to scan the target area. The ray obtains the second image.

Optionally, in an embodiment of the present application, the acquisition module 401 is configured to use a multi-layer flat panel detector to receive rays for scanning the target area, and obtain a first image and a second image respectively through the two layers of flat panels.

Optionally, in an embodiment of the present application, the first element is a water material, and the second element is a bone material.

The image reconstruction method and apparatus provided in the embodiment of the present application acquires a first image and a second image obtained by scanning a target area; and determines a first decomposed image and a second element of the first element in the target area according to the first image and the second image The second decomposed image of ; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, weighted summation is performed on the first decomposed image and the second decomposed image respectively to obtain a reconstructed image. Because different elements are decomposed according to the images obtained under the two energies, and the decomposed images of each element are weighted and summed, the different elements are displayed more clearly and the image quality is improved.

Embodiment four,

Based on the image reconstruction methods provided in Embodiment 1 and Embodiment 2 of the present application, Embodiment 4 of the present application provides an image reconstruction apparatus for executing the image reconstruction methods described in Embodiment 1 and Embodiment 2 above, as shown in FIG. 6 . As shown, the image reconstruction device 60 includes: a processor 601, an imaging source 602, a multi-layer flat panel detector 603, and a frame 604; the imaging source 602 and the multi-layer flat panel detector 603 are arranged on the frame; the processor is used to execute pre-storage The computer program implements the image reconstruction method described in Embodiment 1 and Embodiment 2.

Specifically, the imaging source 602 is used to emit rays to the multi-layer flat panel detector 603; the multi-layer flat panel detector is used to receive the rays sent by the imaging source 602 and generate a first image and a second image, and the first image and the second image are transmitted to the processor;

The processor 601 is configured to acquire a first image and a second image obtained by scanning the target area, the first image and the second image are generated based on different ray energies; determine the first image and the second image in the target area according to the first image and the second image; The first decomposed image of one element and the second decomposed image of the second element; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, the first decomposed image and the second decomposed image are respectively decomposed The images are weighted and summed to obtain a reconstructed image.

The processor 602 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the electronic device may be the same type of processors, such as one or more CPUs; or may be different types of processors, such as one or more CPUs and one or more ASICs.

Embodiment five,

Based on the image reconstruction methods provided in Embodiment 1 and Embodiment 2 of the present application, Embodiment 5 of the present application provides a radiotherapy apparatus for performing the image reconstruction methods described in Embodiment 1 and Embodiment 2 above, as shown in FIG. 7 . , the radiotherapy equipment 70 includes: a processor 701, an imaging source 702, a multi-layer flat panel detector 703, a frame 704, a treatment source 705 and a treatment couch 705; the imaging source 702, the multi-layer flat panel detector 703 and the treatment source 705 are arranged in On the rack; the processor 701 is configured to execute a pre-stored computer program to implement the image reconstruction methods described in Embodiment 1 and Embodiment 2.

Specifically, the imaging source 702 is used to emit rays to the multi-layer flat panel detector 703; the multi-layer flat panel detector is used to receive the rays sent by the imaging source 702 and generate a first image and a second image, and the first image and the second image are transmitted to the processor;

The processor 701 is configured to obtain a first image and a second image obtained by scanning the target area, the first image and the second image are generated based on different ray energies; determine the first image and the second image in the target area according to the first image and the second image. The first decomposed image of one element and the second decomposed image of the second element; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, the first decomposed image and the second decomposed image are respectively decomposed The image is weighted and summed to obtain a reconstructed image;

The treatment source 705 is used to treat the target area; the treatment couch 706 is used to carry the patient.

It should be noted that the frame 704 may be the C-arm frame described in FIG. 7 , and of course, may also be a roller frame, and the type of the frame is not specifically limited here.

Embodiment six,

Based on the image reconstruction methods provided in Embodiment 1 and Embodiment 2 of the present application, an embodiment of the present application provides a computer storage medium, where a computer program is stored on the computer storage medium, and when the processor executes the computer program, the embodiment 1 and The image reconstruction method described in the second embodiment.

Computer storage media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer storage media does not include transitory computer-readable media such as modulated data signals and carrier waves.

The computer storage medium provided by the embodiment of the present application acquires a first image and a second image obtained by scanning a target area; and determines a first decomposed image of the first element in the target area and a second image of the second element according to the first image and the second image. The second decomposed image; using the first weight set corresponding to the first element and the second weight set corresponding to the second element, respectively, performing weighted summation on the first decomposed image and the second decomposed image to obtain a reconstructed image. Because different elements are decomposed according to the images obtained under the two energies, and the decomposed images of each element are weighted and summed, the different elements are displayed more clearly and the image quality is improved.

So far, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain embodiments, multitasking and parallel processing may be advantageous.

It should be understood by those skilled in the art that the embodiments of the present application may be provided as a method, an apparatus, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture, or device that includes the element.

It will be appreciated by those skilled in the art that the embodiments of the present application may be provided as a method, a system or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular transactions or implement particular abstract data types. The application may also be practiced in distributed computing environments where transactions are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

The above descriptions are merely examples of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims (13)

An image reconstruction method, comprising: acquiring a first image and a second image obtained by scanning the target area, where the first image and the second image are generated based on different ray energies; determining a first decomposed image of the first element and a second decomposed image of the second element in the target area according to the first image and the second image; Using the first weight set corresponding to the first element and the second weight set corresponding to the second element, the first decomposed image and the second decomposed image are respectively weighted and summed to obtain a reconstructed image. The method according to claim 1, wherein the first decomposed image of the first element and the second decomposed image of the second element in the target area are determined according to the first image and the second image ,include: According to the first image and the second image, in the target area, calculate the decomposed pixel value of the first element and the decomposed pixel value of the second element contained in each pixel; The first decomposed image and the second decomposed image are obtained according to the decomposed pixel value of the first element and the decomposed pixel value of the second element of each pixel. The method according to claim 1, wherein the method further comprises: Determine at least two distribution bands according to the distribution of the decomposed pixel values of the first element; Determine the weight of each distribution band, and obtain the first set of weights. The method of claim 3, wherein: The smaller the decomposed pixel value of the first element is, the smaller the weight of the corresponding distribution band is, and the larger the decomposed pixel value of the first element is, the larger the weight of the corresponding distribution band is. The method according to claim 1, wherein the first decomposed image is separately analyzed by using a first weight set corresponding to the first element and a second weight set corresponding to the second element. Perform weighted summation with the second decomposed image to obtain a reconstructed image, including: In the first decomposed image, the decomposed pixel value of the first element of each pixel is multiplied by the corresponding weight value in the first weight value set to obtain the first image to be fused of the first element; In the second decomposed image, the decomposed pixel value of the second element of each pixel is multiplied by the corresponding weight value in the second weight value set to obtain the second image to be fused of the second element; The reconstructed image is obtained by adding the pixel values of the corresponding positions of the first image to be fused and the second image to be fused. The method according to claim 1, wherein the acquiring the first image and the second image obtained by scanning the target area comprises: The first image is obtained by scanning the target area with a first ray source at a first energy, and the second image is obtained by scanning the target area with a second ray source at a second energy. The first energy is different from the second energy. The method according to claim 1, wherein the acquiring the first image and the second image obtained by scanning the target area comprises: The first image is obtained by using a first detector to receive rays that scan the target area, and the second image is obtained by using a second detector to receive rays that scan the target area. The method according to claim 1, wherein the acquiring the first image and the second image obtained by scanning the target area comprises: The radiation for scanning the target area is received by a multi-layer flat-panel detector, and the first image and the second image are obtained respectively through two layers of the flat-panel detector. The method according to any one of claims 1-8, wherein the first element is a water material, and the second element is a bone material. An image reconstruction device, comprising: an acquisition module, a decomposition module and a reconstruction module; Wherein, the acquisition module is configured to acquire a first image and a second image obtained by scanning the target area, and the first image and the second image are generated based on different ray energies; the decomposition module, configured to determine the first decomposed image of the first element and the second decomposed image of the second element in the target area according to the first image and the second image; The reconstruction module is configured to use the first weight set corresponding to the first element and the second weight set corresponding to the second element to perform the first decomposed image and the second decomposed image respectively. The weighted summation yields the reconstructed image. A computer storage medium, characterized in that a computer program is stored on the computer storage medium, and when a processor executes the computer program, the image reconstruction method according to any one of claims 1-9 is implemented. An image reconstruction device, comprising: a processor, an imaging source, a multi-layer flat panel detector, and a frame; The imaging source and the multi-layer flat panel detector are arranged on the frame; the processor is configured to execute a pre-stored computer program to implement the image reconstruction method according to any one of claims 1-9. A radiotherapy equipment is characterized by comprising: a processor, an imaging source, a multi-layer flat panel detector, a rack, a treatment source and a treatment couch; The imaging source, the multi-layer flat panel detector and the treatment source are arranged on the frame; the processor is configured to execute a pre-stored computer program to realize the method according to any one of claims 1-9 Image reconstruction method.

Images