X-ray image splicing method, splicing device and X-ray photography system

Abstract

The invention discloses an X-ray image splicing method and device and an X-ray photography system. The X-ray image splicing method comprises the steps that multiple to-be-spliced X-ray images of a splicing body position are obtained, a candidate splicing area of at least one X-ray image is obtained, the multiple X-ray images are displayed on a splicing planning interface, and the candidate splicing area is marked; receiving an operation of an operator on the splicing planning interface, and determining a region of interest in the candidate splicing region; and splicing the plurality of X-ray images based on the region of interest to obtain a spliced image of the spliced body position. According to the method, the region of interest is determined in the overlapping region or the candidate splicing region, and then the X-ray images are spliced based on the region of interest, so that the ghosting problem of anatomical structures / tissues concerned by an operator in the spliced image is reduced; and the definition of a ghosting problem of anatomical structures / tissues concerned by an operator in a spliced image is improved.

Description

Technical Field

[0001] This invention relates to the field of X-ray imaging, and more specifically to a method, device, and system for stitching X-ray images. Background Technology

[0002] Radiographic imaging equipment, a common imaging system in medical digital imaging, is widely used in physical examinations and routine medical imaging diagnosis. Radiographic imaging equipment utilizes radioactive rays (such as X-rays) to create images by passing them through the object being examined. Taking X-ray imaging systems as an example, their advantages, such as fast imaging speed, low radiation dose, clear and detailed images, and the ability to examine the entire body, make them widely used in clinical examinations and one of the main auxiliary tools for doctors in disease diagnosis.

[0003] In some scenarios, a single X-ray imaging session cannot capture the entire body position (such as the spine or lower limbs) (this can be called a stitched position). In such cases, the body position needs to be divided into different areas and X-rayed separately. These multiple X-ray images are then stitched together to obtain a complete X-ray image of the body position (a stitched image). It's important to understand that the imaging position does not refer to the subject's posture, but rather to the part or area of ​​the subject to be imaged.

[0004] How to stitch together multiple X-ray images is a problem worth studying. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method, device and system for stitching X-ray images, which are described in detail below.

[0006] According to a first aspect, one embodiment provides a method for stitching X-ray images, comprising:

[0007] Acquire multiple X-ray images of the body to be stitched together in the desired position;

[0008] Obtain candidate stitching regions of at least one of the X-ray images, wherein the candidate stitching regions of the X-ray images include at least a portion of the overlapping regions between the X-ray image and its adjacent X-ray images in the stitching;

[0009] Multiple X-ray images are displayed on the stitching planning interface, and the candidate stitching areas are identified.

[0010] Receive operator input on the splicing planning interface and determine the region of interest within the candidate splicing area;

[0011] Multiple X-ray images are stitched together based on the region of interest to obtain a stitched image of the stitched body position;

[0012] The stitched image shows the stitched body position.

[0013] In one embodiment, displaying multiple X-ray images on the stitching planning interface includes:

[0014] The multiple X-ray images are displayed on the stitching planning interface based on their adjacent positions in the stitching process; or...

[0015] Based on the positional distribution of the multiple X-ray images in the stitching position, the multiple X-ray images are displayed on the stitching planning interface.

[0016] In one embodiment, identifying the candidate splicing area includes: identifying the candidate splicing area by means of the area defined by lines.

[0017] In one embodiment, the operation of the receiving operator on the stitching planning interface, determining the region of interest within the candidate stitching area, includes:

[0018] The operator selects points within the candidate splicing area on the splicing planning interface and identifies at least one point of interest within the candidate splicing area.

[0019] Within the candidate splicing area, a region containing the point of interest is determined as the region of interest.

[0020] In one embodiment, the operation of the receiving operator on the stitching planning interface, determining the region of interest within the candidate stitching area, includes:

[0021] The system receives a selection operation from the user on the stitching planning interface within the candidate stitching area, and determines the selected area as the region of interest based on the selection operation; or...

[0022] The system receives the drawing operations performed by the operator on the candidate splicing area on the splicing planning interface, and determines the drawing area based on the drawing operations as the region of interest.

[0023] In one embodiment, the operation of the receiving operator on the stitching planning interface, determining the region of interest within the candidate stitching area, includes:

[0024] Anatomical structure information is identified and displayed within the candidate splicing area, and the anatomical structure information includes structural feature points or feature regions.

[0025] The operator confirms the anatomical structure information by receiving confirmation from the operator; the confirmation of the anatomical structure information by receiving confirmation from the operator includes: determining a region of a preset size that contains the structural feature points within the candidate splicing area as the region of interest; or, using the feature region as the region of interest.

[0026] In one embodiment, stitching together multiple X-ray images based on the region of interest to obtain a stitched image of the body position includes:

[0027] Anatomical structures are identified within the region of interest, and image registration is performed on the associated X-ray images based on the identified anatomical structures to obtain the registration results.

[0028] The associated X-ray images are stitched together based on the registration structure.

[0029] According to a second aspect, one embodiment provides a method for stitching X-ray images, comprising:

[0030] Acquire multiple X-ray images of the body to be stitched together in the desired position;

[0031] At least one of the X-ray images is displayed on the stitching planning interface;

[0032] The operator receives the operation of the stitching planning interface and determines the region of interest on at least one of the X-ray images;

[0033] Multiple X-ray images are stitched together based on the region of interest to obtain a stitched image of the stitched body position;

[0034] The stitched image shows the stitched body position.

[0035] In one embodiment, the operation of the receiving operator on the stitching planning interface to determine the region of interest on at least one of the X-ray images includes: receiving the operator's point selection operation, box selection operation, or drawing operation on the stitching planning interface to determine the region of interest.

[0036] In one embodiment, the operator's operation on the stitching planning interface to determine the region of interest on at least one of the X-ray images includes:

[0037] One or more anatomical structures are identified from at least one of the X-ray images displayed on the stitching planning interface to obtain the identification results;

[0038] The system receives confirmation or selection operations from the operator for the identified anatomical structures and designates the confirmed or selected anatomical structures as the region of interest.

[0039] According to a third aspect, one embodiment provides a method for stitching X-ray images, comprising:

[0040] Acquire multiple X-ray images to be stitched together;

[0041] Obtain at least one candidate stitching region of the X-ray image, wherein the candidate stitching region of the X-ray image is at least a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching;

[0042] Determine the region of interest from the candidate splicing regions;

[0043] A stitched image is obtained by stitching together multiple X-ray images based on the region of interest.

[0044] The stitched image is displayed.

[0045] In one embodiment, determining the region of interest from the candidate splicing area includes: displaying the candidate splicing area; and determining the region of interest based on the operator's operation on the candidate splicing area.

[0046] In one embodiment, determining the region of interest based on the operator's operation on the candidate splicing region includes: receiving the operator's point selection operation, box selection operation, or drawing operation on the candidate splicing region to determine the region of interest.

[0047] In one embodiment, determining the region of interest from the candidate splicing region includes: identifying at least one anatomical structure within the overlapping region, and determining the region of interest based on the identified anatomical structure.

[0048] In one embodiment, determining the region of interest based on the identified anatomical structure includes: displaying one or more candidate regions of interest containing the anatomical structure for confirmation or selection; receiving confirmation or selection operations from the operator for the candidate regions of interest; and using the confirmed or selected candidate regions of interest as the region of interest.

[0049] According to a fourth aspect, one embodiment provides a method for stitching X-ray images, comprising:

[0050] Acquire multiple X-ray images to be stitched together;

[0051] A region of interest is determined on at least one of the X-ray images, the region of interest being located within the overlapping area between the X-ray image and an adjacent X-ray image in the stitching and being smaller than the overlapping area;

[0052] A stitched image is obtained by stitching together multiple X-ray images based on the region of interest.

[0053] The stitched image is displayed.

[0054] According to a fifth aspect, one embodiment provides a stitching apparatus for X-ray images, one embodiment comprising:

[0055] Memory, used to store programs;

[0056] A processor for implementing the method as described in any of the embodiments herein by executing a program stored in the memory.

[0057] According to a sixth aspect, one embodiment provides an X-ray imaging system, one embodiment comprising:

[0058] A head unit, the head unit comprising a head unit for emitting X-rays toward a subject being examined;

[0059] An X-ray receiving device, the X-ray receiving device including a detector, the detector being used to receive X-rays that pass through the subject being examined;

[0060] A processor for performing the methods described in any of the embodiments herein.

[0061] The X-ray image stitching method, stitching device, and X-ray imaging system according to the above embodiments reduce the ghosting problem of anatomical structures / tissues of interest in the stitched images by determining the region of interest in the overlapping area or the candidate stitching area, and then stitching the X-ray images based on the region of interest. This improves the clarity of the ghosting problem of anatomical structures / tissues of interest in the stitched images. Attached Figure Description

[0062] Figure 1 This is a schematic diagram illustrating multiple shots taken in a spliced ​​body position in one embodiment;

[0063] Figure 2 This is a schematic diagram of multiple X-ray images obtained by taking multiple photos of a stitched body position in one embodiment, and the overlapping area corresponding to adjacent X-ray images;

[0064] Figure 3 A flowchart illustrating an embodiment of an X-ray image stitching method;

[0065] Figure 4 Several example images are provided to illustrate X-ray images and identify candidate stitching regions;

[0066] Figure 5 To display X-ray images, identify candidate stitching regions, and provide multiple example images of candidate stitching regions;

[0067] Figure 6This is a flowchart illustrating how, in one embodiment, multiple X-ray images are stitched together based on a region of interest to obtain a stitched image of a body position.

[0068] Figure 7 This is a schematic diagram showing a stitched image of the stitched body position in one embodiment;

[0069] Figure 8 A flowchart illustrating an embodiment of an X-ray image stitching method;

[0070] Figure 9 A flowchart illustrating an embodiment of an X-ray image stitching method;

[0071] Figure 10 This is a flowchart illustrating an embodiment of an X-ray image stitching method.

[0072] Figure 11 This is a schematic diagram of the structure of an X-ray imaging system according to one embodiment;

[0073] Figure 12 This is a schematic diagram of the structure of an X-ray imaging system according to one embodiment;

[0074] Figure 13 This is a schematic diagram of the structure of an X-ray imaging system according to one embodiment;

[0075] Figure 14 This is a schematic diagram of the structure of an X-ray imaging system according to one embodiment;

[0076] Figure 15 This is a schematic diagram of the structure of an X-ray imaging system according to one embodiment;

[0077] Figure 16 This is a schematic diagram of the structure of an X-ray imaging system according to one embodiment;

[0078] Figure 17 This is a schematic diagram of the structure of a stitching device for X-ray images according to one embodiment. Detailed Implementation

[0079] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of this application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to this application are not shown or described in the specification. This is to avoid obscuring the core parts of this application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0080] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0081] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0082] Stitching imaging technology has significant value in clinical applications. For example, in fields such as orthopedics, thoracic surgery, and neurosurgery, stitching imaging technology can be used to obtain larger imaging areas, thereby improving the accuracy and efficiency of diagnosis.

[0083] This application involves stitching positions in some of its methods. These positions refer to tissue areas of the subject that require multiple X-ray imaging sessions to obtain a complete radiographic image of the tissue area. For example, stitching positions could be of the chest, abdomen, or lower limbs. It is understood that stitching positions do not refer to a specific posture of the subject.

[0084] Furthermore, multiple X-ray images are taken in the stitched position to obtain multiple images, which are then stitched together. To enable the stitching of these multiple X-ray images, there will be some overlap between adjacent shooting areas during the shooting process. Correspondingly, there will also be overlapping areas between adjacent X-ray images during stitching, which can be called the stitching region. This allows adjacent X-ray images to be matched and fused based on the overlapping region, which is a fundamental aspect of stitching imaging technology. Let's take... Figure 1 For example, when imaging the lower limbs of the subject, there are four X-ray imaging (irradiation) areas from top to bottom: X-ray imaging (irradiation) area 1, X-ray imaging (irradiation) area 2, X-ray imaging (irradiation) area 3, and X-ray imaging (irradiation) area 4. These four X-ray imaging (irradiation) areas can completely cover the lower limbs to be imaged. Furthermore, there are overlapping areas between adjacent X-ray imaging (irradiation) areas. For instance, X-ray imaging (irradiation) area 1 and X-ray imaging (irradiation) area 2 overlap (see the first area filled with a gray diagonal line from top to bottom in the figure), X-ray imaging (irradiation) area 2 and X-ray imaging (irradiation) area 3 overlap (see the second area filled with a gray diagonal line from top to bottom in the figure), and X-ray imaging (irradiation) area 3 and X-ray imaging (irradiation) area 4 overlap (see the third area filled with a gray diagonal line from top to bottom in the figure). Please refer to... Figure 2 Four X-ray images were obtained by taking pictures of X-ray imaging (irradiation) areas 1, 2, 3, and 4, respectively. These images can be referred to as X-ray image 1, X-ray image 2, X-ray image 3, and X-ray image 4. Correspondingly, X-ray image 1 and X-ray image 2 have the same characteristics as X-ray image 4. Figure 1 The overlapping area corresponding to the first image area filled with a gray diagonal line, that is, the gray-filled area 1-a in X-ray image 1 and the gray-filled area 2-a in X-ray image 2, are corresponding overlapping areas, and both correspond to the area in... Figure 1 The first gray-filled imaging area in the image; similarly, X-ray image 2 and X-ray image 3 have the same image size as the first gray-filled imaging area in the image. Figure 1 The overlapping area corresponding to the second image area filled with a gray diagonal line, that is, the gray-filled area 2-b in X-ray image 2 and the gray-filled area 3-a in X-ray image 3, are corresponding overlapping areas, and both correspond to the area in... Figure 1 The second gray-filled imaging area in the image; similarly, X-ray image 3 and X-ray image 4 have the same image area as the second gray-filled imaging area in the image. Figure 1 The overlapping area corresponding to the third image area filled with a gray diagonal line, that is, the gray-filled area 3-b in X-ray image 3 and the gray-filled area 4-a in X-ray image 4, are corresponding overlapping areas, and both correspond to the area in... Figure 1The third gray-filled imaging area in the image; when stitching together X-ray images 1, 2, 3, and 4, X-ray image 1 is adjacent to only X-ray image 2 in the stitching, X-ray image 2 is adjacent to both X-ray image 1 and X-ray image 3 in the stitching, X-ray image 3 is adjacent to both X-ray image 2 and X-ray image 4 in the stitching, and X-ray image 4 is adjacent to only X-ray image 3 in the stitching.

[0085] When faced with multiple X-ray images to be stitched together:

[0086] One approach is to manually align and fuse these multiple X-ray images to obtain a stitched image, which is an X-ray image with a larger field of view. However, manual stitching requires doctors to accurately align and adjust each X-ray image based on their own experience and knowledge, which is labor-intensive and prone to human error.

[0087] Another approach is automatic stitching, which typically matches and registers overlapping areas between adjacent X-ray images to achieve image alignment and fusion. However, the acquisition of X-ray images can be affected by factors such as the movement of the subject or equipment vibration, leading to misalignment and blurring between images, thus affecting the stitching effect. In addition, existing automatic stitching algorithms often require significant computational resources and have certain requirements for image quality; for low-quality images, the stitching effect may be unsatisfactory. Finally, existing automatic stitching algorithms often exhibit ghosting when processing complex anatomical structures (such as the spine and heart), affecting doctors' diagnosis and treatment.

[0088] The inventors analyzed that existing automatic stitching schemes are all based on matching the overlapping areas between adjacent X-ray images. Typically, using the overlapping area as a reference, features (feature points or feature structures) within the overlapping area of ​​adjacent X-ray images are detected or identified, and then image registration and fusion are performed based on the features detected or identified within the overlapping area. Since the overlapping area is generally large and contains many tissues or structures, this results in the stitching effect failing to take into account most of the tissues and structures within the overlapping area, and may even lead to poor stitching effects such as ghosting in the tissues or structures of most interest to the user. Therefore, the inventors proposed further defining a smaller region of interest from the overlapping area, and using this smaller region of interest as a reference for X-ray image stitching. This reduces the ghosting problem of tissues and structures within the aforementioned region of interest in the stitched image, and improves the clarity of the stitched image. This will be explained in detail below.

[0089] Please refer to Figure 3 This application provides a method 1000 for stitching X-ray images (hereinafter referred to as stitching method 1000) in some embodiments, including the following steps:

[0090] Step 110: Obtain multiple X-ray images of the body to be stitched together.

[0091] As mentioned above, the stitching position refers to a tissue area of ​​the subject being examined, which requires multiple X-ray images during X-ray imaging. These multiple X-ray images are then stitched together to obtain a complete radiographic image of the tissue area. For example, the stitching position could be the chest, abdomen, or lower limbs. Understandably, the stitching position does not refer to a specific posture of the subject. Correspondingly, the multiple X-ray images to be stitched together in the stitching position refer to the multiple X-ray images obtained after taking multiple X-ray images in that position.

[0092] Step 120: Obtain candidate stitching regions from at least one X-ray image.

[0093] The candidate stitching region of an X-ray image includes at least a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching. In some examples, the candidate stitching region of an X-ray image includes a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching, or even a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching; in some examples, the candidate stitching region of an X-ray image includes the entire overlapping region between the X-ray image and its adjacent X-ray images in the stitching, or even the candidate stitching region of an X-ray image is simply the overlapping region between the X-ray image and its adjacent X-ray images in the stitching.

[0094] There are several ways to obtain overlapping regions. For example, the overlapping region between adjacent X-ray images can be determined based on the information captured when the X-ray images are taken. Another example is to calculate or match the overlapping regions based on the adjacent X-ray images. After determining the overlapping region, it is easy to determine the candidate stitching region. For example, when the candidate stitching region is an overlapping region, determining the overlapping region also determines the candidate stitching region. When the candidate stitching region is a part of the overlapping region, the part of the overlapping region is selected as the candidate stitching region.

[0095] Step 130: Display the above X-ray images on the stitching planning interface and mark the candidate stitching areas.

[0096] In some embodiments, step 120 obtains the candidate stitching region for each X-ray image, and step 130 identifies the candidate stitching region for each X-ray image on the stitching planning interface.

[0097] In some embodiments, step 120 obtains at least one candidate stitching region of any two adjacent X-ray images, the candidate stitching region including at least a portion of the overlapping region between the two adjacent X-ray images; and step 130 identifies the candidate stitching region on the stitching planning interface.

[0098] In some embodiments, step 130, displaying the multiple X-ray images on the stitching planning interface, includes: displaying the multiple X-ray images on the stitching planning interface based on their adjacent positional relationship in the stitching.

[0099] In some embodiments, step 130, displaying the multiple X-ray images on the stitching planning interface, includes: displaying the multiple X-ray images on the stitching planning interface based on the positional distribution of the multiple X-ray images in the stitching position.

[0100] By displaying these multiple X-ray images according to their adjacent positions or their distribution within the stitched body position, it becomes more intuitive and convenient for the operator to view them and select the region of interest.

[0101] In addition, candidate splicing areas can be marked in various ways on the splicing planning interface. For example, candidate splicing areas can be marked by areas defined by lines on the displayed X-ray image, such as by rectangular boxes or elliptical boxes. Whether to use a rectangular box or an elliptical box depends on the shape of the candidate splicing area itself.

[0102] Figure 4 To show multiple examples of X-ray images and identify candidate stitching regions; in Figure 4 The image displays three X-ray images of the subject taken from top to bottom: X-ray image 1, X-ray image 2, and X-ray image 3. The white dashed boxes on the X-ray images indicate the candidate stitching areas. Figure 4 The general will display X-ray images 1, 2, and 3 sequentially from top to bottom on the stitching planning interface based on their adjacent positions in the stitching or their distribution within the stitching body; Figure 4In Figure (a), candidate stitching regions for each X-ray image are marked on the stitching planning interface. For example, X-ray image 1 has candidate stitching region 1-1 corresponding to its adjacent X-ray image 2; X-ray image 2 has candidate stitching region 2-1 corresponding to its adjacent X-ray image 1 and candidate stitching region 2-2 corresponding to its adjacent X-ray image 3; and X-ray image 3 has candidate stitching region 3-1 corresponding to its adjacent X-ray image 1. In other examples, for any two adjacent X-ray images, the candidate stitching region of one of the X-ray images is marked on the stitching planning interface. That is, only one of candidate stitching region 1-1 and candidate stitching region 2-1 needs to be acquired and marked—or both can be acquired and marked. Similarly, only one of candidate stitching region 2-1 and candidate stitching region 2-2 needs to be acquired and marked—or both can be acquired and marked. Figure 4 (b), (c), (d), (e), and (f) are several corresponding examples.

[0103] Step 140: Receive the operator's input on the splicing planning interface and determine the region of interest within the candidate splicing area.

[0104] In some embodiments, step 140, receiving the operator's operation on the stitching planning interface and determining the region of interest within the candidate stitching area, includes: receiving the operator's point selection operation on the stitching planning interface within the candidate stitching area, confirming at least one point of interest within the candidate stitching area; and determining the region of interest within the candidate stitching area based on the at least one point of interest; for example, step 140 determines a region containing the point of interest within the candidate stitching area as the region of interest.

[0105] In some examples, the region containing the point of interest determined in step 140 is a region of a preset size and preset shape. The preset shape can be, for example, a rectangle, an ellipse, or a circle.

[0106] For example Figure 5 (a) is an example. Figure 5 (a) is based on Figure 4 Taking the splicing planning interface shown in (a) as an example, the operator can... Figure 4 The stitching planning interface shown in (a) is used to operate. A circular region of interest (see the black circular region in candidate stitching region 1-1) is determined based on the point of interest A1 (see the solid black dot in candidate stitching region 1-1). A circular region of interest (see the black circular region in candidate stitching region 2-2) is determined based on the point of interest A2 (see the solid black dot in candidate stitching region 2-2).

[0107] In some examples, step 140 may determine the anatomical structure within the candidate stitching region based on the point of interest, and detect or segment the anatomical structure from the X-ray image, and use the region defined by the outline of the anatomical structure as the region containing the point of interest, i.e., as the region of interest.

[0108] For example Figure 5 (b) is an example. Figure 5 (b) is based on Figure 4 Taking the splicing planning interface shown in (a) as an example, the operator can... Figure 4 The operation is performed on the stitching planning interface shown in (a). The region of interest (see the black outline in candidate stitching region 1-1) is defined by the outline of the spinal anatomy structure determined by the point of interest B1 (see the solid black dot in candidate stitching region 1-1). The region of interest (see the black outline in candidate stitching region 2-2) is defined by the outline of the spinal anatomy structure determined by the point of interest B2 (see the solid black dot in candidate stitching region 2-2).

[0109] In some embodiments, step 140, receiving the operator's operation on the stitching planning interface, and determining the region of interest within the candidate stitching area, may include: receiving the operator's selection operation within the candidate stitching area on the stitching planning interface, and determining the selected area as the region of interest based on the selection operation. The shape of the selected area can be rectangular or elliptical, etc., which can be designed based on actual needs.

[0110] For example Figure 5 (c) is an example. Figure 5 (c) is based on Figure 4 Taking the splicing planning interface shown in (a) as an example, the operator can... Figure 4 Operate on the stitching planning interface shown in (a), and select the regions of interest in candidate stitching region 1-1 and candidate stitching region 2-2 respectively (see the black boxes in candidate stitching region 1-1 and candidate stitching region 2-2 respectively).

[0111] In some embodiments, step 140, receiving the operator's operation on the stitching planning interface, and determining the region of interest within the candidate stitching area, may include: receiving the operator's drawing operation on the candidate stitching area on the stitching planning interface, and determining the drawing area as the region of interest based on the drawing operation.

[0112] For example, the operator can use input tools such as a mouse or trackball to trace the outlines of anatomical structures such as regions of interest or regions of interest within the candidate stitching area of ​​the ultrasound image displayed on the stitching planning interface, thereby determining the region of interest.

[0113] For example Figure 5 (d) is an example. Figure 5 (d) is based on Figure 4 Taking the splicing planning interface shown in (a) as an example, the operator can... Figure 4 Operate on the stitching planning interface shown in (a), and draw regions of interest in candidate stitching region 1-1 and candidate stitching region 2-2 respectively (see the black outline drawn in candidate stitching region 1-1 and the black outline drawn in candidate stitching region 2-2 respectively).

[0114] In some embodiments, step 140, receiving an operator's operation on the stitching planning interface, and determining the region of interest within the candidate stitching area, may include: identifying and displaying anatomical structure information within the candidate stitching area, the anatomical structure information including structural feature points or feature regions; receiving a confirmation operation from the operator to confirm the above-mentioned anatomical structure information; and obtaining the region of interest based on the confirmed anatomical structure information, for example, determining a region of a preset size within the candidate stitching area that contains the above-mentioned structural feature points as the region of interest, or, for example, using a feature region as the region of interest; in some examples, the feature region may be the region defined by the outline of the anatomical structure.

[0115] Identifying anatomical structure information within candidate stitching regions can be based on traditional image detection methods or on machine learning methods for keypoint detection, object detection, and segmentation.

[0116] In addition, the operator's confirmation operation confirms the above anatomical information, which may be a selection instruction from the operator to select one of multiple structural feature points or multiple feature regions.

[0117] Understandably, in some embodiments, the various methods mentioned above can be combined to determine the region of interest from the candidate stitching region. For example, when determining the region of interest within candidate stitching region 1-1, it can be done by the receiving operator selecting points within the candidate stitching region on the stitching planning interface, identifying at least one point of interest within the candidate stitching region, and determining the region of interest based on at least one point of interest. Alternatively, it can be done by the receiving operator selecting a bounding box within the candidate stitching region on the stitching planning interface, and determining the selected region as the region of interest based on the bounding box selection. It can also be done by the receiving operator drawing within the candidate stitching region on the stitching planning interface, and determining the drawn region as the region of interest based on the drawing operation. Alternatively, it can be done by identifying and displaying anatomical structure information within the candidate stitching region. The anatomical structure information includes structural feature points or feature regions, and the receiving operator confirms the aforementioned anatomical structure information. The information is used to obtain the region of interest based on the confirmed anatomical structure information. Similarly, when determining the region of interest within the candidate splicing region 2-1, it can be done by the receiving operator selecting points within the candidate splicing region on the splicing planning interface, confirming at least one point of interest within the candidate splicing region, and determining the region of interest based on at least one point of interest. Alternatively, it can be done by the receiving operator selecting boxes within the candidate splicing region on the splicing planning interface, and determining the selected area as the region of interest based on the box selection operation. Alternatively, it can be done by the receiving operator drawing within the candidate splicing region on the splicing planning interface, and determining the drawn area as the region of interest based on the drawing operation. Alternatively, it can be done by identifying and displaying anatomical structure information within the candidate splicing region, including structural feature points or feature regions, and the receiving operator confirming the above anatomical structure information, and obtaining the region of interest based on the confirmed anatomical structure information.Similarly, when determining the region of interest (ROI) within the candidate stitching region 2-2, it can be achieved through the receiving operator's point selection operation within the candidate stitching region on the stitching planning interface, identifying at least one point of interest (POI) within the candidate stitching region, and determining the ROI based on this at least one POI. Alternatively, it can be achieved through the receiving operator's bounding box selection operation within the candidate stitching region on the stitching planning interface, determining the bounding box region as the ROI based on this bounding box selection operation. It can also be achieved through the receiving operator's drawing operation within the candidate stitching region on the stitching planning interface, determining the drawn region as the ROI based on this drawing operation. Alternatively, it can be achieved by identifying and displaying anatomical structure information within the candidate stitching region. This anatomical structure information includes structural feature points or feature regions, and the receiving operator's confirmation operation confirms the aforementioned anatomical structure information, obtaining the ROI based on the confirmed anatomical structure information. Similarly, when determining the region of interest (ROI) within the candidate stitching region 3-1, it can be achieved through the receiving operator's point selection operation within the candidate stitching region on the stitching planning interface, identifying at least one point of interest (POI) within the candidate stitching region, and determining the ROI based on this at least one POI. Alternatively, it can be achieved through the receiving operator's bounding box selection operation within the candidate stitching region on the stitching planning interface, determining the bounding box region as the ROI based on this bounding box selection operation. It can also be achieved through the receiving operator's drawing operation within the candidate stitching region on the stitching planning interface, determining the drawn region as the ROI based on this drawing operation. Alternatively, it can be achieved by identifying and displaying anatomical structure information within the candidate stitching region, including structural feature points or feature regions, and the receiving operator's confirmation operation confirming the aforementioned anatomical structure information, thereby obtaining the ROI based on the confirmed anatomical structure information.

[0118] Typically, the region of interest is located within the candidate stitching region and is smaller than the candidate stitching region.

[0119] Step 150: Based on the region of interest, stitch together the above multiple X-ray images to obtain a stitched image of the body position.

[0120] Please refer to Figure 6 In some embodiments, step 150, which stitches together the multiple X-ray images based on the region of interest to obtain a stitched image of the body position, may include the following steps:

[0121] Step 151: Based on the region of interest (ROI), perform image registration on the X-ray images associated with the candidate stitching regions to obtain the registration results. For example, in Step 151, anatomical structures are identified within the ROI, and image registration is performed on the associated X-ray images based on the identified anatomical structures to obtain the registration results. Identifying anatomical structures within the ROI can be based on traditional image detection methods or on machine learning methods such as keypoint detection, target detection, and segmentation. Step 152: Perform image stitching on the associated X-ray images based on the registration structure.

[0122] Image registration can be performed directly based on the region of interest (ROI) or by identifying anatomical structures within the ROI. Image registration algorithms can employ feature-point matching, feature-region matching, or mutual information-based methods. The mutual information can be normalized to reduce ghosting. After obtaining the registration results, a weighted average-based image fusion method, such as linear weighted fusion, can be used to seamlessly fuse the registered ROI or its internal anatomical structures, thereby significantly reducing ghosting issues.

[0123] Step 160: Display the stitched image of the stitched body position. Figure 7 An example of a stitched image showing the stitched body position.

[0124] The above are some explanations of the X-ray image stitching method 1000. The operator determines the region of interest (ROI) from the candidate stitching regions based on the anatomical structures / tissues of interest, and then stitches the X-ray images using the ROI as a reference. This ensures that the anatomical structures / tissues within the ROI are clear and of high quality in the resulting stitched image, reducing ghosting issues and improving the clarity of the anatomical structures / tissues of interest in the stitched image.

[0125] Understandably, two adjacent X-ray images can have overlapping regions corresponding to the same overlapping imaging area; correspondingly, two adjacent X-ray images can have two corresponding candidate stitching regions, for example... Figure 4 In Figure (a), candidate stitching region 1-1 on X-ray image 1 and candidate stitching region 2-1 on X-ray image 2 are two corresponding candidate stitching regions, and candidate stitching region 2-2 on X-ray image 2 and candidate stitching region 3-1 on X-ray image 3 are two corresponding candidate stitching regions; usually, it is only necessary to determine the region of interest in one of the two corresponding candidate stitching regions.

[0126] In some embodiments, for any two adjacent X-ray images, at least one of the candidate stitching regions of the X-ray image is obtained and identified, and for any two adjacent X-ray images, a region of interest (ROI) is determined within the candidate stitching region of one of the X-ray images. In this way, when performing image registration on the X-ray images associated with the candidate stitching regions to which the ROI belongs, the image registration for any two adjacent X-ray images is based on their corresponding ROIs. Understandably, the X-ray images associated with the candidate stitching regions to which the ROI belongs are the X-ray images containing the candidate stitching regions and their adjacent X-ray images. For example, let's consider... Figure 4 Taking Figure (a) as an example, the X-ray images associated with candidate stitching region 1-1 are X-ray image 1 and X-ray image 2, the X-ray images associated with candidate stitching region 2-1 are X-ray image 2 and X-ray image 1, the X-ray images associated with candidate stitching region 2-2 are X-ray image 2 and X-ray image 3, and the X-ray images associated with candidate stitching region 3-1 are X-ray image 3 and X-ray image 2.

[0127] Understandably, in examples with multiple X-ray images forming multiple pairs of adjacent X-ray images, it is not necessary to determine and stitch each pair of adjacent X-ray images based on the region of interest. Instead, a portion of the adjacent X-ray images can be determined and stitched based on the region of interest, while other adjacent X-ray images can be stitched using other stitching techniques, such as directly stitching based on overlapping areas or even candidate stitching regions. It is worth noting that... Figure 4 Taking Figure (a) as an example, the region of interest can be determined only in the candidate stitching region 1-1. In this way, X-ray image 1 and X-ray image 2 are stitched based on the region of interest determined in the candidate stitching region 1-1, while X-ray image 2 and X-ray image 3 are stitched based on other stitching techniques, such as directly stitching based on the candidate stitching regions or even overlapping regions of X-ray image 2 and X-ray image 3.

[0128] Therefore, in some examples, when displaying multiple X-ray images and identifying candidate stitching regions on the stitching planning interface, for any two adjacent X-ray images, at least one X-ray image's candidate stitching region can be obtained and identified. Alternatively, candidate stitching regions can be identified for a portion of the adjacent X-ray images, while candidate stitching regions for the other portion of adjacent X-ray images may not be identified. For example, for... Figure 4 For example, you can identify only one of the candidate splicing regions 1-1, 2-1, 2-2, and 3-1.

[0129] Please refer to Figure 8Some embodiments provide a method 1000 for stitching X-ray images, including the following steps:

[0130] Step 210: Obtain multiple X-ray images of the body to be stitched together.

[0131] As mentioned above, the stitching position refers to a tissue area of ​​the subject being examined, which requires multiple X-ray images during X-ray imaging. These multiple X-ray images are then stitched together to obtain a complete radiographic image of the tissue area. For example, the stitching position could be the chest, abdomen, or lower limbs. Understandably, the stitching position does not refer to a specific posture of the subject. Correspondingly, the multiple X-ray images to be stitched together in the stitching position refer to the multiple X-ray images obtained after taking multiple X-ray images in that position.

[0132] Step 220: Display at least one X-ray image on the stitching planning interface;

[0133] The stitching planning interface can display one or more of the above-mentioned X-ray images to be stitched together.

[0134] Step 230: Receive the operator's input on the stitching planning interface and determine the region of interest on at least one X-ray image.

[0135] In step 230, the region of interest is determined from the X-ray image displayed on the stitching planning interface by the operator's operation of the stitching planning interface.

[0136] Typically, the region of interest is located within the overlapping area of ​​the displayed X-ray image and is smaller than the overlapping area.

[0137] In some embodiments, step 230 receives point selection, box selection, or drawing operations from the operator on the splicing planning interface to determine the region of interest.

[0138] In some embodiments, step 230 identifies one or more anatomical structures in one or more X-ray images displayed on the stitching planning interface to obtain identification results, and receives confirmation or selection operations from the operator for the identified anatomical structures, and designates the confirmed or selected anatomical structures as the region of interest.

[0139] There are multiple ways to implement step 230, which can be further described in the above description of step 140, and will not be repeated here.

[0140] Step 240: Based on the region of interest, stitch together the above multiple X-ray images to obtain a stitched image of the body position.

[0141] In some embodiments, step 240 performs image registration on the X-ray images associated with the overlapping region or candidate stitching region to which the region of interest belongs, based on the region of interest, to obtain a registration result; for example, step 240 identifies anatomical structures within the region of interest, and performs image registration on the associated X-ray images based on the identified anatomical structures to obtain a registration result; identifying anatomical structures within the region of interest can be based on traditional image detection methods, or it can be based on machine learning methods to perform key point detection, target detection, and segmentation, etc.; step 240 then performs image stitching on the associated X-ray images based on the registration structure.

[0142] There are multiple ways to implement step 240, which can be further described in the above description of step 150, and will not be repeated here.

[0143] Step 250: Display the stitched image of the stitched body position.

[0144] Understandably, for any two adjacent X-ray images, step 230 determines the region of interest (ROI) on one of the X-ray images. Therefore, in step 240, any two adjacent X-ray images are stitched together based on their corresponding ROIs. Furthermore, in examples with multiple X-ray images forming multiple pairs of adjacent X-ray images, it is not necessary to determine and stitch each pair of adjacent X-ray images based on the ROI. Instead, a portion of the adjacent X-ray images can be determined and stitched based on the ROI, while the remaining adjacent X-ray images can be stitched together using other stitching techniques, such as directly stitching based on overlapping regions.

[0145] Please refer to Figure 9 Some embodiments provide a method 1000 for stitching X-ray images, including the following steps:

[0146] Step 310: Obtain multiple X-ray images to be stitched together.

[0147] Step 320: Obtain candidate stitching regions from at least one X-ray image.

[0148] The candidate stitching region of an X-ray image includes at least a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching. In some examples, the candidate stitching region of an X-ray image includes a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching, or even a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching; in some examples, the candidate stitching region of an X-ray image includes the entire overlapping region between the X-ray image and its adjacent X-ray images in the stitching, or even the candidate stitching region of an X-ray image is simply the overlapping region between the X-ray image and its adjacent X-ray images in the stitching.

[0149] How to obtain candidate stitching regions from at least one X-ray image in step 320 can be found in the description of step 120 above, and will not be repeated here.

[0150] Step 330: Determine the region of interest from the candidate splicing regions.

[0151] Typically, the region of interest is located within the candidate stitching region and is smaller than the candidate stitching region.

[0152] In some embodiments, step 330 displays the candidate splicing regions and determines the region of interest based on the operator's operations on the candidate splicing regions. For example, step 330 receives the operator's point selection operation, box selection operation, or drawing operation on the candidate splicing regions to determine the region of interest.

[0153] In some embodiments, step 330 identifies at least one anatomical structure within the overlapping area, determines a region of interest based on the identified anatomical structure, for example automatically or manually by the operator, such as step 330 displaying one or more candidate regions of interest containing the anatomical structure for confirmation or selection; receiving confirmation or selection of candidate regions of interest by the operator, and using the confirmed or selected candidate region of interest as the region of interest.

[0154] There are multiple ways to implement step 330, which can be further described in the above description of steps 130 and 140, and will not be repeated here.

[0155] Step 340: Based on the region of interest, stitch together the above multiple X-ray images to obtain a stitched image.

[0156] In some embodiments, step 340 performs image registration on the X-ray images associated with the overlapping region or candidate stitching region to which the region of interest belongs, based on the region of interest, to obtain a registration result; for example, step 340 identifies anatomical structures within the region of interest, and performs image registration on the associated X-ray images based on the identified anatomical structures to obtain a registration result; identifying anatomical structures within the region of interest can be based on traditional image detection methods, or it can be based on machine learning methods to perform key point detection, target detection, and segmentation, etc.; step 340 then performs image stitching on the associated X-ray images based on the registration structure.

[0157] There are multiple ways to implement step 340, which can be further described in the above description of step 150, and will not be repeated here.

[0158] Step 350: Display the stitched image.

[0159] Understandably, for any two adjacent X-ray images, step 320 can obtain at least one candidate stitching region of the X-ray image, and for any two adjacent X-ray images, step 330 determines the region of interest within the candidate stitching region of one X-ray image. Thus, in step 340, any two adjacent X-ray images are stitched based on their corresponding regions of interest. Furthermore, in examples with multiple X-ray images forming multiple pairs of adjacent X-ray images, it is not necessary to determine and stitch each pair of adjacent X-ray images based on the region of interest. Instead, a portion of the adjacent X-ray images can be determined and stitched based on the region of interest, while the other portion can be stitched using other stitching techniques, such as directly stitching based on overlapping areas or even candidate stitching regions.

[0160] Please refer to Figure 10 Some embodiments provide a method 1000 for stitching X-ray images, including the following steps:

[0161] Step 410: Obtain multiple X-ray images to be stitched together.

[0162] Step 420: Determine the region of interest on at least one X-ray image.

[0163] In some embodiments, the region of interest is located within the overlapping area between the X-ray image and its adjacent X-ray images in the stitching, and is smaller than the overlapping area.

[0164] Step 420 involves determining the region of interest on the X-ray image. This can be achieved in various ways, such as as described above in steps 120, 130, and 140, as well as steps 220 and 230, and steps 320 and 330. These details will not be repeated here.

[0165] Step 430: Based on the region of interest, stitch together the above multiple X-ray images to obtain a stitched image.

[0166] In some embodiments, step 430 performs image registration on the X-ray images associated with the overlapping regions or candidate stitching regions to which the region of interest belongs, based on the region of interest, to obtain a registration result; for example, step 430 identifies anatomical structures within the region of interest, and performs image registration on the associated X-ray images based on the identified anatomical structures to obtain a registration result; identifying anatomical structures within the region of interest can be based on traditional image detection methods, or it can be based on machine learning methods to perform key point detection, target detection, and segmentation, etc.; step 430 then performs image stitching on the associated X-ray images based on the registration structure.

[0167] There are multiple ways to implement step 430, which can be further described in the above description of step 150, and will not be repeated here.

[0168] Step 440: Display the stitched image.

[0169] Understandably, for any two adjacent X-ray images, step 420 determines the region of interest (ROI) on one of the X-ray images. Therefore, in step 430, any two adjacent X-ray images are stitched together based on their corresponding ROIs. Furthermore, in examples with multiple X-ray images forming multiple pairs of adjacent X-ray images, it is not necessary to determine and stitch each pair of adjacent X-ray images based on the ROI. Instead, a portion of the adjacent X-ray images can be determined and stitched based on the ROI, while the remaining adjacent X-ray images can be stitched together using other stitching techniques, such as directly stitching based on overlapping regions.

[0170] Please refer to Figure 11 , Figure 12 , Figure 13 or Figure 14 Some embodiments provide an X-ray imaging system 100, which includes an X-ray receiving device 10, a head unit 30, and a processor 50, which are described in detail below.

[0171] In some embodiments, the X-ray receiving device 10 includes a detector 13 for receiving X-rays passing through the subject, such as their position to be photographed. The detector 13 is a core component of the X-ray imaging system 100 and plays a decisive role in image quality. In some examples, the detector 13 receives X-rays and ultimately converts them into electrical signals to acquire X-ray images. For example, the detector 13 first converts the X-rays into visible light, and then converts the visible light into electrical signals; the detector 13 can utilize a scintillation layer made of a scintillation material to convert X-rays into visible light, such as cesium iodide (CsI) or gadolinium oxysulfide (GOS). In some examples, the detector 13 is a flat-panel detector.

[0172] In some embodiments, the X-ray receiving device 10 may further include a first support assembly 11 for supporting the detector 13; in some examples, the detector 13 is movably disposed on the first support assembly 11. In some embodiments, the X-ray receiving device 10 may further include a first drive mechanism 12 for driving the detector 13 to move.

[0173] The detector 13 is movably mounted on the first support assembly 11 to adapt to photographing subjects of different heights or to photograph different areas of the subject. Furthermore, in some examples, the operator can manually apply force to the detector 13 to move it; in some examples, the operator issues commands to the processor 50 via function keys, etc., and the processor 50 receives the commands and controls the first drive mechanism 12 to drive the detector 13 to move. In some examples, the movement includes translation and / or rotation.

[0174] There are several ways to implement the first support component 11, which will be explained in detail below.

[0175] Please refer to Figure 15 In one embodiment, the first support assembly 11 includes a column 15, and a detector 13 is movably disposed on the column 15. The detector 13 is capable of moving on the column 15, for example, moving upward or downward. Generally, this X-ray receiving device 10 can be referred to as a stationary X-ray receiving device 10.

[0176] Please refer to Figure 16 In one embodiment, the first support assembly 11 includes a bed 16 and a support structure 17 disposed below the bed 16. The bed 16 is for a person to lie down, while the support structure 17 supports a detector 13, which is movably disposed on the support structure 17, for example, moving along the long axis of the bed 16. Generally, this X-ray receiving device 10 can be referred to as a horizontal X-ray receiving device 10.

[0177] The X-ray imaging system 100 may include a standing X-ray receiver 10 or a horizontal X-ray receiver 10. The X-ray imaging system 100 may also include a standing X-ray receiver 10 and a horizontal X-ray receiver 10; in addition, in such an example, a detector 13 may be configured for the standing X-ray receiver 10 and a detector 13 may be configured for the horizontal X-ray receiver 10.

[0178] The above are some descriptions of the X-ray receiving device 10.

[0179] Understandably, Figure 15 and Figure 16 The X-ray imaging system 100 shown is a fixed X-ray imaging system 100; in some examples, the X-ray imaging system 100 may also be a mobile X-ray imaging system 100.

[0180] In some embodiments, the head unit 30 includes a head 33 for emitting X-rays. For example, the head 33 generates and emits X-rays under a high-voltage signal. In some examples, the head 33 may include a beam limiter 33a; the beam limiter 33a is used to define the projection area of ​​the X-rays emitted by the head 33, which may be referred to as the irradiation field or irradiation field area. Furthermore, before imaging, the operator generally adjusts the light field or light field area of ​​the head 33. That is, the head 33 emits visible light to simulate X-rays, and the area irradiated by the visible light after being limited by the beam limiter 33a (i.e., the light field) simulates the projection area (i.e., the irradiation field) of X-rays during imaging. This allows the operator to intuitively adjust the size and position of the light field before imaging to achieve the function of adjusting the irradiation field of X-rays during imaging.

[0181] In some embodiments, the head unit 30 may further include a second support component 31 and a second drive mechanism 32. The second support component 31 is used to support the head unit 33. The second support component 31 can be implemented in various ways, such as a suspended structure suspended from a room ceiling as shown in the figure. In some embodiments, the head unit 33 is movably disposed on the second support component 31. In some embodiments, the second drive mechanism 32 is used to drive the head unit 33 to move.

[0182] The camera head 33 is movably mounted on the second support assembly 31 to adapt to photographing subjects of different heights or to photograph different areas of the subject. Furthermore, in some examples, the operator can manually apply force to the camera head 33 to move it; in some examples, the operator issues commands to the processor 50 via function keys, etc., and the processor 50 receives the commands and controls the second drive mechanism 32 to drive the camera head 33 to move. In some examples, the movement includes translation and / or rotation.

[0183] The above are some descriptions of the head assembly 30.

[0184] In some embodiments, the X-ray imaging system 100 also includes a human-computer interaction device 60. Figure 13As an example, the human-machine interface device 60 can detect user input commands or operations, such as commands to adjust the X-ray irradiation area, set the exposure time, set the exposure voltage, set the exposure current, perform exposure, control the movement of the head unit 33, or control the movement of the detector 13. In some embodiments, the human-machine interface device 60 may include one or more of a keyboard, mouse, or function keys. In some embodiments, the human-machine interface device 60 can also display information and content, such as a graphical interface, on which one or more controlled objects are set, providing the user with the opportunity to input operation commands through the human-machine interface device 60 to control these controlled objects, thereby performing corresponding control operations. In some examples, the human-machine interface device 60 may include a touch screen display. In some examples, the human-machine interface device 60 may display the stitching planning interface mentioned above and / or the stitched image obtained. In some examples, the human-machine interface device 60 allows the operator to operate the stitching planning interface to determine the area of ​​interest.

[0185] In some embodiments, the processor 50 may be implemented by a circuit, one or more of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, or a microprocessor; in some embodiments, the processor 50 may execute some or all of the steps of the X-ray image stitching method in the various embodiments of this application, or any combination of the steps.

[0186] For example, the processor 50 acquires multiple X-ray images of the body to be stitched, controls the human-computer interaction device 60 to display at least one X-ray image on the stitching planning interface, receives the operator's operation on the stitching planning interface from the human-computer interaction device 60, determines the region of interest on the at least one X-ray image, stitches the multiple X-ray images based on the region of interest to obtain the stitched image of the body, and controls the human-computer interaction device 60 to display the stitched image of the body.

[0187] In a specific example, the processor 50 can acquire multiple X-ray images of the body to be stitched together, and acquire candidate stitching regions of at least one X-ray image. It controls the human-computer interaction device 60 to display the multiple X-ray images on the stitching planning interface and identify the candidate stitching regions. Based on the operation of the human-computer interaction device 60 on the stitching planning interface received by the operator, the processor 50 determines the region of interest within the candidate stitching regions, stitches the multiple X-ray images based on the region of interest, obtains the stitched image of the body position, and controls the human-computer interaction device 60 to display the stitched image of the body position.

[0188] For example, the processor 50 acquires multiple X-ray images to be stitched together, determines the region of interest on at least one X-ray image, stitches the multiple X-ray images together based on the region of interest to obtain a stitched image, and controls the human-computer interaction device 60 to display the stitched image.

[0189] In a specific example, the processor 50 can acquire multiple X-ray images to be stitched together, acquire candidate stitching regions of at least one X-ray image, determine the region of interest from the candidate stitching regions, stitch the multiple X-ray images based on the region of interest to obtain a stitched image, and control the human-computer interaction device 60 to display the stitched image.

[0190] The region of interest in this article can include the anatomical structures / tissues of interest to the operator and is smaller than the overlapping area.

[0191] Please refer to Figure 17Some embodiments also disclose a stitching apparatus 99 for X-ray images, which includes a memory 97 and a processor 98, as described in detail below. In some embodiments, the memory 97 is used to store programs and / or data. In some embodiments, the memory 97 may be a tangible and non-transitory computer-readable medium, such as a flash memory card, solid-state memory, hard disk, etc. In some embodiments, the processor 98 is used to execute the programs stored in the memory 97, thereby performing corresponding steps and methods. For example, processor 98 can be implemented by software, hardware, firmware, or a combination thereof, and can be at least one of the following: circuit, single or multiple application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), central processing units (CPUs), controllers, microcontrollers, and microprocessors, thereby enabling processor 98 to execute some or all of the steps or any combination of the steps of the X-ray image stitching method in the various embodiments of this application.

[0192] For example, the processor 98 acquires multiple X-ray images of the body to be stitched, controls the display of at least one X-ray image on the stitching planning interface, receives the operator's operation on the stitching planning interface, the processor 98 determines the region of interest on the at least one X-ray image, the processor 98 stitches multiple X-ray images based on the region of interest to obtain the stitched image of the body, and controls the display of the stitched image of the body.

[0193] In a specific example, the processor 98 can acquire multiple X-ray images of the body to be stitched, and acquire at least one candidate stitching region of the X-ray image. It controls the display of the multiple X-ray images on the stitching planning interface and identifies the candidate stitching region. Upon receiving the operator's operation on the stitching planning interface, the processor 98 determines the region of interest within the candidate stitching region, stitches the multiple X-ray images based on the region of interest, obtains the stitched image of the body position, and controls the display of the stitched image of the body position.

[0194] For example, processor 98 acquires multiple X-ray images to be stitched together, determines the region of interest on at least one X-ray image, stitches the multiple X-ray images together based on the region of interest to obtain a stitched image, and controls the display of the stitched image.

[0195] In a specific example, the processor 98 can acquire multiple X-ray images to be stitched together, acquire candidate stitching regions of at least one X-ray image, determine the region of interest from the candidate stitching regions, stitch the multiple X-ray images together based on the region of interest to obtain a stitched image, and control the display of the stitched image.

[0196] In some embodiments, the stitching device 99 for X-ray images can be a device such as a computer or a mobile phone.

[0197] This document describes various exemplary embodiments with reference to them. However, those skilled in the art will recognize that changes and modifications can be made to the exemplary embodiments without departing from the scope of this document. For example, various operational steps and components for performing operational steps can be implemented in different ways depending on the specific application or considering any number of cost functions associated with the operation of the system (e.g., one or more steps can be deleted, modified, or combined with other steps).

[0198] In the above embodiments, implementation can be achieved, in whole or in part, by software, hardware, firmware, or any combination thereof. Furthermore, as those skilled in the art will understand, the principles herein can be reflected in a computer program product on a computer-readable storage medium pre-loaded with computer-readable program code. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray discs, etc.), flash memory, and / or the like. These computer program instructions may be loaded onto a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to form a machine, such that instructions executing on the computer or other programmable data processing apparatus can generate means for implementing a specified function. These computer program instructions may also be stored in a computer-readable storage medium that can instruct the computer or other programmable data processing apparatus to operate in a particular manner, such that instructions stored in the computer-readable storage medium can form an article of manufacture including means for implementing the specified function. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to perform a series of operational steps on the computer or other programmable apparatus to produce a computer-implemented process, such that instructions executing on the computer or other programmable apparatus can provide steps for implementing the specified function.

[0199] While the principles herein have been illustrated in various embodiments, numerous modifications to the structure, arrangement, proportions, elements, materials, and components, particularly suited to specific environmental and operational requirements, may be used without departing from the principles and scope of this disclosure. These modifications and other alterations or alterations will be included within the scope of this document.

[0200] The foregoing specific descriptions have been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of this disclosure. Therefore, considerations for this disclosure are to be illustrative rather than restrictive, and all such modifications are to be included within its scope. Similarly, advantages, other advantages, and solutions to problems with respect to various embodiments have been described above. However, benefits, advantages, solutions to problems, and any elements that produce these, or make them more explicit, should not be construed as critical, essential, or necessary. The term “comprising” and any other variations thereof as used herein are non-exclusive inclusion, meaning that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed or not part of the process, method, system, article, or apparatus. Furthermore, the term “coupled” and any other variations thereof as used herein refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections, and / or any other connections.

[0201] Those skilled in the art will recognize that many changes can be made to the details of the above embodiments without departing from the basic principles of the invention. Therefore, the scope of the invention should be determined only by the claims.

Claims

1. A method for stitching X-ray images, characterized in that, include: Acquire multiple X-ray images of the body to be stitched together in the desired position; Obtain candidate stitching regions of at least one of the X-ray images, wherein the candidate stitching regions of the X-ray images include at least a portion of the overlapping regions between the X-ray image and its adjacent X-ray images in the stitching; Multiple X-ray images are displayed on the stitching planning interface, and the candidate stitching areas are identified. Receive operator input on the splicing planning interface and determine the region of interest within the candidate splicing area; Multiple X-ray images are stitched together based on the region of interest to obtain a stitched image of the stitched body position; The stitched image shows the stitched body position.

2. The splicing method as described in claim 1, characterized in that, The display of multiple X-ray images on the stitching planning interface includes: The multiple X-ray images are displayed on the stitching planning interface based on their adjacent positions in the stitching process; or... Based on the positional distribution of the multiple X-ray images in the stitching position, the multiple X-ray images are displayed on the stitching planning interface.

3. The splicing method as described in claim 1 or 2, characterized in that, The identification of the candidate splicing area includes: identifying the candidate splicing area by means of the area defined by lines.

4. The splicing method as described in claim 1, characterized in that, The operation of the receiving operator on the stitching planning interface, including determining the region of interest within the candidate stitching area, includes: The operator selects points within the candidate splicing area on the splicing planning interface and identifies at least one point of interest within the candidate splicing area. Within the candidate splicing area, a region containing the point of interest is determined as the region of interest.

5. The splicing method as described in claim 1, characterized in that, The operation of the receiving operator on the stitching planning interface, including determining the region of interest within the candidate stitching area, includes: The system receives a selection operation from the user on the stitching planning interface within the candidate stitching area, and determines the selected area as the region of interest based on the selection operation; or... The system receives the drawing operations performed by the operator on the candidate splicing area on the splicing planning interface, and determines the drawing area based on the drawing operations as the region of interest.

6. The splicing method as described in claim 1, characterized in that, The operation of the receiving operator on the stitching planning interface, including determining the region of interest within the candidate stitching area, includes: Anatomical structure information is identified and displayed within the candidate splicing area, and the anatomical structure information includes structural feature points or feature regions. The operator confirms the anatomical structure information by receiving confirmation from the operator; the confirmation of the anatomical structure information by receiving confirmation from the operator includes: determining a region of a preset size that contains the structural feature points within the candidate splicing area as the region of interest; or, using the feature region as the region of interest.

7. The splicing method according to any one of claims 1 to 6, characterized in that, The step of stitching together multiple X-ray images based on the region of interest to obtain a stitched image of the body position includes: Anatomical structures are identified within the region of interest, and image registration is performed on the associated X-ray images based on the identified anatomical structures to obtain the registration results. The associated X-ray images are stitched together based on the registration structure.

8. A method for stitching X-ray images, characterized in that, include: Acquire multiple X-ray images of the body to be stitched together in the desired position; At least one of the X-ray images is displayed on the stitching planning interface; The operator receives the operation of the stitching planning interface and determines the region of interest on at least one of the X-ray images; Multiple X-ray images are stitched together based on the region of interest to obtain a stitched image of the stitched body position; The stitched image shows the stitched body position.

9. The splicing method as described in claim 8, characterized in that, The operation of the receiving operator on the stitching planning interface to determine the region of interest on at least one of the X-ray images includes: the receiving operator's point selection operation, box selection operation, or drawing operation on the stitching planning interface to determine the region of interest.

10. The splicing method as described in claim 8, characterized in that, The operator's operation on the stitching planning interface, determining the region of interest on at least one of the X-ray images, includes: One or more anatomical structures are identified from at least one of the X-ray images displayed on the stitching planning interface to obtain the identification results; The system receives confirmation or selection operations from the operator for the identified anatomical structures and designates the confirmed or selected anatomical structures as the region of interest.

11. A method for stitching X-ray images, characterized in that, include: Acquire multiple X-ray images to be stitched together; Obtain at least one candidate stitching region of the X-ray image, wherein the candidate stitching region of the X-ray image is at least a portion of the overlapping region between the X-ray image and its adjacent X-ray images in the stitching; Determine the region of interest from the candidate splicing regions; A stitched image is obtained by stitching together multiple X-ray images based on the region of interest. The stitched image is displayed.

12. The splicing method as described in claim 11, characterized in that, Determining the region of interest from the candidate splicing areas includes: displaying the candidate splicing areas; and determining the region of interest based on the operator's operation on the candidate splicing areas.

13. The splicing method as described in claim 12, characterized in that, The step of determining the region of interest based on the operator's operation on the candidate splicing region includes: receiving the operator's point selection operation, box selection operation, or drawing operation on the candidate splicing region to determine the region of interest.

14. The splicing method as described in claim 11, characterized in that, Determining the region of interest from the candidate splicing region includes: identifying at least one anatomical structure within the overlapping region, and determining the region of interest based on the identified anatomical structure.

15. The splicing method as described in claim 14, characterized in that, The process of determining the region of interest based on the identified anatomical structure includes: displaying one or more candidate regions of interest containing the anatomical structure for confirmation or selection; receiving confirmation or selection operations from the operator for the candidate regions of interest; and using the confirmed or selected candidate regions of interest as the region of interest.

16. A method for stitching X-ray images, characterized in that, include: Acquire multiple X-ray images to be stitched together; A region of interest is determined on at least one of the X-ray images, the region of interest being located within the overlapping area between the X-ray image and an adjacent X-ray image in the stitching and being smaller than the overlapping area; A stitched image is obtained by stitching together multiple X-ray images based on the region of interest. The stitched image is displayed.

17. A stitching device for X-ray images, characterized in that, include: Memory, used to store programs; A processor for implementing the method as described in any one of claims 1 to 16 by executing a program stored in the memory.

18. An X-ray imaging system, characterized in that, include: A head unit, the head unit comprising a head unit for emitting X-rays toward a subject being examined; An X-ray receiving device, the X-ray receiving device including a detector, the detector being used to receive X-rays that pass through the subject being examined; A processor for performing the method as described in any one of claims 1 to 16.

Images