A magnetic resonance abdominal respiration artifact elimination system

Abstract

The present application relates to the technical field of image restoration, and particularly relates to a system for eliminating respiratory artifacts in abdominal magnetic resonance, which can realize the following steps through mutual cooperation between multiple modules: obtaining an image to be de-artifacted, and screening out suspected artifact regions from the image to be de-artifacted; determining artifact performance characteristic values corresponding to the suspected artifact regions according to gradient distribution and grayscale distribution in the suspected artifact regions and the shape of each suspected artifact region; screening out target artifact regions, and determining initial blurring angles and initial blurring sizes corresponding to each target artifact region; correcting the initial blurring angles and the initial blurring sizes corresponding to each target artifact region; and de-artifacting the target artifact regions according to a blurring kernel of the target blurring angles and the target blurring sizes, thereby realizing de-artifacting of the image to be de-artifacted, and improving the accuracy of artifact region identification and the rationality of de-artifacting.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image restoration, and particularly relates to an abdominal magnetic resonance respiration artifact elimination system. BACKGROUND

[0002] With the development of science and technology, the application of image restoration technology is more and more extensive, for example, it can be applied to the elimination of respiratory motion artifacts in abdominal magnetic resonance images. At present, when eliminating artifacts, the method commonly used is: through a blur kernel, the artifact area in the image is eliminated to realize image restoration. In actual situations, the target area is often identified according to the difference in gray value, so the artifact area in the image can be identified according to the difference in gray value.

[0003] However, when identifying the respiratory motion artifact area in the abdominal magnetic resonance image according to the difference in gray value, the following technical problems often exist:

[0004] The gray difference between the respiratory motion artifact and part of the normal tissue area is often not large, so when identifying the respiratory motion artifact area in the abdominal magnetic resonance image, if only the difference in gray value is considered, it is often possible to cause misjudgment of the artifact pixel point, thereby causing poor accuracy of artifact area identification, and further causing poor rationality of artifact elimination. SUMMARY

[0005] In order to solve the technical problem of poor rationality of artifact elimination caused by poor accuracy of artifact area identification, the present application provides an abdominal magnetic resonance respiration artifact elimination system.

[0006] In a first aspect, the present application provides an abdominal magnetic resonance respiration artifact elimination system, which comprises:

[0007] An acquisition and screening module is configured to acquire a to-be-artifact-eliminated image and screen a suspected artifact area from the to-be-artifact-eliminated image;

[0008] An artifact performance feature value determination module is configured to determine an artifact performance feature value corresponding to each suspected artifact area according to the gradient distribution and the gray distribution in each suspected artifact area and the shape of each suspected artifact area;

[0009] An initial parameter determination module is configured to screen a target artifact area from all suspected artifact areas according to the artifact performance feature value and determine an initial blur angle and an initial blur size corresponding to each target artifact area;

[0010] The parameter correction module is configured to correct the initial blur angle and the initial blur size corresponding to each target artifact region according to a historical abdominal magnetic resonance image corresponding to the same breathing phase as the to-be-artifact-removed image, to obtain a target blur angle and a target blur size corresponding to each target artifact region.

[0011] The artifact removal module is configured to remove artifacts from the target artifact region according to the blur kernel of the target blur angle and the target blur size, thereby achieving artifact removal of the to-be-artifact-removed image.

[0012] In combination with the first aspect, in a possible implementation manner, the suspected artifact region is selected from the to-be-artifact-removed image, including:

[0013] The initial blur artifact feature value corresponding to each pixel point in the to-be-artifact-removed image is determined according to the gradient value and the grayscale distribution of each pixel point in the to-be-artifact-removed image.

[0014] If the initial blur artifact feature value corresponding to the pixel point is greater than a preset blur artifact threshold, the pixel point is determined as a suspected artifact edge pixel point.

[0015] The suspected artifact region is constructed according to the suspected artifact edge pixel point in the to-be-artifact-removed image.

[0016] In combination with the first aspect, in a possible implementation manner, the initial blur artifact feature value corresponding to each pixel point in the to-be-artifact-removed image is constructed according to the gradient value and the grayscale distribution of each pixel point in the to-be-artifact-removed image, including:

[0017] Any pixel point in the to-be-artifact-removed image is determined as a marker pixel point, and the initial blur artifact feature value corresponding to the marker pixel point is determined according to the gradient value corresponding to the marker pixel point and the entropy value of the grayscale value of all pixel points in a preset neighborhood corresponding to the marker pixel point.

[0018] In combination with the first aspect, in a possible implementation manner, the artifact performance feature value corresponding to each suspected artifact region is determined according to the gradient distribution and the grayscale distribution in each suspected artifact region and the shape of each suspected artifact region, including:

[0019] The edge blur dynamic value corresponding to each suspected artifact region is determined according to the gradient value and the grayscale value of all edge pixel points in each suspected artifact region.

[0020] The shape feature value corresponding to each suspected artifact region is determined according to the minimum circumscribed rectangle of each suspected artifact region and the gradient direction of all pixel points in each suspected artifact region.

[0021] normalizing the product between the edge blur dynamic value and the shape feature value corresponding to each suspected artifact region to obtain an artifact performance feature value corresponding to each suspected artifact region.

[0022] In a possible implementation manner of the first aspect, the edge blur dynamic value corresponding to each suspected artifact region is determined according to the gradient value and the gray value of each edge pixel point corresponding to each suspected artifact region.

[0023] The difference absolute value between the gradient values of each two edge pixel points on the marked suspected artifact region is determined as a target gradient difference, to obtain a target gradient difference set corresponding to the marked suspected artifact region.

[0024] The entropy value of the gray values of all pixel points in the preset neighborhood corresponding to each edge pixel point on the marked suspected artifact region is determined as a gray representative entropy value corresponding to each edge pixel point on the marked suspected artifact region.

[0025] The edge blur dynamic value corresponding to the marked suspected artifact region is determined according to the maximum target gradient difference in the target gradient difference set corresponding to the marked suspected artifact region, the mean value of the gradient values of all edge pixel points on the marked suspected artifact region, and the mean value of the gray representative entropy values of all edge pixel points on the marked suspected artifact region.

[0026] In a possible implementation manner of the first aspect, the shape feature value corresponding to each suspected artifact region is determined according to the minimum circumscribed rectangle of each suspected artifact region and the gradient direction of each pixel point in each suspected artifact region.

[0027] The angle corresponding to the gradient direction of each pixel point in each suspected artifact region is determined as a gradient direction angle of each pixel point in each suspected artifact region.

[0028] The shape feature value corresponding to each suspected artifact region is determined according to the aspect ratio of the minimum circumscribed rectangle of each suspected artifact region and the standard deviation of the gradient direction angles of all pixel points in each suspected artifact region.

[0029] In a possible implementation manner of the first aspect, the target artifact region is screened from all suspected artifact regions according to the artifact performance feature value.

[0030] If the artifact performance feature value corresponding to the suspected artifact region is greater than a preset artifact performance threshold, the suspected artifact region is determined as the target artifact region.

[0031] With reference to the first aspect, in a possible implementation manner, the determining of the initial blurring angle and the initial blurring size corresponding to each target artifact region comprises:

[0032] performing a fast Fourier transform on each target artifact region to obtain a Fourier spectrum corresponding to each target artifact region;

[0033] detecting a direction of a stripe in the Fourier spectrum corresponding to each target artifact region by Radon transform to obtain the initial blurring angle and the initial blurring size corresponding to each target artifact region.

[0034] With reference to the first aspect, in a possible implementation manner, the correcting of the initial blurring angle and the initial blurring size corresponding to each target artifact region according to the historical abdominal magnetic resonance images corresponding to the same breathing phase as the to-be-artifact-removed image to obtain the target blurring angle and the target blurring size corresponding to each target artifact region comprises:

[0035] determining any one target artifact region in the to-be-artifact-removed image as a to-be-determined artifact region, and determining each historical abdominal magnetic resonance image corresponding to the same breathing phase as the to-be-artifact-removed image as a reference image;

[0036] identifying a historical artifact region from each reference image, and determining an initial blurring angle and an initial blurring size corresponding to each historical artifact region;

[0037] determining a target blurring angle and a target blurring size corresponding to the to-be-determined artifact region according to the initial blurring angle and the initial blurring size corresponding to each historical artifact region in each reference image and the initial blurring angle and the initial blurring size corresponding to the to-be-determined artifact region.

[0038] With reference to the first aspect, in a possible implementation manner, the determining of the target blurring angle and the target blurring size corresponding to the to-be-determined artifact region according to the initial blurring angle and the initial blurring size corresponding to each historical artifact region in each reference image and the initial blurring angle and the initial blurring size corresponding to the to-be-determined artifact region comprises:

[0039] determining an angle reference weight corresponding to each reference image according to a breathing standard degree of a breathing cycle to which each reference image belongs, a mean value and a standard deviation of the initial blurring angle corresponding to all historical artifact regions in each reference image, and the initial blurring angle corresponding to the to-be-determined artifact region;

[0040] According to the respiratory standard degree of the respiratory cycle to which each reference image belongs, the mean and standard deviation of the initial blur size corresponding to all historical artifact regions in each reference image, and the initial blur size corresponding to the to-be-determined artifact region, a size reference weight corresponding to each reference image is determined;

[0041] According to the angle reference weight corresponding to each reference image and the mean of the initial blur angle corresponding to all historical artifact regions in the reference image, and the initial blur angle corresponding to the to-be-determined artifact region, a target blur angle corresponding to the to-be-determined artifact region is determined.

[0042] According to the size reference weight corresponding to each reference image and the mean of the initial blur size corresponding to all historical artifact regions in the reference image, and the initial blur size corresponding to the to-be-determined artifact region, a target blur size corresponding to the to-be-determined artifact region is determined.

[0043] In a second aspect, the present application provides an abdominal magnetic resonance breathing artifact elimination method implemented by an abdominal magnetic resonance breathing artifact elimination system, and the method comprises the following steps:

[0044] An image to be artifact-eliminated is acquired, and a suspected artifact region is screened from the image to be artifact-eliminated;

[0045] According to the gradient distribution and the gray scale distribution in each suspected artifact region, and the shape of each suspected artifact region, an artifact performance characteristic value corresponding to each suspected artifact region is determined.

[0046] According to the artifact performance characteristic value, a target artifact region is screened from all suspected artifact regions, and an initial blur angle and an initial blur size corresponding to each target artifact region are determined.

[0047] According to a historical abdominal magnetic resonance image corresponding to the same respiratory phase as the image to be artifact-eliminated, which is acquired in advance, the initial blur angle and the initial blur size corresponding to each target artifact region are corrected to obtain a target blur angle and a target blur size corresponding to each target artifact region.

[0048] According to the blur kernel of the target blur angle and the target blur size, the artifact elimination of the target artifact region is performed, and the artifact elimination of the image to be artifact-eliminated is realized.

[0049] In a third aspect, a server is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the above-mentioned abdominal magnetic resonance breathing artifact elimination method.

[0050] In a fourth aspect, a computer program product is provided, which comprises computer program code, which, when executed on a computer, causes the computer to perform the above-mentioned abdominal magnetic resonance breathing artifact elimination method.

[0051] In a fifth aspect, a computer-readable storage medium is provided, which stores computer program code, which, when executed on a computer, causes the computer to perform the above-mentioned abdominal magnetic resonance breathing artifact elimination method.

[0052] The present application has the following beneficial effects:

[0053] The abdominal magnetic resonance breathing artifact elimination system of the present application realizes the identification of the target artifact region and the artifact elimination of the image to be artifact-eliminated, solves the technical problem of poor rationality of artifact elimination due to poor accuracy of artifact region identification, and improves the accuracy of artifact region identification and the rationality of artifact elimination. Specifically, the present application quantifies the artifact performance characteristic value corresponding to each suspected artifact region by analyzing the shape of the suspected artifact region and the gradient distribution and gray scale distribution therein, thereby realizing the identification of the target artifact region and improving the accuracy of artifact region identification, so as to improve the rationality of artifact elimination. Secondly, by analyzing the historical abdominal magnetic resonance image corresponding to the same breathing stage as the image to be artifact-eliminated, the initial blur angle and the initial blur size corresponding to each target artifact region are corrected, which to some extent improves the rationality of the setting of the blur angle and the blur size, and further improves the rationality of artifact elimination. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0055] Figure 1 FIG. 1 is a structural schematic diagram of an abdominal magnetic resonance breathing artifact elimination system of the present application;

[0056] Figure 2 FIG. 2 is a flowchart of an abdominal magnetic resonance breathing artifact elimination method of the present application;

[0057] Figure 3 FIG. 3 is a structural schematic diagram of a computer device of the present application. DETAILED DESCRIPTION

[0058] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the specific implementation, structure, features and effects of the technical solutions proposed according to the present application are described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0060] In actual cases, the severity of respiratory artifacts in different tissue structure regions of abdominal magnetic resonance images is often directly related to the motion amplitude of the region, and the motion amplitude of different regions is often different. For example, the motion amplitude of the top of the liver close to the diaphragm is often larger, and the motion amplitude of the kidney away from the diaphragm is often smaller. Therefore, it is necessary to divide the image into different artifact regions, and to adaptively set the blur direction and blur size for different respiratory artifact regions caused by respiratory motion, and then estimate the local blur kernel, and perform dynamic non-uniform deblurring operation on different tissue regions with different blur amounts, to effectively eliminate respiratory artifacts.

[0061] Reference Figure 1 Fig. 1 shows a structural schematic diagram of an abdominal magnetic resonance respiratory artifact elimination system according to the present application. The abdominal magnetic resonance respiratory artifact elimination system comprises:

[0062] The acquisition and screening module 101 is configured to acquire a to-be-artifact-eliminated image, and screen a suspected artifact region from the to-be-artifact-eliminated image.

[0063] The to-be-artifact-eliminated image can be an abdominal magnetic resonance image to be subjected to artifact elimination.

[0064] As an example, the acquisition and screening module 101 specifically implements the following steps:

[0065] Firstly, a to-be-artifact-eliminated image is acquired.

[0066] For example, the abdominal magnetic resonance image of a patient to be detected can be acquired by a magnetic resonance imaging (MRI) technology, as the to-be-artifact-eliminated image, wherein the patient to be detected can be a patient to be subjected to an abdominal magnetic resonance examination.

[0067] Secondly, according to the gradient value and the gray distribution of each pixel point in the to-be-artifact-eliminated image, the initial value of the blur artifact feature corresponding to each pixel point in the to-be-artifact-eliminated image is determined.

[0068] For example, any one pixel point in the to-be-artifact-removed image can be determined as a marked pixel point, and the gradient value corresponding to the marked pixel point and the entropy value of the gray values of all pixel points in the preset neighborhood corresponding to the marked pixel point are determined as the initial value of the blur artifact feature corresponding to the marked pixel point.

[0069] The preset neighborhood can be a preset neighborhood, which can be a 3*3 neighborhood.

[0070] For example, the formula corresponding to the initial value of the blur artifact feature corresponding to the marked pixel point can be:

[0071]

[0072] The initial value of the blur artifact feature corresponding to the marked pixel point is denoted as A The normalization function is denoted as p The entropy value of the gray values of all pixel points in the preset neighborhood corresponding to the marked pixel point is denoted as The exponential function with a natural constant as the base is denoted as D The gradient value corresponding to the marked pixel point is denoted as

[0073] It should be noted that in actual cases, the blur area generated by the respiratory artifact often presents a low edge gradient in the MRI image, and the high entropy of the gray values in the area often leads to a gray disorder. Therefore, when A The greater the value is, the more likely the marked pixel point is an edge point of the blur artifact.

[0074] In the third step, if the initial value of the blur artifact feature corresponding to the pixel point is greater than a preset blur artifact threshold, the pixel point is determined as a suspected artifact edge pixel point.

[0075] The preset blur artifact threshold can be a preset threshold, which can be artificially set based on actual scenarios. For example, the preset blur artifact threshold can be 0.5.

[0076] It should be noted that the suspected artifact edge pixel point can be a coarsely screened artifact edge pixel point.

[0077] In the fourth step, a suspected artifact area is constructed according to the suspected artifact edge pixel points in the to-be-artifact-removed image.

[0078] The suspected artifact area can be an area surrounded by the suspected artifact edge pixel points.

[0079] ​​The artifact performance feature value determination module 102 is configured to determine the artifact performance feature value corresponding to each suspected artifact region according to the gradient distribution and the grayscale distribution in each suspected artifact region, and the shape of each suspected artifact region.

[0080] As an example, determining the artifact performance feature value corresponding to each suspected artifact region can include the following steps:

[0081] In the first step, determining the edge blur dynamic value corresponding to each suspected artifact region according to the gradient value and the grayscale value of each edge pixel point on the suspected artifact region can include the following sub-steps:

[0082] In the first sub-step, any suspected artifact region in the image to be artifact-removed is determined as a marked suspected artifact region, and the absolute value of the difference between the gradient values corresponding to each two edge pixel points on the marked suspected artifact region is determined as a target gradient difference, thereby obtaining a target gradient difference set corresponding to the marked suspected artifact region.

[0083] In the second sub-step, the entropy value of the grayscale value of all pixel points in the preset neighborhood corresponding to each edge pixel point on the marked suspected artifact region is determined as the grayscale representative entropy value corresponding to each edge pixel point on the marked suspected artifact region.

[0084] In the third sub-step, the edge blur dynamic value corresponding to the marked suspected artifact region is determined according to the maximum target gradient difference in the target gradient difference set corresponding to the marked suspected artifact region, the mean value of the gradient values corresponding to all edge pixel points on the marked suspected artifact region, and the mean value of the grayscale representative entropy values corresponding to all edge pixel points on the marked suspected artifact region.

[0085] For example, the formula for determining the edge blur dynamic value corresponding to the marked suspected artifact region can be:

[0086] ;

[0087] wherein, B is the edge blur dynamic value corresponding to the marked suspected artifact region. S is the mean value of the grayscale representative entropy values corresponding to all edge pixel points on the marked suspected artifact region. is an exponential function with a natural constant as the base. H is the maximum target gradient difference in the target gradient difference set corresponding to the marked suspected artifact region. h is the mean value of the gradient values corresponding to all edge pixel points on the marked suspected artifact region.

[0088] It should be noted that, in reality, within the physical context of MRI breathing artifacts, the "blurred dynamics" of the region's edges are often essentially the degree of edge signal diffusion caused by respiratory motion. The edge gradient values ​​of areas with artifacts are often relatively lower than those of clear, normal areas. The degree to which the same region is affected by breathing is often consistent, and the grayscale distribution of normal edges is often regular, while the pixel grayscale distribution in areas with artifacts often becomes disordered. Therefore, when... B The larger the value, the more obvious the artifacts may be at the boundary of the suspected artifact region, and the more likely the suspected artifact region is to be a real artifact region.

[0089] The second step, determining the shape feature value corresponding to each suspected artifact region based on the minimum bounding rectangle of each suspected artifact region and the gradient direction corresponding to all pixels within each suspected artifact region, may include the following sub-steps:

[0090] The first sub-step is to determine the gradient direction angle corresponding to each pixel in each suspected artifact region.

[0091] The second sub-step involves determining the shape feature value corresponding to each suspected artifact region based on the aspect ratio of the minimum bounding rectangle of each suspected artifact region and the standard deviation of the gradient direction angles corresponding to all pixels within each suspected artifact region.

[0092] For example, the formula for determining the shape feature value corresponding to a suspected artifact region can be:

[0093] ;

[0094] in, It is the first in the image to be artifact-removed i The shape feature value corresponding to the suspected artifact region. i It is the sequence number of the suspected artifact region in the image to be artifact-removed. The first in the image to be artifact-removed i The aspect ratio of the smallest bounding rectangle of a suspected artifact region. It is an exponential function with the natural constant as its base. The first in the image to be artifact-removed i The standard deviation of the gradient direction angles of all pixels within a suspected artifact region.

[0095] It should be noted that in reality, the essence of respiratory artifacts is often continuous blurring caused by the periodic movement of organs. Therefore, they should typically appear as stripes extending along the direction of movement. Furthermore, since respiratory artifacts are produced by periodic movement, the blurring direction within the same artifact area should be highly consistent, while the direction of the normal tissue edges is often more random. The greater the value of the first parameter is, the more likely the first suspected artifact region is a real artifact region. i The greater the value of the second parameter is, the more likely the first suspected artifact region is a long strip. The smaller the value of the third parameter is, the more consistent the blur direction in the first suspected artifact region is. i The greater the value of the fourth parameter is, the more likely the first suspected artifact region is a real artifact region. The greater the value of the fifth parameter is, the more likely the first suspected artifact region is a long strip. i The greater the value of the sixth parameter is, the more consistent the blur direction in the first suspected artifact region is.

[0096] In the third step, the product of the edge blur dynamic value and the shape feature value corresponding to each suspected artifact region is normalized to obtain an artifact performance feature value corresponding to each suspected artifact region.

[0097] It should be noted that the greater the artifact performance feature value corresponding to the suspected artifact region is, the more likely the suspected artifact region is a real artifact region.

[0098] The initial parameter determination module 103 is configured to filter out target artifact regions from all suspected artifact regions according to the artifact performance feature value, and determine an initial blur angle and an initial blur size corresponding to each target artifact region.

[0099] As an example, the initial parameter determination module 103 specifically implements the following steps:

[0100] In the first step, if the artifact performance feature value corresponding to the suspected artifact region is greater than a preset artifact performance threshold, the suspected artifact region is determined as a target artifact region.

[0101] The preset artifact performance threshold can be a threshold set in advance, which can be manually set based on the actual scene. For example, the preset artifact performance threshold can be 0.7.

[0102] In the second step, a fast Fourier transform is performed on each target artifact region to obtain a Fourier spectrum corresponding to each target artifact region.

[0103] In the third step, the direction of the stripe in the Fourier spectrum corresponding to each target artifact region is detected by Radon transform to obtain an initial blur angle and an initial blur size corresponding to each target artifact region.

[0104] The initial blur angle and the initial blur size can be the blur angle and the blur size obtained by Radon transform.

[0105] It should be noted that for each target artifact region, the blur kernel can be estimated by analyzing the image block of the region. Since the respiratory artifact generated in the MRI image due to respiration belongs to linear motion blur, its mathematical model is "convolution of the original clear image and the blur kernel". According to the "convolution theorem" of Fourier transform, the frequency spectrum of the clear image and the frequency spectrum of the blur kernel will be multiplied, and the Fourier frequency spectrum of the rectangular blur kernel often presents parallel zero-value stripes, which are physically corresponding to the frequency components of the blur direction, which are often suppressed. For each target artifact region, a frequency domain analysis algorithm can be used on its image block to analyze its Fourier frequency spectrum. The blur often causes the frequency spectrum to have parallel zero-value stripes, the direction of the stripes is perpendicular to the blur direction, and horizontal vibration blur often causes the frequency spectrum to have vertical zero-value stripes; the interval of the stripes is inversely proportional to the blur size, the longer the blur size (the greater the displacement within the exposure time), the wider the interval of the stripes (corresponding to lower frequency components being suppressed). The direction of these stripes can be detected by Radon transform, and the blur angle and blur size of the region can be accurately calculated.

[0106] The parameter correction module 104 is configured to correct the initial blur angle and the initial blur size corresponding to each target artifact region according to the historical abdominal magnetic resonance image corresponding to the same respiratory phase as the to-be-artifact-removed image, to obtain the target blur angle and the target blur size corresponding to each target artifact region.

[0107] In actual situations, in order to facilitate the division of the respiratory phase, when the abdominal magnetic resonance image is collected, the patient can be asked to use the 448 breathing method to breathe, and the respiratory cycle of the patient using the 448 breathing method to breathe can be divided into a plurality of respiratory phases. The number of respiratory phases can be pre-set, and can be equal to 3. For example, if the number of respiratory phases is 3, there can be 3 respiratory phases, which can be an inspiration phase, a breath-holding phase, and an expiration phase. The inspiration phase is often a phase in which the patient inhales a deep breath through the nose or mouth. The breath-holding phase is often a phase in which the patient stops breathing after inhaling a deep breath. The expiration phase is often a phase in which the patient exhales the inhaled gas. The historical abdominal magnetic resonance image can be an abdominal magnetic resonance image of the patient to be detected collected in the same respiratory phase by a magnetic resonance imaging technique before the to-be-artifact-removed image is collected.

[0108] As an example, correcting the initial blur angle and the initial blur size corresponding to each target artifact region to obtain the target blur angle and the target blur size corresponding to each target artifact region can include the following steps:

[0109] In a first step, any one target artifact region in the to-be-artifact-eliminated image is determined as a to-be-determined artifact region, and each historical abdominal magnetic resonance image corresponding to the same breathing phase as the to-be-artifact-eliminated image is determined as a reference image.

[0110] In a second step, a historical artifact region is identified from each reference image, and an initial blurring angle and an initial blurring size corresponding to each historical artifact region are determined.

[0111] It should be noted that the identification method of the historical artifact region can be the same as the identification method of the target artifact region, which will not be described here. The acquisition method of the initial blurring angle and the initial blurring size corresponding to the historical artifact region can be the same as the acquisition method of the initial blurring angle and the initial blurring size corresponding to the target artifact region, which will not be described here.

[0112] In a third step, a target blurring angle and a target blurring size corresponding to the to-be-determined artifact region are determined according to the initial blurring angle and the initial blurring size corresponding to each historical artifact region in each reference image and the initial blurring angle and the initial blurring size corresponding to the to-be-determined artifact region.

[0113] In actual situations, the smaller the difference between the blurring parameters of the to-be-determined artifact region and the blurring parameters of the reference image, the more the reference basis of the reference image from the same breathing motion pattern is established. And the more stable the patient's breathing (without abnormal motion in any direction, such as coughing and shallow and rapid breathing) when the reference image is collected, the more the main direction can truly reflect the normal motion direction of the breathing phase, and the more the blurring kernel parameters of the to-be-determined artifact region are determined. The higher the breathing standard degree of the breathing cycle to which the reference image belongs, the more similar the breathing situation of the breathing cycle to which the reference image belongs and the breathing situation of the breathing cycle to which the to-be-artifact-eliminated image belongs, and the more the reference image has reference value.

[0114] For example, determining the target blurring angle and the target blurring size corresponding to the to-be-determined artifact region can include the following sub-steps:

[0115] In a first sub-step, according to the breathing standard degree of the breathing cycle to which each reference image belongs, the mean and standard deviation of the initial blurring angle corresponding to all historical artifact regions in each reference image, and the initial blurring angle corresponding to the to-be-determined artifact region, an angle reference weight corresponding to each reference image is determined.

[0116] The respiratory standard of the reference image's respiratory cycle can be characterized by the similarity between the respiratory signals of the patient to be tested within the reference image's respiratory cycle and the respiratory signals of the patient to be tested within the same respiratory cycle as the image to be artifact-removed. The similarity between different respiratory signals can be obtained using the Dynamic Time Warping (DTW) algorithm.

[0117] For example, the formula for determining the angle reference weight corresponding to the reference image can be:

[0118] ;

[0119] ;

[0120] in, It is the first j Angle reference weights corresponding to each reference image. j It is the reference image number. It is the first j Initial weights for the angles corresponding to each reference image. G It is the sum of the initial angle weights corresponding to all reference images. It is an absolute value function. It is the initial blur angle corresponding to the undetermined artifact region. It is the first j The mean of the initial blur angles corresponding to all historical artifact regions in the reference image can characterize the first... j The mainstream blur angle of a reference image. It is the first j The standard deviation of the initial blur angles corresponding to all historical artifact regions in a reference image. It is a pre-set factor greater than 0, mainly used to prevent the denominator from being 0, and it can be 0.0001. It is the first j The standard degree of breathing for the respiratory cycle to which each reference image belongs.

[0121] It should be noted that when The smaller the value, the closer the initial blur angle corresponding to the undetermined artifact region is to the first value. j The prevailing blur angle of the first reference image often indicates the first... j The more reference images there are, the more angularly relevant the region of artifact to be determined. The smaller the size, the more likely it is to indicate the first j The more stable the patient's breathing is during the acquisition of the reference image, the more accurately its mainstream direction tends to reflect the normal direction of movement during the respiratory phase, and the more reliable the determination of the fuzzy kernel parameters of the aforementioned undetermined artifact region becomes. The larger the value, the more likely it is to indicate the first jThe more similar the breathing pattern of the reference image to the breathing pattern of the image to be artifact-removed during its breathing cycle, the better the indication of the first reference image's breathing pattern. j The more reference images there are, the more valuable they are. Therefore, when The larger the value, the more likely it is to indicate the first j The higher the angular reference value of the first reference image for the region of artifact to be determined, the more likely it is that the first reference image is more relevant. j The mainstream blur angle of a reference image can, to a certain extent, represent the blur angle of the undetermined artifact region.

[0122] The second sub-step involves determining the size reference weight for each reference image based on the respiratory standard degree of each pre-acquired respiratory cycle, the mean and standard deviation of the initial blur size corresponding to all historical artifact regions in each reference image, and the initial blur size corresponding to the aforementioned undetermined artifact regions.

[0123] For example, the formula for determining the size reference weight corresponding to the reference image can be:

[0124] ;

[0125] ;

[0126] in, It is the first j The size reference weights corresponding to each reference image. j It is the reference image number. It is the first j Initial weights for the dimensions of each reference image. It is the sum of the initial weights of the dimensions corresponding to all reference images. It is an absolute value function. d It is the initial blur size corresponding to the undetermined artifact region. It is the first j The mean of the initial blur size corresponding to all historical artifact regions in the reference image can characterize the first... j The mainstream blur size of a reference image. It is the first j The standard deviation of the initial blur size corresponding to all historical artifact regions in a reference image. It is a pre-set factor greater than 0, mainly used to prevent the denominator from being 0, and it can be 0.0001. It is the first j The standard degree of breathing for the respiratory cycle to which each reference image belongs.

[0127] It should be noted that when The larger the value, the more likely it is to indicate the first jThe higher the size reference of the reference image to the size of the to-be-determined artifact region, the more likely the main blur size of the reference image represents the blur size of the to-be-determined artifact region to a certain extent. j

[0128] The third sub-step is to determine the target blur angle corresponding to the to-be-determined artifact region according to the average of the initial blur angles corresponding to all the historical artifact regions in each reference image and the initial blur angle corresponding to the to-be-determined artifact region.

[0129] For example, the formula for determining the target blur angle corresponding to the to-be-determined artifact region can be:

[0130] ;

[0131] wherein, is the target blur angle corresponding to the to-be-determined artifact region. and . is the weight of , which can be 0.7. is the weight of , which can be 0.3. is the initial blur angle corresponding to the to-be-determined artifact region. N is the number of reference images. j is the serial number of the reference image. is the angle reference weight corresponding to the i-th reference image. j is the average of the initial blur angles corresponding to all the historical artifact regions in the i-th reference image. j

[0132] The fourth sub-step is to determine the target blur size corresponding to the to-be-determined artifact region according to the average of the initial blur sizes corresponding to all the historical artifact regions in each reference image and the initial blur size corresponding to the to-be-determined artifact region.

[0133] For example, the formula for determining the target blur size corresponding to the to-be-determined artifact region can be:

[0134] ;

[0135] wherein, Q is the target blur size corresponding to the to-be-determined artifact region. and . is the weight of d , which can be 0.7. is the weight of , which can be 0.3.​​​d is the initial blur size corresponding to the to-be-determined artifact region. N is the number of reference images. j is the sequence number of the reference image. is the size reference weight corresponding to the j th reference image. is the initial blur size corresponding to all historical artifact regions in the j th reference image.

[0136] The artifact elimination module 105 is configured to perform artifact elimination on the target artifact region according to the blur kernel of the target blur angle and the target blur size, thereby achieving artifact elimination of the to-be-artifact-eliminated image.

[0137] As an example, any one target artifact region in the to-be-artifact-eliminated image can be determined as a to-be-determined artifact region, and the target blur angle and the target blur size corresponding to the to-be-determined artifact region can be determined as a to-be-determined blur angle and a to-be-determined blur size, respectively. The to-be-determined blur angle and the to-be-determined blur size can be used as the blur angle and the blur size of the blur kernel, and the artifact elimination of the to-be-determined artifact region can be achieved through the blur kernel.

[0138] Optionally, after obtaining the blur direction and the blur size of the artifact region, the exclusive blur kernel can be constructed for different regions in combination with the 448 respiration method scene characteristics, that is, the artifact region generates a rectangular linear motion blur kernel consistent with the blur direction and matching the blur size, such as 1x5 pixels kernel when the exhalation period is vertically downward and the blur size is 5. The non-artifact region can use a 1x1 pixel point spread function to form a "region-kernel" mapping. Then, the Wiener deconvolution algorithm is used to perform deconvolution in different regions, and after processing each sub-region independently, the edges are fused by Gaussian smoothing to avoid splicing traces. Finally, the image quality is checked to achieve accurate elimination of respiratory artifacts and retain the details required for diagnosis, which is suitable for clinical application. Since respiration is a continuous motion, the blur kernel between adjacent frames should change smoothly. The smoothing strength can be adjusted according to the change rate of the respiration signal, that is, the difference between adjacent time points of the respiration signal. If the respiration changes slowly, the blur kernels of adjacent frames should be similar; if the respiration changes dramatically, a larger difference is allowed.

[0139] Referring to Figure 2 , based on the same inventive concept as the above method embodiments, the present application provides an abdominal magnetic resonance respiratory artifact elimination method, comprising the following steps:

[0140] Step 201, obtaining a to-be-artifact-eliminated image, and screening a suspected artifact region from the to-be-artifact-eliminated image.

[0141] In step 202, according to the gradient distribution and the gray scale distribution in each suspected artifact region, and the shape of each suspected artifact region, the artifact performance characteristic value corresponding to each suspected artifact region is determined.

[0142] In step 203, according to the artifact performance characteristic value, the target artifact region is screened from all suspected artifact regions, and the initial blurring angle and the initial blurring size corresponding to each target artifact region are determined.

[0143] In step 204, according to the historical abdominal magnetic resonance image corresponding to the same breathing phase as the to-be-artifact-removed image, the initial blurring angle and the initial blurring size corresponding to each target artifact region are corrected to obtain the target blurring angle and the target blurring size corresponding to each target artifact region.

[0144] In step 205, according to the blurring kernel of the target blurring angle and the target blurring size, the artifact removal is performed on the target artifact region, and the artifact removal of the to-be-artifact-removed image is realized.

[0145] Figure 3 is a structural schematic diagram of a computer device provided by an embodiment of the present application. As shown in the example, Figure 3 the computer device 300 includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute the aforementioned abdominal magnetic resonance breathing artifact removal method.

[0146] Based on the same inventive concept as the above method embodiment, the present application provides a server including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the above-mentioned abdominal magnetic resonance breathing artifact removal method.

[0147] Based on the same inventive concept as the above method embodiment, the present application provides a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned abdominal magnetic resonance breathing artifact removal method.

[0148] Based on the same inventive concept as the above method embodiment, the present application provides a computer readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned abdominal magnetic resonance breathing artifact removal method.

[0149] To sum up, the application quantifies the artifact performance characteristic value corresponding to each suspected artifact area by analyzing the shape of the suspected artifact area and the gradient distribution and gray scale distribution in the suspected artifact area, thereby realizing the identification of the target artifact area, improving the accuracy of the artifact area identification, and improving the rationality of the artifact elimination. In addition, by analyzing the historical abdominal magnetic resonance image corresponding to the same breathing stage as the image to be artifact-eliminated, the initial blur angle and the initial blur size corresponding to each target artifact area are corrected, which improves the rationality of the blur angle and blur size setting to a certain extent and further improves the rationality of the artifact elimination.

[0150] The above examples are only used to illustrate the technical solutions of the present application, but not limit the same; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A system for eliminating respiratory artifacts on abdominal magnetic resonance imaging, characterized in that, The system includes: The acquisition and filtering module is used to acquire the image to be artifact-removed and filter out suspected artifact regions from the image to be artifact-removed. The artifact performance feature value determination module is used to determine the artifact performance feature value corresponding to each suspected artifact region based on the gradient distribution and grayscale distribution within each suspected artifact region, as well as the shape of each suspected artifact region. The initial parameter determination module is used to filter out the target artifact region from all suspected artifact regions based on the artifact performance characteristic value, and determine the initial blur angle and initial blur size corresponding to each target artifact region. The parameter correction module is used to correct the initial blur angle and initial blur size of each target artifact region based on the pre-acquired historical abdominal magnetic resonance image with the same respiratory stage as the image to be eliminated, so as to obtain the target blur angle and target blur size of each target artifact region. The artifact removal module is used to remove artifacts in the target artifact region based on the blur kernel of the target blur angle and target blur size, thus realizing the artifact removal of the image to be removed. The step of determining the artifact performance feature value corresponding to each suspected artifact region based on the gradient distribution and grayscale distribution within each suspected artifact region, as well as the shape of each suspected artifact region, includes: determining the edge blur dynamic value corresponding to each suspected artifact region based on the gradient values ​​and grayscale values ​​corresponding to all edge pixels in each suspected artifact region; determining the shape feature value corresponding to each suspected artifact region based on the minimum bounding rectangle of each suspected artifact region and the gradient direction corresponding to all pixels in each suspected artifact region; and normalizing the product between the edge blur dynamic value and the shape feature value corresponding to each suspected artifact region to obtain the artifact performance feature value corresponding to each suspected artifact region.

2. The abdominal magnetic resonance respiratory artifact elimination system according to claim 1, characterized in that, The step of filtering out suspected artifact regions from the image to be artifact-removed includes: Based on the gradient value and grayscale distribution of each pixel in the image to be artifact-removed, the initial value of the blur artifact feature corresponding to each pixel in the image to be artifact-removed is determined. If the initial value of the blur artifact feature corresponding to a pixel is greater than the preset blur artifact threshold, then the pixel is identified as a suspected artifact edge pixel. Based on the suspected artifact edge pixels in the image to be artifact-removed, a suspected artifact region is constructed.

3. The abdominal magnetic resonance respiratory artifact elimination system according to claim 2, characterized in that, The step of constructing initial values ​​for blur artifact features corresponding to each pixel in the image to be removed, based on the gradient value and grayscale distribution of each pixel, includes: Any pixel in the image to be artifact removed is designated as a marker pixel. The gradient value corresponding to the marker pixel and the entropy value of the gray values ​​of all pixels in the preset neighborhood of the marker pixel are used to determine the initial value of the blur artifact feature corresponding to the marker pixel.

4. The abdominal magnetic resonance respiratory artifact elimination system according to claim 1, characterized in that, The step of determining the dynamic edge blur value corresponding to each suspected artifact region based on the gradient value and grayscale value corresponding to all edge pixels on each suspected artifact region includes: Any suspected artifact region in the image to be artifact removed is identified as a marked suspected artifact region, and the absolute value of the difference between the gradient values ​​corresponding to every two edge pixels in the marked suspected artifact region is identified as the target gradient difference, thus obtaining the target gradient difference set corresponding to the marked suspected artifact region. The entropy value of the grayscale value of all pixels in the preset neighborhood corresponding to each edge pixel in the marked suspected artifact region is determined as the grayscale representative entropy value of each edge pixel in the marked suspected artifact region. The edge blur dynamic value corresponding to the marked suspected artifact region is determined based on the largest target gradient difference in the target gradient difference set corresponding to the marked suspected artifact region, the average gradient value of all edge pixels in the marked suspected artifact region, and the average gray-level entropy value of all edge pixels in the marked suspected artifact region.

5. The abdominal magnetic resonance respiratory artifact elimination system according to claim 1, characterized in that, The step of determining the shape feature value corresponding to each suspected artifact region based on the minimum bounding rectangle of each suspected artifact region and the gradient direction corresponding to all pixels within each suspected artifact region includes: The angle corresponding to the gradient direction of each pixel in each suspected artifact region is determined as the gradient direction angle of each pixel in each suspected artifact region. Based on the aspect ratio of the minimum bounding rectangle of each suspected artifact region and the standard deviation of the gradient direction angles of all pixels within each suspected artifact region, the shape feature value corresponding to each suspected artifact region is determined.

6. The abdominal magnetic resonance respiratory artifact elimination system according to claim 1, characterized in that, The step of filtering out the target artifact region from all suspected artifact regions based on artifact performance characteristic values ​​includes: If the artifact performance characteristic value corresponding to the suspected artifact region is greater than the preset artifact performance threshold, then the suspected artifact region is determined as the target artifact region.

7. The abdominal magnetic resonance respiratory artifact elimination system according to claim 1, characterized in that, Determining the initial blur angle and initial blur size corresponding to each target artifact region includes: Perform a Fast Fourier Transform on each target artifact region to obtain the Fourier spectrum corresponding to each target artifact region; By using Radon transform, the direction of the stripes in the Fourier spectrum corresponding to each target artifact region is detected, and the initial blur angle and initial blur size corresponding to each target artifact region are obtained.

8. The abdominal magnetic resonance respiratory artifact elimination system according to claim 1, characterized in that, The step involves correcting the initial blur angle and initial blur size of each target artifact region based on a pre-acquired historical abdominal MRI image corresponding to the same respiratory stage as the image to be artifact-removed, to obtain the target blur angle and target blur size for each target artifact region, including: Any target artifact region in the image to be artifact-removed is determined as the artifact region to be determined, and each historical abdominal MRI image with the same respiratory stage as the image to be artifact-removed is determined as the reference image. Identify historical artifact regions from each reference image and determine the initial blur angle and initial blur size for each historical artifact region; Based on the initial blur angle and initial blur size corresponding to each historical artifact region in each reference image, and the initial blur angle and initial blur size corresponding to the undetermined artifact region, the target blur angle and target blur size corresponding to the undetermined artifact region are determined.

9. The abdominal magnetic resonance respiratory artifact elimination system according to claim 8, characterized in that, The step of determining the target blur angle and target blur size corresponding to the undetermined artifact region based on the initial blur angle and initial blur size corresponding to each historical artifact region in each reference image, and the initial blur angle and initial blur size corresponding to the undetermined artifact region, includes: Based on the respiratory standard degree of each reference image to which it belongs, the mean and standard deviation of the initial blur angles corresponding to all historical artifact regions in each reference image, and the initial blur angles corresponding to the undetermined artifact regions, the angle reference weights corresponding to each reference image are determined. Based on the respiratory standard degree of each reference image to which it belongs, the mean and standard deviation of the initial blur size corresponding to all historical artifact regions in each reference image, and the initial blur size corresponding to the undetermined artifact region, the size reference weight corresponding to each reference image is determined. The target blur angle corresponding to the undetermined artifact region is determined based on the average of the angle reference weights corresponding to each reference image and the initial blur angles corresponding to all historical artifact regions within them, as well as the initial blur angles corresponding to the undetermined artifact region. The target blur size of the undetermined artifact region is determined based on the average of the size reference weights corresponding to each reference image and the initial blur size of all historical artifact regions within it, as well as the initial blur size of the undetermined artifact region.

Images