Method, device, electronic device and storage medium for correcting image motion artifacts

Abstract

The application relates to a method and device for correcting image motion artifacts, an electronic device and a storage medium, wherein the method for correcting image motion artifacts comprises the following steps: acquiring an initial image to be processed, wherein the initial image is generated based on initial raw data; performing threshold segmentation processing on the initial image to generate a plurality of isosurface parts, and the plurality of isosurface parts constitute a first image; generating first raw data based on the first image, and generating second raw data based on the first raw data and the initial raw data; and generating a second image based on the second raw data, wherein the second image is an image after motion artifact correction. Through the application, the problem that image motion artifacts cannot be safely and stably corrected in the related art is solved, and the technical effect of safely and stably correcting image motion artifacts is achieved.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, apparatus, electronic device, and storage medium for correcting motion artifacts in images. Background Technology

[0002] In clinical diagnosis and radiotherapy, motion artifacts often appear in images due to movement. For example, during signal acquisition in computed tomography (CT) scans, bar-shaped or arc-shaped artifacts distributed along the phase encoding direction are caused by voluntary and involuntary movements of the human body or vascular pulsation. Their strength is related to the magnetic field strength, amplitude of movement, and direction of movement.

[0003] Current methods for dealing with motion artifacts include increasing the scanning angle, such as to 420°, to reduce the impact of the moving view. However, this approach undoubtedly increases the dose, thus exposing patients to significant radiation exposure. While AI-based solutions can achieve good results in images, they lack training data and theoretical foundations, and clinical images may produce uncontrollable results.

[0004] There is currently no effective solution to the problem of the inability to safely and stably correct motion artifacts in related technologies. Summary of the Invention

[0005] This embodiment provides a method, apparatus, electronic device, and storage medium for correcting image motion artifacts, in order to solve the problem that image motion artifacts cannot be corrected safely and stably in related technologies.

[0006] Firstly, this embodiment provides a method for correcting image motion artifacts, the method comprising:

[0007] Acquire an initial image to be processed, wherein the initial image is generated based on initial raw data;

[0008] The initial image is subjected to threshold segmentation to generate a first image;

[0009] First raw data is generated based on the first image, and second raw data is generated based on the first raw data and the initial raw data;

[0010] A second image is generated based on the second generated data, wherein the second image is an image after motion artifact correction.

[0011] In some embodiments, the threshold segmentation process performed on the initial image to generate the first image includes:

[0012] The initial image is segmented according to the segmentation threshold to generate multiple equal parts;

[0013] The same isopleth portion has the same display information, which includes the CT value of the initial image, and multiple isopleth portions constitute the first image.

[0014] In some embodiments, the segmentation threshold includes a first segmentation threshold and a second segmentation threshold;

[0015] The plurality of equivalent portions include a first equivalent portion, a second equivalent portion, and a third equivalent portion.

[0016] In some embodiments, the method further includes:

[0017] Before generating the first raw data based on the first image, the first image is sharpened.

[0018] In some embodiments, generating second-generation data based on the first-generation data and the initial-generation data includes:

[0019] Based on the boundary gradients of the first generated data and the initial data, the motion information of the initial generated data is determined;

[0020] The second data is generated based on the motion information of the initial data, the first data, and the initial data.

[0021] In some of these embodiments, the motion information includes motion intensity;

[0022] The step of generating the second data based on the motion information of the initial data, the first data, and the initial data includes:

[0023] Based on the motion intensity of the initial data, the second data is obtained by weighted summation of the first data and the initial data;

[0024] The weighting coefficient of the first data is positively correlated with the exercise intensity, while the weighting coefficient of the initial data is negatively correlated with the exercise intensity.

[0025] In some embodiments, generating second-generation data based on the first-generation data and the initial-generation data includes:

[0026] The initial raw data is registered and corrected based on the first raw data, and the second raw data is generated based on the registered and corrected initial raw data.

[0027] Secondly, this embodiment provides an apparatus for correcting image motion artifacts, the apparatus comprising:

[0028] The image acquisition module is used to acquire an initial image to be processed, wherein the initial image is generated based on initial raw data;

[0029] An image segmentation module is used to perform threshold segmentation processing on the initial image to generate a first image;

[0030] A data generation module is used to generate first raw data based on the first image, and to generate second raw data based on the first raw data and the initial raw data;

[0031] An image generation module is used to generate a second image based on the second generated data, wherein the second image is an image after motion artifact correction.

[0032] Thirdly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for correcting image motion artifacts as described in the first aspect above.

[0033] Fourthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the method for correcting image motion artifacts as described in the first aspect.

[0034] Compared with related technologies, the method for correcting motion artifacts in images provided in this embodiment first performs threshold segmentation on an initial image to obtain a first image. The first image has multiple isopleths, and these isopleths are uniform. Motion artifacts in the first image are reduced or eliminated, but some detailed features are lost. Then, first raw data is generated from the first image, and second raw data is generated based on the first raw data and the initial raw data. Finally, a second image with motion artifact correction is generated based on the second raw data, thereby reducing the influence of motion at the raw data level. The second image combines the advantages of the first and initial images, reducing motion artifacts in the initial image while preserving as much of its detailed features as possible. This solves the problem of not being able to safely and stably correct motion artifacts in related technologies, achieving a safe and stable technical effect for correcting motion artifacts in images.

[0035] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0036] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 This is a hardware structure block diagram of the terminal for the method of correcting image motion artifacts in this embodiment.

[0038] Figure 2 This is a flowchart of the method for correcting image motion artifacts in this embodiment.

[0039] Figure 3 This is a flowchart of a method for correcting image motion artifacts according to a preferred embodiment.

[0040] Figure 4 This is a structural block diagram of the device for correcting motion artifacts in images according to this embodiment. Detailed Implementation

[0041] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0042] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0043] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the method of correcting image motion artifacts in this embodiment. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0044] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the method for correcting image motion artifacts in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0045] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0046] This embodiment provides a method for correcting image motion artifacts. Figure 2 This is a flowchart of the method for correcting image motion artifacts in this embodiment. Figure 2 As shown, the process includes the following steps:

[0047] Step S210: Obtain the initial image to be processed, wherein the initial image is generated based on the initial raw data.

[0048] Specifically, the image processing device first acquires the initial image to be processed. The initial image is generated from unprocessed raw data; that is, the initial image refers to an image that has not undergone any processing and contains a certain degree of motion artifacts. The method in this embodiment aims to reduce the motion artifacts in the initial image.

[0049] Step S220: Threshold segmentation is performed on the initial image to generate multiple equal parts, and the multiple equal parts constitute the first image.

[0050] Specifically, after acquiring the initial image, the image processing device performs thresholding segmentation. Thresholding segmentation is a region-based image segmentation technique that categorizes pixels in an image into several classes. In this step, since the initial image contains various objects, a segmentation threshold can be determined based on these objects, and segmentation is then performed based on this threshold. For example, common medical images typically include bone, soft tissue, and air. Two segmentation thresholds can be determined based on these three objects, serving as the segmentation cutoff values. Based on these two thresholds, the initial image is then segmented into three equal parts, corresponding to bone, soft tissue, and air, respectively. It should be noted that soft tissue in different scanned areas has different types, so the two segmentation thresholds need to be adjusted appropriately according to the specific type of soft tissue during segmentation. In other words, thresholding segmentation makes each part of the initial image more uniform, thereby eliminating or reducing motion artifacts that may exist in each part of the image.

[0051] In one embodiment, the same equivalent portion has the same display information, which includes the CT values ​​of the initial image.

[0052] Specifically, the image processing equipment segments the initial image into multiple isopleths based on a predetermined segmentation threshold. Each isopleths share the same display information, which refers to the CT value. In threshold segmentation of medical images, different objects in the image have different CT values. Therefore, segmentation can be performed based on the differences in CT values ​​across different parts of the image. The segmentation threshold is a preset CT value. Generating multiple isopleths through threshold segmentation means first segmenting the image into multiple image parts based on the differences in CT values, and then unifying the CT values ​​within the same image part, thus obtaining multiple isopleths. By unifying the CT values ​​within the same image part, the image part becomes more uniform, thereby eliminating or reducing motion artifacts in each image part. After threshold segmentation, the initial image yields the first image.

[0053] Step S230: Generate first raw data based on the first image, and generate second raw data based on the first raw data and the initial raw data.

[0054] Specifically, in the previous step, the image processing device obtained a first image by thresholding the initial image. The first image has multiple isopleths, and each isopleth has the same display information, thus resulting in uniform display. Since motion artifacts in the first image are reduced or eliminated, it can be used as a reference image for subsequent image processing. Specifically, the first image is projected forward to generate first raw data, which constitutes the first image. Then, the initial raw data is combined with the first raw data to generate second raw data, which is used to generate the second image. The second image is the target image obtained by processing the initial image using the method flow in this embodiment.

[0055] It should be further explained that the first image obtained in step S220 is also an image with reduced or eliminated motion artifacts, but the CT values ​​of each image region are standardized, thus losing some detailed features and therefore cannot be used as the target image. This step, however, combines and compares the first raw data and the initial raw data, performing image correction at the raw data level. While reducing motion artifacts, it preserves as many detailed features as possible from the initial image, thereby obtaining a second image with reduced motion artifacts and some preserved detailed features.

[0056] Step S240: Generate a second image based on the second raw data, wherein the second image is an image after motion artifact correction.

[0057] Specifically, after obtaining the second raw data, the image processing device generates a second image using it. This second raw data is derived from both the first and initial raw data, combining the advantages of both. Therefore, the second image combines the strengths of both the first and initial images; for example, it has fewer motion artifacts and better image detail compared to the first image.

[0058] Through the above steps, the image processing device first performs threshold segmentation on the initial image to obtain a first image. The first image contains multiple isopleths, and these isopleths are uniform. Motion artifacts in the first image are reduced or eliminated, but some detailed features are lost in the process. Then, first raw data is generated from the first image, followed by second raw data generated based on the first raw data and the initial raw data. Finally, a second image with corrected motion artifacts is generated based on the second raw data, thus correcting motion effects at the raw data level. The second image combines the advantages of the first and initial images, correcting motion artifacts in the initial image while preserving as much of its detailed features as possible. This solves the problem of unsafe and stable correction of image motion artifacts in related technologies, achieving a safe and stable technical effect for correcting image motion artifacts.

[0059] In some embodiments, the segmentation threshold includes a first segmentation threshold and a second segmentation threshold; the plurality of equal parts include a first equal part, a second equal part, and a third equal part.

[0060] Specifically, in this embodiment, the segmented image mainly includes three types of objects, thus requiring the generation of a third isopleth segment. For example, when the initial image includes bone, soft tissue, and air, image segmentation is performed based on the CT values ​​between these objects. First, a bone threshold (first segmentation threshold) and an air threshold (second segmentation threshold) are determined, both being specific CT values ​​determined based on the objects. Generally, bone CT values ​​are greater than soft tissue CT values, and soft tissue CT values ​​are greater than air CT values. Therefore, the lower limit of the bone CT value range can be used as the bone threshold, and the upper limit of the air CT value range can be used as the air threshold. During threshold segmentation, image regions with CT values ​​greater than or equal to the bone threshold are classified as bone images, image regions with CT values ​​less than or equal to the air threshold are classified as air images, and image regions with CT values ​​less than the bone threshold but greater than the air threshold are classified as soft tissue images. Furthermore, the CT values ​​of bone images can be unified to a first CT value (obtaining the first isopleth portion), which is determined from the range of bone CT values; the CT values ​​of soft tissue images can be unified to a second CT value (obtaining the second isopleth portion), which is determined from the range of soft tissue CT values; and the CT values ​​of air images can be unified to zero (obtaining the third isopleth portion). This results in three uniform isopleth portions. Furthermore, the first and second CT values ​​are not fixed and can be adjusted according to the actual situation. For example, due to bone sclerosis, the bone edges of the body and skull are different, thus the CT values ​​of the two types of bones differ. Therefore, the first CT value can be adaptively modified according to the specific type of bone in the image (skull or body bone); similarly, the CT values ​​of muscle and fat may differ, so the second CT value can be adaptively modified according to the specific composition of the soft tissue in the image (muscle or fat).

[0061] In some embodiments, the method for correcting image motion artifacts, in step S230, generates first raw data based on a first image, and prior to this step, further includes sharpening the first image.

[0062] Specifically, the first image contains multiple isopleths, with boundaries between them. Image sharpening can enhance these boundaries, thereby increasing the contrast between the subsequent first-generation data and the initial data.

[0063] In some embodiments, step S230, generating second-generation data based on the first-generation data and the initial-generation data, specifically includes:

[0064] Step S231: Determine the motion information of the initial data based on the boundary gradients of the first generation data and the initial data;

[0065] Step S232: Generate second data based on the motion information of the initial data, the first data, and the initial data.

[0066] Specifically, the gradients along the channel direction of the first-generation data are compared with those of the initial-generation data to identify moving views. For example, if a view in the initial-generation data jumps between indices 50 and 500 along the channel direction, while a view in the first-generation data jumps between indices 20 and 470, then this view is misaligned, indicating that it is a moving view. Through this comparison method, moving view data can be identified within the initial-generation data, thus obtaining its motion information. Finally, based on this motion information, the second-generation data is generated using both the first and initial-generation data.

[0067] Furthermore, the motion information includes motion intensity. In step S232, second-generation data is generated based on the motion information from the initial data, the first-generation data, and the initial data. Specifically, this includes:

[0068] Based on the motion intensity of the initial data, the second data is obtained by weighted summation of the first data and the initial data;

[0069] Among them, the weight coefficient of the first data is positively correlated with the view motion intensity, while the weight coefficient of the initial data is negatively correlated with the view motion intensity.

[0070] Specifically, through the boundary gradient comparison described above, not only can we identify view data with motion in the initial raw data, but we can also determine the view motion intensity based on the amount of view misalignment. Therefore, motion information includes motion intensity. When generating the second raw data, the initial raw data and the first raw data are weighted and summed according to the motion intensity of the initial raw data to obtain the second raw data. The greater the view motion intensity, the more severe the motion artifacts in the initial image. Therefore, the second raw data needs to be closer to the first raw data (to better correct motion artifacts), hence the first raw data has a larger weight coefficient. Conversely, the smaller the view motion intensity, the less severe the motion artifacts in the initial image. Therefore, the second raw data needs to be closer to the initial raw data (to better preserve image detail features), hence the initial raw data has a larger weight coefficient. As described above, in actual operation, it is necessary to weigh the weights between the first raw data and the initial raw data based on the view motion intensity in the initial raw data. It should be noted that the above content has given a qualitative method for determining the weight coefficients, but the specific weight coefficients need to be determined according to the actual situation. Adaptive adjustments can be made even under the same actual situation; there is no single quantitative calculation method.

[0071] In the above embodiments, a method for generating second-generation data at the level of raw data is provided. In addition to obtaining second-generation data by weighted summation of first-generation data and initial-generation data, second-generation data can also be obtained by registering initial-generation data.

[0072] Therefore, in some other embodiments, step S230, generating second-generation data based on the first-generation data and the initial-generation data, specifically includes:

[0073] The initial dataset is registered and corrected based on the first dataset, and the second dataset is generated based on the registered and corrected initial dataset.

[0074] In this embodiment, registration correction refers to selecting a two-dimensional view composed of the view and channel directions of raw data, and then performing image registration on this two-dimensional view. Specifically, taking the two-dimensional view of the first raw data as the reference benchmark image, determining the offset vector between the two-dimensional view of the initial raw data and the two-dimensional view of the first raw data, and then using a non-rigid registration algorithm to non-rigidly register the two-dimensional view of the initial raw data to the space where the two-dimensional view of the first raw data is located, so as to obtain the two-dimensional view of the second raw data. Finally, a second raw data with less or no motion information is obtained, and through this second raw data, a second image with reduced or removed motion artifacts can be obtained. In this embodiment, mainly through the non-rigid registration algorithm, the view motion intensity in the initial raw data is reduced. It should be noted that the non-rigid registration algorithm in this embodiment can adopt common existing non-rigid registration algorithms, and the registration process is a common existing non-rigid registration process, so it will not be described in detail in this embodiment. The core of this embodiment is to use the phase diagram of the first raw data as the reference benchmark image and perform non-rigid registration on the phase diagram of the initial raw data, so as to obtain the second raw data with reduced motion intensity.

[0075] The following further illustrates the technical solutions in the present application through specific preferred embodiments.

[0076] Figure 3 It is a flowchart of the method for correcting image motion artifacts in this preferred embodiment. As Figure 3 shown, the preferred process of the method for correcting image motion artifacts includes the following steps:

[0077] Step S310, obtain the original raw data.

[0078] Step S320, generate an image with motion artifacts.

[0079] Specifically, generate an image with motion artifacts from the original raw data.

[0080] Step S330, threshold-segment the image into water, bone, and air, and perform image enhancement and sharpening.

[0081] Specifically, perform threshold segmentation and sharpening on the image with motion artifacts to enhance the contour clarity of the boundary, and obtain Image1 threshold-segmented into common water, bone, and air. The boundaries of the threshold segmentation are:

[0082] CT(bp >= bone threshold) = A

[0083] CT(bp = < air threshold) = 0

[0084] CT(air threshold < bp < bone threshold) = B

[0085] A represents the bone threshold, B represents the soft tissue threshold, and these three equations segment the image into equal parts of air, soft tissue, and bone structure, thereby removing artifacts that cause inhomogeneities in a uniform tissue. Specifically, bp represents the CT value of an object in the image. The first equation unifies the CT values ​​of image portions with CT values ​​greater than or equal to the bone threshold to A; the second equation unifies the CT values ​​of image portions with CT values ​​less than or equal to the air threshold to 0; and the third equation unifies the CT values ​​of image portions with CT values ​​greater than the air threshold and less than the bone threshold to B.

[0086] If the composition of the object to be reconstructed is known in advance, the thresholds A and B above can be adjusted appropriately. For example, the CT values ​​of muscle and fat may be different, so the threshold B may be different. Similarly, the CT values ​​of the bones in the body and the bones in the head may be different due to bone sclerosis, which may also lead to different thresholds A.

[0087] Thresholding can remove or reduce motion artifacts in the reconstructed material, serving as the gold standard for orthogonal projection. Image sharpening is also for high contrast at the back boundary of subsequent orthogonal projections.

[0088] Step S340: The projected image yields static raw data (equivalent to the first raw data).

[0089] Specifically, the reference static image above (the image after thresholding and sharpening, equivalent to the first image) is projected directly to obtain the reference static generated data: Projection = ReBp(Image1).

[0090] Step S350: Compare the boundary gradients of static raw data and original raw data.

[0091] Step S360: Identify view data with motion in the raw data.

[0092] Step S370: Reduce the weight of this view and reconstruct the image.

[0093] Specifically, in the above three steps, the gradient in the channel direction of the static raw data and the gradient in the channel direction of the original raw data are compared to determine which views are in motion, and the corrected raw data is obtained by weighting the two raw data.

[0094] For example, if the raw data has a gradient in a certain view direction, and there is a jump between index 50 and index 500 in the channel direction, while the static data has a jump between index 20 and index 470 in the channel direction, then this view is misaligned, which is a moving view.

[0095] If the static raw data is a and the original raw data is b, the weight coefficient is generated based on the exercise intensity determined above. The weight can be a formula related to the exercise intensity. Finally, the corrected c = a*weight + (1-weight)*b, where c is the corrected raw data (equivalent to the second raw data). The greater the exercise intensity, the greater the weight coefficient.

[0096] Finally, based on the corrected raw data, a reconstructed image with motion artifacts corrected (equivalent to the second image) is obtained.

[0097] It should be further explained that, in addition to obtaining the corrected raw data through the steps described above, the original raw data can also be registered and corrected based on reference static raw data to obtain the corrected raw data. Image registration involves treating the sine graph of the raw data as an image, finding the offset vectors between the two raw data sets, and finally obtaining a raw data set with minimal motion.

[0098] This embodiment also provides an apparatus for correcting image motion artifacts. This apparatus is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that perform a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0099] Figure 4 This is a structural block diagram of the device for correcting image motion artifacts in this embodiment. Figure 4 As shown, the device includes:

[0100] Image acquisition module 410 is used to acquire an initial image to be processed, wherein the initial image is generated based on initial raw data;

[0101] Image segmentation module 420 is used to perform threshold segmentation processing on the initial image to generate a first image;

[0102] The data generation module 430 is used to generate first raw data based on the first image, and to generate second raw data based on the first raw data and the initial raw data;

[0103] Image generation module 440 is used to generate a second image based on the second generated data, wherein the second image is an image after motion artifact correction.

[0104] Through the cooperation of the aforementioned modules, the image processing device first performs threshold segmentation on the initial image to obtain a first image. The first image contains multiple isopleths, and these isopleths are uniform. Motion artifacts in the first image are reduced or eliminated, but some detailed features are lost in the process. Then, first raw data is generated from the first image, followed by second raw data based on the first raw data and the initial raw data. Finally, a second image with corrected motion artifacts is generated based on the second raw data, thus correcting motion effects at the raw data level. The second image combines the advantages of both the first and initial images, correcting motion artifacts in the initial image while preserving as much of its detailed features as possible.

[0105] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0106] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0107] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0108] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0109] S1, Obtain the initial image to be processed, wherein the initial image is generated based on the initial raw data.

[0110] S2, perform threshold segmentation on the initial image to generate multiple equal parts, and the multiple equal parts constitute the first image.

[0111] S3, generate first raw data based on the first image, and generate second raw data based on the first raw data and the initial raw data.

[0112] S4, Generate a second image based on the second data, wherein the second image is an image after motion artifact correction.

[0113] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0114] Furthermore, in conjunction with the image motion artifact correction methods provided in the above embodiments, this embodiment can also provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the image motion artifact correction methods described in the above embodiments.

[0115] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0116] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0117] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0118] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

Claims

1. A method for correcting motion artifacts in an image, characterized in that, The method includes: Acquire an initial image to be processed, wherein the initial image is generated based on initial raw data; The initial image is subjected to threshold segmentation to generate multiple equal parts, and the multiple equal parts constitute the first image; First raw data is generated based on the first image, and second raw data is generated based on the first raw data and the initial raw data; The step of generating second-generation data based on the first-generation data and the initial-generation data includes: determining the motion information of the initial-generation data according to the boundary gradients of the first-generation data and the initial-generation data; and generating the second-generation data according to the motion information of the initial-generation data, the first-generation data, and the initial-generation data. The step of determining the motion information of the initial generated data based on the boundary gradients of the first generated data and the initial generated data includes: comparing the channel direction gradient of the first generated data and the channel direction gradient of the initial generated data, and determining that there is moving view data in the initial generated data based on the jumps of the first generated data in the channel direction and the jumps of the initial generated data in the channel direction, so as to obtain the motion information of the initial generated data. A second image is generated based on the second generated data, wherein the second image is an image after motion artifact correction.

2. The method for correcting image motion artifacts according to claim 1, characterized in that, The same isopleths have the same display information, which includes the CT values ​​of the initial image.

3. The method for correcting image motion artifacts according to claim 2, characterized in that, The segmentation thresholds include a first segmentation threshold and a second segmentation threshold; The plurality of equivalent portions include a first equivalent portion, a second equivalent portion, and a third equivalent portion.

4. The method for correcting image motion artifacts according to claim 1, characterized in that, The method further includes: Before generating the first raw data based on the first image, the first image is sharpened.

5. The method for correcting image motion artifacts according to claim 1, characterized in that, The motion information includes motion intensity; The step of generating the second data based on the motion information of the initial data, the first data, and the initial data includes: Based on the motion intensity of the initial data, the second data is obtained by weighted summation of the first data and the initial data; The weighting coefficient of the first raw data is correlated with the exercise intensity, and the weighting coefficient of the initial raw data is negatively correlated with the exercise intensity.

6. The method for correcting image motion artifacts according to any one of claims 1 to 4, characterized in that, The process of generating second birth data based on the first birth data and the initial birth data includes: The initial raw data is registered and corrected based on the first raw data, and the second raw data is generated based on the registered and corrected initial raw data.

7. An apparatus for correcting motion artifacts in images, characterized in that, The device includes: The image acquisition module is used to acquire an initial image to be processed, wherein the initial image is generated based on initial raw data; An image segmentation module is used to perform threshold segmentation processing on the initial image to generate a first image; A data generation module is used to generate first raw data based on the first image, and to generate second raw data based on the first raw data and the initial raw data; The data generation module is further configured to determine the motion information of the initial data based on the boundary gradient of the first generated data and the initial generated data; and generate the second generated data based on the motion information of the initial data, the first data, and the initial data. The data generation module is further configured to compare the channel direction gradient of the first generated data with the channel direction gradient of the initial generated data, and determine that there is moving view data in the initial generated data based on the jump in the channel direction of the first generated data and the jump in the channel direction of the initial generated data, so as to obtain the motion information of the initial generated data. An image generation module is used to generate a second image based on the second generated data, wherein the second image is an image after motion artifact correction.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method for correcting image motion artifacts as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for correcting image motion artifacts as described in any one of claims 1 to 6.

Images