X-ray image processing method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to the field of image processing, and provides an X-ray image processing method and device, an electronic device and a storage medium. The method comprises: using an X-ray imaging system to perform multiple exposures on at least one body part of a target object to obtain a plurality of first X-ray sub-images; and performing image post-processing on the plurality of first X-ray sub-images to obtain a medical image, wherein the image post-processing comprises processing the plurality of first X-ray sub-images using a virtual grid and performing image stitching, or comprises performing image stitching on the plurality of first X-ray sub-images and processing the stitched image using a virtual grid, and the virtual grid is used to filter out noise caused by scattered rays in the image. The method can save the equipment cost caused by the physical grid, thereby reducing the equipment cost, labor cost and time cost of obtaining the medical image.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and more particularly to an X-ray image processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] X-ray imaging, also known as X-ray film, is a technique that uses the penetrating power of X-rays to image the internal structure of the human body or object. X-ray imaging has wide applications in the medical field. Doctors can use X-ray images to observe structural information within a patient's body, such as lesions in the bones, lungs, and abdomen, thereby diagnosing diseases such as fractures, pneumonia, and tumors. Furthermore, X-ray imaging can be used to screen for potential health problems, such as osteoporosis and tuberculosis.

[0003] When X-rays irradiate the human body, they scatter, producing scattered rays. If left untreated, this scattering introduces noise into the X-ray image, degrading its quality, such as reduced resolution and contrast. Current technology typically uses a physical grid on X-ray imaging equipment to filter out scattered rays. However, the degree of X-ray scattering is related to the thickness of the body part being irradiated, and the effectiveness of the grid depends on its parameters, such as thickness and spacing. Therefore, before exposure, the grid parameters need to be adjusted based on the thickness of the body part to be examined, and sometimes the grid needs to be removed, making the X-ray image acquisition process more complex. In image stitching scenarios requiring multiple X-ray images, repeated grid adjustments or even disassembly and reassembly may be necessary, leading to higher equipment, labor, and time costs for X-ray image acquisition. Furthermore, post-processing of the acquired X-ray images to obtain medical images further increases the equipment, labor, and time costs associated with acquiring medical images. Summary of the Invention

[0004] In view of this, the present disclosure proposes an X-ray image processing method, apparatus, electronic device and storage medium. The method uses a virtual grid to process the image, achieving a function similar to that of a physical grid, which can save the equipment cost of a physical grid, thereby reducing the equipment cost, labor cost and time cost of acquiring medical images.

[0005] According to one aspect of this disclosure, an X-ray image processing method is provided, the method comprising: performing multiple exposures on at least one body part of a target object using an X-ray imaging system to obtain a plurality of first X-ray sub-images; performing image post-processing on the plurality of first X-ray sub-images to obtain a medical image, wherein the image post-processing includes processing the plurality of first X-ray sub-images separately using a virtual grid and performing image stitching, or includes stitching the plurality of first X-ray sub-images and processing the stitched image using a virtual grid, the virtual grid being used to filter out noise caused by scattered rays in the image.

[0006] In one possible implementation, using a virtual grid includes processing the first X-ray sub-image or the stitched image based on a scatter image, wherein the scatter image is obtained by performing a Fourier transform filter on the first X-ray sub-image or the stitched image.

[0007] In one possible implementation, using a virtual grid further includes adjusting the contrast of the image processed by the virtual grid based on adjustment parameters.

[0008] In one possible implementation, the image post-processing further includes: adjusting the exposure and downsampling each first X-ray sub-image to obtain a corresponding second X-ray sub-image, and then processing the multiple second X-ray sub-images separately using a virtual grid and stitching the images together, or stitching the multiple second X-ray sub-images together and processing the stitched image using a virtual grid.

[0009] In one possible implementation, the image post-processing further includes: performing image enhancement processing on the stitched image and each second X-ray sub-image respectively to obtain the medical image.

[0010] In one possible implementation, the image enhancement processing includes at least one of vertical equalization, multi-resolution enhancement, tissue equalization, inverse gamma distribution transformation, window adjustment, and lookup table mapping.

[0011] In one possible implementation, after stitching the plurality of first X-ray sub-images and processing the stitched image using a virtual grid, the image post-processing further includes denoising the plurality of first X-ray sub-images based on a scatter image, wherein the scatter image is obtained by performing Fourier transform filtering on the stitched image.

[0012] In one possible implementation, the denoising process includes: removing noise caused by scattered lines from the second X-ray sub-image based on the relationship between any second X-ray sub-image and a first region in the stitched image corresponding to the second X-ray sub-image, and a second region in the scatter image corresponding to the second X-ray sub-image, wherein the second X-ray sub-image is obtained by adjusting the exposure and downsampling the first X-ray sub-image.

[0013] According to another aspect of this disclosure, an X-ray image processing apparatus is provided, the apparatus comprising: a first acquisition module for performing multiple exposures on at least one body part of a target object using an X-ray imaging system to acquire a plurality of first X-ray sub-images; and a second acquisition module for performing image post-processing on the plurality of first X-ray sub-images to obtain a medical image, wherein the image post-processing includes processing the plurality of first X-ray sub-images separately using a virtual grid and performing image stitching, or includes stitching the plurality of first X-ray sub-images and processing the stitched image using a virtual grid, the virtual grid being used to filter out noise caused by scattered rays in the image.

[0014] In one possible implementation, using a virtual grid includes processing the first X-ray sub-image or the stitched image based on a scatter image, wherein the scatter image is obtained by performing a Fourier transform filter on the first X-ray sub-image or the stitched image.

[0015] In one possible implementation, using a virtual grid further includes adjusting the contrast of the image processed by the virtual grid based on adjustment parameters.

[0016] In one possible implementation, the image post-processing further includes: adjusting the exposure and downsampling each first X-ray sub-image to obtain a corresponding second X-ray sub-image, and then processing the multiple second X-ray sub-images separately using a virtual grid and stitching the images together, or stitching the multiple second X-ray sub-images together and processing the stitched image using a virtual grid.

[0017] In one possible implementation, the image post-processing further includes: performing image enhancement processing on the stitched image and each second X-ray sub-image respectively to obtain the medical image.

[0018] In one possible implementation, the image enhancement processing includes at least one of vertical equalization, multi-resolution enhancement, tissue equalization, inverse gamma distribution transformation, window adjustment, and lookup table mapping.

[0019] In one possible implementation, after stitching the plurality of first X-ray sub-images and processing the stitched image using a virtual grid, the image post-processing further includes denoising the plurality of first X-ray sub-images based on a scatter image, wherein the scatter image is obtained by performing Fourier transform filtering on the stitched image.

[0020] In one possible implementation, the denoising process includes: removing noise caused by scattered lines from the second X-ray sub-image based on the relationship between any second X-ray sub-image and a first region in the stitched image corresponding to the second X-ray sub-image, and a second region in the scatter image corresponding to the second X-ray sub-image, wherein the second X-ray sub-image is obtained by adjusting the exposure and downsampling the first X-ray sub-image.

[0021] According to another aspect of this disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above-described method when executing instructions stored in the memory.

[0022] According to another aspect of this disclosure, a non-volatile computer-readable storage medium is provided that stores computer program instructions thereon, wherein the computer program instructions, when executed by a processor, implement the above-described method.

[0023] According to another aspect of this disclosure, a computer program product is provided, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs the above-described method.

[0024] According to the X-ray image processing method of this disclosure, multiple first X-ray sub-images can be acquired by repeatedly exposing at least one body part of a target object using an X-ray imaging system. A medical image is obtained by post-processing the multiple first X-ray sub-images. The post-processing includes processing the multiple first X-ray sub-images separately using a virtual grid and then stitching them together, or stitching the multiple first X-ray sub-images together and processing the stitched image using a virtual grid. The virtual grid is used to filter out noise caused by scattered rays in the image; therefore, the medical image can be an image with noise removed due to scattered rays. The virtual grid achieves a function similar to a physical grid, eliminating the need for a physical grid and saving equipment costs associated with physical grids. It also eliminates the need for manual adjustment of the virtual grid, avoiding image quality degradation due to improper grid use. Since the virtual grid is used during post-processing, multiple first X-ray images can be acquired continuously, greatly accelerating the acquisition of multiple first X-ray images and saving labor and time costs. In summary, the X-ray image processing method of this disclosure can save the equipment cost caused by physical filter grids, thereby reducing the equipment cost, labor cost and time cost of acquiring medical images.

[0025] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0026] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0027] Figure 1 Exemplary application scenarios of the X-ray image processing method according to embodiments of the present disclosure are shown.

[0028] Figure 2 A schematic diagram illustrating the flow of an X-ray image processing method according to an embodiment of the present disclosure is shown.

[0029] Figure 3 Examples of multiple first X-ray sub-images according to embodiments of the present disclosure are shown.

[0030] Figure 4 Examples of medical images obtained according to embodiments of this disclosure are shown.

[0031] Figure 5 A schematic diagram illustrating an implementation of noise reduction processing according to an embodiment of the present disclosure is shown.

[0032] Figure 6 An example of the steps included in image post-processing according to an embodiment of the present disclosure is shown.

[0033] Figure 7 Another example of the steps included in image post-processing according to embodiments of the present disclosure is shown.

[0034] Figure 8 An example of a medical image processed by an X-ray image processing method according to an embodiment of the present disclosure is shown.

[0035] Figure 9 A schematic diagram showing the structure of the region of interest according to an embodiment of the present disclosure.

[0036] Figure 10 A schematic diagram showing the structure of an X-ray image processing apparatus according to an embodiment of the present disclosure is provided.

[0037] Figure 11 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0038] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0039] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0040] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0041] Figure 1 Exemplary application scenarios of the X-ray image processing method according to embodiments of the present disclosure are shown.

[0042] like Figure 1 As shown, the X-ray image processing method of this disclosure embodiment can be applied to a first device, which can be an X-ray imaging device, on which an X-ray imaging system (not shown) can be provided.

[0043] The first device did not have a physical filter grid installed.

[0044] The first device can execute the X-ray image processing method of this disclosure embodiment, using an X-ray imaging system to perform multiple exposures on at least one body part of a target object to obtain multiple X-ray images (the first X-ray sub-images described below), and then perform image post-processing on the multiple X-ray images to obtain a medical image. The first device can display the medical image to a radiologist or output it to a terminal device (not shown) used by a radiologist, where the terminal device displays the medical image. The radiologist can analyze the health condition of the target object based on the medical image.

[0045] Those skilled in the art should understand that the first device can also output multiple X-ray images to a second device (not shown). The second device can be a terminal device or a server. The second device performs image post-processing on the multiple X-ray images to obtain medical images. This disclosure does not limit whether the acquisition of X-ray images and the post-processing of X-ray images must be performed by the same device.

[0046] Those skilled in the art should understand that post-processing of X-ray images can also be performed jointly by the first device and the second device. This disclosure does not limit which steps of image post-processing are performed by the first device and the second device respectively.

[0047] Figure 2 A schematic diagram illustrating the flow of an X-ray image processing method according to an embodiment of the present disclosure is shown.

[0048] like Figure 2 As shown, in one possible implementation, the method includes:

[0049] Step S21: At least one body part of the target object is exposed multiple times using an X-ray imaging system to obtain multiple first X-ray sub-images;

[0050] Step S22: Perform image post-processing on multiple first X-ray sub-images to obtain a medical image. The image post-processing includes processing the multiple first X-ray sub-images separately using a virtual grid and then stitching the images together, or stitching the multiple first X-ray sub-images together and processing the stitched image using a virtual grid. The virtual grid is used to filter out noise caused by scattered rays in the image.

[0051] For example, first, based on the target's examination needs, determine which body parts of the target person should be exposed. For instance, if the target person wants their right leg examined, the body parts to be exposed could include the right hip, thigh, knee, calf, ankle, and foot. Or, if the target person wants their right ankle examined, only the right ankle needs to be exposed; no other body parts need to be exposed.

[0052] Step S21 can be executed by using an X-ray imaging system to perform multiple exposures on at least one body part of the target object to obtain multiple first X-ray sub-images. When exposing multiple body parts of the target object, each part can be exposed once or multiple times. When exposing one body part of the target object, that body part can be exposed multiple times. Each exposure yields one first X-ray sub-image, therefore multiple first X-ray sub-images can be obtained after multiple exposures.

[0053] Figure 3 Examples of multiple first X-ray sub-images according to embodiments of the present disclosure are shown.

[0054] like Figure 3 As shown, the number of exposures and the range of each exposure can be preset. For example, the number of exposures and the range of each exposure can be determined based on the size of the detector and the body part to be exposed (i.e., the exposure area). Specifically, the starting and ending positions of the exposure area can be set based on the optical images acquired by the camera. The ranges of two adjacent exposures may include a preset overlap.

[0055] Specifically, for example, the first exposure can be of the right ankle and foot, resulting in image img11; the second exposure can be of the right knee and calf, resulting in image img12; the third exposure can be of the right thigh, resulting in image img13; and the fourth exposure can be of the right hip, resulting in image img14.

[0056] When exposing certain body parts, a portion of a nearby body part (i.e., a pre-defined overlapping portion) may also appear in the first X-ray sub-image obtained. For example, image img11 is obtained by exposing the ankle and foot, but also includes a portion of the lower leg.

[0057] according to Figure 3 As can be seen, images img11-img14 already include all body parts of the target object's right leg, so the exposure can be stopped after obtaining image img14.

[0058] Those skilled in the art will understand that as long as the acquired multiple first X-ray sub-images can include all body parts of the target object that need to be examined, the embodiments of this disclosure do not limit the specific number of exposures or which body parts are targeted in each exposure.

[0059] Next, step S22 can be executed to perform image post-processing on multiple first X-ray sub-images to obtain a medical image. Since no physical grid was used when acquiring the first X-ray sub-images, the image post-processing can include processing the image using a virtual grid. The virtual grid can simulate the function of a physical grid through an algorithm to filter out noise caused by scattered rays in the image. Therefore, the effect of the medical image finally obtained after using a virtual grid during image post-processing is similar to the effect of the medical image obtained in the prior art by using a physical grid when exposing the image and performing image post-processing without using a virtual grid.

[0060] To improve image display, multiple first X-ray sub-images can be stitched together during image post-processing, so that the stitched image can include all exposed body parts. Image processing can be performed on each of the multiple first X-ray sub-images separately before stitching, or image processing can be performed on the image obtained by stitching the multiple first X-ray sub-images together using a virtual grid. This embodiment does not restrict the order of image stitching and image processing using a virtual grid during image post-processing, as long as the final medical image includes both the stitched image and the image obtained using the virtual grid.

[0061] Figure 4 Examples of medical images obtained according to embodiments of this disclosure are shown.

[0062] like Figure 4 As shown, image img10 can be a medical image obtained by post-processing images img11-img14. It can be seen that image img10 already includes all body parts of the target object's right leg. And according to... Figure 4 As can be seen, the image img10 does not have any ghosting or blurring, and the contrast is also high, which can meet the needs of health assessment.

[0063] According to the X-ray image processing method of this disclosure, multiple first X-ray sub-images can be acquired by repeatedly exposing at least one body part of a target object using an X-ray imaging system. A medical image is obtained by post-processing the multiple first X-ray sub-images. The post-processing includes processing the multiple first X-ray sub-images separately using a virtual grid and then stitching them together, or stitching the multiple first X-ray sub-images together and processing the stitched image using a virtual grid. The virtual grid is used to filter out noise caused by scattered rays in the image; therefore, the medical image can be an image with noise removed due to scattered rays. The virtual grid achieves a function similar to a physical grid, eliminating the need for a physical grid and saving equipment costs associated with physical grids. It also eliminates the need for manual adjustment of the virtual grid, avoiding image quality degradation due to improper grid use. Since the virtual grid is used during post-processing, multiple first X-ray images can be acquired continuously, greatly accelerating the acquisition of multiple first X-ray images and saving labor and time costs. In summary, the X-ray image processing method of this disclosure can save the equipment cost caused by physical filter grids, thereby reducing the equipment cost, labor cost and time cost of acquiring medical images.

[0064] Compared to using physical grids, medical images acquired using virtual grids in tilt and out-of-focus exposure scenarios are of better quality, and potential residual artifacts and ringing artifacts are avoided, which can further improve image quality.

[0065] The following section provides an example of the steps involved in image processing using a virtual grid.

[0066] In one possible implementation, using a virtual grid includes processing a first X-ray sub-image or a stitched image based on a scatter image, wherein the scatter image is obtained by performing a Fourier transform filter on the first X-ray sub-image or the stitched image.

[0067] For example, processing the first X-ray sub-image using a virtual grid could involve performing a Fast Fourier Transform (FFT) filter on the first X-ray sub-image to obtain a scatter image, and then subtracting the scatter image from the first X-ray sub-image to remove noise from the first X-ray sub-image. In this case, the scatter image may include noise caused by scattered rays in the first X-ray sub-image.

[0068] Similarly, processing the stitched image using a virtual grid can involve performing a Fast Fourier Transform (FFT) filter on the stitched image to obtain a scatter image, and then subtracting the scatter image from the stitched image, thereby removing noise from the stitched image. In this case, the scatter image may include noise caused by scattering lines in the stitched image.

[0069] In this way, noise caused by scattered rays can be filtered out.

[0070] In one possible implementation, using a virtual grid further includes adjusting the contrast of the image processed by the virtual grid based on adjustment parameters.

[0071] For example, adjustment parameters can be used to adjust the contrast of an image. These parameters are related to the grid ratio and grid density of the physical grid when acquiring images including the same body parts using a physical grid. Multiple levels can be set for the adjustment parameters; the higher the level, the greater the contrast change caused by the adjustment. For example, selection or adjustment buttons for the adjustment parameters can be provided in a graphical user interface, allowing users to select or adjust them as needed. In one example, three levels can be preset: high, medium, and low. This disclosure does not limit the number of adjustment parameter levels or the degree of contrast change corresponding to each level.

[0072] In scenarios where a virtual grid is used to process the first X-ray sub-image, the image obtained after processing with the virtual grid can be the result of subtracting the first X-ray sub-image from the scatter image. Adjustment parameters can be used to adjust the contrast of this image. Since the body parts included in this image are the same as those included in the first X-ray sub-image, the corresponding setting for each first X-ray sub-image can be determined based on the body parts included in each first X-ray sub-image. Then, the adjustment parameters used for the virtual grid can be determined based on the settings corresponding to multiple first X-ray sub-images. When processing each first X-ray sub-image separately using the virtual grid, the adjustment parameters used for the virtual grid can be the same.

[0073] For example, the level corresponding to each first X-ray sub-image can be determined first. If the number of first X-ray sub-images corresponding to the high level is the largest, then the adjustment parameter used for the virtual grid can be determined to be high level. This disclosure does not limit the specific implementation method for determining the adjustment parameter used for the virtual grid based on multiple first X-ray sub-images, as long as the determined adjustment parameter can improve the quality of some of the first X-ray sub-images. After subtracting the first X-ray sub-image from the scatter image, the contrast of the image is then adjusted using the adjustment parameter.

[0074] Similarly, in scenarios where a virtual grid is used to process the stitched image, the resulting image can be the image obtained by subtracting the stitched image from the scatter image. Adjustment parameters can be used to adjust the contrast of this image. Since the body parts included in this image are the same as those included in the stitched image, the adjustment parameters used for the virtual grid can be determined based on the body parts included in the stitched image. Exemplary methods for determining the adjustment parameters have been described above and will not be repeated here.

[0075] This method can improve the contrast of an image processed by a virtual grid.

[0076] Those skilled in the art will understand that image processing using a virtual grid can include more or fewer steps, as long as noise caused by scattering lines can be removed. The embodiments of this disclosure do not limit the specific steps included in image processing using a virtual grid.

[0077] It is understandable that image post-processing can include more steps than image stitching and image processing using virtual grids.

[0078] In one possible implementation, image post-processing further includes:

[0079] Each first X-ray sub-image is subjected to exposure adjustment and downsampling to obtain a corresponding second X-ray sub-image. Then, multiple second X-ray sub-images are processed separately using a virtual grid and then stitched together. Alternatively, multiple second X-ray sub-images are stitched together and the stitched image is processed using a virtual grid.

[0080] For example, before processing the first X-ray sub-image using a virtual grid, the first X-ray sub-image can be subjected to milliampere seconds scaling and downsampling to obtain the corresponding second X-ray sub-image.

[0081] Exposure adjustment is primarily achieved by adjusting the milliampere seconds (mAs) value of the image. mAs represents the product of current and time in the X-ray tube and is a crucial parameter for X-ray exposure. mAs determines the number of X-rays, i.e., the total amount of X-ray photons that penetrate the object being imaged. A higher mAs value produces more X-ray photons, thus increasing image brightness; conversely, a lower mAs value reduces image brightness. In image post-processing, adjusting the mAs value (i.e., mAs scaling) can alter image brightness, thereby improving image quality, balancing image contrast and brightness, and optimizing evaluation results. Downsampling reduces the amount of image data, lowering the cost of subsequent image processing steps.

[0082] The method for adjusting exposure and downsampling can be determined based on the application scenario requirements. Both exposure adjustment and downsampling can be implemented based on existing technologies, and the details of exposure adjustment and downsampling will not be elaborated here.

[0083] In this way, the noise removal effect of the virtual grid can be improved and the data processing cost of image processing using the virtual grid can be reduced.

[0084] In this case, a virtual grid can be used to process multiple second X-ray sub-images separately and then stitch them together. The specific implementation method is the same as that for processing multiple first X-ray sub-images separately and then stitching them together using a virtual grid, and will not be repeated here. Alternatively, multiple second X-ray sub-images can be stitched together and the stitched image can be processed using a virtual grid. The specific implementation method is the same as that for stitching multiple first X-ray sub-images and processing the stitched image using a virtual grid, and will not be repeated here.

[0085] It is understood that the first X-ray sub-image can also be processed directly using a virtual grid, or the exposure can be adjusted before processing the first X-ray sub-image using a virtual grid, and downsampling can be performed after processing the first X-ray sub-image using a virtual grid. This embodiment of the present disclosure does not limit whether exposure adjustment and downsampling are necessary before processing the first X-ray sub-image using a virtual grid.

[0086] In one possible implementation, after stitching together multiple first X-ray sub-images and processing the stitched image using a virtual grid, the image post-processing further includes denoising the multiple first X-ray sub-images based on a scatter image, wherein the scatter image is obtained by performing Fourier transform filtering on the stitched image.

[0087] For example, as mentioned above, when processing the stitched image using a virtual grid, a scatter image is obtained, which includes noise caused by scattered rays in the stitched image. It is understood that noise caused by scattered rays also exists in the X-ray sub-images (including the first X-ray sub-image and the second X-ray sub-image obtained after exposure adjustment and / or downsampling). To improve the accuracy of health assessments based on medical images, after stitching the first X-ray sub-image and processing the stitched image using a virtual grid, denoising can be performed on multiple X-ray sub-images separately based on the scatter image. The purpose of denoising is to remove noise caused by scattered rays. The denoised X-ray sub-images and the stitched image after image enhancement are stored together in a memory, which can be the memory within the imaging system, a cloud storage, or a Picture Archiving and Communication System (PACS). If certain body parts are still blurry after image enhancement of the stitched image, the denoised X-ray sub-images can be viewed to improve the accuracy of health status analysis.

[0088] The following describes an exemplary implementation of noise reduction processing.

[0089] In one possible implementation, the noise reduction process includes:

[0090] Based on the relationship between any second X-ray sub-image and the first region corresponding to the second X-ray sub-image in the stitched image, and the second region corresponding to the second X-ray sub-image in the scatter image, noise caused by scattered lines in the second X-ray sub-image is removed. The second X-ray sub-image is obtained by adjusting the exposure and downsampling the first X-ray sub-image.

[0091] Specifically, similar to removing noise from a stitched image, to remove noise from an X-ray sub-image, subtracting the X-ray sub-image from its corresponding scatter plot sub-image yields the corresponding high-quality X-ray sub-image. Since the scatter plot is obtained from the stitched image, to obtain the scatter plot sub-image for each region, the ratio between the scatter plot sub-image and the scatter plot for each region needs to be determined. Therefore, the relationship between the scatter plot sub-image and the scatter plot for each region can be obtained through the ratio between each X-ray sub-image and the stitched image, thus obtaining the scatter plot for each region. In some embodiments, the ratio between each X-ray sub-image and the stitched image can be obtained from the binary image corresponding to the stitched image.

[0092] Figure 5 A schematic diagram illustrating an implementation of noise reduction processing according to an embodiment of the present disclosure is shown.

[0093] like Figure 5 As shown, assume that the multiple first X-ray sub-images are img1-img3. The image obtained by stitching together the multiple first X-ray sub-images can be stitched_img. The scatter plot can be stitched_ScatterMap.

[0094] Each first X-ray sub-image undergoes exposure adjustment and downsampling to obtain a second X-ray sub-image. For each second X-ray sub-image, a first region corresponding to that second X-ray sub-image in the stitched image and a second region corresponding to that second X-ray sub-image in the scatter image can be extracted. The second X-ray sub-image and its corresponding first and second regions can have the same size and include the same body parts.

[0095] Figure 5 Taking the first X-ray sub-image img2 as an example, the second X-ray sub-image img22 can be obtained after adjusting the exposure and downsampling of image img2. Furthermore, when stitching multiple second X-ray sub-images, only a portion of the second X-ray sub-image img22 may be retained in the stitched image. In this case, the size of image img22 can be adjusted to match the size of the portion of the stitched image that belongs to the second X-ray sub-image img22.

[0096] The stitched image contains a first region, `stitchedImg_sub2`, corresponding to image `img22`. Based on image `img22` and the first region `stitchedImg_sub2`, the correlation between the pixel values ​​of image `img22` and the pixel values ​​of the first region `stitchedImg_sub2` can be determined. The scatter plot also contains a second region, `stitchedScatterMap_sub2`, corresponding to image `img22`. Given the known correlation between the pixel values ​​of image `img22` and the pixel values ​​of the first region `stitchedImg_sub2`, an image `ScatterMap_sub2` can be obtained such that image `ScatterMap_sub2` has the same correlation with the second region `stitchedScatterMap_sub2`.

[0097] In this case, noise caused by scattering lines in image img22 can be removed using image ScatterMap_sub2. For example, the pixel value of each pixel in image img22 can be subtracted from the pixel value of the corresponding pixel in image ScatterMap_sub2.

[0098] In this way, when the virtual grid is applied to the stitched image, noise caused by scattered lines in each second X-ray sub-image can be removed, and the noise removal method of multiple second X-ray sub-images is kept consistent with the noise removal method of the stitched image.

[0099] In one possible implementation, image post-processing further includes:

[0100] Image enhancement processing was performed on the stitched image and each second X-ray sub-image to obtain a medical image.

[0101] For example, after adjusting the exposure and downsampling, a virtual grid can be used to process each second X-ray sub-image separately, and then the processed second X-ray sub-images can be stitched together. The stitched image can be used directly as a medical image, or further image enhancement processing can be performed to obtain the corresponding medical image. Each processed second X-ray sub-image can also be individually enhanced to obtain the corresponding medical image. If the medical image obtained after image enhancement still has some blurry body parts, the medical image obtained after image enhancement processing of the second X-ray sub-images including the corresponding body parts can be viewed. This method makes health assessments more accurate.

[0102] Those skilled in the art will understand that if a virtual grid is applied to the first X-ray sub-image that has not been adjusted for exposure and downsampled during image post-processing, image enhancement processing can also be performed on the processed first X-ray sub-image to obtain a medical image.

[0103] In one possible implementation, image enhancement processing includes at least one of vertical equalization, multi-resolution enhancement, tissue equalization, inverse gamma distribution transformation, window adjustment, and lookup table mapping.

[0104] Vertical equalization (VE) refers to applying equalization techniques in the vertical direction of an image, which can enhance the image's contrast.

[0105] Vertical equalization can be implemented based on existing technologies. For example, existing technologies such as histogram equalization can be used to segment the gray levels of an image vertically and adjust the gray levels of each segment through equalization. This disclosure does not limit the specific equalization technique used in the vertical equalization step, as long as it enhances image quality.

[0106] Multi-resolution enhancement (MR) is a method for enhancing images using multi-resolution analysis techniques. Multi-resolution analysis is a technique that decomposes an image into components of different scales and frequencies. By processing the image at different resolution levels, useful information in the image can be effectively extracted and enhanced. Commonly used multi-resolution enhancement techniques include wavelet transform and pyramid decomposition. Multi-resolution enhancement can be implemented based on existing technologies, and its specific implementation methods will not be elaborated upon here.

[0107] Tissue equalization (TE) is an image processing technique that decomposes an image into regions of different densities, processes each region separately, and then weighted and integrates these images to obtain a new image. This technique ensures that tissues of different densities are displayed well in the final image, thereby improving image contrast and clarity, which helps doctors make more accurate diagnoses and treatments. Tissue equalization can be implemented based on existing technologies, and its specific implementation methods will not be elaborated upon here.

[0108] The Inverse Gamma Transform (IGT) can be used for image enhancement and restoration. It utilizes the properties of its probability density function to perform a non-linear transformation on an image, thereby improving its contrast and sharpness. Specifically, the IGT can control the gray-level distribution of an image by adjusting its shape and scale parameters. When an image is generally too dark or too bright, selecting appropriate parameter values ​​can make the gray-level distribution more uniform, thus improving the image's visual effect. Furthermore, the IGT can also be used for image noise reduction, further improving image quality by reducing the impact of noise. The IGT can be implemented using existing technologies, and its specific implementation will not be elaborated upon here.

[0109] Smart Windowing, also known as window width and window level adjustment, is a technique that enhances image contrast and brightness by adjusting the grayscale range of an image. In medical image processing, because medical images often have a very wide grayscale range (potentially thousands of grayscale levels), while the grayscale range of a monitor is limited (typically 0-255), smart windowing is needed to selectively display the grayscale range of interest. Window width and window level (also known as window center) are two key parameters of smart windowing. Window width defines the range of grayscale levels displayed in the image, while window level determines the center value of that range. By adjusting these two parameters, the contrast and brightness of the image can be changed, thereby highlighting specific tissue structures or lesions. Smart windowing can be implemented based on existing technologies, and the specific implementation methods will not be elaborated here.

[0110] Lookup table mapping (LUT) is a technique that quickly transforms input values ​​into output values ​​through a predefined mapping relationship. In image processing, LUTs are commonly used to map pixel values ​​(such as RGB values) of an image to new pixel values ​​to achieve specific visual effects.

[0111] LUTs (Low-Value Transformers) work by using a predefined array or table that stores the mapping between input and output values. When an image needs to be transformed, the output value can be quickly obtained by looking up the corresponding input value in the LUT. In image processing, a LUT is typically a three-dimensional array used to store all possible input color values ​​in the RGB color space and their corresponding output color values. Thus, for each pixel in the image, its new color value can be obtained by looking up the LUT.

[0112] Table lookup mapping can be implemented based on existing technologies, and the specific implementation methods of table lookup mapping will not be elaborated here.

[0113] Those skilled in the art will understand that image enhancement processing may include more or fewer steps, as long as the quality of the processed image is improved. This disclosure does not limit the specific steps included in the image enhancement processing.

[0114] This approach can further improve the quality of medical images and make the methods for improving medical image quality more flexible.

[0115] Figure 6 An example of the steps included in image post-processing according to an embodiment of the present disclosure is shown.

[0116] like Figure 6As shown, image post-processing of the first X-ray sub-image may include the following steps: first, adjusting the exposure and downsampling each first X-ray sub-image; then, processing the downsampled image using a virtual grid. Next, stitching the images processed by the virtual grid, and performing image enhancement processing on the stitched image to obtain a medical image. Finally, performing image enhancement processing on the images processed by the virtual grid to obtain the medical image. The specific implementation methods of each step have been described above and will not be repeated here.

[0117] Figure 7 Another example of the steps included in image post-processing according to embodiments of the present disclosure is shown.

[0118] like Figure 7 As shown, image post-processing of the first X-ray sub-image may include the following steps: first, downsampling and adjusting the exposure of each first X-ray sub-image; then, stitching the exposure-adjusted images together. A virtual grid is used to process the stitched image. Image enhancement processing is performed on the image processed by the virtual grid to obtain a medical image. When processing the stitched image using the virtual grid, a scatter plot corresponding to the stitched image is also generated. Based on this scatter plot and the stitched image, denoising processing can be performed on the exposure-adjusted image. Image enhancement processing is then performed on the denoised image to obtain the medical image. The specific implementation methods of each step have been described above and will not be repeated here.

[0119] Those skilled in the art will understand that image post-processing may include more or fewer steps, as long as the image post-processing includes processing multiple first X-ray sub-images separately using a virtual grid and then stitching the images together, or includes stitching multiple first X-ray sub-images together and processing the stitched image using a virtual grid. The embodiments of this disclosure do not limit the specific steps included in the image post-processing.

[0120] Figure 8 An example of a medical image processed by an X-ray image processing method according to an embodiment of the present disclosure is shown below. Figure 8 The medical images shown are evaluated using the following methods and with the results of the evaluation.

[0121] like Figure 8 As shown, the medical image obtained by the X-ray image processing method according to the embodiment of this disclosure is an X-ray image of the right leg, and five regions of interest (Roi 1-Roi 5) can be set on the medical image. Figure 9 A schematic diagram showing the structure of the region of interest according to an embodiment of the present disclosure is provided. The region of interest is annular, that is... Figure 9The black portion in the image. The average pixel value of the circular region inside the region of interest is used as the signal value of that region of interest, and the average pixel value of the annular region outside the region of interest is used as the background value of that region of interest.

[0122] The right leg of a target object can be exposed using an existing X-ray imaging device with a physical grid filter, resulting in multiple sample X-ray sub-images, which are then stitched together to form a sample medical image. Five regions of interest are also positioned identically on the sample medical image.

[0123] The quality of medical images can be assessed using two metrics: the relative contrast improvement factor (Rel.CIF) and the relative contrast noise ratio (Rel.CNR).

[0124] Below is an example of how the relative contrast improvement factor is calculated.

[0125] For both the sample medical image and the medical image of this embodiment, the difference between the background value and the signal value of each region of interest (ROI) is calculated, and then the ratio of this difference to the background value is calculated to obtain the contrast of the ROI. The contrast of the ROI in the sample medical image can be CR_Grid, while the contrast of the ROI in the medical image of this embodiment can be CR_AG.

[0126] The difference between the contrast of the region of interest (ROI) of the medical image in this embodiment and the contrast of the ROI of the sample medical image can be calculated as CR_AG-CR_Grid. Then, the ratio of this difference to the contrast of the ROI of the sample medical image (CR_AG-CR_Grid) / CR_Grid can be calculated to obtain the relative contrast improvement factor Rel.CIF of the ROI of the medical image in this embodiment.

[0127] Below is an example of how to calculate the relative contrast-to-noise ratio.

[0128] The standard deviation Sigma of pixel values ​​in the region of interest (ROI) at the same location in the medical image of this embodiment and the sample medical image can be calculated. The difference between the background value and the signal value of the ROI in the medical image of this embodiment can be calculated, and the ratio of this difference to the standard deviation is used as the contrast-to-noise ratio (CNR_AG) of the ROI in the medical image of this embodiment. The difference between the background value and the signal value of the ROI in the sample medical image can be calculated, and the ratio of this difference to the standard deviation is used as the contrast-to-noise ratio (CNR_Grid) of the ROI in the sample medical image. The difference between CNR_AG and CNR_Grid is calculated, and then the ratio of this difference to CNR_Grid, i.e., (CNR_AG - CNR_Grid) / CNR_Grid, is used as the relative contrast-to-noise ratio (Rel.CNR) of the ROI in the medical image of this embodiment.

[0129] Table 1 shows the relative contrast improvement factor (Rel.CIF) of each region of interest in a medical image obtained by the X-ray image processing method according to an embodiment of the present disclosure, when the first X-ray sub-image is used as the object of a virtual grid during image post-processing.

[0130] Table 1

[0131] Area of ​​Interest Relative Contrast Improvement Factor (Rel.CIF) Roi 1 0.05372 Roi 2 0.198624 Roi 3 0.384295 Roi 4 -0.03399 Roi 5 -0.12747

[0132] As can be seen from Table 1, 60% of the regions of interest in the medical images obtained by this embodiment have positive relative contrast improvement factors (Rel.CIF). Therefore, the quality of the medical images obtained by this embodiment is better than that of the sample medical images in the prior art.

[0133] Combination Figure 3 and Figure 8 It can be seen that the region of interest (ROI) Roi 1 belongs to the first X-ray sub-image img11, ROI 2 and Roi 3 ​​belong to the first X-ray sub-image img12, and ROI 4 and Roi 5 belong to the first X-ray sub-image img14. Tables 2-4 also show the relative contrast improvement factor (Rel.CIF) of the ROI after image enhancement processing for each first X-ray sub-image. At this point, the first X-ray sub-images obtained by existing techniques can be used as sample medical images after image enhancement processing. The calculation method of the relative contrast improvement factor (Rel.CIF) has been described above and will not be repeated here.

[0134] Table 2

[0135]

[0136] As can be seen from Tables 2-4, the relative contrast improvement factor (Rel.CIF) of the region of interest in most of the first X-ray sub-images after image enhancement processing is positive. Therefore, the quality of the first X-ray sub-images after image enhancement processing obtained in this embodiment is likely to be better than that of the sample medical images in the prior art.

[0137] Table 5 shows the relative contrast improvement factor (Rel.CIF) of each region of interest in a medical image obtained by the X-ray image processing method according to embodiments of the present disclosure when the stitched image is used as the object of a virtual grid during image post-processing.

[0138] Table 5

[0139] Area of ​​Interest Relative Contrast Improvement Factor (Rel.CIF) Roi 1 0.023902 Roi 2 0.144857 Roi 3 0.403847 Roi 4 0.199675 Roi 5 -0.12444

[0140] As can be seen from Table 5, the relative contrast improvement factor (Rel.CIF) of 80% of the regions of interest in the medical images obtained by the embodiments of this disclosure is positive. Therefore, the quality of the medical images obtained by the embodiments of this disclosure is better than that of the sample medical images of the prior art.

[0141] Regions of interest (ROIs) Roi 1 belong to the first X-ray sub-image img1, RoIs 2 and RoIs 3 belong to the first X-ray sub-image img2, and RoIs 4 and RoIs 5 belong to the first X-ray sub-image img4. Tables 6-8 also show the relative contrast improvement factor (Rel.CIF) of the regions of interest after image enhancement processing for each first X-ray sub-image. At this point, the first X-ray sub-images acquired using existing techniques can be used as sample medical images after image enhancement processing. The calculation method of the relative contrast improvement factor (Rel.CIF) has been described above and will not be repeated here.

[0142] Table 6

[0143]

[0144] As can be seen from Tables 6-8, the relative contrast improvement factor (Rel.CIF) of the region of interest in most of the first X-ray sub-images after image enhancement processing is positive. Therefore, the quality of the first X-ray sub-images after image enhancement processing obtained in this embodiment is likely to be better than that of the sample medical images in the prior art.

[0145] This disclosure also proposes an X-ray image processing apparatus. Figure 10 A schematic diagram showing the structure of an X-ray image processing apparatus according to an embodiment of the present disclosure is provided.

[0146] like Figure 10 As shown, in one possible implementation, the device includes:

[0147] The first acquisition module 10 is used to perform multiple exposures on at least one body part of the target object using an X-ray imaging system to acquire multiple first X-ray sub-images.

[0148] The second acquisition module 11 is used to perform image post-processing on the plurality of first X-ray sub-images to obtain a medical image. The image post-processing includes processing the plurality of first X-ray sub-images separately using a virtual grid and then stitching the images together, or stitching the plurality of first X-ray sub-images together and processing the stitched image using a virtual grid. The virtual grid is used to filter out noise caused by scattered rays in the image.

[0149] In one possible implementation, using a virtual grid includes processing the first X-ray sub-image or the stitched image based on a scatter image, wherein the scatter image is obtained by performing a Fourier transform filter on the first X-ray sub-image or the stitched image.

[0150] In one possible implementation, using a virtual grid further includes adjusting the contrast of the image processed by the virtual grid based on adjustment parameters.

[0151] In one possible implementation, the image post-processing further includes: adjusting the exposure and downsampling each first X-ray sub-image to obtain a corresponding second X-ray sub-image, and then processing the multiple second X-ray sub-images separately using a virtual grid and stitching the images together, or stitching the multiple second X-ray sub-images together and processing the stitched image using a virtual grid.

[0152] In one possible implementation, the image post-processing further includes: performing image enhancement processing on the stitched image and each second X-ray sub-image respectively to obtain the medical image.

[0153] In one possible implementation, the image enhancement processing includes at least one of vertical equalization, multi-resolution enhancement, tissue equalization, inverse gamma distribution transformation, window adjustment, and lookup table mapping.

[0154] In one possible implementation, after stitching the plurality of first X-ray sub-images and processing the stitched image using a virtual grid, the image post-processing further includes denoising the plurality of first X-ray sub-images based on a scatter image, wherein the scatter image is obtained by performing Fourier transform filtering on the stitched image.

[0155] In one possible implementation, the denoising process includes: removing noise caused by scattered lines from the second X-ray sub-image based on the relationship between any second X-ray sub-image and a first region in the stitched image corresponding to the second X-ray sub-image, and a second region in the scatter image corresponding to the second X-ray sub-image, wherein the second X-ray sub-image is obtained by adjusting the exposure and downsampling the first X-ray sub-image.

[0156] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0157] This disclosure also proposes a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the above-described method. The computer-readable storage medium can be volatile or non-volatile.

[0158] This disclosure also proposes an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0159] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs the above-described method.

[0160] Figure 11 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. For example, electronic device 1900 may be provided as a server or terminal device. (Refer to...) Figure 11 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0161] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). Electronic device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM FreeBSD TM Or similar.

[0162] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of an electronic device 1900 to perform the above-described method.

[0163] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0164] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0165] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0166] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0167] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0168] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0169] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0170] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0171] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. An X-ray image processing method, characterized in that, The method includes: At least one body part of the target object is exposed multiple times using an X-ray imaging system to obtain multiple first X-ray sub-images; Post-processing is performed on the plurality of first X-ray sub-images to obtain a medical image. The post-processing includes processing the plurality of first X-ray sub-images separately using a virtual grid and then stitching the images together, or stitching the plurality of first X-ray sub-images together and processing the stitched image using a virtual grid. The virtual grid is used to filter out noise caused by scattered rays in the image.

2. The method according to claim 1, characterized in that, Using a virtual grid includes processing the first X-ray sub-image or the stitched image based on a scatter image, wherein the scatter image is obtained by performing a Fourier transform filter on the first X-ray sub-image or the stitched image.

3. The method according to claim 2, characterized in that, The use of a virtual grid further includes adjusting the contrast of the image processed by the virtual grid based on adjustment parameters.

4. The method according to claim 1, characterized in that, The image post-processing further includes: Each first X-ray sub-image is subjected to exposure adjustment and downsampling to obtain a corresponding second X-ray sub-image. Then, multiple second X-ray sub-images are processed separately using a virtual grid and then stitched together. Alternatively, the multiple second X-ray sub-images are stitched together and the stitched image is processed using a virtual grid.

5. The method according to claim 4, characterized in that, The image post-processing further includes: The stitched image and each second X-ray sub-image are subjected to image enhancement processing to obtain the medical image.

6. The method according to claim 5, characterized in that, The image enhancement processing includes at least one of vertical equalization, multi-resolution enhancement, tissue equalization, inverse gamma distribution transformation, window adjustment, and lookup table mapping.

7. The method according to claim 1, characterized in that, After stitching the plurality of first X-ray sub-images together and processing the stitched image using a virtual grid, the image post-processing further includes denoising the plurality of first X-ray sub-images based on a scatter image, wherein the scatter image is obtained by performing Fourier transform filtering on the stitched image.

8. The method according to claim 7, characterized in that, The noise reduction process includes: Based on the relationship between any second X-ray sub-image and the first region corresponding to the second X-ray sub-image in the stitched image, and the second region corresponding to the second X-ray sub-image in the scatter image, noise caused by scattered lines in the second X-ray sub-image is removed, wherein the second X-ray sub-image is obtained by adjusting the exposure and downsampling the first X-ray sub-image.

9. An X-ray image processing apparatus, characterized in that, The device includes: The first acquisition module is used to expose at least one body part of the target object multiple times using an X-ray imaging system to acquire multiple first X-ray sub-images. The second acquisition module is used to perform image post-processing on the plurality of first X-ray sub-images to obtain a medical image. The image post-processing includes processing the plurality of first X-ray sub-images separately using a virtual grid and then stitching the images together, or stitching the plurality of first X-ray sub-images together and processing the stitched image using a virtual grid. The virtual grid is used to filter out noise caused by scattered rays in the image.

10. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the method of any one of claims 1 to 8 when executing instructions stored in the memory.

11. A non-volatile computer-readable storage medium storing computer program instructions thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 8.

Images