CN111991015B - Three-dimensional image stitching method, device, equipment, system and storage medium - Google Patents

Abstract

The present application relates to a three-dimensional image stitching method, device, equipment, system and storage medium. It is applied to an X-ray medical imaging system, wherein the X-ray medical imaging system includes a detector and an array X-ray source, wherein the array X-ray source includes a plurality of X-ray sources with different projection angles, and imaging areas corresponding to the X-ray sources are formed on the detector; the method includes: obtaining projection data of each area of the part to be detected; the projection data is generated by exposing each area to the X-ray source in the array X-ray source at at least two different projection angles relative to the each area; performing three-dimensional image reconstruction on the projection data of each area respectively to obtain each reconstructed image block; and stitching each reconstructed image block according to the relative position relationship between each reconstructed image block to obtain a three-dimensional reconstructed image of the part to be detected. The use of this method can improve the quality of the three-dimensional reconstructed image.

Description

Three-dimensional image stitching method, device, equipment, system and storage medium

Technical Field

The present application relates to the field of image processing technology, and in particular to a three-dimensional image stitching method, device, equipment, system and storage medium.

Background technique

With the continuous development of X-ray technology, when performing breast examinations on patients, most of the time, the patient's X-ray data is collected by an X-ray machine, and then the collected data is reconstructed to obtain a medical image of the patient's breast area. The medical image is then analyzed to obtain the patient's image analysis results.

In general, in traditional breast X-ray medical imaging products, a single rotating light source with a hot cathode is usually used. In order to perform multi-angle X-ray scanning, the X-ray light source is fixed on a rotating frame to perform arc motion for X-ray scanning. Due to the motion artifacts caused by mechanical movement and the time delay caused by the thermal electron emission mechanism, the spatial resolution of the scanned image is reduced, the scanning time is prolonged, and motion artifacts are easily generated during the shooting process, thereby affecting the quality of the three-dimensional tomographic image.

Therefore, how to improve the spatial resolution of three-dimensional images and thus improve the quality of three-dimensional tomographic images has become a technical problem that needs to be solved urgently.

Summary of the invention

Based on this, it is necessary to provide a three-dimensional image stitching method, device, equipment, system and storage medium that can improve the quality of three-dimensional reconstructed images in response to the above technical problems.

A three-dimensional image stitching method is applied to an X-ray medical imaging system, wherein the X-ray medical imaging system includes a detector and an array X-ray source, wherein the array X-ray source includes a plurality of X-ray sources with different projection angles, and imaging areas corresponding to the X-ray sources are formed on the detector; the method includes:

Acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

Reconstructing the three-dimensional image of the projection data of each imaging area to obtain a plurality of reconstructed image blocks;

According to the relative position relationship between the reconstructed image blocks, the reconstructed image blocks are spliced to obtain a three-dimensional reconstructed image of the part to be detected.

In one embodiment, the array X-ray source includes a linear array ray source and a planar array ray source, and the projection data of each imaging area is respectively subjected to three-dimensional image reconstruction to obtain a plurality of reconstructed image blocks, including:

Acquire a plurality of first imaging regions corresponding to the linear array ray source and a plurality of second imaging regions corresponding to the planar array ray source;

According to the plurality of first imaging regions, obtaining overlapping portions corresponding to the plurality of first imaging regions, and according to the plurality of second imaging regions, obtaining overlapping portions corresponding to the plurality of second imaging regions;

Obtaining a plurality of overlapping regions according to overlapping portions corresponding to the plurality of first imaging regions and overlapping portions corresponding to the plurality of second imaging regions;

The projection data of each overlapping area are respectively reconstructed into three-dimensional images to obtain a plurality of reconstructed image blocks.

In one embodiment, the method of obtaining overlapping portions corresponding to the plurality of first imaging regions according to the plurality of first imaging regions and obtaining overlapping portions corresponding to the plurality of second imaging regions according to the plurality of second imaging regions includes:

Performing intersection operation processing on the multiple first imaging regions to obtain overlapping parts corresponding to the multiple first imaging regions;

An intersection operation is performed on the plurality of second imaging regions to obtain overlapping portions corresponding to the plurality of second imaging regions.

In one embodiment, the above-mentioned performing intersection operation processing on the multiple first imaging regions to obtain the overlapping parts corresponding to the multiple first imaging regions includes:

Performing intersection operation processing on two adjacent first imaging areas in the plurality of first imaging areas to obtain a plurality of first boundary points corresponding to each of the two adjacent first imaging areas, and obtaining an overlapping portion corresponding to each of the two adjacent first imaging areas according to the plurality of first boundary points;

The above-mentioned intersection operation processing is performed on the multiple second imaging regions to obtain the overlapping parts corresponding to the multiple second imaging regions, including:

An intersection operation is performed on two adjacent second imaging areas among the plurality of second imaging areas to obtain a plurality of second boundary points corresponding to each of the two adjacent second imaging areas, and an overlapping portion corresponding to each of the two adjacent second imaging areas is obtained according to the plurality of second boundary points.

In one embodiment, obtaining the overlapping portion corresponding to each two adjacent first imaging regions according to the plurality of first boundary points includes:

Determine a portion enclosed by a plurality of first boundary points corresponding to each two adjacent first imaging regions as an overlapping portion corresponding to each two adjacent first imaging regions;

Obtaining the overlapping portion corresponding to each two adjacent second imaging regions according to the plurality of second boundary points includes:

A portion enclosed by a plurality of second boundary points corresponding to each two adjacent second imaging regions is determined as an overlapping portion corresponding to each two adjacent second imaging regions.

In one embodiment, obtaining the overlapping portion corresponding to each two adjacent first imaging regions according to the plurality of first boundary points includes:

Fitting a plurality of first boundary points corresponding to each two adjacent first imaging regions to obtain an overlapping portion corresponding to each two adjacent first imaging regions;

Obtaining the overlapping portion corresponding to each two adjacent second imaging regions according to the plurality of second boundary points includes:

A plurality of second boundary points corresponding to each two adjacent second imaging regions are fitted to obtain an overlapping portion corresponding to each two adjacent second imaging regions.

In one embodiment, each of the above-mentioned reconstructed image blocks includes a plurality of sub-image slices; the above-mentioned splicing of the reconstructed image blocks according to the relative position relationship between the reconstructed image blocks to obtain a three-dimensional reconstructed image of the part to be detected includes:

Obtaining slice information of each sub-image slice in each reconstructed image block;

splicing the sub-image slices of each reconstructed image block according to the relative position relationship between the reconstructed image blocks and the slice information of each sub-image slice to obtain a plurality of image slices;

The multiple image slices are determined as a three-dimensional reconstructed image of the part to be detected.

In one embodiment, the slice information of the sub-image slices includes the layer number of the sub-image slices; and the sub-image slices of each reconstructed image block are spliced according to the relative position relationship between the reconstructed image blocks and the slice information of each sub-image slice to obtain a plurality of image slices, including:

According to the layer number of each sub-image slice in each reconstructed image block, each sub-image slice in the same layer is determined;

Determine the splicing order between the sub-image slices in the same layer according to the relative position relationship between the reconstructed image blocks; the splicing order includes a front-to-back splicing order, a left-to-right splicing order, or a top-to-bottom splicing order;

The sub-image slices in the same layer are spliced according to the splicing order between the sub-image slices in the same layer to obtain a plurality of image slices.

A three-dimensional image stitching device is applied to an X-ray medical imaging system, wherein the X-ray medical imaging system comprises a detector and an array X-ray source, wherein the array X-ray source comprises a plurality of X-ray sources with different projection angles, and each imaging area corresponding to each X-ray source is formed on the detector; the device comprises:

An acquisition module is used to acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

A reconstruction module, used to perform three-dimensional image reconstruction on the projection data of each imaging area to obtain multiple reconstructed image blocks;

The splicing module is used to splice the reconstructed image blocks according to the relative position relationship between the reconstructed image blocks to obtain a three-dimensional reconstructed image of the part to be detected.

A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

Acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

Reconstructing the three-dimensional image of the projection data of each imaging area to obtain a plurality of reconstructed image blocks;

According to the relative position relationship between the reconstructed image blocks, the reconstructed image blocks are spliced to obtain a three-dimensional reconstructed image of the part to be detected.

An X-ray medical imaging system comprises an array X-ray source, a compression plate, a detector, and the above-mentioned computer device.

In one embodiment, the array X-ray source includes a plurality of X-ray sources, each of which is a field emission X-ray source.

In one of the embodiments, the array X-ray source includes a linear array ray source and a planar array ray source; the linear array ray source is arranged on the breast wall side of the part to be detected, and the planar array ray source is arranged on the side away from the breast wall side of the part to be detected; the setting position of the linear array ray source has an inclination angle relative to the setting position of the planar array ray source.

A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

Acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

Reconstructing the three-dimensional image of the projection data of each imaging area to obtain a plurality of reconstructed image blocks;

According to the relative position relationship between the reconstructed image blocks, the reconstructed image blocks are spliced to obtain a three-dimensional reconstructed image of the part to be detected.

The above-mentioned three-dimensional image stitching method, device, equipment, system and storage medium can obtain the projection data of the part to be detected in each imaging area, reconstruct the projection data of each imaging area respectively, obtain each reconstructed image block, and stitch each reconstructed image block according to the relative position relationship between each reconstructed image block to obtain a three-dimensional reconstructed image of the part to be detected. Among them, the method is applied to an X-ray medical imaging system, the X-ray medical imaging system includes a detector and an array X-ray source, the array X-ray source includes a plurality of X-ray sources with different projection angles, and each imaging area corresponding to each X-ray source is formed on the detector. The above-mentioned projection data is generated by the exposure of the part to be detected by the plurality of X-ray sources. In this method, since the part does not need to be rotated and scanned when the array X-ray source is used to collect data on the part, on the one hand, the scanning time can be shortened and the radiation time for the patient can be reduced; on the other hand, the motion artifacts caused by the movement of the light source can be avoided, and the quality of the generated image can be improved; further, using this method, more projection data can be collected in the same time, so that the spatial resolution of the image can be improved.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a diagram showing an application environment of a three-dimensional image stitching method according to an embodiment;

FIG2 is a schematic diagram of a flow chart of a three-dimensional image stitching method in one embodiment;

FIG3 is an exemplary diagram of using an array X-ray source to expose and photograph a part in one embodiment;

FIG4 is an exemplary diagram of imaging areas of each X-ray source in an array X-ray source in one embodiment;

FIG5 is a schematic flow chart of a three-dimensional image stitching method in another embodiment;

FIG6 is an exemplary diagram of obtaining an overlapping portion of two adjacent imaging areas in another embodiment;

FIG7 is a schematic flow chart of a three-dimensional image stitching method in another embodiment;

FIG8 is a structural block diagram of a three-dimensional image stitching device in one embodiment;

FIG. 9 is a diagram showing the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

The three-dimensional image stitching method provided in the embodiment of the present application can be applied to the X-ray medical imaging system 10 shown in Figure 1, which includes an array X-ray source 101, a compression plate 102, a detector 103 and a computer device 104.

The array X-ray source 101 is used to emit X-rays. The array X-ray source includes a plurality of X-ray sources, each of which is a field emission X-ray source and can emit X-rays. Optionally, the array X-ray source includes one or more of a linear array ray source and a planar array ray source. That is to say, the array X-ray source may include only a linear array ray source, only a planar array ray source, or both a linear array ray source and a planar array ray source. In addition, the linear array ray sources here may be arranged in a straight line, or in a folded line, or in a curved line. The planar array ray source may be composed of two or more X-ray sources arranged in a planar shape (such as a matrix). The number of X-ray sources specifically included in the linear array ray source and the planar array ray source may be set according to actual conditions. For example, the linear array ray source may include 15 X-ray sources, and the planar array ray source may include 25 X-ray sources in 5 rows and 5 columns.

Furthermore, the linear array ray source is arranged on the chest wall side of the part to be detected, and the planar array ray source is arranged on the side away from the chest wall side of the part to be detected; the arrangement position of the linear array ray source has an inclination angle relative to the arrangement position of the planar array ray source. In other words, the linear array ray source can be arranged on the chest wall side of the part to be detected, and the chest wall side can refer to the side of the part away from the nipple, so as to avoid X-rays penetrating the human body and causing radiation to the human body, and the inclination angle can be set according to actual conditions, such as 5 degrees or 10 degrees, etc.

The compression plate 102 may be disposed between the array X-ray source 101 and the detector 103 to compress the part to be detected so that the part to be detected is in a thin and uniform state, which is convenient for subsequent data collection and detection.

In addition, the X-ray irradiation area of the linear array ray source can be perpendicular or approximately perpendicular to the compression plate at the irradiation surface close to the chest wall, so as to avoid the X-rays of the linear array ray source from passing through the chest wall and causing unnecessary X-ray radiation to the human body. Approximately perpendicular can be understood as the deviation angle from the vertical state is not greater than a preset threshold (such as 1°, 2°, 5°, etc.). For example, approximately perpendicular can include the angle between the irradiation surface of the irradiation area of the linear array X-ray source close to the chest wall and the compression plate being between 89°-91°, 88°-92°, 85°-95°, etc. The planar array ray source can be set in parallel with the detector.

The detector 103 is used to detect the projection data of the X-rays emitted by the array X-ray source 101 after passing through the part to be detected, and transmit the collected projection data to the computer device 104 for processing. The part to be detected is located between the detector 103 and the compression plate 102, and the detector here can be a flat panel detector.

The computer device 104 may be a server, which may be implemented by an independent server or a server cluster composed of multiple servers. Of course, it may also be a terminal, which may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, portable wearable devices, etc.

It should be noted that the execution subject of the following embodiments of the present application can be a computer device or an X-ray medical imaging system. The following description will take a computer device as an example.

In one embodiment, a three-dimensional image stitching method is provided. This embodiment involves a specific process of reconstructing a three-dimensional reconstructed image of a part to be inspected based on projection data of various regions of the part to be inspected. As shown in FIG2 , the method may include the following steps:

S202, obtaining projection data of the part to be detected on each imaging area; the projection data is generated by correspondingly exposing the part to be detected by multiple X-ray sources in the array X-ray source.

In this step, when the array X-ray source is exposing and photographing the part to be detected, the relative position between the array X-ray source and the detector is fixed.

The array X-ray source includes multiple X-ray sources with different projection angles, that is, each X-ray source has a different projection angle when exposing the part to be detected, so correspondingly, the imaging area of each X-ray source on the detector is also different, so each imaging area corresponding to each X-ray source will be formed on the detector. Here, the part to be detected can be a breast to be detected, or other parts to be detected.

Taking the array X-ray source including the linear array ray source and the planar array ray source as an example, an example diagram of the array X-ray source exposing and photographing the part to be detected can be shown in Figure 3, and the imaging area of each X-ray source in the array X-ray source can be shown in Figure 4. It should be noted that Figures 3 and 4 are only examples and do not affect the substantive content of the embodiments of the present application.

Specifically, each X-ray source in the array X-ray source can be used to expose the part to be detected with X-rays (which can be exposed simultaneously or sequentially), and the detector is used to collect the exposed X-rays, so that each X-ray source will have a corresponding imaging area on the detector, and each imaging area includes projection data corresponding to each X-ray source. Here, the projection data corresponding to each imaging area can be referred to as the projection data of the part to be detected on each imaging area.

Afterwards, the detector can transmit the projection data of the detected part to be detected on each imaging area to the computer device, so that the computer device can obtain the projection data of the part to be detected on each imaging area.

S204, performing three-dimensional image reconstruction on the projection data of each imaging area to obtain a plurality of reconstructed image blocks.

The reconstructed image blocks here may be three-dimensional reconstructed image blocks. When performing three-dimensional image reconstruction, an image reconstruction algorithm may be used, and the image reconstruction algorithm may be a filtered back projection method, a maximum likelihood method, an iterative method, an algebraic method, a minimum likelihood method, a Fourier transform method, a convolution back projection method, etc.

Specifically, after obtaining the projection data of the part to be detected on each imaging area, that is, the projection data on each imaging area on the detector, the computer device can use an image reconstruction algorithm to directly reconstruct the projection data on each imaging area to obtain a three-dimensional reconstructed image block corresponding to each imaging area.

Of course, the projection data of each imaging area can also be processed, for example, the projection data of the overlapping area of each adjacent imaging area is taken, and the image reconstruction algorithm is used to reconstruct the projection data of each overlapping area respectively to obtain the three-dimensional reconstructed image block corresponding to each reconstructed area.

S206 , splicing the reconstructed image blocks according to the relative position relationship between the reconstructed image blocks to obtain a three-dimensional reconstructed image of the part to be detected.

In this embodiment, when the array X-ray source is exposing and photographing the part to be detected, the relative position between the array X-ray source and the detector is fixed. At the same time, the relative position relationship between each X-ray source in the array X-ray source is also fixed (for example, the linear array light source 1 is in front of the linear array light source 2, etc.), and the relative position relationship between the imaging areas corresponding to each X-ray source on the detector is the same as the relative position relationship between each X-ray source, so the relative position relationship between the imaging areas corresponding to each X-ray source on the detector can also be obtained (for example, the imaging area of the linear array light source 1 is in front of the imaging area of the linear array light source 2, etc.).

Specifically, after the computer device obtains the relative positional relationship between each imaging area, each reconstructed image block is reconstructed based on the projection data of each imaging area, so the relative positional relationship between each reconstructed image block can be obtained. Afterwards, the computer device can stitch each reconstructed image block in a certain order according to the relative positional relationship between each reconstructed image block to obtain a stitched reconstructed image, that is, a three-dimensional reconstructed image of the part to be detected.

The certain order may include from front to back or from back to front, or from top to bottom or from bottom to top, or from left to right or from right to left, and of course other orders are also possible.

In the above three-dimensional image stitching method, the projection data of the part to be detected in each imaging area can be obtained, and the projection data of each imaging area can be reconstructed into a three-dimensional image to obtain each reconstructed image block, and each reconstructed image block can be stitched according to the relative position relationship between each reconstructed image block to obtain a three-dimensional reconstructed image of the part to be detected. Among them, the method is applied to an X-ray medical imaging system, which includes a detector and an array X-ray source, the array X-ray source includes a plurality of X-ray sources with different projection angles, and each imaging area corresponding to each X-ray source is formed on the detector. The above projection data is generated by the exposure of the part to be detected by the plurality of X-ray sources. In this method, since the part does not need to be rotated and scanned when the array X-ray source is used to collect data on the part, on the one hand, the scanning time can be shortened and the radiation time for the patient can be reduced; on the other hand, the motion artifacts caused by the movement of the light source can be avoided, and the quality of the generated image can be improved; further, using this method, more projection data can be collected in the same time, so that the spatial resolution of the image can be improved.

In another embodiment, another three-dimensional image stitching method is provided. This embodiment involves an array X-ray source including a linear array ray source and a planar array ray source. Then, how to reconstruct the projection data of each imaging area to obtain the specific process of each reconstructed image block. Based on the above embodiment, as shown in FIG5 , the above S204 may include the following steps:

S302, acquiring a plurality of first imaging regions corresponding to the linear array ray source and a plurality of second imaging regions corresponding to the planar array ray source.

In this step, before the array X-ray source exposes and photographs the part to be inspected, the relative positions of the linear array ray sources and the planar array ray sources in the array X-ray source are fixed, and the relative positions of the linear array ray sources, the planar array ray sources and the detector are also fixed, so that the projection area of each X-ray source at the detector end can be determined.

Here, the imaging region of each X-ray source in the linear array ray source can be recorded as a first imaging region, and the imaging region of each X-ray source in the planar array ray source can be recorded as a second imaging region.

It should be noted that the X-ray sources in the linear array ray source and the planar array ray source are both field emission X-ray sources, which are ray sources that use cold cathode technology to generate electron beams. However, this cold cathode technology is currently limited by insufficient cathode power. Therefore, in this embodiment, a linear array ray source array is set on one side of the breast wall, and a planar array ray source array is set in other areas. This not only makes up for the problem of insufficient power on the breast wall side, but also ensures that the rays emitted by the ray source do not penetrate the human body. Therefore, in this embodiment, a linear array ray source and a planar array ray source are used as array X-ray sources to image the part to be detected.

Furthermore, when a linear array ray source and a planar array ray source are used to image a part to be inspected, each X-ray source in the linear array ray source and the planar array ray source exposes the part to be inspected sequentially or one by one to obtain projection data of the part to be inspected on multiple first imaging areas corresponding to the linear array ray source, and projection data of the part to be inspected on multiple second imaging areas corresponding to the planar array ray source.

S304, obtaining overlapping parts corresponding to the multiple first imaging areas according to the multiple first imaging areas, and obtaining overlapping parts corresponding to the multiple second imaging areas according to the multiple second imaging areas.

In this step, in order to reconstruct a three-dimensional image, projection data at the overlapping area of multiple X-ray source imaging areas are generally used. Since the overlapping part has more information, the reconstructed image is more accurate. When obtaining the overlapping area, the overlapping part can be obtained for each first imaging area of the linear array ray source first, or the overlapping part can be obtained for each second imaging area of the planar array ray source first, or the overlapping part can be obtained for each first imaging area and each second imaging area at the same time.

Then, when obtaining the overlapping part, optionally, an intersection operation can be performed on multiple first imaging areas to obtain the overlapping parts corresponding to the multiple first imaging areas; and an intersection operation can be performed on multiple second imaging areas to obtain the overlapping parts corresponding to the multiple second imaging areas.

In summary, the overlapping parts corresponding to the multiple first imaging regions and the overlapping parts corresponding to the multiple second imaging regions can be finally obtained.

S306 , obtaining a plurality of overlapping regions according to the overlapping portions corresponding to the plurality of first imaging regions and the overlapping portions corresponding to the plurality of second imaging regions.

In this step, the overlapping parts corresponding to the above-mentioned multiple first imaging areas and the overlapping parts corresponding to the multiple second imaging areas are combined to obtain multiple overlapping parts. Since the overlapping parts correspond to the imaging areas, they are all two-dimensional and are also areas, they are recorded here as multiple overlapping areas.

S308, performing three-dimensional image reconstruction on the projection data of each overlapping area to obtain a plurality of reconstructed image blocks.

In this step, after the overlapping areas of all imaging areas are obtained, the projection data of each overlapping area can be obtained from the projection data of each imaging area, and the projection data of each overlapping area can be reconstructed to obtain a reconstructed image block corresponding to each overlapping area.

The three-dimensional image stitching method provided in this embodiment can obtain the overlapping areas corresponding to the multiple imaging areas of the linear array ray source and the overlapping areas corresponding to the multiple imaging areas of the planar array ray source, and reconstruct the projection data of the obtained multiple overlapping areas to obtain each reconstructed image block. The method of this embodiment can improve the accuracy of the reconstructed image block, and thus improve the accuracy of the finally obtained three-dimensional reconstructed image.

In another embodiment, another three-dimensional image stitching method is provided, and this embodiment involves a specific process of how to take the intersection of each first imaging area and each second imaging area to obtain the corresponding overlapping part. Based on the above embodiment, the intersection process in S304 may include the following steps 1 and 2:

Step 1: perform intersection operation on two adjacent first imaging areas among the multiple first imaging areas to obtain multiple first boundary points corresponding to each of the two adjacent first imaging areas, and obtain the overlapping part corresponding to each of the two adjacent first imaging areas based on the multiple first boundary points.

In this step, the imaging area of each X-ray source in the array X-ray source on the detector is fixed, and the size of the detector is usually fixed. Then, by establishing a coordinate system with the two boundaries of the detector as coordinate axes and any corner point as the origin, the position coordinates of each first imaging area on the detector can be obtained. By extracting the edge points of the position coordinates of each first imaging area, the coordinates of the boundary points of each first imaging area can be obtained.

Since the overlapping area is generally for two adjacent imaging areas, when taking the intersection here, it is usually for each two adjacent first imaging areas. Then the coordinates of the boundary points of each two adjacent first imaging areas can be matched. The matching here refers to comparing whether there are the same boundary point coordinates in the boundary point coordinates of each two adjacent first imaging areas. If there are, the same boundary point coordinates are considered to be the boundary point coordinates of the overlapping part. In short, the coordinates of the boundary points of the overlapping area of each two adjacent first imaging areas can be obtained in this way. The boundary points here are recorded as first boundary points, which are usually multiple.

After obtaining a plurality of first boundary points of the overlapping area of each two adjacent first imaging areas, optionally, the portion surrounded by the plurality of first boundary points corresponding to each two adjacent first imaging areas may be determined as the overlapping portion corresponding to each two adjacent first imaging areas.

Of course, optionally, a plurality of first boundary points corresponding to each two adjacent first imaging regions may be fitted to obtain an overlapping portion corresponding to each two adjacent first imaging regions.

Here, the multiple first boundary points corresponding to each two adjacent first imaging regions are fitted, which may be curve fitting or linear fitting, or other fitting methods. In short, the overlapping part corresponding to each two adjacent first imaging regions can be obtained.

Step 2: perform intersection operation on two adjacent second imaging areas among the multiple second imaging areas to obtain multiple second boundary points corresponding to each two adjacent second imaging areas, and obtain the overlapping part corresponding to each two adjacent second imaging areas based on the multiple second boundary points.

In this step, referring to the above step 1, the coordinates of the boundary points of the overlapping area of each two adjacent second imaging areas can be obtained. The boundary points here are recorded as second boundary points, and there are usually multiple of them.

After obtaining a plurality of second boundary points of the overlapping area of each two adjacent second imaging areas, optionally, the portion surrounded by the plurality of second boundary points corresponding to each two adjacent second imaging areas may be determined as the overlapping portion corresponding to each two adjacent second imaging areas.

Of course, optionally, a plurality of second boundary points corresponding to each two adjacent second imaging regions may be fitted to obtain an overlapping portion corresponding to each two adjacent second imaging regions.

Here, the multiple second boundary points corresponding to each two adjacent second imaging regions are fitted, which can be curve fitting or linear fitting, and of course other fitting methods can also be used. In short, the overlapping part corresponding to each two adjacent second imaging regions can be obtained.

For example, referring to FIG. 6 , it is assumed that a group of two adjacent imaging areas (which may be two first imaging areas or two second imaging areas) are rectangular areas A and B, respectively. Imaging area A is a solid rectangular area in the figure, and there are a total of 6 boundary points on its four boundaries, namely a1-a6. Taking two-dimensional coordinates as an example, the coordinates of these 6 boundary points are (1,15), (1,12), (1,6), (20,6), (20,12), and (20,15), respectively. Imaging area B is a dotted rectangular area in the figure, namely b1-b6. Taking two-dimensional coordinates as an example, the coordinates of these 6 boundary points are (1,12), (1,6), (1,3) respectively. , (20,3), (20,6), (20,12); comparing the 12 boundary points a1-a6 and b1-b6, it can be seen that a2 has the same coordinates as b1, a3 has the same coordinates as b2, a4 has the same coordinates as b5, and a5 has the same coordinates as b6. It can be seen that these four pairs of coordinates are the same boundary point coordinates. Taking the coordinates of imaging area A as an example, the a2 coordinate and the a3 coordinate can be connected, the a3 coordinate and the a4 coordinate can be connected, and the a4 coordinate and the a5 coordinate can be connected respectively to obtain the rectangular area surrounded by a2, a3, a4, and a5, which is also the rectangular area surrounded by b1, b2, b5, and b6, that is, the overlapping area of imaging area A and imaging area B is obtained.

This operation can be performed for all other adjacent imaging regions, so that the overlapping areas of all adjacent imaging regions can be obtained.

It should be noted that there is no time sequence restriction for the above steps 1 and 2, that is, step 1 may be performed first and then step 2, or step 2 may be performed first and then step 1, and of course, steps 1 and 2 may also be performed simultaneously.

The three-dimensional image stitching method provided in this embodiment can obtain the intersection of each adjacent first imaging area and the intersection of each adjacent second imaging area to obtain the corresponding overlapping part. Through the method of this embodiment, a more accurate overlapping area can be obtained, so that in the subsequent image reconstruction, the obtained projection data is more accurate, that is, the reconstructed data source is more accurate, and the accuracy of the three-dimensional reconstructed image obtained based on the projection data will also be higher.

In another embodiment, another three-dimensional image stitching method is provided. This embodiment involves a specific process of stitching each of the above-mentioned reconstructed image blocks including multiple sub-image slices to obtain a three-dimensional reconstructed image. Based on the above embodiment, as shown in FIG7 , the above S206 may include the following steps:

S402: Obtain slice information of each sub-image slice in each reconstructed image block.

In this step, the slice information of the sub-image slice may include the layer number, layer thickness, etc. of the sub-image slice.

When using an image reconstruction algorithm to reconstruct three-dimensional images of each overlapping area, the layer thickness of the reconstructed image slice, the image imaging size, etc. can be set in advance. In this way, after reconstructing each overlapping area, the size of the reconstructed image block corresponding to each overlapping area can be obtained. Through the size and layer thickness of the reconstructed image block, the layer number of each sub-image slice in each reconstructed image block can be obtained.

In addition, the layer thickness can be represented by the reconstruction interval. The number of sub-image slices included in each reconstructed image block is usually equal.

S404 , according to the relative position relationship between the reconstructed image blocks and the slice information of the sub-image slices, the sub-image slices of the reconstructed image blocks are spliced to obtain a plurality of image slices.

In this step, after obtaining the relative position relationship between the reconstructed image blocks and the layer number of each sub-image slice in each reconstructed image block, the reconstructed image blocks can be spliced in sequence using the relative position relationship and the layer number. Optionally, the following steps B1-B3 can be used for splicing:

B1, according to the layer number of each sub-image slice in each reconstructed image block, determine each sub-image slice in the same layer.

B2, determining a splicing order between sub-image slices in the same layer according to the relative position relationship between the reconstructed image blocks; the splicing order includes a front-to-back splicing order, a left-to-right splicing order, or a top-to-bottom splicing order.

B3, splicing the sub-image slices in the same layer according to the splicing order between the sub-image slices in the same layer to obtain multiple image slices.

Specifically, after obtaining the layer number of each sub-image slice in each reconstructed image block, the sub-image slices belonging to the same layer number can be found therefrom, and then each group of sub-image slices with the same layer number can be spliced into a layer of image slice from front to back or from back to front, or from top to bottom or from bottom to top, or from left to right or from right to left in the same positional relationship as the reconstructed image blocks. Each group of sub-image slices with the same layer number can be spliced in this way, thus obtaining multiple layers of image slices.

S406: Determine the multiple image slices as a three-dimensional reconstructed image of the part to be detected.

When stitching the groups of sub-image slices, they are usually stitched layer by layer from large to small according to the size of the layer number, or stitched layer by layer from small to large, so that multiple layers of image slices arranged in sequence can be obtained. Afterwards, these multiple layers of image slices arranged in sequence can be used as the three-dimensional reconstructed image of the part to be detected.

The three-dimensional image stitching method provided in this embodiment can obtain the information of each sub-image slice in each reconstructed image block, and stitch the sub-image slices in each reconstructed image block in combination with the relative position relationship between each reconstructed image block to obtain multiple image slices, that is, to obtain a three-dimensional reconstructed image of the part to be detected. In this method, since each sub-image slice can be stitched according to the information of each sub-image slice and the relative position relationship between each reconstructed image block, the image slices of each layer obtained by stitching are more accurate, and the three-dimensional reconstructed image of the part to be detected is also more accurate.

It should be understood that, although the steps in the flowcharts of Figures 2, 5, and 7 are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in Figures 2, 5, and 7 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

In one embodiment, as shown in FIG8 , a three-dimensional image stitching device is provided, which is applied to an X-ray medical imaging system, wherein the X-ray medical imaging system includes a detector and an array X-ray source, wherein the array X-ray source includes a plurality of X-ray sources with different projection angles, and each imaging area corresponding to each X-ray source is formed on the detector; the device includes: an acquisition module 10, a reconstruction module 11 and a stitching module 12, wherein:

An acquisition module 10 is used to acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

A reconstruction module 11 is used to perform three-dimensional image reconstruction on the projection data of each imaging area to obtain multiple reconstructed image blocks;

The stitching module 12 is used to stitch the reconstructed image blocks according to the relative position relationship between the reconstructed image blocks to obtain a three-dimensional reconstructed image of the part to be detected.

The specific definition of the three-dimensional image stitching device can refer to the definition of the three-dimensional image stitching method above, which will not be repeated here.

In another embodiment, another three-dimensional image stitching device is provided. Based on the above embodiment, the array X-ray source includes a linear array ray source and a planar array ray source, and the reconstruction module 11 may include an imaging area acquisition unit, an overlapping part determination unit, an overlapping area acquisition unit and a reconstruction unit, wherein:

An imaging region acquisition unit, used for acquiring a plurality of first imaging regions corresponding to the linear array ray source and a plurality of second imaging regions corresponding to the planar array ray source;

An overlapping portion determining unit, configured to obtain overlapping portions corresponding to the plurality of first imaging regions according to the plurality of first imaging regions, and to obtain overlapping portions corresponding to the plurality of second imaging regions according to the plurality of second imaging regions;

An overlapping region acquisition unit, configured to obtain a plurality of overlapping regions according to overlapping portions corresponding to the plurality of first imaging regions and overlapping portions corresponding to the plurality of second imaging regions;

The reconstruction unit is used to perform three-dimensional image reconstruction on the projection data of each overlapping area to obtain a plurality of reconstructed image blocks.

Optionally, the overlapping portion determining unit may include a first intersection taking subunit and a second intersection taking subunit, wherein:

A first intersection subunit is used to perform an intersection operation on the multiple first imaging regions to obtain overlapping parts corresponding to the multiple first imaging regions;

The second intersection subunit is used to perform intersection operation processing on the multiple second imaging areas to obtain overlapping parts corresponding to the multiple second imaging areas.

Optionally, the first intersection subunit is specifically used to perform an intersection operation on two adjacent first imaging areas among the multiple first imaging areas to obtain a plurality of first boundary points corresponding to each of the two adjacent first imaging areas, and obtain an overlapping portion corresponding to each of the two adjacent first imaging areas according to the plurality of first boundary points;

The above-mentioned intersection subunit is specifically used to perform intersection operation on two adjacent second imaging areas among multiple second imaging areas to obtain multiple second boundary points corresponding to each two adjacent second imaging areas, and obtain the overlapping part corresponding to each two adjacent second imaging areas based on the multiple second boundary points.

Optionally, the first intersection subunit is specifically configured to determine a portion enclosed by a plurality of first boundary points corresponding to each two adjacent first imaging regions as an overlapping portion corresponding to each two adjacent first imaging regions;

Optionally, the second intersection subunit is specifically configured to determine a portion enclosed by a plurality of second boundary points corresponding to each two adjacent second imaging regions as an overlapping portion corresponding to each two adjacent second imaging regions.

Optionally, the first intersection subunit is specifically used to fit a plurality of first boundary points corresponding to each two adjacent first imaging regions to obtain an overlapping portion corresponding to each two adjacent first imaging regions;

Optionally, the second intersection subunit is specifically configured to fit a plurality of second boundary points corresponding to each two adjacent second imaging regions to obtain an overlapping portion corresponding to each two adjacent second imaging regions.

In another embodiment, another three-dimensional image stitching device is provided. Based on the above embodiment, each of the above reconstructed image blocks includes multiple sub-image slices; the above stitching module 12 may include an information acquisition unit, a stitching unit and an image determination unit, wherein:

An information acquisition unit, used for acquiring slice information of each sub-image slice in each reconstructed image block;

a splicing unit, configured to splice the sub-image slices of each reconstructed image block according to the relative position relationship between the reconstructed image blocks and the slice information of each sub-image slice, so as to obtain a plurality of image slices;

The image determination unit is used to determine the multiple image slices as a three-dimensional reconstructed image of the part to be detected.

Optionally, the slice information of the sub-image slice includes a layer number of the sub-image slice; the splicing unit may include a layer number determination subunit, a splicing order determination subunit and a splicing subunit, wherein:

A layer number determination subunit, used to determine the sub-image slices in the same layer according to the layer numbers of the sub-image slices in each reconstructed image block;

A splicing order determination subunit is used to determine the splicing order between the sub-image slices in the same layer according to the relative position relationship between the reconstructed image blocks; the splicing order includes a front-to-back splicing order, a left-to-right splicing order, or a top-to-bottom splicing order;

The splicing subunit is used to splice the sub-image slices in the same layer according to the splicing order between the sub-image slices in the same layer to obtain multiple image slices.

The specific definition of the three-dimensional image stitching device can refer to the definition of the three-dimensional image stitching method above, which will not be repeated here.

Each module in the above three-dimensional image stitching device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

In one embodiment, a computer device is provided. Taking the computer device as a terminal as an example, its internal structure diagram can be shown in Figure 9. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a three-dimensional image splicing method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

Acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

Reconstructing the three-dimensional image of the projection data of each imaging area to obtain a plurality of reconstructed image blocks;

According to the relative position relationship between the reconstructed image blocks, the reconstructed image blocks are spliced to obtain a three-dimensional reconstructed image of the part to be detected.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

Acquire multiple first imaging areas corresponding to the linear array ray source and multiple second imaging areas corresponding to the planar array ray source; obtain overlapping parts corresponding to the multiple first imaging areas based on the multiple first imaging areas, and obtain overlapping parts corresponding to the multiple second imaging areas based on the multiple second imaging areas; obtain multiple overlapping areas based on the overlapping parts corresponding to the multiple first imaging areas and the overlapping parts corresponding to the multiple second imaging areas; perform three-dimensional image reconstruction on the projection data of each overlapping area respectively to obtain multiple reconstructed image blocks.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

An intersection operation is performed on the multiple first imaging regions to obtain overlapping parts corresponding to the multiple first imaging regions; and an intersection operation is performed on the multiple second imaging regions to obtain overlapping parts corresponding to the multiple second imaging regions.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

An intersection operation is performed on two adjacent first imaging areas among the multiple first imaging areas to obtain a plurality of first boundary points corresponding to each of the two adjacent first imaging areas, and an overlapping portion corresponding to each of the two adjacent first imaging areas is obtained based on the plurality of first boundary points; an intersection operation is performed on two adjacent second imaging areas among the multiple second imaging areas to obtain a plurality of second boundary points corresponding to each of the two adjacent second imaging areas, and an overlapping portion corresponding to each of the two adjacent second imaging areas is obtained based on the plurality of second boundary points.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

The portion enclosed by the multiple first boundary points corresponding to each two adjacent first imaging areas is determined as the overlapping portion corresponding to each two adjacent first imaging areas; the portion enclosed by the multiple second boundary points corresponding to each two adjacent second imaging areas is determined as the overlapping portion corresponding to each two adjacent second imaging areas.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

A plurality of first boundary points corresponding to each two adjacent first imaging regions are fitted to obtain an overlapping portion corresponding to each two adjacent first imaging regions; a plurality of second boundary points corresponding to each two adjacent second imaging regions are fitted to obtain an overlapping portion corresponding to each two adjacent second imaging regions.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

The slice information of each sub-image slice in each reconstructed image block is obtained; the sub-image slices of each reconstructed image block are spliced according to the relative position relationship between the reconstructed image blocks and the slice information of each sub-image slice to obtain a plurality of image slices; and the plurality of image slices are determined as a three-dimensional reconstructed image of the part to be detected.

In one embodiment, when the processor executes the computer program, the following steps are also implemented:

According to the layer number of each sub-image slice in each reconstructed image block, the sub-image slices in the same layer are determined; according to the relative position relationship between the reconstructed image blocks, the splicing order between the sub-image slices in the same layer is determined; the splicing order includes a front-to-back splicing order or a left-to-right splicing order or a top-to-bottom splicing order; according to the splicing order between the sub-image slices in the same layer, the sub-image slices in the same layer are spliced to obtain multiple image slices.

In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Acquire projection data of the part to be detected on each imaging area; the projection data is generated by exposing the part to be detected correspondingly by multiple X-ray sources in the array X-ray source;

Reconstructing the three-dimensional image of the projection data of each imaging area to obtain a plurality of reconstructed image blocks;

According to the relative position relationship between the reconstructed image blocks, the reconstructed image blocks are spliced to obtain a three-dimensional reconstructed image of the part to be detected.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

Acquire multiple first imaging areas corresponding to the linear array ray source and multiple second imaging areas corresponding to the planar array ray source; obtain overlapping parts corresponding to the multiple first imaging areas based on the multiple first imaging areas, and obtain overlapping parts corresponding to the multiple second imaging areas based on the multiple second imaging areas; obtain multiple overlapping areas based on the overlapping parts corresponding to the multiple first imaging areas and the overlapping parts corresponding to the multiple second imaging areas; perform three-dimensional image reconstruction on the projection data of each overlapping area respectively to obtain multiple reconstructed image blocks.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

An intersection operation is performed on the multiple first imaging regions to obtain overlapping parts corresponding to the multiple first imaging regions; and an intersection operation is performed on the multiple second imaging regions to obtain overlapping parts corresponding to the multiple second imaging regions.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

An intersection operation is performed on two adjacent first imaging areas among the multiple first imaging areas to obtain a plurality of first boundary points corresponding to each adjacent two first imaging areas, and an overlapping portion corresponding to each adjacent two first imaging areas is obtained based on the plurality of first boundary points; an intersection operation is performed on two adjacent second imaging areas among the multiple second imaging areas to obtain a plurality of second boundary points corresponding to each adjacent two second imaging areas, and an overlapping portion corresponding to each adjacent two second imaging areas is obtained based on the plurality of second boundary points.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

The portion enclosed by the multiple first boundary points corresponding to each two adjacent first imaging areas is determined as the overlapping portion corresponding to each two adjacent first imaging areas; the portion enclosed by the multiple second boundary points corresponding to each two adjacent second imaging areas is determined as the overlapping portion corresponding to each two adjacent second imaging areas.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

A plurality of first boundary points corresponding to each two adjacent first imaging regions are fitted to obtain an overlapping portion corresponding to each two adjacent first imaging regions; a plurality of second boundary points corresponding to each two adjacent second imaging regions are fitted to obtain an overlapping portion corresponding to each two adjacent second imaging regions.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

The slice information of each sub-image slice in each reconstructed image block is obtained; the sub-image slices of each reconstructed image block are spliced according to the relative position relationship between the reconstructed image blocks and the slice information of each sub-image slice to obtain a plurality of image slices; and the plurality of image slices are determined as a three-dimensional reconstructed image of the part to be detected.

In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

According to the layer number of each sub-image slice in each reconstructed image block, the sub-image slices in the same layer are determined; according to the relative position relationship between the reconstructed image blocks, the splicing order between the sub-image slices in the same layer is determined; the splicing order includes a front-to-back splicing order or a left-to-right splicing order or a top-to-bottom splicing order; according to the splicing order between the sub-image slices in the same layer, the sub-image slices in the same layer are spliced to obtain multiple image slices.

Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims (10)

1. A three-dimensional image stitching method, characterized in that it is applied to an X-ray medical imaging system, the X-ray medical imaging system comprises a detector and an array X-ray source, the relative position between the array X-ray source and the detector is fixed; the array X-ray source comprises a plurality of X-ray sources with different projection angles, the array X-ray source comprises a linear array ray source and a planar array ray source; the linear array ray source is arranged on the chest wall side of the part to be detected, and the planar array ray source is arranged on the side away from the chest wall side of the part to be detected; there is an inclination angle between the setting position of the linear array ray source and the setting position of the planar array ray source; the detector is formed with imaging areas corresponding to the X-ray sources; the method comprises: Acquiring projection data of the part to be detected on each imaging area; the projection data is generated by correspondingly exposing the part to be detected by a plurality of X-ray sources in the array X-ray source; Respectively performing three-dimensional image reconstruction on the projection data of each imaging area to obtain a plurality of reconstructed image blocks; According to the relative positional relationship between the reconstructed image blocks, the reconstructed image blocks are spliced to obtain a three-dimensional reconstructed image of the part to be detected. 2. The method according to claim 1, characterized in that the array X-ray source comprises a linear array ray source and a planar array ray source, and the acquiring of projection data of any adjacent overlapping areas in each of the imaging areas, and performing three-dimensional image reconstruction on the projection data of each of the overlapping areas to obtain a plurality of reconstructed image blocks comprises: Acquire a plurality of first imaging regions corresponding to the linear array ray source and a plurality of second imaging regions corresponding to the planar array ray source; According to the plurality of first imaging regions, obtaining overlapping portions corresponding to the plurality of first imaging regions, and according to the plurality of second imaging regions, obtaining overlapping portions corresponding to the plurality of second imaging regions; Obtaining a plurality of overlapping regions according to overlapping portions corresponding to the plurality of first imaging regions and overlapping portions corresponding to the plurality of second imaging regions; The projection data of each overlapping area are respectively subjected to three-dimensional image reconstruction to obtain the multiple reconstructed image blocks. 3. The method according to claim 2, characterized in that the step of obtaining overlapping portions corresponding to the plurality of first imaging regions according to the plurality of first imaging regions and obtaining overlapping portions corresponding to the plurality of second imaging regions according to the plurality of second imaging regions comprises: Performing intersection operation processing on the multiple first imaging regions to obtain overlapping parts corresponding to the multiple first imaging regions; An intersection operation is performed on the plurality of second imaging regions to obtain overlapping portions corresponding to the plurality of second imaging regions. 4. The method according to any one of claims 1 to 3, characterized in that each of the reconstructed image blocks includes a plurality of sub-image slices; and the step of splicing the reconstructed image blocks according to the relative positional relationship between the reconstructed image blocks to obtain the three-dimensional reconstructed image of the part to be detected comprises: Acquire slice information of each sub-image slice in each of the reconstructed image blocks; splicing the sub-image slices of each reconstructed image block according to the relative position relationship between the reconstructed image blocks and the slice information of each sub-image slice to obtain a plurality of image slices; The multiple image slices are determined as a three-dimensional reconstructed image of the part to be detected. 5. The method according to claim 4, characterized in that the slice information of the sub-image slices includes the layer number of the sub-image slices; and the step of splicing the sub-image slices of each of the reconstructed image blocks according to the relative position relationship between the reconstructed image blocks and the slice information of each of the sub-image slices to obtain a plurality of image slices comprises: Determine, according to the layer number of each sub-image slice in each of the reconstructed image blocks, each sub-image slice in the same layer; Determining a splicing order between the sub-image slices in the same layer according to the relative position relationship between the reconstructed image blocks; the splicing order includes a front-to-back splicing order, a left-to-right splicing order, or a top-to-bottom splicing order; The sub-image slices in the same layer are spliced according to the splicing order between the sub-image slices in the same layer to obtain the multiple image slices. 6. A three-dimensional image stitching device, characterized in that it is applied to an X-ray medical imaging system, the X-ray medical imaging system comprises a detector and an array X-ray source, the relative position between the array X-ray source and the detector is fixed; the array X-ray source comprises a plurality of X-ray sources with different projection angles, the array X-ray source comprises a linear array ray source and a planar array ray source; the linear array ray source is arranged on the chest wall side of the part to be detected, and the planar array ray source is arranged on the side away from the chest wall side of the part to be detected; there is an inclination angle between the setting position of the linear array ray source and the setting position of the planar array ray source; the detector is formed with imaging areas corresponding to the X-ray sources; the device comprises: An acquisition module, used for acquiring projection data of the part to be detected on each imaging area; the projection data is generated by correspondingly exposing the part to be detected by a plurality of X-ray sources in the array X-ray source; A reconstruction module, used for performing three-dimensional image reconstruction on the projection data of each imaging area to obtain a plurality of reconstructed image blocks; The splicing module is used to splice the reconstructed image blocks according to the relative position relationship between the reconstructed image blocks to obtain a three-dimensional reconstructed image of the part to be detected. 7. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the computer program. 8. An X-ray medical imaging system, characterized in that the system comprises an array X-ray source, a compression plate, a detector, and the computer device according to claim 7. 9 . The system according to claim 8 , wherein the compression plate is disposed between the array X-ray source and the detector for compressing a part to be detected. 10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.