Image correction method and electronic equipment

Abstract

The invention provides an image correction method and electronic equipment, and relates to the technical field of medical treatment. According to the specific implementation scheme, a to-be-corrected first reconstructed image is acquired, wherein the first reconstructed image comprises an occlusion artifact; iterative correction is carried out based on the first reconstructed image, and a corrected second reconstructed image is obtained after iteration is finished; wherein in one iteration, the reconstructed image obtained by the last iteration is processed to obtain a reconstructed domain artifact image, and the first reconstructed image is corrected based on the reconstructed domain artifact image to obtain a reconstructed image of the current iteration. Thus, the occlusion artifacts in the reconstructed image are iteratively corrected, the occlusion artifacts in the reconstructed image can be more accurately removed, and the accuracy of image correction is improved.

Description

Technical Field

[0001] This disclosure relates to the field of medical technology, and in particular to an image correction method and electronic device. Background Technology

[0002] When using cone beam computed tomography (CBCT) for imaging, a beam stop array (BSA) is usually used for scattering correction to avoid poor image quality caused by scattering of X-ray signals emitted from the CBCT X-ray source.

[0003] Currently, when using BSA for scattering correction, because BSA completely blocks X-ray signals, the CBCT detector cannot receive X-ray signals in the shadow area corresponding to the BSA, resulting in the projected image lacking X-ray information in the shadow area. In this case, interpolation is typically used to supplement the X-ray information in the shadow area.

[0004] However, directly using interpolation to complete the X-ray information of the shadow area may introduce large errors, which will be amplified in the subsequent image reconstruction process, resulting in occlusion artifacts. Summary of the Invention

[0005] This disclosure provides an image correction method and electronic device for iteratively correcting occlusion artifacts in reconstructed images, thereby improving the accuracy of image correction.

[0006] According to one aspect of this disclosure, an image correction method is provided, the method comprising:

[0007] Obtain the first reconstructed image to be corrected, which includes occlusion artifacts;

[0008] Iterative correction is performed based on the first reconstructed image, and a corrected second reconstructed image is obtained at the end of the iteration. In each iteration, the reconstructed image obtained in the previous iteration is processed to obtain a reconstruction domain artifact image, and the first reconstructed image is corrected based on the reconstruction domain artifact image to obtain the reconstructed image of the current iteration.

[0009] In some possible implementations, the reconstructed image obtained from the previous iteration is processed to obtain a reconstruction domain artifact image, including:

[0010] The reconstructed image obtained from the previous iteration is projected forward from multiple preset angles to obtain forward projected images from multiple angles.

[0011] Based on orthogonal projection images from multiple angles, determine projection domain artifact images from multiple angles;

[0012] Back-projecting the projection domain artifact images from multiple angles yields the reconstructed domain artifact images.

[0013] In some possible implementations, projection domain artifact images at multiple angles are determined based on orthogonal projection images at multiple angles, including:

[0014] Interpolate the artifact regions in the orthographic projection images at each angle to obtain the interpolated orthographic projection images at each angle;

[0015] Based on the orthographic projection images at each angle and the interpolated orthographic projection images at each angle, the projection domain artifact images at each angle are determined.

[0016] In some possible implementations, the method further includes, before interpolating the artifact regions in the orthographically projected images at various angles:

[0017] Obtain the occlusion artifact image, which is used to indicate the location of occlusion artifacts in the projected image;

[0018] Based on the occlusion artifact images, the artifact regions in the orthogonal projection images at various angles are determined.

[0019] In some possible implementations, acquiring the occlusion artifact image includes:

[0020] Obtain the empty field projection image, which is the projection image when there is no object being scanned;

[0021] Image segmentation is performed on the empty field projection image to obtain the shadowed and non-shadowed regions in the empty field projection image;

[0022] Based on the shadow and non-shadow regions in the open-field projection image, the open-field projection image is binarized to obtain the occlusion artifact image.

[0023] In some possible implementations, the projection domain artifact image for each angle is determined based on the orthographic projection image at each angle and the interpolated orthographic projection image at each angle, including:

[0024] The first difference image obtained by subtracting the orthographic projection image at each angle from the interpolated orthographic projection image at each angle is used as the projection domain artifact image at each angle; or,

[0025] The second difference image obtained by subtracting the orthogonal projection image of each angle from the orthogonal projection image of each angle is determined as the projection domain artifact image of each angle.

[0026] In some possible implementations, when the projection domain artifact images at each angle are first difference images, the first reconstructed image is corrected based on the reconstruction domain artifact images to obtain the reconstructed image for this iteration, including:

[0027] Add the first reconstructed image to the reconstruction domain artifact image to obtain the reconstructed image for this iteration; or,

[0028] When the projection domain artifact images at each angle are the second difference images, the first reconstructed image is corrected based on the reconstruction domain artifact images to obtain the reconstructed image for this iteration, including:

[0029] Subtract the first reconstructed image from the reconstructed domain artifact image to obtain the reconstructed image for this iteration.

[0030] In some possible implementations, the method further includes:

[0031] The iteration ends when the difference in pixel value between the reconstructed images obtained from two adjacent iterations is less than a preset pixel value threshold.

[0032] In some possible implementations, the reconstructed image is a CBCT image, and the occlusion artifact is a BSA occlusion artifact.

[0033] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0034] At least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0035] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the image correction method provided in this disclosure.

[0036] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the electronic device to perform the image correction method provided in this disclosure.

[0037] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the image correction method provided in this disclosure.

[0038] The technical solution provided in this disclosure offers an iterative correction method for occlusion artifacts in reconstructed images, which can effectively remove occlusion artifacts and thus improve the quality of the reconstructed images. Specifically, in each iteration, the reconstructed image obtained from the previous iteration is used to determine the artifact image in the reconstruction domain, and then the original reconstructed image is corrected. In this way, each iteration is based on the result of the previous iteration, enabling the gradual identification of occlusion artifacts through multiple iterations. This allows for accurate identification of the artifact image in the reconstruction domain, thereby more accurately removing occlusion artifacts from the original reconstructed image and improving the accuracy of image correction.

[0039] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0040] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0041] Figure 1 This is a schematic diagram illustrating the implementation environment of an image correction method according to an embodiment of this disclosure;

[0042] Figure 2 This is a cross-sectional schematic diagram of an image scanning device shown in an embodiment of this disclosure;

[0043] Figure 3 This is a schematic diagram of a BSA shown in an embodiment of this disclosure;

[0044] Figure 4 This is a schematic flowchart illustrating an image correction method according to an embodiment of this disclosure;

[0045] Figure 5 This is a schematic flowchart illustrating another image correction method according to an embodiment of this disclosure;

[0046] Figure 6 This is a schematic diagram of an open-field projection image shown in an embodiment of this disclosure;

[0047] Figure 7 This is a schematic diagram of an occlusion artifact image shown in an embodiment of this disclosure;

[0048] Figure 8 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this disclosure. Detailed Implementation

[0049] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0050] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0051] First, the application scenarios involved in the embodiments of this disclosure will be described. The image correction method provided in the embodiments of this disclosure can be applied to the field of medical technology, specifically to the scenario of medical image scanning.

[0052] In medical imaging, CBCT is used to scan a subject (such as a patient) to obtain projected images of the subject from multiple angles. Then, based on these projected images, computer graphics and image processing techniques are used to convert the original projected images into reconstructed images suitable for diagnosis. Because reconstructed images provide clearer and more detailed information about the internal structures of the human body, the accuracy of disease diagnosis can be improved.

[0053] When using CBCT scanning for imaging, because the X-ray source of CBCT uses cone-beam X-rays, the X-ray signal may interact with the scanned object during the imaging process, resulting in scattering. This scattering of the X-ray signal can cause problems such as poor reconstructed image quality, including decreased contrast and inaccurate computed tomography (CT) values.

[0054] In CBCT, contrast is used to characterize the differences in X-ray signal absorption by different tissues of the scanned object. For example, bone absorbs X-ray signals strongly and therefore appears as a high-brightness area in the reconstructed image. Conversely, soft tissue absorbs X-ray signals weakly and therefore appears as a low-brightness area in the reconstructed image. However, X-ray signal scattering can reduce CBCT contrast, thus affecting the quality of the reconstructed image. The CT value in CBCT is a quantitative indicator measuring the absorption capacity of different tissues of the scanned object for X-ray signals. However, X-ray signal scattering can introduce additional scattered signals, leading to errors in CT value calculation and thus affecting the quality of the reconstructed image.

[0055] To overcome the problem of poor image quality caused by scattering of X-ray signals emitted from the CBCT X-ray source, beam blocking structures (BSAs) are typically placed between the CBCT X-ray source and the scanned object, or between the CBCT detector and the scanned object, to achieve scatter correction. A BSA is a plate composed of multiple high-absorption (high-attenuation) beam blocking elements (such as lead or tungsten cylinders). These beam blocking elements block the X-ray signal, ensuring that the detector receives only scattered signals in the shadowed area corresponding to the beam blocking element. Understandably, due to the low-frequency characteristics of the scattered signal (i.e., low spatial frequency), this means that the scattered signal changes more slowly and is more uniformly distributed in space. Therefore, by measuring the scattered signal received by the CBCT detector and combining it with interpolation methods (such as bilinear interpolation, spline interpolation, etc.), the scattering distribution of the entire imaging area can be obtained, thus enabling scatter correction.

[0056] Currently, when using BSA for scattering correction, because BSA completely blocks X-ray signals, the CBCT detector cannot receive X-ray signals in the shadow area corresponding to the BSA, resulting in the projected image lacking X-ray information in the shadow area. In this case, interpolation is typically used to supplement the X-ray information in the shadow area.

[0057] However, due to the high-frequency characteristics of X-ray signals (i.e., high spatial frequency), X-ray signals change more rapidly and are more complexly distributed in space. Therefore, directly using interpolation to complete the X-ray information in the shadow area may introduce large errors, which will be amplified in the subsequent image reconstruction process, resulting in occlusion artifacts and reducing the accuracy of diagnosis.

[0058] Based on this, embodiments of this disclosure provide an image correction method, offering an iterative correction scheme for occlusion artifacts in reconstructed images. This effectively removes occlusion artifacts from reconstructed images, thereby improving the quality of the reconstructed images. Specifically, in each iteration, the reconstructed image obtained from the previous iteration is used to determine the artifact image in the reconstruction domain, and then the original reconstructed image is corrected. In this way, each iteration is based on the result of the previous iteration, enabling the gradual identification of occlusion artifacts through multiple iterations. This allows for accurate identification of the artifact image in the reconstruction domain, leading to more accurate removal of occlusion artifacts from the original reconstructed image and improving the accuracy of image correction.

[0059] Figure 1 This is a schematic diagram illustrating the implementation environment of an image correction method according to an embodiment of this disclosure. See also... Figure 1 The implementation environment includes: image scanning device 101 and electronic device 102.

[0060] The imaging scanning device 101 is used to acquire images of the tumor site and surrounding normal tissue of the scanned object. In some embodiments, the imaging scanning device 101 may be a CBCT device.

[0061] In this embodiment of the present disclosure, the image scanning device 101 is used to acquire projected images of the scanned object from multiple angles and send the projected images from multiple angles to the electronic device 102. The projected images from multiple angles are used to generate a reconstructed image for the electronic device 102 to perform an image correction method.

[0062] Electronic device 102 is a device connected to image scanning device 101. In some embodiments, electronic device 102 may be at least one of devices such as smartphones, smartwatches, desktop computers, laptops, virtual reality terminals, augmented reality terminals, wireless terminals, and laptop computers. In other embodiments, electronic device 102 may be an independent physical server, a server cluster or distributed file system composed of multiple physical servers, or at least one of cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data or artificial intelligence platforms. This disclosure does not limit the scope of the embodiments.

[0063] In this embodiment of the present disclosure, the electronic device 102 is used to acquire a first reconstructed image to be corrected, the first reconstructed image including occlusion artifacts; perform iterative correction based on the first reconstructed image, and obtain a corrected second reconstructed image at the end of the iteration; wherein, in one iteration, the reconstructed image obtained in the previous iteration is processed to obtain a reconstruction domain artifact image, and the first reconstructed image is corrected based on the reconstruction domain artifact image to obtain the reconstructed image of the current iteration.

[0064] Figure 2 This is a cross-sectional schematic diagram of an image scanning device according to an embodiment of this disclosure. See also... Figure 2 The imaging scanning device includes: a frame 201, an X-ray source 202, a support device 203, a detector 204, and a BSA 205.

[0065] The gantry 201 can be a rotatable gantry. The X-ray source 202 and detector 204 are mounted opposite each other on the gantry 201, and the BSA 205 is positioned below the X-ray source 202. The X-ray source 202 emits X-rays (imaging rays). The support device 203 supports the object being scanned, such as a support bed. The detector 204 acquires the X-rays transmitted from the X-ray source 202 through the BSA 205 and the scanned object, as well as the scattered signals in cases of scattering.

[0066] BSA205 is used to block the transmission of X-rays. Figure 3 This is a schematic diagram of a BSA according to an embodiment of this disclosure. See also Figure 3 A BSA can include n*n beam blocking elements, such as Figure 3 The lead or tungsten points shown form an n*n array, where n is a positive integer greater than 0. Figure 3 Let's take n=9 as an example to illustrate BSA.

[0067] In some embodiments, when the object being scanned is on the support device 203, the rotation of the frame 201 can drive the X-ray source 202, BSA 205 and detector 204 to scan around the object at multiple angles, and multiple angle projection images can be acquired on the detector 204.

[0068] It should be noted that the X-ray source 202, BSA 205, and detector 204 can also be mounted on the gantry of the radiotherapy equipment. The gantry of the radiotherapy equipment is equipped with a radiotherapy head that can emit therapeutic rays for radiotherapy of the radiotherapy recipient. By rotating the gantry of the radiotherapy equipment, the X-ray source 202, BSA 205, and detector 204 can be driven to scan the radiotherapy recipient from multiple angles, and multiple angle projection images can be acquired on the detector 204. The radiotherapy recipient can be guided by the projection images from multiple angles.

[0069] The following is based on Figure 1 The implementation environment shown will be used to describe the methods provided in the embodiments of this disclosure.

[0070] Figure 4 This is a schematic flowchart illustrating an image correction method according to an embodiment of this disclosure. In some embodiments, the image correction method comprises the above-described... Figure 1 The electronic device shown performs this action. Figure 4 As shown, the method includes the following steps.

[0071] S401, The electronic device acquires the first reconstructed image to be corrected.

[0072] The first reconstructed image refers to the CBCT image, i.e., the CBCT reconstructed image.

[0073] In some embodiments, the first reconstructed image is reconstructed based on projection images from multiple angles acquired by an image scanning device. The corresponding process may include: an electronic device acquiring projection images from multiple angles from the image scanning device, interpolating shadow regions in the projection images from multiple angles, and obtaining the first reconstructed image. Here, the projection images from multiple angles acquired by the image scanning device are projection images acquired from multiple angles for the scanned object.

[0074] In this embodiment of the disclosure, the first reconstructed image includes occlusion artifacts. These occlusion artifacts can be BSA occlusion artifacts. It is understood that due to the high-frequency characteristics of X-ray signals (i.e., high spatial frequency), X-ray signals change more rapidly and are distributed more complexly in space. Therefore, directly using interpolation to complete the X-ray information in the shadow region may introduce significant errors, which will be amplified during subsequent image reconstruction, leading to the generation of occlusion artifacts.

[0075] S402. The electronic device performs iterative correction based on the first reconstructed image and obtains the corrected second reconstructed image at the end of the iteration; wherein, in one iteration, the reconstructed image obtained in the previous iteration is processed to obtain a reconstruction domain artifact image, and the first reconstructed image is corrected based on the reconstruction domain artifact image to obtain the reconstructed image of the current iteration.

[0076] The second reconstructed image refers to the reconstructed image obtained after iterative correction, i.e., the reconstructed image after removing occlusion artifacts. The reconstruction domain artifact image refers to the image of occlusion artifacts in the reconstructed image domain, i.e., the three-dimensional artifact image.

[0077] In some embodiments, for the first iteration, the electronic device processes the first reconstructed image to obtain a reconstruction domain artifact image, and corrects the first reconstructed image based on the reconstruction domain artifact image to obtain the reconstructed image of the first iteration. Then, based on the reconstructed image of the first iteration, the next iteration is performed. For any iteration after the first iteration, the reconstructed image obtained in the previous iteration is processed to obtain a reconstruction domain artifact image, and the first reconstructed image is corrected based on the reconstruction domain artifact image to obtain the reconstructed image of the current iteration. Finally, at the end of the iteration, the reconstructed image obtained at the end of the iteration is acquired as the second reconstructed image.

[0078] The technical solution provided in this disclosure offers an iterative correction method for occlusion artifacts in reconstructed images, which can effectively remove occlusion artifacts and thus improve the quality of the reconstructed images. In each iteration, the reconstructed image obtained from the previous iteration is used to determine the artifact image in the reconstruction domain, and then the original reconstructed image is corrected. This ensures that each iteration is based on the result of the previous iteration, enabling the gradual identification of occlusion artifacts through multiple iterations. This accurate identification of the artifact image in the reconstruction domain leads to more precise removal of occlusion artifacts from the original reconstructed image, improving the accuracy of image correction.

[0079] The following is based on Figure 5 The process of any iteration of the iterative correction is described. Figure 5 This is a schematic flowchart illustrating another image correction method according to an embodiment of this disclosure. Figure 5As shown, for any iteration of the iterative correction process, the method includes the following steps.

[0080] S501. The electronic device projects the reconstructed image obtained in the previous iteration onto multiple preset angles to obtain forward-projected images from multiple angles.

[0081] The preset multiple angles can range from 0 degrees to 360 degrees. In some possible implementations, the preset multiple angles can be evenly distributed, such as adjacent angles being spaced equidistantly (e.g., 1 degree). Alternatively, in other possible implementations, the preset multiple angles can be non-uniformly distributed, such as adjacent angles being spaced unequally. Or, in still other possible implementations, the preset multiple angles can be specific angles selected according to specific needs, such as one or more key angles selected from (0 degrees, 360 degrees). This disclosure does not limit these aspects. It is worth noting that the preset multiple angles for forward projection are the same as the multiple angles (e.g., the rotation angle of the gantry) used by the image scanning device during scanning and imaging.

[0082] Forward projection refers to the process of projecting a three-dimensional reconstructed image along a specific direction to generate a two-dimensional projected image. In some possible implementations, an electronic device can utilize computer software or a mathematical calculation model to forward project the reconstructed image obtained from the previous iteration, obtaining forward projected images from multiple angles. The computer software is software that provides forward projection functionality. The mathematical calculation model is a calculation model that provides forward projection functionality. It is worth noting that the electronic device can also use other methods to achieve forward projection of the reconstructed image, such as calculating the projection value of each pixel based on a projection matrix to obtain a forward projected image, etc., and this disclosure does not limit this approach.

[0083] For example, see Figure 5 Using multiple preset angles θ1, θ2…θ n For example, after forward projection of the reconstructed image obtained in the previous iteration, multiple forward projected images can be obtained, namely θ1, θ2…θ n Orthogonal projection image at an angle.

[0084] S502, The electronic device determines the artifact region in the orthogonal projection image at each angle based on the occlusion artifact image.

[0085] The occlusion artifact image, also known as a mask image, is used to indicate the location of occlusion artifacts in the projected image. For example, the occlusion artifact image is used to indicate the pixel location of the occlusion artifact in the projected image, such as pixel coordinates.

[0086] In this embodiment of the disclosure, the occlusion artifact image is a binary image with the same size as the forward-projected image. A binary image is an image with pixel values ​​of 0 or 1, where 0 represents black and 1 represents white.

[0087] In some embodiments, taking the example that a pixel with a pixel value of 1 in the occlusion artifact image corresponds to an artifact region, the above-described S502 can be replaced by: determining the position of a first pixel with a pixel value of 1 from the occlusion artifact image. Furthermore, for each angle of the orthogonal projection image, a second pixel position corresponding to the first pixel position is determined in the orthogonal projection image, and the determined second pixel position is used as the position of the artifact region. Here, the first pixel position refers to the position of the occlusion artifact in the occlusion artifact image. The second pixel position refers to the position of the occlusion artifact in the orthogonal projection image.

[0088] In other embodiments, taking the example of a pixel with a value of 0 in the occlusion artifact image corresponding to an artifact region, the above-described S502 can be replaced by: determining the position of a first pixel with a value of 0 from the occlusion artifact image. Furthermore, for each angle of the orthogonal projection image, a second pixel position corresponding to the first pixel position is determined in the orthogonal projection image, and the determined second pixel position is used as the position of the artifact region.

[0089] In the above embodiments, by utilizing the occlusion artifact image, the artifact region in the forward projection image at each angle can be accurately determined, thereby improving the accuracy of artifact region determination.

[0090] Before implementing this solution, the electronic device also acquires occlusion artifact images, and the corresponding process may include the following steps one to three.

[0091] Step 1: Electronic equipment acquires the empty field projection image.

[0092] Among them, the empty field projection image is the projection image when there is no object being scanned.

[0093] In some embodiments, the image scanning device acquires an empty-field projection image even when no object is being scanned. The image scanning device then sends the empty-field projection image to an electronic device, which in turn receives the image.

[0094] For example, an image scanning device sends an open-field projection image at a target angle to an electronic device. The target angle is one of a set of preset angles. The electronic device then receives the open-field projection image at the target angle.

[0095] For example, the image scanning device sends open-field projection images from multiple angles to the electronic device. The electronic device then receives these open-field projection images from multiple angles and performs an average processing on them to obtain an averaged open-field projection image. This averaging process involves averaging the pixel values ​​at the same location across multiple images. By averaging open-field projection images from multiple angles, a more representative open-field projection image can be obtained, laying the foundation for subsequently obtaining highly accurate occlusion artifact images.

[0096] Step 2: The electronic device performs image segmentation on the open field projection image to obtain the shadowed and non-shadowed areas in the open field projection image.

[0097] Image segmentation refers to the process of dividing an image into multiple non-overlapping regions. In this embodiment of the present disclosure, image segmentation is used to distinguish shadowed regions from other regions (i.e., non-shadowed regions) in an open-field projection image. It is understood that shadowed regions refer to regions formed by the obstruction of the beam blocking element of the BSA, while non-shadowed regions refer to unobstructed regions.

[0098] For example, Figure 6 This is a schematic diagram illustrating an open-field projection image according to an embodiment of this disclosure. See also... Figure 6 The shaded area can include Figure 6 Multiple shaded points in the image, and non-shaded areas may include Figure 6 The area outside of several shaded points. Understandably, the pixel values ​​in shaded areas are generally lower (darker), while the pixel values ​​in unshaded areas are higher (brighter).

[0099] In some embodiments, the electronic device may perform image segmentation based on a preset pixel threshold. The corresponding process may include: identifying pixels with pixel values ​​less than the preset pixel threshold from a plurality of pixels included in the open-field projection image; defining the region formed by pixels with pixel values ​​less than the preset pixel threshold as a shadow region; and defining other regions outside the shadow region as non-shadow regions. The preset pixel threshold is used to filter pixels located in shadow regions. It is understood that pixels with pixel values ​​less than the preset pixel threshold are considered to be located in shadow regions.

[0100] In other embodiments, the electronic device may perform image segmentation based on an image segmentation model. The corresponding process may include: inputting an empty-field projection image into the image segmentation model, processing the empty-field projection image through the image segmentation model to obtain shadow regions and non-shadow regions in the empty-field projection image. The image segmentation model is used to identify shadow regions and non-shadow regions in the image.

[0101] It is worth noting that electronic devices can also use other methods to achieve the above-mentioned image segmentation of the open field projection image, such as image segmentation based on clustering algorithms or image segmentation based on edge detection. This disclosure does not limit the scope of the embodiments.

[0102] Step 3: The electronic device performs binarization processing on the open field projection image based on the shadow and non-shadow regions in the image to obtain the occlusion artifact image.

[0103] Binarization refers to converting pixel values ​​in an image to 0 or 1, thereby converting the image into a binary image.

[0104] In some embodiments, the electronic device converts the pixel values ​​of pixels included in the shadowed areas of the open-field projected image to 0, and converts the pixel values ​​of pixels included in the non-shadowed areas to 1. For example, Figure 7 This is a schematic diagram illustrating an occlusion artifact image according to an embodiment of this disclosure. See also... Figure 7 As shown in (7-1), the pixel value of the shaded area is 0, which is represented by black shadow points, and the pixel value of the non-shaded area is 1, which is represented by white areas.

[0105] Alternatively, in other embodiments, the electronic device converts the pixel values ​​of pixels included in the shadowed regions of the open-field projection image to 1, and converts the pixel values ​​of pixels included in the non-shadowed regions to 0. For example, see [link to relevant documentation]. Figure 7 As shown in (7-2), the pixel value of the shaded area is 1, which is represented by white shadow points, and the pixel value of the non-shaded area is 0, which is represented by black areas.

[0106] Based on steps one through three above, image segmentation is performed on the empty-field projection image to determine multiple shadow points in the image, thereby generating a binarized occlusion artifact image. Acquiring the empty-field projection image allows for the determination of the scattering distribution when no object is being scanned, which is beneficial for subsequent identification of the shadow regions formed on the detector by each beam blocker in the BSA. Furthermore, binarization significantly improves the effectiveness of subsequent image correction.

[0107] S503. The electronic device interpolates the artifact regions in the orthogonal projection images at various angles to obtain the orthogonal projection images after interpolation at each angle.

[0108] Based on S502 to S503 above, the artifact regions in the orthogonal projection images at each angle are interpolated using the occlusion artifact image to obtain the interpolated orthogonal projection images at each angle. For example, see... Figure 5 Taking a forward-projected image at a certain angle as an example, in Figure 5In step S502, the artifact region in the orthogonal projection image at that angle can be determined using the occlusion artifact image. Furthermore, in Figure 5 In step S503 shown, the artifact region in the orthographic projection image at that angle is interpolated to obtain the orthographic projection image after interpolation at that angle.

[0109] In some embodiments, the interpolation method can be any one of nearest neighbor interpolation, bilinear interpolation, piecewise interpolation, and spline interpolation, and the embodiments disclosed herein do not limit this method.

[0110] S504. The electronic device determines the projection domain artifact image for each angle based on the orthogonal projection image at each angle and the orthogonal projection image after interpolation at each angle.

[0111] Among them, the projection domain artifact image refers to the image of occlusion artifacts in the projection image domain, that is, a two-dimensional artifact image.

[0112] Implementation Method 1: The electronic device determines the first difference image obtained by subtracting the orthogonal projection image of each angle from the interpolated orthogonal projection image of each angle, and uses it as the projection domain artifact image of each angle.

[0113] The first difference image refers to the difference image obtained by subtracting the interpolated forward projection image from the original forward projection image. For example, if the original forward projection image is F1 and the interpolated forward projection image is F2, the first difference image A1 is F1-F2.

[0114] Method 2: The electronic device determines the second difference image by subtracting the forward projection image of each angle from the forward projection image of each angle after interpolation, and uses this difference image as the projection domain artifact image of each angle.

[0115] The second difference image refers to the difference image obtained by subtracting the original forward projection image from the interpolated forward projection image. For example, if the original forward projection image is F1 and the interpolated forward projection image is F2, the second difference image A2 is F2-F1.

[0116] For example, see Figure 5 Taking a forward-projected image at a certain angle as an example, in Figure 5 In S504 shown, by subtracting the original forward projection image from the interpolated forward projection image, a second difference image can be obtained, which serves as the projection domain artifact image for that angle.

[0117] It is understandable that the above image subtraction process refers to the process of subtracting the pixel values ​​at the same position in the image.

[0118] The above steps S502 to S504 describe how an electronic device determines projection domain artifact images from multiple angles based on forward-projected images from multiple angles. Thus, by using forward projection, the image of the occlusion artifact in the projected image domain is determined, laying the foundation for subsequently determining the image of the occlusion artifact in the reconstructed image domain.

[0119] S505. The electronic device back-projects the projection domain artifact images from multiple angles to obtain the reconstructed domain artifact images.

[0120] Back projection refers to the process of projecting a two-dimensional image back into three-dimensional space along the projection direction to obtain a reconstructed three-dimensional image. In some possible implementations, the electronic device can use computer software or a mathematical calculation model to back project projection domain artifact images from multiple angles to obtain reconstructed domain artifact images. The computer software is software that provides back projection functionality. The mathematical calculation model is a calculation model that provides back projection functionality. It is worth noting that the electronic device can also use other methods to achieve back projection of projection domain artifact images, and this disclosure does not limit this approach.

[0121] S506. The electronic device corrects the first reconstructed image based on the artifact image of the reconstruction domain to obtain the reconstructed image of this iteration.

[0122] Implementation Method 1: When the projection domain artifact images at each angle are the first difference images, the above S506 can be replaced by: the electronic device adding the first reconstructed image and the reconstruction domain artifact image to obtain the reconstructed image of this iteration.

[0123] For example, taking the first reconstructed image as I and the first difference image as A1, the reconstructed image I′ in this iteration is also I+A1.

[0124] In the second implementation method, when the projection domain artifact images at each angle are the second difference images, the above S506 can be replaced by: the electronic device subtracting the first reconstructed image from the reconstructed domain artifact image to obtain the reconstructed image of this iteration.

[0125] For example, taking the first reconstructed image as I and the second difference image as A2, the reconstructed image I′ in this iteration is also I-A2.

[0126] For example, see Figure 5 ,exist Figure 5 In step S505, backprojection is performed using projection domain artifact images (such as the second difference image) from multiple angles to obtain a reconstruction domain artifact image. Furthermore, in... Figure 5 In S506 shown, the first reconstructed image is subtracted from the reconstructed domain artifact image to obtain the reconstructed image for this iteration.

[0127] S507. The electronic device determines whether the difference pixel value between the reconstructed images obtained from two adjacent iterations is less than the preset pixel value threshold. If yes, execute S508; otherwise, execute S509.

[0128] The difference pixel value between reconstructed images refers to the sum of pixel differences at the same location in two reconstructed images.

[0129] In some embodiments, for reconstructed images obtained from two adjacent iterations, the pixel values ​​at the same location in the two reconstructed images are subtracted to obtain the pixel difference at the same location. Then, the pixel differences at multiple locations at the same location are summed to obtain the difference pixel value between the reconstructed images.

[0130] Understandably, the difference pixel value between reconstructed images is used to characterize the difference between two reconstructed images obtained from two adjacent iterations. The smaller the difference pixel value between reconstructed images, the more similar the reconstructed images obtained from the two iterations are, which means that the accuracy of the current iteration correction is higher.

[0131] S508, the electronic device terminates the iteration when the difference pixel value between the reconstructed images obtained from two adjacent iterations is less than a preset pixel value threshold.

[0132] S509. The electronic device responds to the fact that the difference pixel value between the reconstructed images obtained from two adjacent iterations is greater than a preset pixel value threshold, and continues to execute the next iteration process.

[0133] In some embodiments, S501 to S507 are performed based on the reconstructed image obtained in this iteration to continue the next iteration process.

[0134] The technical solution provided in this disclosure offers an iterative correction method for occlusion artifacts in reconstructed images, effectively removing occlusion artifacts and improving the quality of the reconstructed images. In each iteration, based on a calibrated occlusion artifact image, operations such as forward projection and back projection are used to determine the reconstruction domain artifact image, which is then used to correct the original reconstructed image. Thus, through multiple iterations, by continuously using forward and back projection to estimate the reconstruction domain artifact image caused by occlusion artifacts, occlusion artifacts are gradually identified, leading to accurate identification of the reconstruction domain artifact image. This, in turn, enables more accurate removal of occlusion artifacts from the original reconstructed image, improving the accuracy of image correction.

[0135] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the image correction method provided by the present disclosure.

[0136] According to embodiments of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause an electronic device to perform the image correction method provided in the present disclosure.

[0137] According to embodiments of this disclosure, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the image correction method provided in this disclosure.

[0138] In some embodiments, Figure 8 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this disclosure. Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. Electronic device 800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 800 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0139] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the electronic device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0140] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0141] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as image correction methods. For example, in some embodiments, the image correction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the image correction method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform an image correction method by any other suitable means (e.g., by means of firmware).

[0142] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user, such as a cathode ray tube (CRT) or liquid crystal display (LCD) monitor; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0146] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0147] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0148] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An image correction method, characterized in that, include: Obtain a first reconstructed image to be corrected, the first reconstructed image including occlusion artifacts; Based on the first reconstructed image, iterative correction is performed, and a corrected second reconstructed image is obtained at the end of the iteration; wherein, in one iteration, the reconstructed image obtained in the previous iteration is processed to obtain a reconstruction domain artifact image, and the first reconstructed image is corrected based on the reconstruction domain artifact image to obtain the reconstructed image of the current iteration.

2. The method according to claim 1, characterized in that, The process of processing the reconstructed image obtained from the previous iteration to obtain the reconstructed domain artifact image includes: According to multiple preset angles, the reconstructed image obtained in the previous iteration is projected forward to obtain forward projected images at the multiple angles; Based on the forward projection images from the multiple angles, determine the projection domain artifact images from the multiple angles. The artifact images of the projection domain at the multiple angles are back-projected to obtain the artifact images of the reconstruction domain.

3. The method according to claim 2, characterized in that, The determination of projection domain artifact images based on the forward projection images from the multiple angles includes: Interpolate the artifact regions in the orthographic projection images at each angle to obtain the interpolated orthographic projection images at each angle; Based on the orthographic projection images at each angle and the interpolated orthographic projection images at each angle, the projection domain artifact images at each angle are determined.

4. The method according to claim 3, characterized in that, Before interpolating the artifact regions in the orthogonal projection images at each angle, the method further includes: Obtain an occlusion artifact image, which is used to indicate the position of the occlusion artifact in the projected image; Based on the occlusion artifact image, the artifact regions in the orthogonal projection image at each angle are determined.

5. The method according to claim 4, characterized in that, The acquisition of the occlusion artifact image includes: Acquire an empty field projection image, wherein the empty field projection image is a projection image in the absence of a scanned object; The open field projection image is segmented to obtain the shadowed and non-shadowed regions in the open field projection image; Based on the shadow and non-shadow regions in the open field projection image, the open field projection image is binarized to obtain the occlusion artifact image.

6. The method according to claim 3, characterized in that, The determination of projection domain artifact images at each angle based on the orthographic projection images at each angle and the interpolated orthographic projection images at each angle includes: The first difference image obtained by subtracting the orthographic projection image at each angle from the interpolated orthographic projection image at each angle is used as the projection domain artifact image at each angle; or, The second difference image obtained by subtracting the orthogonal projection image of each angle from the orthogonal projection image of each angle is determined as the projection domain artifact image of each angle.

7. The method according to claim 6, characterized in that, When the projection domain artifact images at each angle are the first difference image, the step of correcting the first reconstructed image based on the reconstruction domain artifact images to obtain the reconstructed image for this iteration includes: Add the first reconstructed image to the artifact image of the reconstructed domain to obtain the reconstructed image for this iteration; or, When the projection domain artifact images at each angle are second difference images, the step of correcting the first reconstructed image based on the reconstruction domain artifact images to obtain the reconstructed image for this iteration includes: Subtracting the first reconstructed image from the reconstructed domain artifact image yields the reconstructed image for this iteration.

8. The method according to claim 1, characterized in that, The method further includes: The iteration ends when the difference in pixel value between the reconstructed images obtained from two adjacent iterations is less than a preset pixel value threshold.

9. The method according to claim 1, characterized in that, The reconstructed image is a cone-beam computed tomography (CBCT) image, and the occlusion artifact is a beam blocking array (BSA) occlusion artifact.

10. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 9.

Images