CN118379313B - A medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation - Google Patents

Abstract

The present invention relates to the field of plaque segmentation technology, and specifically to a medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation. The method obtains multiple vascular segmentation areas; obtains the probability of plaque existence in each vascular segmentation area according to the grayscale fluctuation characteristics of the pixel points in each vascular segmentation area, the morphological change characteristics of the corresponding vascular segmentation area, and the grayscale distribution of the neighborhood; obtains the possibility that the pixel point belongs to the boundary edge between the plaque and the blood vessel according to the gradient characteristics of each pixel point in each vascular segmentation area, the local grayscale change degree, and the corresponding probability of plaque existence; adjusts the grayscale value of the pixel point, obtains the enhanced grayscale value of each pixel point, and obtains the intracranial MRA grayscale enhanced image; and segments the plaque. The present invention improves the accuracy of plaque segmentation by adaptively enhancing the grayscale value of the pixel points at the boundary edge between the plaque and the blood vessel.

Description

Method for dividing medical images of intracranial arteriosclerosis plaques of patients suffering from atrial fibrillation

Technical Field

The invention relates to the technical field of plaque segmentation, in particular to a medical image segmentation method for intracranial arteriosclerosis plaques of patients suffering from atrial fibrillation.

Background

The arteriosclerotic plaque is one of important manifestations of intracranial vascular lesions, the intracranial arteriosclerotic plaque is precisely segmented by utilizing an image processing technology, the size and the distribution of the plaque are more clearly known, and the influence degree of the arteriosclerotic plaque on blood vessels is evaluated; meanwhile, for long-term observation of intracranial arteriosclerosis, the plaque segmentation technology based on image processing can provide more accurate and reliable data support.

In the prior art, the threshold segmentation is adopted to realize the simple division of the gray level of the blood vessel image, but because the medical image of the intracranial arteriosclerosis plaque generally has complex gray level distribution and contrast variation, the blood flow in the blood vessel of the region is reduced due to the existence of the plaque, the contrast between the plaque and the blood vessel in the image is lower, and the accuracy of the plaque segmentation result is poor.

Disclosure of Invention

In order to solve the technical problems of low contrast between plaque and blood vessel and poor accuracy of plaque segmentation results, the invention aims to provide a method for segmenting intracranial arteriosclerosis plaque medical images of patients suffering from atrial fibrillation, which adopts the following technical scheme:

the invention provides a method for segmenting medical images of intracranial arteriosclerotic plaques of patients suffering from atrial fibrillation, which comprises the following steps:

Acquiring an intracranial MRA gray scale image of a patient suffering from atrial fibrillation; the intracranial MRA gray scale image comprises a blood vessel region;

Obtaining a plurality of blood vessel segmentation areas according to edge morphological characteristics in the neighborhood range of each edge pixel point in the blood vessel area; obtaining plaque existence probability of each blood vessel segmentation region according to gray scale fluctuation characteristics of pixel points in each blood vessel segmentation region, morphological change characteristics of the corresponding blood vessel segmentation region and neighborhood gray scale distribution;

according to the gradient characteristics, the local gray level change degree and the corresponding plaque existence probability of each pixel point in each blood vessel segmentation area, the possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel is obtained; according to the possibility of each pixel point, the gray value of each pixel point is adjusted, the enhancement gray value of each pixel point is obtained, and an intracranial MRA gray enhancement image is obtained;

and dividing the plaque according to the intracranial MRA gray scale enhancement image.

Further, the method for acquiring the blood vessel segmentation region comprises the following steps:

Traversing each edge pixel point neighborhood range in the blood vessel region, and constructing a minimum circumscribed rectangle of each pixel point neighborhood range; for any edge pixel point in the neighborhood range, respectively acquiring the connection line direction of the edge pixel point towards two adjacent edge pixel points, and calculating an included angle between each connection line direction and the length direction of the minimum circumscribed rectangle to be used as a direction included angle;

calculating the difference of the included angles of the two connecting line directions corresponding to the directions, and taking the difference as the difference of the included angles;

If the difference of the included angles of the edge pixel points is larger than a preset angle and the difference of the included angles of the edge pixel points is larger than the difference of the included angles of the adjacent edge pixel points, marking the edge pixel points as divided pixel points;

and dividing the neighborhood range of the edge pixel point along the normal direction of the dividing pixel point in the extending direction of the blood vessel to obtain a plurality of blood vessel segmentation areas.

Further, the method for obtaining the plaque existence probability comprises the following steps:

Calculating the variance of gray values of all pixel points in each blood vessel segmentation area to be used as gray fluctuation characteristics;

Calculating the relative distance between the edge pixel point in the extending direction of each blood vessel segmentation area and other edge pixel points in the corresponding normal direction, and calculating the difference between the maximum relative distance and the minimum relative distance as a morphological change characteristic;

Obtaining gray difference characteristics between the blood vessel segmentation areas and adjacent blood vessel segmentation areas in the corresponding extending directions according to the neighborhood gray distribution of the blood vessel segmentation areas;

and calculating the product of the gray scale fluctuation feature, the morphological change feature and the gray scale difference feature as the plaque existence probability of each blood vessel segmentation area.

Further, the method for acquiring the gray scale difference feature comprises the following steps:

calculating the gray value average value of all pixel points in each blood vessel segmentation area as a first average value; calculating the gray value average value of all pixel points in each adjacent blood vessel segmentation area in the extending direction of each blood vessel segmentation area, and taking the gray value average value as a second average value; calculating the difference between the second average value and the first average value as a first difference value; and calculating the average value of the first difference values between each blood vessel segmentation region and all adjacent blood vessel segmentation regions in the corresponding extending direction as a gray level difference characteristic.

Further, the method for acquiring the local gray scale variation degree comprises the following steps:

For each pixel point in the blood vessel segmentation area on two sides of the normal line of the gradient direction, acquiring a preset number of pairs of adjacent pixel points;

Calculating the difference of gray values between each pair of adjacent pixel points to be used as gray difference; and calculating the average value of the gray differences between all pairs of adjacent pixel points as the local gray change degree.

Further, the method for acquiring the possibility comprises the following steps:

Obtaining the possibility that each pixel belongs to the boundary edge of the plaque and the blood vessel according to an obtaining formula of the possibility, wherein the obtaining formula of the possibility is as follows:

; wherein, Representing the first in a segmented region of a blood vesselThe possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel; Represent the first The pixel point is atPlaque presence probability for individual vessel segment regions; Represent the first The pixel point is atMinimum pixel gradient in each vessel segment region; Represent the first The pixel point is atPixel gradient maximum values in the individual vessel segment regions; Represent the first Gradient values of the individual pixels; Represent the first Local gray scale variation of each pixel point; the representation takes absolute value.

Further, the method for acquiring the enhanced gray value comprises the following steps:

normalizing the possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel, and calculating the product of the normalization result and the gray value of the corresponding pixel point to be used as a gray weighting value;

and calculating the sum of the gray weighting value and the gray value to obtain the enhanced gray value of each pixel point.

Further, the segmenting plaque from the intracranial MRA gray scale enhanced image comprises:

And (3) adopting an Ojin method threshold segmentation algorithm to the intracranial MRA gray enhancement image to obtain the plaque.

Further, the method for acquiring the blood vessel region comprises the following steps:

Performing local self-adaptive threshold segmentation on the intracranial MRA gray level image to obtain a binary image; canny edge detection is carried out on the intracranial MRA gray level image, and an edge image is obtained; and carrying out exclusive or fusion on the binary image and the edge image to obtain a blood vessel region.

Further, the method for obtaining the relative distance is to calculate the Euclidean distance.

The invention has the following beneficial effects:

According to the invention, a plurality of blood vessel segmentation areas are obtained according to the edge morphological characteristics in the neighborhood range of each edge pixel point in the blood vessel area, so that local changes can be captured more accurately, and more accurate and practical blood vessel segmentation areas can be obtained; according to the gray scale fluctuation characteristics of pixel points in each blood vessel segmentation area, the morphological change characteristics of the corresponding blood vessel segmentation area and the neighborhood gray scale distribution, the plaque existence probability of each blood vessel segmentation area is obtained, whether plaque exists in the blood vessel segmentation area is judged more accurately, and the situation that a non-plaque area is misjudged as a plaque area is avoided; according to the gradient characteristics, the local gray level change degree and the corresponding plaque existence probability of each pixel point in each blood vessel segmentation area, the possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel is obtained, the possibility degree of the pixel point at the boundary edge of the plaque and the blood vessel is evaluated, and the position of the boundary edge is accurately depicted; according to the possibility of each pixel point, the gray value of each pixel point is adjusted, the enhanced gray value of each pixel point is obtained, an intracranial MRA gray enhanced image is obtained, the gray values of the pixel points are adjusted more pertinently, the contrast between blood vessels and plaques is more obvious, and the blood vessel structure can be observed and identified more clearly; the plaque is segmented. According to the invention, the gray value of the boundary edge pixel point of the plaque and the blood vessel is adaptively enhanced, so that the accuracy of plaque segmentation is improved.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for segmenting medical images of intracranial arteriosclerotic plaque in patients with atrial fibrillation according to an embodiment of the present invention;

FIG. 2 is a schematic representation of an intracranial MRA image containing arteriosclerotic plaque, in accordance with an embodiment of the present invention;

FIG. 3 is a schematic diagram of a binary image of an intracranial MRA gray scale image according to an embodiment of the present invention;

FIG. 4 is a schematic illustration of an edge image of an intracranial MRA gray scale image, according to an embodiment of the present invention;

Fig. 5 is a schematic diagram of determining a split pixel when there is a blood vessel overlapping or a plaque in a blood vessel area where an edge pixel is located according to an embodiment of the present invention.

Detailed Description

In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to specific implementation, structure, characteristics and effects of the method for dividing the intracranial arteriosclerotic plaque medical image of the patient suffering from atrial fibrillation according to the invention by combining the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

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.

The following specifically describes a specific scheme of the method for dividing the medical image of the intracranial arteriosclerotic plaque of the patient suffering from atrial fibrillation provided by the invention with reference to the accompanying drawings.

Referring to fig. 1, a flowchart of a method for dividing an intra-atrial arteriosclerotic plaque medical image of an atrial fibrillation patient according to an embodiment of the present invention is shown, and the method specifically includes:

step S1: acquiring an intracranial MRA gray scale image of a patient suffering from atrial fibrillation; the intracranial MRA gray scale image includes a vascular region.

In the embodiment of the invention, in order to accurately identify the position, size and shape of the plaque, thereby improving the diagnosis accuracy of the intracranial arteriosclerotic plaque, further guiding the selection of a treatment scheme, and accurately dividing the intracranial arteriosclerotic plaque of an atrial fibrillation patient; diagnosing plaque conditions generated by intracranial arteriosclerosis of patients suffering from atrial fibrillation, and acquiring detailed images of intracranial vessels of the patients usually by means of a magnetic resonance vascular imaging (MRA) technology; firstly, detecting the movement of water molecules in a body on the basis of a magnetic field and radio frequency pulses by using a magnetic resonance imaging MRI machine for an atrial fibrillation patient, reconstructing a vascular structure and a blood flow state by measuring signals generated by blood flow, and acquiring an intracranial magnetic resonance vascular imaging MRA image; as shown in fig. 2, a schematic representation of an intracranial MRA image containing arteriosclerotic plaque is shown, with arrows pointing to the intracranial arteriosclerotic plaque.

In one embodiment of the invention, the acquired intracranial MRA image is preprocessed to enhance the quality of the image and acquire an intracranial MRA gray scale image of the patient suffering from atrial fibrillation in order to facilitate the subsequent image processing process. It should be noted that the image preprocessing operation is a technical means well known to those skilled in the art, and may be specifically set according to a specific implementation scenario, and in one embodiment of the present invention, a graying algorithm and gaussian filtering are adopted to perform preprocessing to obtain an intracranial MRA gray image, so that the outline and details of the image can be highlighted, so that the image is clearer, and operations such as feature extraction and image recognition are easier to perform. The specific graying algorithm and gaussian filtering are well known to those skilled in the art, and will not be described in detail herein.

Since a large amount of information exists in the intracranial MRA gray scale image, the subsequent processing is affected, and in order to separate out the region of interest as far as possible, the image information is simplified, and the vascular region is analyzed.

In one embodiment of the present invention, a method for acquiring a vascular region includes:

Performing local self-adaptive threshold segmentation on the intracranial MRA gray image to obtain a binary image, wherein a schematic diagram of the binary image of the intracranial MRA gray image is shown in FIG. 3; canny edge detection is carried out on the intracranial MRA gray scale image to obtain an edge image, as shown in FIG. 4, which shows a schematic diagram of the edge image of the intracranial MRA gray scale image; and carrying out exclusive or fusion on the binary image and the edge image to obtain a blood vessel region.

By selecting a proper threshold value, the blood vessel can be distinguished from surrounding tissues, so that the blood vessel structure is more prominent in the image; in the MRA gray level image, the edge of the blood vessel usually has obvious brightness change, and the edge of the blood vessel can be further highlighted through an edge detection algorithm, so that the outline of the blood vessel is clearer; by combining the threshold segmentation and edge detection methods, the vascular area can be extracted more accurately, and false detection and omission rate are reduced. Specific local adaptive threshold segmentation, canny edge detection, and exclusive or fusion are well known to those skilled in the art, and will not be described herein.

Step S2: obtaining a plurality of blood vessel segmentation areas according to edge morphological characteristics in the neighborhood range of each edge pixel point in the blood vessel area; and obtaining the plaque existence probability of each blood vessel segmentation region according to the gray scale fluctuation characteristic of the pixel point in each blood vessel segmentation region, the morphological change characteristic of the corresponding blood vessel segmentation region and the neighborhood gray scale distribution.

The blood vessel presents complicated and changeable forms, the blood vessels in different areas possibly have different bending degrees, bifurcation conditions and width changes, the local changes can be more accurately captured by analyzing the edge form characteristics in the neighborhood range of each edge pixel point, and the adaptation adjustment is carried out according to the actual change condition of the blood vessel area, so that the blood vessel segmentation area which is more accurate and accords with the actual is obtained. Therefore, a plurality of blood vessel segmentation areas are obtained according to the edge morphological characteristics in the neighborhood range of each edge pixel point in the blood vessel area.

Preferably, in one embodiment of the present invention, the method for acquiring a segmented region of a blood vessel includes:

Traversing each edge pixel point neighborhood range in the blood vessel region, and constructing a minimum circumscribed rectangle of each pixel point neighborhood range; for any edge pixel point in the neighborhood range, respectively acquiring the connection line direction of the edge pixel point towards two adjacent edge pixel points, and calculating an included angle between each connection line direction and the length direction of the minimum circumscribed rectangle to be used as a direction included angle;

calculating the difference of the included angles of the two connecting line directions corresponding to the directions, and taking the difference as the difference of the included angles;

if the difference of the included angles of the edge pixel points is larger than a preset angle and the difference of the included angles of the edge pixel points is larger than the difference of the included angles of the adjacent edge pixel points, marking the edge pixel points as divided pixel points; fig. 5 shows a schematic diagram of determining a split pixel when there is a blood vessel overlap or a plaque in a blood vessel region where an edge pixel is located, where the left image is that there is a blood vessel overlap in the blood vessel region where the edge pixel is located, and the right image is that there is a plaque in the blood vessel region where the edge pixel is located; in the figure, the arrow direction is the line direction, and the intersection point between the arrows is the divided pixel point.

And dividing the neighborhood range of the edge pixel point along the normal direction of the dividing pixel point in the extending direction of the blood vessel to obtain a plurality of blood vessel segmentation areas.

It should be noted that, in one embodiment of the present invention, because of the complex intracranial vascular structure, the neighborhood range of each edge pixel is locally analyzed, which is helpful for capturing the fine changes of the morphology and structure of the blood vessel, and the method for acquiring the neighborhood range of the edge pixel is as follows: taking the preset times of the number of the pixels in the blood vessel region in the gradient direction of the edge pixels as the length of a neighborhood range, and forming the neighborhood range of the edge pixels in the range of the blood vessel region, wherein the preset times is 3 times; the preset angle is 5 degrees; in other embodiments of the present invention, the neighborhood range, the preset times and the preset angles may be specifically set according to specific situations, which are not limited and described herein.

The morphological change characteristics describe the shape and structure change of the segmented region of the blood vessel, when the plaque exists, the morphology of the blood vessel in the image is concave, so that the blood vessel channel is narrowed, and the morphological change is larger; the gray level fluctuation characteristics reflect the change condition of the gray level value of the pixel points in the blood vessel segmentation area, the blood flow of the blood vessel is reduced by the plaque, the sent signal is reduced, the gray level value of the existing area is smaller and the gray level fluctuation characteristics are larger; normally, the gray values between the segmented regions of the blood vessel are close, the difference is small, but the gray value of the region becomes small due to the existence of the plaque, the gray difference becomes large, and the probability of the plaque existence is larger. And therefore, the plaque existence probability of each blood vessel segmented region is obtained according to the gray scale fluctuation characteristic of the pixel point in each blood vessel segmented region, the morphological change characteristic of the corresponding blood vessel segmented region and the neighborhood gray scale distribution.

Preferably, in one embodiment of the present invention, the method for acquiring plaque existence probability includes:

Calculating the variance of gray values of all pixel points in each blood vessel segmentation area to be used as gray fluctuation characteristics;

Calculating the relative distance between the edge pixel point in the extending direction of each blood vessel segmentation area and other edge pixel points in the corresponding normal direction, and calculating the difference between the maximum relative distance and the minimum relative distance as a morphological change characteristic;

Obtaining gray difference characteristics between the blood vessel segmentation areas and adjacent blood vessel segmentation areas in the corresponding extending directions according to the neighborhood gray distribution of the blood vessel segmentation areas;

And calculating the product of the gray fluctuation feature, the morphological change feature and the gray difference feature as the plaque existence probability of each blood vessel segmentation area.

Preferably, in one embodiment of the present invention, the method for acquiring the gray scale difference feature includes:

calculating the gray value average value of all pixel points in each blood vessel segmentation area as a first average value; calculating the gray value average value of all pixel points in each adjacent blood vessel segmentation area in the extending direction of each blood vessel segmentation area, and taking the gray value average value as a second average value; calculating the difference between the second average value and the first average value as a first difference value; and calculating the average value of the first difference values between each blood vessel segmentation region and all adjacent blood vessel segmentation regions in the corresponding extending direction as a gray level difference characteristic.

In one embodiment of the present invention, the formulation of plaque presence probability is expressed as:

；

Wherein, Represent the firstPlaque presence probability for individual vessel segment regions; Represent the first The number of pixels of each vessel segmentation area; Represent the first Sequence numbers of pixel points in the individual vessel segmentation areas; Represent the first The first blood vessel segment regionGray values of the individual pixels; Represent the first Gray value average values of all pixel points in each blood vessel segmentation area; Represent the first The difference between the maximum relative distance and the minimum relative distance in the individual vessel segment regions; Represent the first The number of adjacent vessel segment regions in the direction of extension of the individual vessel segment regions; Represent the first Sequence numbers of adjacent blood vessel segment areas in the extending direction of the blood vessel segment areas; Represent the first First of the segmented regions of the blood vesselThe gray value average value of all pixel points in each adjacent blood vessel segmentation area.

In the formula of the plaque presence probability,The formula for solving the variance of the gray values of all pixel points in each blood vessel segment area is represented by the firstThe larger the gray scale fluctuation characteristic is, the larger the gray scale change of the pixel points of the blood vessel segmentation area is, and the more likely the pixel points of the blood vessel segmentation area are plaque existence areas; the smaller the gray fluctuation characteristic is, the more uniform the gray change of the pixel points of the blood vessel segmentation area is, and the more normal the blood vessel area is; The larger the morphological change feature, the larger the change in the blood vessel width, and the more likely the plaque existence region; For the gray scale difference characteristics between each blood vessel segment region and all adjacent blood vessel segment regions in the corresponding extending direction, the larger the gray scale difference characteristics are, the smaller the gray scale average value of the blood vessel segment region is, the larger the gray scale average value difference between each blood vessel segment region and all adjacent blood vessel segment regions in the corresponding extending direction is, the more likely to be plaque existence regions, and conversely, the smaller the gray scale difference characteristics are, the smaller the gray scale average value difference between each blood vessel segment region and all adjacent blood vessel segment regions in the corresponding extending direction is, and the greater the probability of being normal regions is; therefore, the larger the gradation fluctuation feature is, the larger the morphological change feature is, the larger the gradation difference feature is, the greater the probability of belonging to the plaque-present region is, and the greater the plaque-present probability of the blood vessel segment region is.

It should be noted that, in one embodiment of the present invention, the method for obtaining the relative distance is to calculate the euclidean distance, and the obtaining interval of the relative distance is 1 pixel point; other basic mathematical operations may be used to obtain the relative distance in other embodiments of the present invention, and the specific manner is a technical means well known to those skilled in the art, and will not be described herein.

Step S3: according to the gradient characteristics, the local gray level change degree and the corresponding plaque existence probability of each pixel point in each blood vessel segmentation area, the possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel is obtained; and adjusting the gray value of each pixel point according to the possibility of each pixel point, obtaining the enhanced gray value of each pixel point, and obtaining the intracranial MRA gray enhanced image.

The gradient characteristic is an important index for measuring the local structural change of the image, and the gradient change of the pixel points is usually more remarkable at the boundary edge of the plaque and the blood vessel due to larger structural difference, and the gradient characteristic is larger; at the boundary edge of the blood vessel and the plaque, gray values at two sides of the boundary edge often change obviously due to different tissue types and densities, so that whether the pixel point is positioned on the boundary edge can be further confirmed by calculating the local gray change degree of the pixel point, and the larger the local gray change degree is, the more likely the pixel point is positioned at the boundary of different tissue types is indicated; the larger the plaque existence probability of the blood vessel segmentation area is, the larger the credibility that the pixel points belong to the boundary edge of the plaque and the blood vessel is; and therefore, the possibility that each pixel belongs to the boundary edge of the plaque and the blood vessel is obtained according to the gradient characteristic, the local gray level change degree and the corresponding plaque existence probability of each pixel in each blood vessel segmentation area.

Preferably, in one embodiment of the present invention, the method for acquiring the local gray scale variation degree includes:

For each pixel point in the blood vessel segmentation area on two sides of the normal line of the gradient direction, acquiring a preset number of pairs of adjacent pixel points; calculating the difference of gray values between each pair of adjacent pixel points to be used as gray difference; and calculating the average value of gray differences between all pairs of adjacent pixel points to be used as the local gray change degree.

In one embodiment of the invention, the local gray scale variability is formulated as:

；

Wherein, Represent the firstLocal gray scale variation of each pixel point; Represent the first Serial numbers of adjacent pixel points on two sides of the normal line of each pixel point in the gradient direction; Represent the first Normal of each pixel point in gradient directionSide NoGray values of the individual pixels; Represent the first Normal of each pixel point in gradient directionSide NoGray values of the individual pixels; Represent the first The number of adjacent pixels is selected on two sides of the normal line of the gradient direction of each pixel.

In the formula of the local gray scale variation, the larger the gray scale value difference of the adjacent pixel points at two sides of the normal line is, the more the two sides are not in the same area, and the more likely the two sides belong to the boundary edge of the plaque and the blood vessel; the smaller the difference of gray values of adjacent pixel points at two sides of the normal line is, the more likely to be the same type of region is, and the smaller the local variation degree is.

It should be noted that, in one embodiment of the present invention, the preset number3, Namely selecting 3 pairs of adjacent pixel points on two sides of the normal line; in other embodiments of the present invention, the preset number of sizes may be specifically set according to specific situations, which are not limited and described herein.

Preferably, in one embodiment of the present invention, the method for acquiring a possibility includes:

Obtaining the possibility that each pixel belongs to the boundary edge of the plaque and the blood vessel according to an obtaining formula of the possibility, wherein the obtaining formula of the possibility is as follows:

；

Wherein, Representing the first in a segmented region of a blood vesselThe possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel; Represent the first The pixel point is atPlaque presence probability for individual vessel segment regions; Represent the first The pixel point is atMinimum pixel gradient in each vessel segment region; Represent the first The pixel point is atPixel gradient maximum values in the individual vessel segment regions; Represent the first Gradient values of the individual pixels; Represent the first Local gray scale variation of each pixel point; the representation takes absolute value.

In the acquisition formula of the likelihood that the probability is high,Represent the firstThe pixel point is atMinimum gradient of each blood vessel segment regionThe gradient value of each pixel point is different, when the difference is larger, the firstThe larger the gradient value of each pixel point is, the greater the possibility that the pixel point belongs to the boundary edge of the plaque and the blood vessel is; Represent the first The pixel point is atMaximum gradient of individual vessel segment region and the firstThe gradient value of each pixel point is different, and when the difference is smaller, the firstThe closer the gradient value of each pixel point is to the maximum value, the greater the possibility that the pixel point belongs to the boundary edge of the plaque and the blood vessel; To prevent the first The formula denominator is 0 when the gradient value of each pixel point is equal to the maximum value, resulting in the situation that the formula has no meaning,The ratio of the two differences is shown, the greater the ratio is, the firstThe larger the gradient value of each pixel point is, the greater the possibility that the pixel point belongs to the boundary edge of the plaque and the blood vessel is; first, theThe pixel point is atThe larger the plaque existence probability of each blood vessel segmentation area is, the larger the confidence of the possibility judgment of whether the pixel points belong to the boundary edge of the plaque and the blood vessel is; first, theThe larger the local gray level variation of each pixel point is, the larger the gray level difference of the pixel point at two sides of the normal line of the gradient direction is, and the more likely the pixel point belongs to the boundary edge of the plaque and the blood vessel.

It should be noted that, in other embodiments of the present invention, in order to more accurately locate and analyze the boundary edge between the blood vessel and the plaque, the processing range is limited to the minimum area including the segmented area of the blood vessel, so as to reduce erroneous judgment caused by inconsistent morphology change or trend, improve the accuracy of boundary edge detection, and an operator may also construct a minimum bounding rectangle of each segmented area of the blood vessel, and analyze the possibility that each pixel point in the minimum bounding rectangle belongs to the boundary edge between the plaque and the blood vessel.

The gray value represents the original brightness and color information of the pixel point and reflects the structure and characteristics of different areas in the image; the greater the possibility that the pixel points belong to the boundary edges of the plaque and the blood vessel, the more likely the situation that the area structure changes, the more important the analysis of different areas, the more the gray value needs to be enhanced, the more obvious the contrast between the blood vessel and the plaque can be caused by enhancing the gray value, and the more clear observation and recognition of the blood vessel structure are facilitated. The gray value of each pixel is adjusted according to the probability of each pixel, the enhanced gray value of each pixel is obtained, and the intracranial MRA gray enhanced image is obtained.

Preferably, in one embodiment of the present invention, the method for acquiring the enhanced gray value includes:

Normalizing the possibility that each pixel point belongs to the boundary edge of the plaque and the blood vessel, and calculating the product of the normalization result and the gray value of the corresponding pixel point to be used as a gray weighting value; and calculating the sum of the gray weighting value and the gray value to obtain the enhanced gray value of each pixel point. In one embodiment of the invention, the formula for enhancing the gray value is:

；

Wherein, Represent the firstEnhanced gray values of the individual pixels; Represent the first Gray values of the individual pixels; Represent the first The likelihood that individual pixels belong to plaque and vessel boundary edges; Representation of the first pair The likelihood that each pixel belongs to the boundary edge of plaque and blood vessel is normalized.

In the formula for enhancing the gray value,Representation of the first pairThe individual pixels are gray-scale enhanced according to the likelihood of belonging to plaque and vessel boundary edges,The gray weighting value is expressed, the greater the probability that each pixel belongs to the boundary edge of the plaque and the blood vessel, the greater the gray weighting value, and the greater the gray value of the pixel after being enhanced, the more the contrast between the plaque and the blood vessel is highlighted.

It should be noted that, in an embodiment of the present invention, the normalization of the likelihood that the pixel points belong to the boundary edges of the plaque and the blood vessel may be performed by using basic mathematical operations such as maximum and minimum normalization, standard deviation normalization, etc., and the specific manner is a technical means well known to those skilled in the art, which is not described herein.

Step S4: the plaque is segmented according to the intracranial MRA gray scale enhancement image.

After the enhancement gray value of the pixel point is obtained, the enhancement operation of the intracranial MRA gray image is completed, the accuracy of the result of subsequent image processing is effectively improved, the contrast of the boundary edge between the amplified blood vessel and the plaque is highlighted, the integrity of plaque segmentation is improved, and the plaque is segmented according to the intracranial MRA gray enhancement image.

Preferably, in one embodiment of the present invention, segmenting plaque from intracranial MRA gray scale enhancement images comprises:

And (3) adopting an Ojin method threshold segmentation algorithm to the intracranial MRA gray enhancement image to obtain the plaque.

By accurately segmenting the plaque, it is helpful to provide a physician with clearer information about the size, location, shape, and relationship with surrounding blood vessels, facilitating more accurate diagnosis and treatment planning. It should be noted that, the specific oxford method threshold segmentation algorithm is a technical means well known to those skilled in the art, and is not limited and described herein in detail.

In summary, the present invention obtains a plurality of segmented regions of blood vessels; obtaining plaque existence probability of each blood vessel segmentation region according to gray scale fluctuation characteristics of pixel points in each blood vessel segmentation region, morphological change characteristics of the corresponding blood vessel segmentation region and neighborhood gray scale distribution; obtaining the possibility that the pixel points belong to the boundary edges of the plaque and the blood vessel according to the gradient characteristics, the local gray level change degree and the corresponding plaque existence probability of each pixel point in each blood vessel segmentation area; the gray value of each pixel point is adjusted, the enhancement gray value of each pixel point is obtained, and an intracranial MRA gray enhancement image is obtained; the plaque is segmented. According to the invention, the gray value of the boundary edge pixel point of the plaque and the blood vessel is adaptively enhanced, so that the accuracy of plaque segmentation is improved.

It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

Claims (6)

1. A medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation, characterized in that the method comprises: Acquire an intracranial MRA grayscale image of a patient with atrial fibrillation; the intracranial MRA grayscale image includes a vascular area; According to the edge morphological features of the neighborhood of each edge pixel point in the vascular region, multiple vascular segmentation regions are obtained; according to the grayscale fluctuation features of the pixels in each vascular segmentation region, the morphological change features of the corresponding vascular segmentation region and the neighborhood grayscale distribution, the probability of plaque existence in each vascular segmentation region is obtained; According to the gradient characteristics of each pixel point in each blood vessel segmentation area, the local grayscale change degree and the corresponding plaque existence probability, the possibility of each pixel point belonging to the boundary edge between the plaque and the blood vessel is obtained; according to the possibility of each pixel point, the grayscale value of each pixel point is adjusted to obtain the enhanced grayscale value of each pixel point, and the intracranial MRA grayscale enhanced image is obtained; Segmenting the plaque according to the intracranial MRA grayscale enhanced image; The method for obtaining the plaque existence probability includes: Calculate the variance of the grayscale values of all pixels in each blood vessel segmentation area as the grayscale fluctuation feature; Calculate the relative distance between the edge pixel points in the extension direction of each blood vessel segment area and other edge pixel points in the corresponding normal direction, and calculate the difference between the maximum relative distance and the minimum relative distance as the morphological change feature; According to the neighborhood grayscale distribution of the blood vessel segmentation region, the grayscale difference feature between the blood vessel segmentation region and the adjacent blood vessel segmentation region in the corresponding extension direction is obtained; Calculating the product of the grayscale fluctuation feature, the morphological change feature and the grayscale difference feature as the probability of plaque existence in each blood vessel segment area; The method for acquiring the grayscale difference feature includes: Calculate the mean grayscale value of all pixels in each blood vessel segmentation area as the first mean; calculate the mean grayscale value of all pixels in each adjacent blood vessel segmentation area in the extension direction of each blood vessel segmentation area as the second mean; calculate the difference between the second mean and the first mean as the first difference; calculate the mean of the first difference between each blood vessel segmentation area and all adjacent blood vessel segmentation areas in the corresponding extension direction as the grayscale difference feature; The method for obtaining the possibility includes: The possibility of each pixel belonging to the boundary edge between the plaque and the blood vessel is obtained according to the possibility acquisition formula. The possibility acquisition formula is: ;in, Indicates the first The probability that a pixel belongs to the boundary between plaque and blood vessel; Indicates The pixel is located at The probability of plaque presence in each vascular segment area; Indicates The pixel is located at Minimum value of pixel gradient in each blood vessel segmentation area; Indicates The pixel is located at The maximum value of pixel gradient in each blood vessel segment area; Indicates The gradient value of each pixel; Indicates The local grayscale variation of each pixel; Indicates taking the absolute value; The method for obtaining the enhanced grayscale value comprises: Normalize the possibility of each pixel belonging to the boundary edge of the plaque and the blood vessel, and calculate the product of the normalized result and the gray value of the corresponding pixel as the gray weighted value; The sum of the grayscale weighted value and the grayscale value is calculated to obtain the enhanced grayscale value of each pixel. 2. According to the medical image segmentation method of intracranial arteriosclerotic plaque in patients with atrial fibrillation in claim 1, it is characterized in that the method for obtaining the blood vessel segmentation area comprises: Traverse the neighborhood range of each edge pixel point in the blood vessel area and construct the minimum circumscribed rectangle of the neighborhood range of each pixel point; for any edge pixel point in the neighborhood range, obtain the direction of the line connecting the edge pixel point to two adjacent edge pixels, and calculate the angle between each connecting line direction and the long direction of the minimum circumscribed rectangle as the direction angle; Calculate the difference between the angles of the two connecting line directions corresponding to the directions as the angle difference; If the angle difference of the edge pixel points is greater than the preset angle, and the angle difference of the edge pixel points is greater than the angle difference of adjacent edge pixel points, the edge pixel points are marked as segmentation pixels; The neighborhood range of edge pixel points is segmented along the normal direction of the segmentation pixel points in the extending direction of the blood vessel to obtain multiple blood vessel segmentation areas. 3. The medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation according to claim 1, characterized in that the method for obtaining the local grayscale variation comprises: For each pixel point in the blood vessel segmentation area, a preset number of pairs of adjacent pixel points are obtained on both sides of the normal line in the gradient direction; The difference in grayscale values between each pair of adjacent pixel points is calculated as the grayscale difference; and the average of the grayscale differences between all pairs of adjacent pixel points is calculated as the local grayscale variation. 4. The medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation according to claim 1, wherein segmenting the plaques according to the intracranial MRA grayscale enhanced image comprises: The plaques were obtained by using Otsu threshold segmentation algorithm on the gray-scale enhanced images of intracranial MRA. 5. The medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation according to claim 1, characterized in that the method for obtaining the blood vessel region comprises: The intracranial MRA grayscale image was segmented by local adaptive threshold to obtain a binary image; the intracranial MRA grayscale image was detected by Canny edge detection to obtain an edge image; the binary image and the edge image were XOR-fused to obtain the vascular area. 6. The medical image segmentation method for intracranial arteriosclerotic plaques in patients with atrial fibrillation according to claim 1 is characterized in that the relative distance is obtained by calculating the Euclidean distance.