An image processing method, apparatus, electronic device, and storage medium

Abstract

The application discloses an image processing method and device, electronic equipment and storage medium, wherein the method comprises: performing partition processing on a to-be-processed image corresponding to a target user to obtain at least one to-be-processed partition; for each to-be-processed partition, determining a to-be-evaluated attribute corresponding to the current partition according to to-be-recognized information corresponding to the current partition; and determining a target evaluation attribute corresponding to the to-be-processed image according to the to-be-evaluated attribute corresponding to at least one to-be-processed partition. Through partition processing on a magnetic resonance image corresponding to a hip joint part, at least one to-be-processed partition is obtained, and the condition degree of each to-be-processed partition is evaluated respectively, so that the condition degree of the hip joint part corresponding to each to-be-processed partition is determined comprehensively according to the to-be-evaluated attribute corresponding to each to-be-processed partition, and the effect of accurately and quickly evaluating the condition of the hip joint part of a user is realized.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to an image processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] Ankylosing spondylitis is a chronic disease, and since the hip joint is the most commonly affected extra-vertebral joint, with an involvement rate as high as 20%-40%, it is a major cause of injury and disease in patients seeking treatment.

[0003] Currently, hip joint diagnosis primarily relies on the attending physician visually examining the patient's MRI images to determine the severity of the condition in the hip joint area, thus identifying the appropriate treatment. However, this method heavily depends on the attending physician's clinical experience, resulting in low diagnostic efficiency and potentially inaccurate results.

[0004] To address these issues, it is necessary to improve the methods for assessing the severity of conditions in the hip joint. Summary of the Invention

[0005] This invention provides an image processing method, apparatus, electronic device, and storage medium to address the problems of low diagnostic efficiency and inaccurate diagnostic results in assessing the severity of hip joint conditions in patients.

[0006] In a first aspect, embodiments of the present invention provide an image processing method, comprising:

[0007] The image to be processed corresponding to the target user is partitioned to obtain at least one partition to be processed.

[0008] For each partition to be processed, the attribute to be evaluated corresponding to the current partition is determined based on the identification information corresponding to the current partition; wherein, the identification information includes at least one of bone marrow edema information, hip joint effusion information, and femoral head deformation information;

[0009] Based on the attribute to be evaluated corresponding to at least one partition to be processed, determine the target evaluation attribute corresponding to the image to be processed.

[0010] Secondly, embodiments of the present invention also provide an image processing apparatus, comprising:

[0011] The partitioning determination module is used to partition the image to be processed corresponding to the target user, and obtain at least one partition to be processed.

[0012] The attribute to be evaluated determination module is used to determine the attribute to be evaluated corresponding to the current partition based on the identification information corresponding to the current partition for each partition to be processed; wherein, the identification information includes at least one of bone marrow edema information, hip joint effusion information, and femoral head deformation information;

[0013] The target evaluation attribute determination module is used to determine the target evaluation attribute corresponding to the image to be processed based on the evaluation attribute corresponding to at least one partition to be processed.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the image processing method according to any embodiment of the present invention.

[0018] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions that are used to cause a processor to execute the image processing method described in any embodiment of the present invention.

[0019] The advantages of this invention are:

[0020] The technical solution of this invention involves partitioning an image corresponding to a target user to obtain at least one partition. After evaluating each partition, the severity of the target user's condition is assessed based on the corresponding evaluation attributes. Specifically, for each partition, an evaluation attribute is determined based on the identification information corresponding to that partition. Specifically, when assessing the condition of each partition, the presence of bone marrow edema, the presence of hip joint effusion, and the depth of the hip joint effusion can be used to evaluate the corresponding partition and obtain the corresponding evaluation attribute. The severity of the condition corresponding to each partition is then determined based on the evaluation attribute. Based on this, according to the evaluation attributes corresponding to at least one partition to be processed, a target evaluation attribute corresponding to the image to be processed is determined. Since the image to be processed is partitioned during condition assessment, and the degree of condition is assessed for each partition, when finally determining the degree of condition corresponding to the target user, the evaluation attributes corresponding to each partition can be superimposed to obtain the target evaluation attribute, which is used to characterize the degree of condition corresponding to the target user. This solves the problems of low diagnostic efficiency and inaccurate diagnostic results for the hip joint of patients. By partitioning the magnetic resonance image corresponding to the hip joint to obtain at least one partition to be processed, and assessing the degree of condition for each partition, the degree of condition corresponding to the hip joint is comprehensively determined based on the evaluation attributes corresponding to each partition, achieving accurate and rapid assessment of the hip joint condition of patients.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an image processing method provided according to Embodiment 1 of the present invention;

[0024] Figure 2This is a schematic diagram of a normal hip joint provided in Embodiment 1 of the present invention;

[0025] Figure 3 This is a flowchart of an image processing method provided according to Embodiment 2 of the present invention;

[0026] Figure 4 This is a schematic diagram of the partition template to be used according to Embodiment 2 of the present invention;

[0027] Figure 5 This is a schematic diagram of region division of the image to be processed based on the partition template to be used according to Embodiment 2 of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of an image processing device according to Embodiment 3 of the present invention;

[0029] Figure 7 This is a schematic diagram of the structure of an electronic device that implements the image processing method of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0032] Example 1

[0033] Figure 1 The present invention provides a flowchart of an image processing method according to an embodiment of the present invention. This embodiment is applicable to situations where the condition of a patient's hip joint can be quickly and accurately assessed based on the patient's magnetic resonance imaging. The method can be executed by an image processing device, which can be implemented in hardware and / or software and can be configured in a computing device capable of executing the image processing method.

[0034] like Figure 1 As shown, the method includes:

[0035] S110. Perform partitioning on the image to be processed corresponding to the target user to obtain at least one partition to be processed.

[0036] In this technical solution, the target user refers to a patient undergoing MRI imaging of the hip joint to assess the severity of the condition based on the MRI images. It should be noted that the target user's hip joints are symmetrically distributed left and right. When assessing the condition of the hip joint, both sides can be evaluated separately. In this technical solution, the hip joint image corresponding to the left hip joint or the hip joint image corresponding to the right hip joint is used as an example for illustration.

[0037] The image to be processed can be understood as an MRI image containing the hip joint area of ​​the target user, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of a normal hip joint. Using the raw STIR sequence data from the image to be processed, the hip joint can be clearly observed, and the condition of the hip joint can be determined based on the processed image, allowing for diagnosis and treatment. It is understood that the image to be processed includes the hip joint region, femoral head region, and acetabulum region. A region to be processed refers to at least one sub-region obtained after partitioning the image. The regions to be processed include the region corresponding to the femoral head region and the region corresponding to the acetabulum region.

[0038] Specifically, an image of the target user's hip joint is taken using an MRI scanner to obtain an image to be processed corresponding to the target user. Further, in order to assess the condition of the target user's hip joint based on the image to be processed, optionally, the image to be processed corresponding to the target user can be partitioned to obtain at least one partition to be processed.

[0039] S120. For each partition to be processed, determine the attribute to be evaluated corresponding to the current partition based on the identification information corresponding to the current partition.

[0040] The information to be identified can be understood as indicator information for assessing the condition of the area corresponding to the current partition. This information includes at least one of the following: bone marrow edema information, hip joint effusion information, and femoral head deformation information. The attribute to be evaluated can be understood as an assessment value used to characterize the severity of the condition of the target user relative to the area corresponding to the current partition. A higher attribute indicates a more severe condition in the current partition, and correspondingly, a less healthy area; conversely, a lower attribute indicates a milder condition in the current partition, and correspondingly, a healthier area.

[0041] Furthermore, based on the attributes to be evaluated corresponding to each partition to be processed, the condition of the target user's hip joint can be quickly and accurately assessed.

[0042] For example, after partitioning the image to be processed, nine partitions corresponding to the femoral head region and three partitions corresponding to the acetabulum region can be obtained. Further, a condition assessment is performed on each partition in the image to be processed to obtain corresponding assessment attributes, thereby assessing the degree of condition of the target user's hip joint based on these attributes.

[0043] Optionally, based on the identification information corresponding to the current partition, determine the attribute to be evaluated corresponding to the current partition, including: performing bone marrow edema detection on the current partition and obtaining the detection result; if the detection result includes at least one piece of bone marrow edema information, then determine the attribute to be evaluated corresponding to the current partition as the first attribute to be evaluated; if the detection result does not include bone marrow edema information, then determine the attribute to be evaluated corresponding to the current partition as the second attribute to be evaluated.

[0044] The first and second attributes to be evaluated can be understood as evaluation values ​​used to assess the severity of the condition of the current partition based on bone marrow edema information. If the current partition contains at least one piece of bone marrow edema information, the evaluation attribute corresponding to the current partition is the first attribute to be evaluated; if the current partition does not contain bone marrow edema information, the evaluation attribute corresponding to the current partition is the second attribute to be evaluated.

[0045] In practical applications, in order to determine the attribute to be evaluated corresponding to the current partition, the presence of bone marrow edema information in the current partition can be used to determine the attribute to be evaluated corresponding to the current partition.

[0046] For example, when performing partitioning processing on an image to be processed, this technical solution can finely divide the image based on a pre-set partitioning template to obtain at least one partition to be processed. Taking one of the partitions to be processed as the current partition as an example, based on the brightness information corresponding to each pixel in the current partition, it can be determined whether bone marrow edema information exists in the current partition. For example, a brightness threshold is set, and the current partition includes at least one connected component. If the average brightness corresponding to at least one pixel in the connected component is greater than the brightness threshold, it can be determined that bone marrow edema information exists in the current partition. Alternatively, the number of pixels greater than the brightness threshold can be determined based on the brightness information of at least one pixel in the connected component. If the number of pixels greater than the brightness threshold in the connected component is greater than a preset number of pixels, it can be determined that bone marrow edema information exists in the current partition. Further, if one or more bone marrow edema information exists in the current partition, the evaluation attribute corresponding to the current partition is determined as the first evaluation attribute, for example, the first evaluation attribute is set to "1". If no bone marrow edema information exists in the current partition, the evaluation attribute corresponding to the current partition is determined as the second evaluation attribute, for example, the second evaluation attribute is set to "0".

[0047] Optionally, based on the identification information corresponding to the current partition, determine the attribute to be evaluated corresponding to the current partition, including: determining the hip joint effusion area within the current partition; determining a target vertical line from at least one candidate vertical line perpendicular to the reference axis based on the reference axis corresponding to the hip joint effusion area; determining the effusion depth information corresponding to the hip joint effusion area based on the vertical line length information corresponding to the target vertical line; and determining a third attribute to be evaluated corresponding to the current partition based on the effusion depth information.

[0048] In practical applications, hip joint effusion detection is performed on the current partition to determine if a hip joint effusion region exists within that partition. If it exists, a reference axis corresponding to the hip joint effusion region is determined. The reference axis is the line connecting the two farthest pixels on the boundary line of the hip joint effusion region. For example, if the hip joint effusion region is roughly elliptical, the major axis corresponding to the elliptical shape is used as the reference axis for that region.

[0049] Furthermore, using the reference axis as a benchmark, at least one pixel on the boundary line of the hip joint effusion region is perpendicular to the reference axis to obtain at least one candidate perpendicular line. Based on the number of pixels corresponding to each candidate perpendicular line and the image resolution corresponding to the current partition, the length information of the perpendicular line corresponding to each candidate perpendicular line is determined. The candidate perpendicular line corresponding to the longest perpendicular line length is taken as the target perpendicular line. Here, the perpendicular length information of the target perpendicular line refers to the total length information of the target perpendicular line. Taking the hip joint effusion region as an elliptical shape as an example, the target perpendicular line refers to the minor axis of the ellipse, and correspondingly, the perpendicular length information of the target perpendicular line is the length of the minor axis.

[0050] The effusion depth information can be understood as an indicator used to characterize the degree of abnormality in the area corresponding to the current partition. The third attribute to be evaluated can be understood as an evaluation value used to characterize the degree of abnormality in the area corresponding to the current partition when hip joint effusion exists in the current partition.

[0051] Specifically, it is determined whether a hip joint effusion region exists in the current partition. If so, the variability of the current partition needs to be further evaluated based on the hip joint effusion region. Specifically, if a hip joint effusion region exists in the current partition, the line connecting the two pixels furthest from the boundary of this region is used as the reference axis for the region. Further, perpendicular lines are drawn from each pixel on the boundary of the hip joint effusion region to the reference axis, and the longest perpendicular line is selected as the target perpendicular line. Based on this, the hip joint effusion depth information is determined according to the length of the target perpendicular line, and a third attribute to be evaluated corresponding to the current partition is determined based on the effusion depth information of the hip joint effusion region.

[0052] For example, the vertical length information is used as the liquid depth information. If the liquid depth information is between 0 and 1.9 mm, the third attribute to be evaluated corresponding to the current partition is determined to be "0"; if the liquid depth information is between 2 and 3.9 mm, the third attribute to be evaluated corresponding to the current partition is determined to be "1"; if the liquid depth information is greater than or equal to 4 mm, the third attribute to be evaluated corresponding to the current partition is determined to be "2".

[0053] It should be noted that if there are multiple hip joint effusion areas in the current partition, the severity of the condition in the current partition will be assessed based on the hip joint effusion area with the largest area.

[0054] S130. Determine the target evaluation attribute corresponding to the image to be processed based on the evaluation attribute corresponding to at least one partition to be processed.

[0055] Among them, the target assessment attribute refers to the assessment value corresponding to the degree of disease in the target user's hip joint.

[0056] In practical applications, the target evaluation attribute corresponding to the image to be processed is determined based on the evaluation attribute corresponding to at least one partition to be processed. This includes: superimposing the evaluation attributes corresponding to at least one partition to be processed to obtain the target evaluation attribute corresponding to the image to be processed.

[0057] For example, the image to be processed includes nine regions corresponding to the femoral head and three regions corresponding to the acetabulum. Based on the first, second, and third evaluation attributes corresponding to each region, the evaluation attributes corresponding to the respective regions are determined. Furthermore, the evaluation attributes are superimposed to obtain the target evaluation attribute.

[0058] Taking one of the partitions to be processed as an example, if the partition to be processed includes bone marrow edema information, then the first attribute to be evaluated is 1 and the second attribute to be evaluated is 0. At the same time, if the partition to be processed includes a hip joint effusion area and the corresponding third attribute to be evaluated is 2, then the attribute to be evaluated corresponding to the partition to be processed can be determined to be 3.

[0059] After determining the evaluation attributes corresponding to each partition to be processed, the evaluation attributes of each partition to be processed are superimposed to obtain the target evaluation attribute. For example, if the evaluation attributes of the 12 partitions to be processed are 0, 1, 0, 2, 0, 3, 0, 0, 1, 0, 0 and 2 respectively, then the target evaluation attribute corresponding to the image to be processed is 9.

[0060] Based on this, the severity of the condition corresponding to the hip joint of the target user can be determined according to the target assessment attribute corresponding to the image to be processed. The higher the target assessment attribute, the more severe the condition, and vice versa.

[0061] The technical solution of this invention involves partitioning an image corresponding to a target user to obtain at least one partition. After evaluating each partition, the severity of the target user's condition is assessed based on the corresponding evaluation attributes. Specifically, for each partition, an evaluation attribute is determined based on the identification information corresponding to that partition. Specifically, when assessing the condition of each partition, the presence of bone marrow edema, the presence of hip joint effusion, and the depth of the hip joint effusion can be used to evaluate the corresponding partition and obtain the corresponding evaluation attribute. The severity of the condition corresponding to each partition is then determined based on the evaluation attribute. Based on this, according to the evaluation attributes corresponding to at least one partition to be processed, a target evaluation attribute corresponding to the image to be processed is determined. Since the image to be processed is partitioned during condition assessment, and the degree of condition is assessed for each partition, when finally determining the degree of condition corresponding to the target user, the evaluation attributes corresponding to each partition can be superimposed to obtain the target evaluation attribute, which is used to characterize the degree of condition corresponding to the target user. This solves the problems of low diagnostic efficiency and inaccurate diagnostic results for the hip joint of patients. By partitioning the magnetic resonance image corresponding to the hip joint to obtain at least one partition to be processed, and assessing the degree of condition for each partition, the degree of condition corresponding to the hip joint is comprehensively determined based on the evaluation attributes corresponding to each partition, achieving accurate and rapid assessment of the hip joint condition of patients.

[0062] Example 2

[0063] Figure 3 The flowchart is a second embodiment of the image processing method provided by the present invention. Optionally, the image to be processed corresponding to the target user is partitioned to obtain at least one partition to be processed for refinement.

[0064] like Figure 3 As shown, the method includes:

[0065] S210. Based on the pre-set partition template to be used, the image to be processed is divided into regions to obtain at least one partition to be processed.

[0066] The partition template to be used can be understood as a template used to partition the image into regions. See [link to relevant documentation]. Figure 4The partition template to be used includes 9 partitions to be processed corresponding to the femoral head region and 3 partitions to be processed corresponding to the acetabulum region.

[0067] For example, when performing partitioning processing based on the image to be processed, the image to be processed can be partitioned based on a pre-set partitioning template to obtain at least one partition to be processed. In this technical solution, at least one partition to be processed includes 9 sector regions corresponding to the femoral head region and 3 sector regions corresponding to the acetabulum.

[0068] It is understood that the partitioning of the image to be processed in this technical solution is an example. In practical applications, the partitioning of the image to be processed can be carried out according to the actual situation. For example, when partitioning the femoral head region, the number of partitions to be processed is not limited to 9 sectors. Similarly, when partitioning the acetabulum region, the number of partitions to be processed is not limited to 3 sectors.

[0069] Specifically, based on a pre-set partition template to be used, the image to be processed is divided into regions to obtain at least one partition to be processed, including: performing deformation detection on the femoral head region in the processed sub-image to obtain the femoral head deformation result corresponding to the femoral head region; and determining the target placement area of ​​the partition template to be used in the femoral head region based on the femoral head deformation result.

[0070] The femoral head deformation result includes either no femoral head deformation or femoral head deformation. The target placement area can be understood as the placement area of ​​the partition template to be used in the image to be processed.

[0071] In practical applications, when partitioning an image to be processed, it is mainly based on a pre-set partitioning template. Therefore, it is necessary to pre-set the partitioning template according to actual needs. After placing the partitioning template in the image to be processed, the template is used to determine the nine partitions corresponding to the femoral head region and the three partitions corresponding to the acetabulum region. See [link to relevant documentation]. Figure 5 .

[0072] It should be noted that when the target user's hip joint is healthy, the edges of the femoral head region in the image being processed are usually smooth. In other words, under normal circumstances, the femoral head region in the image being processed represents an undeformed femoral head. However, when the target user's femoral head is abnormal, the corresponding femoral head region in the image being processed will undergo deformation to some extent. For example, if osteophytes are present in the femoral head, the edges of the femoral head region in the image being processed will appear jagged and uneven. In other words, the deformation result corresponding to the femoral head region represents femoral head deformation.

[0073] Therefore, in order to more accurately partition the regions in the image to be processed based on the partitioning template to be used, the requirements for the target placement area of ​​the partitioning template in the image to be processed are also different when the deformation results of the femoral head region are different.

[0074] Optionally, the target placement area includes a first target placement area and a second target placement area. Determining the target placement area corresponding to the partition template to be used in the femoral head region includes: if the femoral head deformation result is that the femoral head is not deformed, then the placement area of ​​the partition template to be used in the femoral head region is the first target placement area; if the femoral head deformation result is that the femoral head is deformed, then the placement area of ​​the partition template to be used in the femoral head region is determined as the second target placement area based on the proportion of the deformed area.

[0075] The first target placement area does not include osteophytes or acetabulum.

[0076] In practical applications, the placement of the partition template is typically determined based on the femoral head region in the image to be processed. Specifically, the center position of the femoral head region must first be determined, and the center position of the partition template is then aligned with the center position of the femoral head region. The size of the partition template is then adjusted according to the size of the femoral head region to determine its placement area in the image. However, in practice, the center positions of the femoral head region and the partition template are not the only placement criteria. The femoral head deformation results corresponding to the femoral head region must also be considered to ultimately determine the target placement area corresponding to the partition template.

[0077] Specifically, if the femoral head deformation result shows no deformation, the center of the partition template to be used can be placed at the center of the femoral head region to obtain the first target placement area corresponding to the partition template. The size of the partition template to be used can then be adjusted according to the size of the femoral head region. It should be noted that when determining the size of the first target placement area, it is necessary to adjust the size of the first target placement area to exclude the acetabulum and osteophytes.

[0078] In a specific example, if the femoral head deformation result is that the femoral head is not deformed, the edge contour of the femoral head region can be extracted based on the edge contour extraction algorithm. The edge contour includes multiple pixels. Furthermore, the center point coordinates corresponding to the edge contour are determined by the gray-scale weighted centering method.

[0079] Specifically, the position coordinates and grayscale values ​​of each pixel within the edge contour are obtained, and the grayscale centroid coordinates are determined using the grayscale weighting method.

[0080]

[0081] Where x0 and y0 are the gray-level centroid coordinates of the femoral head region image, x i and y i f represents the position coordinates of the i-th pixel in the image of the femoral head region. i This represents the grayscale value of the i-th pixel contained in the femoral head region, where i is an integer greater than or equal to 1 and less than or equal to n, and n is the number of pixels contained in the femoral head region.

[0082] Furthermore, the edge contour of the femoral head region is used as the boundary for grayscale weighting. The pixel positions are weighted by the grayscale values ​​of pixels within the femoral head region, and the grayscale centroid is then calculated as the center position of the femoral head region. Correspondingly, when placing the partition template to be used, the center position of the partition template can be placed corresponding to the center position of the femoral head region.

[0083] Specifically, based on the grayscale features of the femoral head region image, a first weighting coefficient is determined for the coordinates corresponding to the center position (i.e., the coordinates of the first center point). First, based on the grayscale features of the femoral head region image, the grayscale value of the center point corresponding to the center position and the edge grayscale values ​​of the pixels are obtained. The grayscale distribution level is determined based on the grayscale values ​​of the center position and the edge grayscale values, where the grayscale distribution level = (grayscale value of the first center point - edge grayscale value) / 255. After determining the grayscale distribution level at each pixel within the femoral head region, the grayscale distribution level is normalized to obtain the first weighting coefficient corresponding to the center point position. Specifically, an ellipse least squares fitting is performed on all pixels constituting the sub-pixel level edge to obtain the fitted ellipse.

[0084]

[0085] Here, B, C, D, E, and F represent the parameters of the equation of the ellipse corresponding to the fitted ellipse. These parameters can be solved using least-squares fitting, thus obtaining the expression for the fitted ellipse.

[0086] The center coordinates of the fitted ellipse are determined based on the parameters of the ellipse equation corresponding to the fitted ellipse.

[0087] Specifically, after determining the parameters of the ellipse equation corresponding to the fitted ellipse, the center coordinates of the fitted ellipse can be determined using the following formula:

[0088]

[0089] Where x'0 and y'0 are the coordinates of the center point of the fitted ellipse, and B, C, D, and E are all parameters of the equation corresponding to the fitted ellipse.

[0090] (x'0, y'0) is used as the coordinates of the second center point of the femoral head region, and the second weighting coefficient of the second center point coordinates is determined.

[0091] Furthermore, the coordinates of the first center point and the coordinates of the second center point are multiplied by the corresponding first weighting coefficient and the second weighting coefficient, respectively, and the products are summed to obtain the coordinates of the center point of the femoral head region, that is, the coordinate point position corresponding to the center position of the partition template to be used.

[0092] If the result of femoral head deformation is femoral head deformity, in order to achieve partitioning of the image to be processed, when determining the second target placement area corresponding to the partition template to be used, a small number of acetabula or osteophytes may be allowed in the second target placement area.

[0093] In a specific example, if the result of femoral head deformation is femoral head deformity, then the centroid of the femoral head region can be used as the center point, that is, the position corresponding to the center point of the partition template to be used.

[0094] Specifically, the edge contour of the femoral head region is extracted, and the Euclidean distance of the centroid of the femoral head region is calculated for each pixel of the edge contour, forming a distance set G. Further, upper and lower thresholding is applied to the distance set G to obtain set H, and a point count thresholding is applied to set H to obtain set I, where elements in I are sets of contour points with 8-neighborhood connections. A feature point detector is applied to each point in each element of set I to calculate the response, and the coordinates of the point with the strongest response in each element are the corner points. The edge contour of the femoral head region refers to a set D, where each element is represented by an ordered pair (x, y), where x is the horizontal coordinate and y is the vertical coordinate.

[0095] The center of mass of the femoral head region can be calculated using the following formula:

[0096]

[0097] Where N is the radius of the local region, x i The x-coordinate of the i-th pixel on the edge contour of the femoral head region is represented by y. i This represents the ordinate of the i-th pixel on the edge contour of the femoral head region. The x-coordinate of the centroid of the femoral head region is given. The vertical coordinate is the centroid of the femoral head region.

[0098] Based on this, the centroid of the femoral head region can be determined, and the position corresponding to the obtained centroid coordinates can be used as the position of the center point of the partition template to be used.

[0099] It should be noted that when determining the partitioning template to be used, if an acetabulum or osteophyte is detected, the area size of the acetabulum or osteophyte can be further determined. When adjusting the size of the second target placement area, it is necessary to minimize the number of acetabulums or osteophytes within the second target placement area. For example, the area ratio of the acetabulum or osteophyte in the femoral head region can be preset. For instance, the area ratio of the acetabulum or osteophyte in the second target placement area is less than 10%, to ensure that the presence of a small number of acetabulums or osteophytes does not affect the partitioning of the image to be processed based on the partitioning template to be used, and that after obtaining at least one partition to be processed, the accuracy of the evaluation of the variability of each partition to be processed is not affected.

[0100] S220. For each partition to be processed, determine the attribute to be evaluated corresponding to the current partition based on the identification information corresponding to the current partition.

[0101] S230. Determine the target evaluation attribute corresponding to the image to be processed based on the evaluation attribute corresponding to at least one partition to be processed.

[0102] The technical solution of this embodiment, based on a pre-set partition template, divides the image to be processed into regions to obtain at least one partition to be processed. By determining whether there is deformation in the femoral head region of the image to be processed, a target placement region corresponding to the partition template is determined. Specifically, if there is no femoral head deformation, the center position of the partition template is set at the center position of the femoral head region, and the placement region corresponding to the partition template is constrained to obtain a first target placement region, that is, the first target placement region does not include the acetabulum or osteophytes. If there is femoral head deformation, the target placement region of the partition template is determined as a second target placement region, and the size of the partition template is adjusted to minimize the inclusion of the acetabulum or osteophytes in the second target placement region. By using the deformation information of the femoral head region in the image to be processed, the placement position of the partition template in the image to be processed is set more accurately, thereby achieving more accurate partitioning of the image to be processed and obtaining at least one partition to be processed.

[0103] Example 3

[0104] Figure 6 This is a schematic diagram of the structure of an image processing device provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes: a partition determination module 310, a target attribute determination module 320, and a target evaluation attribute determination module 330.

[0105] The partitioning determination module 310 is used to partition the image to be processed corresponding to the target user to obtain at least one partition to be processed.

[0106] The attribute determination module 320 is used to determine the attribute to be evaluated corresponding to the current partition for each partition to be processed, based on the identification information corresponding to the current partition; wherein, the identification information includes at least one of bone marrow edema information, hip joint effusion information, and femoral head deformation information.

[0107] The target evaluation attribute determination module 330 is used to determine the target evaluation attribute corresponding to the image to be processed based on the evaluation attribute corresponding to at least one partition to be processed.

[0108] The technical solution of this invention involves partitioning an image corresponding to a target user to obtain at least one partition. After evaluating each partition, the severity of the target user's condition is assessed based on the corresponding evaluation attributes. Specifically, for each partition, an evaluation attribute is determined based on the identification information corresponding to that partition. Specifically, when assessing the condition of each partition, the presence of bone marrow edema, the presence of hip joint effusion, and the depth of the hip joint effusion can be used to evaluate the corresponding partition and obtain the corresponding evaluation attribute. The severity of the condition corresponding to each partition is then determined based on the evaluation attribute. Based on this, according to the evaluation attributes corresponding to at least one partition to be processed, a target evaluation attribute corresponding to the image to be processed is determined. Since the image to be processed is partitioned during condition assessment, and the degree of condition is assessed for each partition, when finally determining the degree of condition corresponding to the target user, the evaluation attributes corresponding to each partition can be superimposed to obtain the target evaluation attribute, which is used to characterize the degree of condition corresponding to the target user. This solves the problems of low diagnostic efficiency and inaccurate diagnostic results for the hip joint of patients. By partitioning the magnetic resonance image corresponding to the hip joint to obtain at least one partition to be processed, and assessing the degree of condition for each partition, the degree of condition corresponding to the hip joint is comprehensively determined based on the evaluation attributes corresponding to each partition, achieving accurate and rapid assessment of the hip joint condition of patients.

[0109] Optionally, the partitioning module includes: a partitioning submodule, used to divide the image to be processed into regions based on a pre-set partitioning template to be used, to obtain at least one partition to be processed; wherein the partition to be processed includes at least one image partition corresponding to the femoral head and at least one image partition corresponding to the acetabulum.

[0110] Optionally, the partitioning determination submodule includes: a deformation result determination unit, used to perform deformation detection on the femoral head region in the processed sub-image to obtain the femoral head deformation result corresponding to the femoral head region; wherein, the femoral head deformation result includes either no deformation of the femoral head or deformation of the femoral head;

[0111] The placement area determination unit is used to determine the target placement area of ​​the partition template to be used in the femoral head region based on the femoral head deformation results.

[0112] Optionally, the placement area determination unit includes: a first determination subunit, used to determine the placement area of ​​the partition template to be used in the femoral head region as the first target placement area if the femoral head deformation result is that the femoral head is not deformed; wherein, the first target placement area does not include osteophytes or acetabulum;

[0113] The second determining subunit is used to determine the placement area of ​​the partition template to be used in the femoral head region as the second target placement area based on the proportion of the deformed area if the femoral head deformation result is that the femoral head has been deformed.

[0114] Optionally, the attribute determination module includes: a detection submodule, used to perform bone marrow edema detection on the current partition and obtain the detection results;

[0115] The first attribute to be evaluated determination submodule is used to determine the attribute to be evaluated corresponding to the current partition as the first attribute to be evaluated if the detection result includes at least one bone marrow edema information.

[0116] The second attribute to be evaluated determination submodule is used to determine the attribute to be evaluated corresponding to the current partition as the second attribute to be evaluated if the test result does not include bone marrow edema information.

[0117] Optional, Attribute to be evaluated determination module: Effusion area determination submodule, used to determine the hip joint effusion area within the current partition;

[0118] The target vertical line determination submodule is used to determine the target vertical line from at least one candidate vertical line perpendicular to the reference axis, based on the reference axis corresponding to the hip joint effusion area.

[0119] The depth information determination submodule is used to determine the effusion depth information corresponding to the hip joint effusion area based on the vertical length information corresponding to the target vertical line.

[0120] The third attribute to be evaluated determination submodule is used to determine the third attribute to be evaluated corresponding to the current partition based on the liquid depth information.

[0121] Optionally, a target evaluation attribute determination module is used to overlay the evaluation attributes corresponding to at least one partition to be processed to obtain the target evaluation attributes corresponding to the image to be processed.

[0122] The image processing apparatus provided in the embodiments of the present invention can execute the image processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0123] Example 4

[0124] Figure 7 A schematic diagram of the structure of an electronic device 10 according to an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0125] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0126] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0127] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as image processing methods.

[0128] In some embodiments, the image processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the image processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the image processing method by any other suitable means (e.g., by means of firmware).

[0129] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0130] Computer programs for implementing the image processing methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0131] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0132] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0133] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0134] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0135] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0136] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An image processing method, characterized in that, include: Based on a pre-set partition template, the image to be processed corresponding to the target user is divided into regions to obtain at least one partition to be processed; wherein, the partition to be processed includes at least one image partition corresponding to the femoral head and at least one image partition corresponding to the acetabulum. For each partition to be processed, the attribute to be evaluated corresponding to the current partition is determined based on the identification information corresponding to the current partition; wherein, the identification information includes at least one of bone marrow edema information, hip joint effusion information, and femoral head deformation information; Based on the evaluation attribute corresponding to at least one partition to be processed, determine the target evaluation attribute corresponding to the image to be processed; The step of dividing the image to be processed corresponding to the target user into regions based on a pre-set partition template to obtain at least one partition to be processed includes: performing deformation detection on the femoral head region in the image to be processed to obtain a femoral head deformation result corresponding to the femoral head region; wherein the femoral head deformation result includes either no deformation or deformation of the femoral head; and determining the target placement area of ​​the partition template to be used corresponding to the femoral head region based on the femoral head deformation result. The target placement area includes a first target placement area and a second target placement area. Determining the target placement area corresponding to the partition template to be used in the femoral head region includes: if the femoral head deformation result is that the femoral head is not deformed, then the placement area of ​​the partition template to be used in the femoral head region is determined as the first target placement area; wherein the first target placement area does not include osteophytes or acetabulum; if the femoral head deformation result is that the femoral head is deformed, then the placement area of ​​the partition template to be used in the femoral head region is determined as the second target placement area based on the proportion of the deformed area.

2. The method according to claim 1, characterized in that, The step of determining the attribute to be evaluated corresponding to the current partition based on the identification information corresponding to the current partition includes: Bone marrow edema was detected in the current partition, and the results were obtained. If the detection result includes at least one bone marrow edema information, then the attribute to be evaluated corresponding to the current partition is determined to be the first attribute to be evaluated. If the detection results do not include the bone marrow edema information, then the attribute to be evaluated corresponding to the current partition is determined to be the second attribute to be evaluated.

3. The method according to claim 1, characterized in that, The step of determining the attribute to be evaluated corresponding to the current partition based on the identification information corresponding to the current partition includes: Identify the area of ​​hip joint effusion within the current partition; Based on the reference axis corresponding to the hip joint effusion area, a target vertical line is determined from at least one candidate vertical line perpendicular to the reference axis. Based on the length information of the vertical line corresponding to the target vertical line, the effusion depth information corresponding to the hip joint effusion area is determined; The third attribute to be evaluated corresponding to the current partition is determined based on the fluid depth information.

4. The method according to claim 1, characterized in that, The step of determining the target evaluation attribute corresponding to the image to be processed based on the evaluation attribute corresponding to at least one partition to be processed includes: The attributes to be evaluated corresponding to at least one partition to be processed are superimposed to obtain the target evaluation attributes corresponding to the image to be processed.

5. An image processing apparatus, characterized in that, include: The partitioning module is used to divide the image to be processed corresponding to the target user into regions based on a pre-set partitioning template to be used, so as to obtain at least one partition to be processed; wherein, the partition to be processed includes at least one image partition corresponding to the femoral head and at least one image partition corresponding to the acetabulum. The attribute to be evaluated determination module is used to determine the attribute to be evaluated corresponding to the current partition based on the identification information corresponding to the current partition for each partition to be processed; wherein, the identification information includes at least one of bone marrow edema information, hip joint effusion information, and femoral head deformation information; The target evaluation attribute determination module is used to determine the target evaluation attribute corresponding to the image to be processed based on the evaluation attribute corresponding to at least one partition to be processed. The partitioning determination module includes: a deformation result determination unit, used to perform deformation detection on the femoral head region in the image to be processed, and obtain the femoral head deformation result corresponding to the femoral head region; wherein the femoral head deformation result includes the femoral head not deformed or the femoral head deformed; and a placement area determination unit, used to determine the target placement area of ​​the partitioning template to be used in the femoral head region according to the femoral head deformation result. The target placement area includes a first target placement area and a second target placement area. The placement area determination unit includes: a first determination subunit, used to determine the placement area of ​​the partition template to be used within the femoral head area as the first target placement area if the femoral head deformation result is that the femoral head is not deformed; wherein the first target placement area does not include osteophytes or acetabulum; and a second determination subunit, used to determine the placement area of ​​the partition template to be used within the femoral head area as the second target placement area based on the deformation area ratio if the femoral head deformation result is that the femoral head is deformed.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to implement the image processing method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the image processing method according to any one of claims 1-4.

Images