Three-dimensional segmentation method for hematoma area in craniocerebral MRI scanning image

Abstract

The invention relates to the technical field of region segmentation, in particular to a three-dimensional segmentation method for a hematoma region in a craniocerebral MRI scanning image, and the method comprises the steps: obtaining a target 3D image corresponding to a to-be-detected patient through craniocerebral MRI scanning; determining a T1 gradual change expression factor and a T2 gradual change expression factor of each voxel point in each preset direction according to the T1 and T2 weighted gray level change conditions of each voxel point in each preset direction; screening out a T1 main gradual change direction and a T2 main gradual change direction corresponding to each voxel point; determining a fuzzy possible factor corresponding to each voxel point and an overall main gradual change direction, and making a gradual change vertical plane to which each voxel point belongs; determining a red and swollen possible factor corresponding to each voxel point; and segmenting a target hematoma area from the target 3D image according to the position corresponding to the voxel point, the gray value and the red and swollen possible factor. According to the invention, the segmentation of the hematoma region is realized, and the accuracy of the segmentation of the hematoma region is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of region segmentation, and in particular to a three-dimensional segmentation method for a hematoma region in a cranial MRI scanning image. Background Art

[0002] With the development of science and technology, the application of image region segmentation technology is becoming more and more extensive, for example, it can be applied to hematoma region segmentation. At present, when performing region segmentation, the method usually adopted is: according to the difference of gray value, the required region is segmented from the image.

[0003] However, when segmenting the hemorrhage area from the brain MRI scan image based on the grayscale value, the following technical problems often occur: Due to the diffusion of the hematoma area, there is often a fuzzy area with unclear categories between the hematoma area and the normal tissue area, so that the boundary grayscale difference between the hematoma area and the normal tissue area is not obvious. At this time, if the hematoma area is segmented directly based on the difference in grayscale values, it often leads to poor accuracy in the segmentation of the hematoma area. Summary of the invention

[0004] In order to solve the technical problem of poor accuracy in hematoma region segmentation, the present invention proposes a three-dimensional segmentation method for hematoma regions in cranial MRI scan images.

[0005] In a first aspect, the present invention provides a method for three-dimensional segmentation of a hematoma region in a cranial MRI scan image, the method comprising: Obtain the target 3D image corresponding to the patient to be tested through cranial MRI scanning; Determine the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image; According to the T1 gradient expression factor and T2 gradient expression factor of each voxel point in all preset directions, the main T1 gradient direction and the main T2 gradient direction corresponding to each voxel point are screened out; According to the T1 main gradient direction and T2 main gradient direction corresponding to each voxel point, determine the fuzzy possible factor and the overall main gradient direction corresponding to each voxel point, and make the gradient vertical plane to which each voxel point belongs; Determine the possible redness and swelling factor corresponding to each voxel point according to the angle between each voxel point and the overall main gradient direction corresponding to its neighboring voxel point on the gradient vertical plane; According to the corresponding position, gray value and possible factors of redness and swelling of the voxel points, the target hematoma area is segmented from the target 3D image.

[0006] In combination with the first aspect, in a possible implementation, determining the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image includes: Determine any voxel point in the target 3D image as a marked voxel point, and determine any preset direction as a marked direction; In the marking direction of the marked voxel point, a preset number of voxel points closest to the marked voxel point are screened to form a voxel point sequence of the marked voxel point in the marking direction; Determine the T1 gradient expression factor of the marked voxel point in the marked direction according to the difference between the T1 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction, wherein the T1 weighted grayscale value corresponding to the voxel point is the grayscale value of the voxel point on the T1 weighted image; Similarly, the T2 gradient expression factor of the marked voxel point in the marking direction is determined based on the difference between the T2 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marking direction, wherein the T2 weighted grayscale value corresponding to the voxel point is the grayscale value corresponding to the voxel point on the T2 weighted image.

[0007] In combination with the first aspect, in a possible implementation manner, determining the T1 gradient expression factor of the marked voxel point in the marked direction according to the difference between the T1 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction includes: Determine the absolute value of the accumulated value of the difference between the T1 weighted grayscale values ​​corresponding to all adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction as the T1 gradient difference index of the marked voxel point in the marked direction; According to the T1 gradient difference index of the marked voxel point in the marked direction, the T1 gradient expression factor of the marked voxel point in the marked direction is determined, wherein the T1 gradient difference index is positively correlated with the T1 gradient expression factor.

[0008] In combination with the first aspect, in a possible implementation, the step of screening out the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point according to the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in all preset directions includes: The preset directions with the largest T1 gradient expression factor and the largest T2 gradient expression factor are selected from all preset directions of each voxel point, and are used as the main T1 gradient direction and the main T2 gradient direction corresponding to each voxel point, respectively.

[0009] In combination with the first aspect, in a possible implementation, determining the possible blur factor and the overall main gradient direction corresponding to each voxel point according to the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point includes: Determine the fuzzy possible factor corresponding to each voxel point according to the angle between the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point, the difference between the T1 weighted gray value and the T2 weighted gray value corresponding to each voxel point, and the maximum T1 gradient expression factor and the maximum T2 gradient expression factor corresponding to each voxel point, wherein the maximum T1 gradient expression factor corresponding to the voxel point is the maximum value of the T1 gradient expression factors of the voxel point in all preset directions, and the maximum T2 gradient expression factor corresponding to the voxel point is the maximum value of the T2 gradient expression factors of the voxel point in all preset directions; According to the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point, the T1 unit vector and the T2 unit vector corresponding to each voxel point are constructed, wherein the T1 unit vector is a unit vector with the direction of the T1 main gradient direction, and the T2 unit vector is a unit vector with the direction of the T2 main gradient direction; The direction of the sum vector between the T1 unit vector and the T2 unit vector corresponding to each voxel point is determined as the overall main gradient direction corresponding to each voxel point.

[0010] In combination with the first aspect above, in a possible implementation, the formula corresponding to the fuzzy possibility factor corresponding to the voxel point is: ;in, The target 3D image The fuzzy possible factors corresponding to individual pixels; is the serial number of the voxel point in the target 3D image; The target 3D image The maximum T1 gradient performance factor corresponding to the individual pixel; The target 3D image The maximum T2 gradient expression factor corresponding to the individual pixel; is a natural exponential function; The target 3D image The absolute value of the difference between the T1-weighted grayscale value and the T2-weighted grayscale value corresponding to the individual pixel point; The target 3D image The angle between the main gradient direction of T1 and the main gradient direction of T2 corresponding to the individual pixel.

[0011] In combination with the first aspect, in a possible implementation manner, making a gradient vertical plane to which each voxel point belongs includes: Any voxel point in the target 3D image is determined as a marked voxel point, and a plane perpendicular to the overall main gradient direction corresponding to the marked voxel point is drawn through the marked voxel point, which is recorded as the gradient vertical plane to which the marked voxel point belongs.

[0012] In combination with the first aspect above, in a possible implementation, the formula corresponding to the possible factor of redness and swelling corresponding to the voxel point is: ;in, The target 3D image Possible factors of redness and swelling corresponding to individual pigment points; is the serial number of the voxel point in the target 3D image; The target 3D image The number of neighboring voxel points in the target circular neighborhood corresponding to the individual voxel point; The target circular neighborhood corresponding to the individual pixel is The preset circular neighborhood of individual pixels on the gradient vertical plane to which they belong; The target 3D image The serial number of the neighboring voxel point in the target circular neighborhood corresponding to the individual voxel point; is a natural exponential function; It is the absolute value function; The target 3D image The first The overall main gradient direction corresponding to the neighborhood voxel point is The angle between the main gradient directions of the whole corresponding to the individual pixels; The target 3D image The first The fuzzy possibility factor corresponding to the neighborhood voxel points; is the number of radians equal to 180°.

[0013] In combination with the first aspect, in a possible implementation, segmenting a target hematoma area from a target 3D image according to a position, a gray value, and a possible factor of redness and swelling corresponding to a voxel point includes: According to the corresponding position, gray value and possible factor of redness and swelling of the voxel points, the voxel points in the target 3D image are clustered to obtain the target clustering cluster; According to the T1-weighted grayscale value and T2-weighted grayscale value corresponding to all voxel points in each target cluster, the target redness and swelling factor corresponding to each target cluster is determined, wherein the T1-weighted grayscale value is negatively correlated with the target redness and swelling factor, and the T2-weighted grayscale value is positively correlated with the target redness and swelling factor; If the target redness and swelling factor corresponding to the target cluster is greater than the preset redness and swelling threshold, the target cluster is determined as the target hematoma area.

[0014] In combination with the first aspect above, in a possible implementation, in the process of clustering voxel points in the target 3D image, the formula corresponding to the target distance measurement between the voxel points and the cluster center is: ; ; ;in, The target 3D image Individual points and The target distance metric between cluster centers; is the serial number of the voxel point in the target 3D image; is the serial number of the cluster center; and Respectively characterize the Individual points and The position difference and grayscale difference between cluster centers; The target 3D image The fuzzy possible factors corresponding to individual pixels; The target 3D image Possible factors of redness and swelling corresponding to individual pigment points; It is The possible factors of redness and swelling corresponding to the cluster centers; It is the absolute value function; , and They are The horizontal coordinate, vertical coordinate and vertical coordinate in the voxel coordinate corresponding to the individual voxel point; , and They are The horizontal coordinate, vertical coordinate and vertical coordinate in the voxel coordinates corresponding to the cluster center; and They are T1-weighted grayscale value and T2-weighted grayscale value corresponding to individual pixel points; and They are The T1-weighted grayscale value and T2-weighted grayscale value corresponding to the cluster center.

[0015] In a second aspect, the present invention provides a three-dimensional segmentation system for hematoma areas in cranial MRI scan images, the system comprising: A 3D image acquisition module is used to acquire a target 3D image corresponding to the patient to be tested through a cranial MRI scan; A gradient expression factor determination module is used to determine the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image; The main gradient direction screening module is used to screen out the T1 main gradient direction and T2 main gradient direction corresponding to each voxel point according to the T1 gradient expression factor and T2 gradient expression factor of each voxel point in all preset directions; The factor direction plane acquisition module is used to determine the fuzzy possible factor and the overall main gradient direction corresponding to each voxel point according to the T1 main gradient direction and T2 main gradient direction corresponding to each voxel point, and to make the gradient vertical plane to which each voxel point belongs; A redness and swelling possible factor determination module is used to determine the redness and swelling possible factor corresponding to each voxel point according to the angle between each voxel point and the overall main gradient direction corresponding to the neighboring voxel point on the gradient vertical plane to which it belongs; The hematoma region segmentation module is used to segment the target hematoma region from the target 3D image according to the corresponding position, gray value and possible factor of redness and swelling of the voxel point.

[0016] 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 method in the first aspect or any possible implementation of the first aspect.

[0017] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0018] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0019] The present invention has the following beneficial effects: The present invention provides a three-dimensional segmentation method for hematoma region in a cranial MRI scan image, which realizes the segmentation of hematoma region, solves the technical problem of poor accuracy of hematoma region segmentation, and improves the accuracy of hematoma region segmentation. Compared with the segmentation of hematoma region directly based on the difference of grayscale value, the present invention not only considers the grayscale value, but also comprehensively considers multiple factors related to hematoma region segmentation, such as T1 gradient expression factor, T2 gradient expression factor, fuzzy possible factor and redness possible factor, so that the target hematoma region representing the real hematoma region can be segmented relatively accurately from the target 3D image, thereby improving the accuracy of hematoma region segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A flowchart of a method for three-dimensional segmentation of a hematoma region in a cranial MRI scan image of the present invention; Figure 2 A schematic diagram of the composition structure of a three-dimensional segmentation system for hematoma area in a cranial MRI scan image of the present invention; Figure 3 The figure is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION

[0022] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0023] Unless defined otherwise, 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 invention belongs.

[0024] refer to Figure 1 , shows the process of some embodiments of a method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to the present invention. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images comprises the following steps: Step S1, obtaining a target 3D image corresponding to the patient to be detected through a cranial MRI scan.

[0025] The brain MRI scan may be an MRI scan in a brain MRI (Magnetic Resonance Imaging) examination, which may generate a 3D (3 Dimensions) image. The patient to be tested may be a patient to be tested for brain redness and swelling. The target 3D image may be a 3D image representing the brain of the patient to be tested.

[0026] It should be noted that MRI uses the principle of Nuclear Magnetic Resonance (NMR). Based on the different attenuation of the released energy in different structural environments inside the material, the emitted electromagnetic waves are detected by applying an external gradient magnetic field to obtain the position and type of the atomic nuclei that make up the object, so that a structural image inside the object can be drawn. The 3D image generated by MRI scanning can be composed of multiple MRI images. For example, a three-dimensional image can be constructed based on multiple MRI images of the brain of the patient to be tested by constructing a point cloud. The three-dimensional image constructed at this time is the target 3D image. Among them, a single MRI image, also called a slice image, is a two-dimensional image that shows the cross-sectional information of the test site.

[0027] Each slice image can correspond to a T1-weighted image and a T2-weighted image. In T1-weighted images, fat and tissues with less water content usually appear as high-brightness signals, while tissues with high water content usually appear as low-darkness signals. In T2-weighted images, tissues with high water content usually appear as high-brightness signals, while fat and tissues with low water content appear as low-darkness signals. For example, tissues with high water content can be hematoma areas. Fat and tissues with low water content can be, but are not limited to, muscles and bones. In general, point clouds are a simpler and more unified structure that is easier to learn, and point clouds are easier to operate during geometric transformations and deformations because their connectivity often does not need to be updated.

[0028] As an example, a 3D image of the brain of a patient to be tested may be acquired through an MRI scanner as a target 3D image.

[0029] Step S2, determining the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image.

[0030] Among them, the target 3D image is a three-dimensional volume data format, which is a stereo data set composed of a series of pixel points (called voxels in three-dimensional images), each voxel point represents a small volume element in space, similar to a small cube in three-dimensional space. The preset direction can be a preset grayscale change analysis direction. For example, there can be 18 preset directions, which can be: 0° direction, 20° direction, 40° direction, 60° direction, 80° direction, 100° direction, 120° direction, 140° direction, 160° direction, 180° direction, 200° direction, 220° direction, 240° direction, 260° direction, 280° direction, 300° direction, 320° direction, 340° direction.

[0031] As an example, this step may include the following steps: In the first step, any voxel point in the target 3D image is determined as a marked voxel point, and any preset direction is determined as a marked direction.

[0032] In the second step, a preset number of voxel points closest to the marked voxel point are screened out in the marked direction of the marked voxel point to form a voxel point sequence of the marked voxel point in the marked direction.

[0033] The preset number may be a preset number of voxel points. For example, the preset number may be 7. The voxel points in the voxel point sequence of the marked voxel point in the above-mentioned marking direction may be sorted according to the distance between them and the marked voxel point, that is, the smaller the distance between them and the marked voxel point, the closer they are to the front in the voxel point sequence.

[0034] The third step is to determine the T1 gradient expression factor of the marked voxel point in the marked direction according to the difference between the T1 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction.

[0035] The T1-weighted grayscale value corresponding to the voxel point may be the grayscale value corresponding to the voxel point on the T1-weighted image, that is, the grayscale value of the voxel point on the T1-weighted image to which it belongs.

[0036] For example, determining the T1 gradient expression factor of the marked voxel point in the marked direction may include the following sub-steps: In the first sub-step, the absolute value of the accumulated value of the difference between the T1 weighted grayscale values ​​corresponding to all adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction is determined as the T1 gradient difference index of the marked voxel point in the marked direction.

[0037] The second sub-step is to determine the T1 gradient expression factor of the marked voxel point in the marked direction according to the T1 gradient difference index of the marked voxel point in the marked direction.

[0038] Among them, the T1 gradient difference index can be positively correlated with the T1 gradient performance factor.

[0039] For example, the formula corresponding to the T1 gradient expression factor of the voxel point in the target 3D image in the preset direction can be determined as follows: ; ; ;in, The target 3D image The individual point is T1 gradient performance factor in a preset direction. It is the serial number of the voxel point in the target 3D image. is the sequence number of the preset direction. The target 3D image The individual point is The T1 gradient difference index in the preset direction. The target 3D image The mean value of the T1 gradient difference index of the individual voxel points in all preset directions. Generally speaking, the mean value of the T1 gradient difference index of the voxel points in all preset directions is often not 0, so Can be used as the denominator. If there is a voxel point whose mean value of T1 gradient difference index in all preset directions is 0, a small positive factor can be added to the denominator, such as " "replace in ”. It is the absolute value function. The target 3D image The individual point is The number of voxel points in a voxel point sequence in a preset direction. The target 3D image The individual point is The sequence number of the voxel point in the voxel point sequence in a preset direction. The target 3D image The individual point is In the voxel point sequence in a preset direction, the The T1-weighted grayscale value corresponding to each individual pixel. The target 3D image The individual point is In the voxel point sequence in a preset direction, the The T1-weighted grayscale value corresponding to each individual pixel. is the number of preset directions.

[0040] It should be noted that, in actual situations, the blurred area between the hematoma area and the surrounding normal brain tissue often has a grayscale gradient, that is, the grayscale value of the voxel points in the blurred area tends to increase or decrease along one direction in different weighted images. For normal tissue areas or hematoma areas, the density of the tissue itself is relatively similar. Therefore, for normal tissue areas or hematoma areas, the grayscale value of the voxel points therein tends not to increase or decrease along one direction in different weighted images. The larger the value, the higher the The individual point is The T1-weighted grayscale value in the preset direction is more likely to increase or decrease gradually, which often indicates that the The first pixel in the T1-weighted image The gray value near the individual pixel is more likely to be along the The individual element The increase or decrease in the preset direction often indicates that the The more likely a voxel point is to be in the fuzzy region. The larger the The more likely a voxel point is to be in the fuzzy area.

[0041] In the fourth step, similarly, according to the difference between the T2 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction, the T2 gradient expression factor of the marked voxel point in the marked direction is determined.

[0042] The T2 weighted grayscale value corresponding to the voxel point may be the grayscale value corresponding to the voxel point on the T2 weighted image, that is, the grayscale value of the voxel point on the T2 weighted image to which it belongs. The larger the T2 gradient expression factor of the marked voxel point in the marked direction, the more likely it is that the T2 weighted grayscale value of the marked voxel point in the marked direction is gradually increasing or decreasing, and the grayscale value near the marked voxel point in the T2 weighted image is more likely to increase or decrease along the marked direction of the marked voxel point, which often indicates that the marked voxel point is more likely to be a voxel point in the fuzzy area.

[0043] It should be noted that the method for obtaining the T2 gradient expression factor of the marked voxel point in the marked direction may be the same as the method for obtaining the T1 gradient expression factor of the marked voxel point in the marked direction, which will not be described in detail here.

[0044] Step S3, according to the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in all preset directions, the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point are screened out.

[0045] As an example, the preset directions with the largest T1 gradient expression factor and the largest T2 gradient expression factor can be screened out from all preset directions of each voxel point as the main T1 gradient direction and the main T2 gradient direction corresponding to each voxel point, respectively.

[0046] Step S4, according to the T1 main gradient direction and T2 main gradient direction corresponding to each voxel point, determine the fuzzy possible factor and the overall main gradient direction corresponding to each voxel point, and make the gradient vertical plane to which each voxel point belongs.

[0047] As an example, this step may include the following steps: In the first step, the possible fuzzy factor corresponding to each voxel point is determined based on the angle between the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point, the difference between the T1 weighted gray value and the T2 weighted gray value corresponding to each voxel point, and the maximum T1 gradient expression factor and the maximum T2 gradient expression factor corresponding to each voxel point.

[0048] The method for obtaining the angle between the main gradient direction of T1 and the main gradient direction of T2 may be: a straight line with the main gradient direction of T1 as a straight line direction is recorded as a first straight line, a straight line with the main gradient direction of T2 as a straight line direction is recorded as a second straight line, and the angle between the first straight line and the second straight line is determined as the angle between the main gradient direction of T1 and the main gradient direction of T2. The maximum T1 gradient expression factor corresponding to the voxel point may be the maximum value of the T1 gradient expression factors of the voxel point in all preset directions, that is, the T1 gradient expression factor of the voxel point in the main gradient direction of T1. The maximum T2 gradient expression factor corresponding to the voxel point may be the maximum value of the T2 gradient expression factors of the voxel point in all preset directions, that is, the T2 gradient expression factor of the voxel point in the main gradient direction of T2.

[0049] For example, the formula for determining the fuzzy possibility factor corresponding to the voxel point can be: ;in, The target 3D image The fuzzy possibility factor corresponding to the individual pixel. It is the serial number of the voxel point in the target 3D image. The target 3D image The maximum T1 gradient expression factor corresponding to an individual pixel. The target 3D image The maximum T2 gradient expression factor corresponding to an individual pixel. is a natural exponential function. The target 3D image The absolute value of the difference between the T1-weighted grayscale value and the T2-weighted grayscale value corresponding to the individual pixel point. The target 3D image The angle between the main gradient direction of T1 and the main gradient direction of T2 corresponding to the individual pixel.

[0050] It should be noted that when The larger the In the T1-weighted image corresponding to the individual pixel point, The gray value near the individual pixel is more likely to be along the An increase or decrease in a preset direction of an individual pixel often indicates that The more likely a voxel point is to be in the fuzzy region. The larger the In the T2-weighted image corresponding to the individual pixel point, The gray value near the individual pixel is more likely to be along the An increase or decrease in a preset direction of an individual pixel often indicates that The more likely a voxel point is to be in the fuzzy area.

[0051] In actual situations, fat and tissues with less water content often appear as high-brightness signals in T1-weighted images, but low-darkness signals in T2-weighted images. Therefore, the grayscale differences between fat and tissues with less water content in different weighted images are relatively large. Tissues with high water content often appear as low-darkness signals in T1-weighted images, but high-brightness signals in T2-weighted images. Therefore, the grayscale differences between tissues with high water content in different weighted images are relatively large. The grayscale differences between voxel points in the fuzzy area in different weighted images are often not large. The smaller the time, the more likely it is that The smaller the difference between the T1-weighted grayscale value and the T2-weighted grayscale value corresponding to the individual pixel point, the The smaller the grayscale difference between individual pixels in different weighted images, the better the The more likely a voxel point is to be in the fuzzy area.

[0052] In actual situations, the angle between the grayscale gradient directions of the blurred area in different weighted images is often small. The smaller the time, the more likely it is that The smaller the angle between the main gradient direction of T1 and the main gradient direction of T2 corresponding to the individual pixel point, the smaller the angle between the main gradient direction of T1 and the main gradient direction of T2. The more likely a voxel point is to be in the fuzzy region. The larger the The more likely a voxel point is to be in the fuzzy area.

[0053] In the second step, according to the T1 main gradient direction and T2 main gradient direction corresponding to each voxel point, the T1 unit vector and T2 unit vector corresponding to each voxel point are constructed.

[0054] The T1 unit vector may be a unit vector with a direction that is the main gradient direction of T1, and the T2 unit vector may be a unit vector with a direction that is the main gradient direction of T2.

[0055] In the third step, the direction of the sum vector between the T1 unit vector and the T2 unit vector corresponding to each voxel point is determined as the overall main gradient direction corresponding to each voxel point.

[0056] In the fourth step, any voxel point in the target 3D image is determined as a marked voxel point, and a plane perpendicular to the overall main gradient direction corresponding to the marked voxel point is drawn through the marked voxel point, which is recorded as the gradient vertical plane to which the marked voxel point belongs.

[0057] Among them, the marked voxel point is in the gradient vertical plane to which it belongs.

[0058] Step S5, determining the possible redness and swelling factor corresponding to each voxel point according to the angle between each voxel point and the overall main gradient direction corresponding to its neighboring voxel points on the gradient vertical plane to which it belongs.

[0059] Among them, any voxel point in the target 3D image can be determined as a marked voxel point; the neighborhood voxel points of the marked voxel point on the gradient vertical plane to which it belongs can be voxel points in the target circular neighborhood corresponding to the marked voxel point. The target circular neighborhood corresponding to the marked voxel point is a preset circular neighborhood of the marked voxel point on the gradient vertical plane to which it belongs. The preset circular neighborhood can be a pre-set circular area, and its radius can be 5. The marked voxel point is located at the center of its corresponding target circular neighborhood. The method for obtaining the angle between the two overall main gradient directions can be: the two overall main gradient directions are respectively recorded as the first direction and the second direction, the straight line with the first direction as the straight line direction is recorded as the first temporary straight line, the straight line with the second direction as the straight line direction is recorded as the second temporary straight line, and the angle between the first temporary straight line and the second temporary straight line is determined as the angle between the two overall main gradient directions.

[0060] As an example, the formula for determining the possible factor of redness and swelling corresponding to a voxel point may be: ;in, The target 3D image The possible factors of redness and swelling corresponding to individual pixel points. It is the serial number of the voxel point in the target 3D image. The target 3D image The number of neighboring voxel points in the target circular neighborhood corresponding to the individual voxel point. The target circular neighborhood corresponding to the individual pixel is The preset circular neighborhood of an individual pixel on the gradient perpendicular plane to which it belongs. The target 3D image The sequence number of the neighboring voxel point in the target circular neighborhood corresponding to the voxel point. is a natural exponential function. It is the absolute value function. The target 3D image The first The overall main gradient direction corresponding to the neighborhood voxel point is The angle between the overall main gradient directions corresponding to individual pixels. The target 3D image The first The fuzzy possibility factor corresponding to the neighborhood voxel points. is the number of radians equal to 180°.

[0061] It should be noted that in actual situations, when a hematoma occurs, the hematoma area in the brain tends to spread gradually. However, due to the limitations of the surrounding brain tissue and structure where the actual lesion area is located, the spreading process is often disordered, that is, it usually presents an irregular shape. For example, it can often expand according to the anatomical structure of the surrounding brain tissue, and can often spread along cavities such as cerebral sulci and ventricles. Therefore, its outer contour in the 3D image is irregular. For the actual hematoma area located in the fuzzy area that is easy to misjudge, it often has a main direction during the spreading process. For example, when the hematoma area spreads forward along a certain gap, it is affected by gravity and pressure, and it often diffuses in the plane perpendicular to this direction. In other words, the more the voxel point diffuses on the gradient vertical plane to which it belongs, the more likely the voxel point is to represent the actual hematoma located in the fuzzy area. When The smaller the time, the more likely it is that The closer to the maximum direction angle , often indicating the Individual points and The more dissimilar the overall main gradient directions corresponding to the neighboring voxel points are, the more likely it is that the The more likely that individual pixels have diffused on the gradient vertical plane to which they belong, the more likely it is that the The more likely an individual pixel represents an actual hematoma, the more likely it is that it is located in the blurred area. Can be used as When The larger the The more likely the voxel points in the target circular neighborhood corresponding to the individual voxel points are to be in the fuzzy area, the more likely it is that the voxel points calculated at this time are Therefore, when The larger the value, the higher the The more likely an individual pixel represents an actual hematoma, the more likely it is that it is located in the blurred area.

[0062] Step S6, segmenting the target hematoma area from the target 3D image according to the position, gray value and possible factor of redness and swelling corresponding to the voxel point.

[0063] As an example, this step may include the following steps: In the first step, the voxel points in the target 3D image are clustered according to the corresponding positions, gray values ​​and possible factors of redness and swelling of the voxel points to obtain the target clusters.

[0064] For example, a preset number of voxel points can be randomly selected from the target 3D image as initial clustering centers, and the voxel points in the target 3D image are clustered by a Kmeans (K-means clustering algorithm, iterative clustering analysis) algorithm, wherein the preset number can be a preset number of cluster clusters, for example, the preset number can be 2. In the process of clustering the voxel points in the target 3D image, the formula corresponding to the target distance measurement between the voxel points and the clustering center can be: ; ; ;in, The target 3D image Individual points and The target distance measure between cluster centers. It is the serial number of the voxel point in the target 3D image. is the ordinal number of the cluster center. and Respectively characterize the Individual points and The position difference and grayscale difference between cluster centers. The target 3D image The fuzzy possibility factor corresponding to the individual pixel. The target 3D image The possible factors of redness and swelling corresponding to individual pixel points. It is The possible factors of redness and swelling corresponding to the cluster centers. It is the absolute value function. , and They are The horizontal, vertical and vertical coordinates of the voxel coordinates corresponding to the individual voxel points. , and They are The horizontal, vertical and vertical coordinates of the voxel coordinates corresponding to the cluster center. and They are The T1-weighted grayscale value and T2-weighted grayscale value corresponding to each individual pixel. and They are The T1-weighted grayscale value and T2-weighted grayscale value corresponding to the cluster center.

[0065] It should be noted that when The smaller the time, the more likely it is that The closer the individual pixel is to the The cluster center often indicates The more likely the individual point is to be The clusters where the cluster centers are located are one class. The smaller the time, the more likely it is that Individual points and The more similar the weighted gray values ​​between the cluster centers are, the more likely they are to be The more likely the individual point is to be The clusters where the cluster centers are located are one class. yes When The larger the The greater the blur of individual pixels, the more likely it is that The more an individual pixel is affected by blur, the larger it should be. Characterize the degree of hematoma change. The smaller the time, the more likely it is that Individual points and The more similar the hematoma degrees between the cluster centers are, the more likely it is that The more likely the individual point is to be The clusters where the cluster centers are located are of one type. Therefore, when The smaller the time, the more likely it is that The more likely the individual point is to be The clusters where the cluster centers are located are of one type. In other words, the smaller the target distance metric between the voxel point and the cluster center, the more likely it is that the voxel point should be classified into the cluster where the cluster center is located.

[0066] In the second step, the target redness and swelling factor corresponding to each target cluster is determined according to the T1-weighted grayscale value and T2-weighted grayscale value corresponding to all voxel points in each target cluster.

[0067] The T1 weighted gray value may be negatively correlated with the target redness and swelling factor, and the T2 weighted gray value may be positively correlated with the target redness and swelling factor.

[0068] For example, the formula for determining the target redness and swelling factor corresponding to the target cluster can be: ;in, It is The target swelling factor corresponding to each target cluster. is the sequence number of the target cluster. is a normalization function. It is The mean of the T1-weighted grayscale values ​​corresponding to all voxel points in the target cluster. It is The mean of the T2-weighted grayscale values ​​corresponding to all voxel points in the target cluster. It is a pre-set factor greater than 0, mainly used to prevent the denominator from being 0, for example, It can be 0.001.

[0069] It should be noted that the hematoma area often appears as a low dark signal in T1-weighted images, and its gray value in T1-weighted images is often small; while it often appears as a high bright signal in T2-weighted images, and its gray value in T2-weighted images is often large. The larger the The area represented by the target cluster is more likely to be a hematoma area.

[0070] In the third step, if the target redness and swelling factor corresponding to the target cluster is greater than the preset redness and swelling threshold, the target cluster is determined as the target hematoma area.

[0071] The preset redness and swelling threshold may be a preset threshold for screening the hematoma area. For example, the preset redness and swelling threshold may be 0.6.

[0072] Optionally, if it is known that there is a hematoma in the brain of the patient to be detected, the target cluster with the largest corresponding target redness and swelling factor can also be directly determined as the target hematoma area.

[0073] refer to Figure 2Based on the same inventive concept as the above method embodiment, the present invention provides a three-dimensional segmentation system for hematoma areas in cranial MRI scan images, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the above computer program is executed by the processor, the steps of a three-dimensional segmentation method for hematoma areas in cranial MRI scan images can specifically include: The 3D image acquisition module 201 is used to acquire a target 3D image corresponding to the patient to be detected through a cranial MRI scan; The gradient expression factor determination module 202 is used to determine the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image; The main gradient direction screening module 203 is used to screen out the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point according to the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in all preset directions; The factor direction plane acquisition module 204 is used to determine the possible fuzzy factor and the overall main gradient direction corresponding to each voxel point according to the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point, and to make a gradient vertical plane to which each voxel point belongs; The redness and swelling possible factor determination module 205 is used to determine the redness and swelling possible factor corresponding to each voxel point according to the angle between each voxel point and the overall main gradient direction corresponding to the neighboring voxel point on the gradient vertical plane to which it belongs; The hematoma region segmentation module 206 is used to segment the target hematoma region from the target 3D image according to the position, gray value and possible factor of redness and swelling corresponding to the voxel point.

[0074] Figure 3 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 3 As shown, 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 any one of the three-dimensional segmentation methods for hematoma areas in cranial MRI scan images introduced above.

[0075] Based on the same inventive concept as the above method embodiment, the present invention 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 any one of the above methods for three-dimensional segmentation of hematoma areas in cranial MRI scan images.

[0076] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, the computer executes any one of the above-mentioned three-dimensional segmentation methods for hematoma areas in cranial MRI scan images.

[0077] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned methods for three-dimensional segmentation of hematoma areas in cranial MRI scan images.

[0078] In summary, compared with the direct segmentation of the hematoma area based on the grayscale value difference, the present invention, in addition to considering the grayscale value, also comprehensively considers multiple factors related to the hematoma area segmentation, such as T1 gradient expression factor, T2 gradient expression factor, fuzzy possibility factor and redness and swelling possibility factor, etc., so that the target hematoma area representing the real hematoma area can be relatively accurately segmented from the target 3D image, thereby improving the accuracy of hematoma area segmentation.

[0079] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A three-dimensional segmentation method for hematoma area in cranial MRI scan images, characterized in that: The following steps are involved: Obtain the target 3D image corresponding to the patient to be tested through cranial MRI scanning; Determine the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image; According to the T1 gradient expression factor and T2 gradient expression factor of each voxel point in all preset directions, the main T1 gradient direction and the main T2 gradient direction corresponding to each voxel point are screened out; According to the T1 main gradient direction and T2 main gradient direction corresponding to each voxel point, determine the fuzzy possible factor and the overall main gradient direction corresponding to each voxel point, and make the gradient vertical plane to which each voxel point belongs; Determine the possible redness and swelling factor corresponding to each voxel point according to the angle between each voxel point and the overall main gradient direction corresponding to its neighboring voxel point on the gradient vertical plane, and the fuzzy possible factor corresponding to the voxel point; According to the corresponding position, gray value and possible factors of redness and swelling of the voxel points, the target hematoma area is segmented from the target 3D image.

2. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 1, characterized in that: The step of determining the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in each preset direction according to the T1 and T2 weighted grayscale changes of each voxel point in each preset direction in the target 3D image includes: Determine any voxel point in the target 3D image as a marked voxel point, and determine any preset direction as a marked direction; In the marking direction of the marked voxel point, a preset number of voxel points closest to the marked voxel point are screened to form a voxel point sequence of the marked voxel point in the marking direction; Determine the T1 gradient expression factor of the marked voxel point in the marked direction according to the difference between the T1 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction, wherein the T1 weighted grayscale value corresponding to the voxel point is the grayscale value of the voxel point on the T1 weighted image; Similarly, the T2 gradient expression factor of the marked voxel point in the marking direction is determined based on the difference between the T2 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marking direction, wherein the T2 weighted grayscale value corresponding to the voxel point is the grayscale value corresponding to the voxel point on the T2 weighted image.

3. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 2, characterized in that: Determining the T1 gradient expression factor of the marked voxel point in the marked direction according to the difference between the T1 weighted grayscale values ​​corresponding to adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction includes: Determine the absolute value of the accumulated value of the difference between the T1 weighted grayscale values ​​corresponding to all adjacent voxel points in the voxel point sequence of the marked voxel point in the marked direction as the T1 gradient difference index of the marked voxel point in the marked direction; According to the T1 gradient difference index of the marked voxel point in the marked direction, the T1 gradient expression factor of the marked voxel point in the marked direction is determined, wherein the T1 gradient difference index is positively correlated with the T1 gradient expression factor.

4. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 1, characterized in that: The method of screening out the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point according to the T1 gradient expression factor and the T2 gradient expression factor of each voxel point in all preset directions includes: The preset directions with the largest T1 gradient expression factor and the largest T2 gradient expression factor are selected from all preset directions of each voxel point, and are used as the main T1 gradient direction and the main T2 gradient direction corresponding to each voxel point, respectively.

5. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 1, characterized in that: The determining of the possible fuzzy factor and the overall main gradient direction corresponding to each voxel point according to the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point includes: Determine the fuzzy possible factor corresponding to each voxel point according to the angle between the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point, the difference between the T1 weighted gray value and the T2 weighted gray value corresponding to each voxel point, and the maximum T1 gradient expression factor and the maximum T2 gradient expression factor corresponding to each voxel point, wherein the maximum T1 gradient expression factor corresponding to the voxel point is the maximum value of the T1 gradient expression factors of the voxel point in all preset directions, and the maximum T2 gradient expression factor corresponding to the voxel point is the maximum value of the T2 gradient expression factors of the voxel point in all preset directions; According to the T1 main gradient direction and the T2 main gradient direction corresponding to each voxel point, the T1 unit vector and the T2 unit vector corresponding to each voxel point are constructed, wherein the T1 unit vector is a unit vector with the direction of the T1 main gradient direction, and the T2 unit vector is a unit vector with the direction of the T2 main gradient direction; The direction of the sum vector between the T1 unit vector and the T2 unit vector corresponding to each voxel point is determined as the overall main gradient direction corresponding to each voxel point.

6. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 5, characterized in that: The formula corresponding to the fuzzy possible factor corresponding to the voxel point is: ;in, The target 3D image The fuzzy possible factors corresponding to individual pixels; is the serial number of the voxel point in the target 3D image; The target 3D image The maximum T1 gradient performance factor corresponding to the individual pixel; The target 3D image The maximum T2 gradient expression factor corresponding to the individual pixel; is a natural exponential function; The target 3D image The absolute value of the difference between the T1-weighted grayscale value and the T2-weighted grayscale value corresponding to the individual pixel point; The target 3D image The angle between the main gradient direction of T1 and the main gradient direction of T2 corresponding to the individual pixel.

7. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 1, characterized in that: The step of making a gradient vertical plane to which each voxel point belongs includes: Any voxel point in the target 3D image is determined as a marked voxel point, and a plane perpendicular to the overall main gradient direction corresponding to the marked voxel point is drawn through the marked voxel point, which is recorded as the gradient vertical plane to which the marked voxel point belongs.

8. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 1, characterized in that: The formula corresponding to the possible factor of redness and swelling corresponding to the voxel point is: ;in, The target 3D image Possible factors of redness and swelling corresponding to individual pigment points; is the serial number of the voxel point in the target 3D image; The target 3D image The number of neighboring voxel points in the target circular neighborhood corresponding to the individual voxel point; The target circular neighborhood corresponding to the individual pixel is The preset circular neighborhood of individual pixels on the gradient vertical plane to which they belong; The target 3D image The serial number of the neighboring voxel point in the target circular neighborhood corresponding to the individual voxel point; is a natural exponential function; It is the absolute value function; The target 3D image The first The overall main gradient direction corresponding to the neighborhood voxel point is The angle between the overall main gradient directions corresponding to individual pixel points; The target 3D image The first The fuzzy possibility factor corresponding to the neighborhood voxel points; is the number of radians equal to 180°.

9. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 1, characterized in that: The method of segmenting a target hematoma area from the target 3D image according to the position, gray value and possible factor of redness and swelling corresponding to the voxel point includes: According to the corresponding position, gray value and possible factor of redness and swelling of the voxel points, the voxel points in the target 3D image are clustered to obtain the target clustering cluster; According to the T1-weighted grayscale value and T2-weighted grayscale value corresponding to all voxel points in each target cluster, the target redness and swelling factor corresponding to each target cluster is determined, wherein the T1-weighted grayscale value is negatively correlated with the target redness and swelling factor, and the T2-weighted grayscale value is positively correlated with the target redness and swelling factor; If the target redness and swelling factor corresponding to the target cluster is greater than the preset redness and swelling threshold, the target cluster is determined as the target hematoma area.

10. The method for three-dimensional segmentation of hematoma area in cranial MRI scan images according to claim 9, characterized in that: In the process of clustering voxel points in the target 3D image, the formula corresponding to the target distance measurement between the voxel points and the cluster center is: ； ； ;in, The target 3D image Individual points and The target distance metric between cluster centers; is the serial number of the voxel point in the target 3D image; is the serial number of the cluster center; and Respectively characterize the Individual points and The position difference and grayscale difference between cluster centers; The target 3D image The fuzzy possible factors corresponding to individual pixels; The target 3D image Possible factors of redness and swelling corresponding to individual pigment points; It is The possible factors of redness and swelling corresponding to the cluster centers; It is the absolute value function; , and They are The horizontal coordinate, vertical coordinate and vertical coordinate in the voxel coordinate corresponding to the individual voxel point; , and They are The horizontal coordinate, vertical coordinate and vertical coordinate in the voxel coordinates corresponding to the cluster center; and They are T1-weighted grayscale value and T2-weighted grayscale value corresponding to individual pixel points; and They are The T1-weighted grayscale value and T2-weighted grayscale value corresponding to the cluster center.

Images