A method and system for imaging detection of hemorrhagic brain stem cell damage, and a storage medium

Abstract

The present invention discloses a method and system for detecting hemorrhagic brain stem cell damage images, the method comprising: obtaining a medical image of the brain to be detected; graying the medical image to be detected to obtain a gray image of the brain to be detected, and determining brain gray points according to the gray values ​​of each pixel in the gray image of the brain to be detected; dividing the gray image of the brain to be detected according to the brain gray points and recording gray point data; obtaining a brain blood area contour of the gray image of the brain to be detected according to an edge detection algorithm; and judging whether there is brain hemorrhage in the medical image of the brain to be detected according to each gray point data and the brain blood area contour; determining the brain blood area contour and gray point data by clustering the brain gray points; the brain blood area contour can quickly know the blood accumulation area of ​​the brain, and obtain accurate brain hemorrhage analysis of the brain blood accumulation area through the gray point data, thereby improving the efficiency and accuracy of detection.

Description

Technical Field

[0001] The present invention relates to the field of MRI image detection and recognition, and in particular to an image detection method and system for hemorrhagic brain stem cell damage, and a storage medium. Background Art

[0002] Cerebral hemorrhage is a common medical disease. It is induced by diseases such as hypertension, cerebral aneurysm, head trauma, and cerebral vascular malformations. It is one of the important causes of human death and disability. Whether the cerebral hemorrhage enters the brain is an important indicator to measure the severity of cerebral hemorrhage.

[0003] Because there is a layer of blood retina on the surface of the sulcus structure of the brain, when blood circulates through the capillaries, medical staff and machine recognition often make wrong judgments after the brain images are taken by machines such as magnetic resonance imaging and CT imaging. At the same time, due to factors such as human movement and emotional excitement, the blood circulation of the brain will be temporarily accelerated, leading to misjudgment. And under the influence of the above factors, the speed of medical staff and machine recognition will also be greatly affected.

[0004] Therefore, the current recognition of whether there is brain hemorrhage has low efficiency and poor accuracy, especially the poor accuracy in distinguishing true hemorrhage and motor congestion. To address this problem, an imaging detection method for hemorrhagic brain stem cell damage is urgently needed to improve the efficiency and accuracy of identifying whether there is brain hemorrhage. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for detecting hemorrhagic brain stem cell damage images, and a storage medium, which solves the above-mentioned technical problems pointed out in the prior art.

[0006] The present invention provides a method for imaging detection of hemorrhagic brain stem cell damage, comprising the following steps:

[0007] Acquire a medical image of the brain to be detected; grayscale the medical image to be detected to obtain a grayscale image of the brain to be detected, and determine the brain grayscale point according to the grayscale value of each pixel in the grayscale image of the brain to be detected;

[0008] The brain grayscale image to be detected is divided according to the brain grayscale points to record the grayscale point data; the brain blood area contour of the brain grayscale image to be detected is obtained according to the edge detection algorithm; and whether there is cerebral hemorrhage in the brain medical image to be detected is judged according to each of the grayscale point data and the brain blood area contour.

[0009] Preferably, the grayscale image of the brain to be detected is divided according to the brain grayscale points to record the grayscale point data; the brain blood area contour of the grayscale image of the brain to be detected is obtained according to the edge detection algorithm, and whether there is cerebral hemorrhage in the medical image of the brain to be detected is judged according to each of the grayscale point data and the brain blood area contour. The specific operation steps are as follows:

[0010] Calculate the grayscale value of each pixel of the grayscale image of the brain to be detected, and determine it as a brain grayscale point by judging it according to the grayscale value; if the grayscale value of each pixel is greater than a preset grayscale value threshold o, retain the pixel that is greater than the preset grayscale value threshold o, and determine the retained pixel as a brain grayscale point; if the grayscale value of each pixel is less than or equal to the preset grayscale value threshold o, perform subsequent operations on the pixel that is less than or equal to the preset grayscale value threshold o;

[0011] Clustering the same grayscale value of each brain grayscale point to obtain different first-level brain grayscale point clusters; and recording grayscale point data through the first-level brain grayscale point clusters;

[0012] The brain grayscale image to be detected forms the outline of the brain blood area through the edge detection algorithm; the pixel points with the grayscale value less than or equal to the preset grayscale value threshold o are clustered with the same grayscale value to obtain the second-level brain grayscale point cluster; the second-level brain grayscale point cluster is judged to be less than the preset brain grayscale contour point threshold t; if the second-level brain grayscale point cluster is less than the preset brain grayscale contour point threshold t, the second-level brain grayscale point cluster is judged to be the brain grayscale contour point, and the brain grayscale contour points are connected to form the brain blood area outline of the brain grayscale points; if the second-level brain grayscale point cluster is greater than or equal to the preset brain grayscale contour point threshold t, the second-level brain grayscale point cluster is eliminated;

[0013] Whether there is brain bleeding is determined by the brain blood area contour and gray point data.

[0014] Preferably, the gray point data include: brain hemorrhage, blood circulation in the retina, and rapid blood circulation in the brain after human exercise leading to temporary congestion of the brain.

[0015] Preferably, the specific operation steps of judging whether the brain is bleeding by the brain blood area contour and gray point data are as follows:

[0016] Determine whether the brain blood area contour is bleeding by using the gray point data; determine the contour gray level of the brain blood area contour by a range between a preset first threshold W and a second threshold N;

[0017] When the brain blood area contour is greater than the first threshold W and less than the second threshold N, the brain blood area contour is a medium contour grayscale level, and the brain blood area contour at the brain position is judged to be cerebral hemorrhage according to the grayscale point data; if the brain blood area contour is less than the first threshold W or greater than the second threshold N, the brain blood area contour is determined to be a high contour grayscale level or a low contour grayscale level, and no cerebral hemorrhage is found in the brain blood area contour at the brain position according to the grayscale point data.

[0018] Preferably, the contour gray level of the brain blood area contour is determined by a range between a preset first threshold value W and a second threshold value N, and the specific operation steps are as follows:

[0019] The first threshold W and the second threshold N are determined by using the grayscale values ​​of the brain grayscale contour points of the brain blood area contour and the average grayscale value of the entire grayscale image to be detected; when the contour grayscale level of the brain blood area contour of the first-level brain grayscale point cluster is less than the first threshold W, the brain blood area contour of the first-level brain grayscale point cluster is too small, and the brain blood area contour of the first-level brain grayscale point cluster is of a low contour grayscale level, and it is determined that the blood circulation of the blood retina is good, and there is no brain bleeding;

[0020] When the contour gray level of the brain blood region contour is greater than the second threshold value W, the brain blood region contour of the first-level brain gray point cluster is larger, and the brain blood region contour of the first-level brain gray point cluster is of a high contour gray level, and it is determined that the rapid blood circulation in the brain after human exercise leads to temporary congestion of the brain, and there is no brain bleeding;

[0021] When the contour grayscale level of the brain grayscale contour is greater than the first threshold W and less than the second threshold N, the brain blood area contour of the first-level brain grayscale point cluster is a medium contour grayscale level, and brain hemorrhage is determined based on the current grayscale point data.

[0022] Preferably, the first threshold W and the second threshold N are determined by using the grayscale values ​​of the brain grayscale contour points of the brain blood area contour and the average grayscale value of the entire grayscale image to be detected, which specifically includes the following steps:

[0023] The formula for calculating the first threshold W by obtaining the average grayscale value De of the entire grayscale image to be detected and the grayscale value of the brain grayscale contour point through the adaptive threshold algorithm is:

[0024]

[0025] Wherein, H is the first proportional coefficient, (Ro1, Ro2, Ro3, ..., Ron) are the grayscale values ​​of the brain grayscale contour points of the brain blood area contour; at the same time, the above-mentioned brain blood area contour is composed of n brain grayscale contour points; De is the average grayscale value of the entire grayscale image to be detected; K is the basic threshold;

[0026] The second threshold N is calculated by the proportionality coefficient of the first threshold W, and the calculation formula is:

[0027]

[0028] Wherein, B is the second proportional coefficient, and the second proportional coefficient B is greater than the first proportional coefficient H;

[0029] The contour grayscale level of the brain blood region contour is determined by the first threshold W and the second threshold N, and whether the brain is bleeding is determined by the contour grayscale level of the brain blood region contour.

[0030] Preferably, the step of determining the grayscale level of the contour of the brain blood region by using the first threshold W and the second threshold N, and determining whether the brain is bleeding by using the grayscale level of the contour of the brain blood region, specifically includes the following steps:

[0031] Obtaining the middle contour gray level of the brain gray contour through the range between the first threshold W and the second threshold N, and further determining whether the brain is bleeding based on the middle contour gray level of the brain gray contour and the gray point data;

[0032] A limit grayscale threshold c is preset by an adaptive threshold algorithm. If the grayscale value of the first-level brain grayscale point cluster is greater than or less than the preset limit grayscale threshold c, it is determined that the proportion of grayscale point data belonging to the brain hemorrhage state is greater than the threshold of the proportion of grayscale point data belonging to the brain non-hemorrhage state; if the grayscale value of the first-level brain grayscale point cluster is equal to the preset limit grayscale threshold c, it is determined that the proportion of grayscale point data belonging to the brain hemorrhage state is less than the threshold of the proportion of grayscale point data belonging to the brain non-hemorrhage state, and subsequent steps are performed;

[0033] The average grayscale value of the grayscale values ​​of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour is calculated; the average grayscale value of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour is compared with the grayscale value of the grayscale point data through a preset contrast threshold z; if the average grayscale value of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour and the grayscale value of the grayscale point data are both greater than the preset contrast threshold z, then there is cerebral hemorrhage in the brain medical image to be detected; if the medium grayscale level of the brain grayscale contour is When the average grayscale value of the grayscale contour points of the grayscale level of the brain is less than or equal to the preset contrast threshold z, the comparison between the two fails, and the first threshold W and the second threshold N are recalculated through the adaptive threshold algorithm, and the contour grayscale level of the brain grayscale contour is detected in the range between the first threshold W and the second threshold N; if the grayscale value of the grayscale point data is less than or equal to the preset contrast threshold z, the comparison between the two fails, and the preset boundary grayscale threshold c is iterated through the adaptive threshold algorithm until the comparison between the two is successful and greater than the preset contrast threshold z.

[0034] Accordingly, the present invention also proposes a hemorrhagic brain stem cell injury imaging detection system, comprising: a gray point module, a gray data module, and a brain result module;

[0035] The grayscale point module is used to obtain a medical image of the brain to be detected; grayscale the medical image to be detected to obtain a grayscale image of the brain to be detected, and determine the brain grayscale point according to the grayscale value of each pixel in the grayscale image of the brain to be detected;

[0036] The grayscale data module is used to obtain the brain grayscale points to divide the grayscale image of the brain to be detected and record the grayscale point data; obtain the brain blood area contour of the grayscale image of the brain to be detected according to the edge detection algorithm;

[0037] The brain result module is used to determine whether there is cerebral hemorrhage in the brain medical image to be detected based on each of the grayscale point data and the brain blood area contour.

[0038] Correspondingly, the present application also relates to a storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of a method for imaging detection of hemorrhagic brain stem cell damage are implemented.

[0039] Compared with the prior art, the embodiments of the present invention have at least the following technical advantages:

[0040] From the analysis of the above-mentioned hemorrhagic brain stem cell injury imaging detection method provided by the present invention, it can be known that in specific applications, the brain grayscale points are determined by the grayscale values ​​of each pixel point of the grayscale image of the brain to be detected, and the brain grayscale points can be further clustered according to the same grayscale value to determine the brain blood area contour and grayscale point data; the brain blood area contour can be used to quickly know the blood accumulation area in the brain, and the accurate brain hemorrhage analysis of the brain blood accumulation area can be obtained through the grayscale point data, thereby improving the efficiency and accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A flow chart of a method for imaging detection of hemorrhagic brain stem cell damage provided in Example 1 of the present invention;

[0043] Figure 2 This is a flow chart of the overall structure of a method for imaging detection of hemorrhagic brain stem cell damage provided in Example 1 of the present invention;

[0044] Figure 3 A flow chart of determining brain hemorrhage in a method for detecting hemorrhagic brain stem cell damage by imaging provided in Example 1 of the present invention;

[0045] Figure 4 A schematic diagram of a brain blood accumulation area of ​​a first-level brain grayscale point cluster of a hemorrhagic brain stem cell injury imaging detection method provided in Example 1 of the present invention;

[0046] Figure 5 A schematic diagram of the outline of the brain blood region of the brain blood accumulation region of a hemorrhagic brain stem cell injury imaging detection method provided in Example 1 of the present invention;

[0047] Figure 6 A double-threshold determination flow chart of a method for detecting hemorrhagic brain stem cell damage by imaging provided in Example 1 of the present invention;

[0048] Figure 7 A contour grayscale level determination flow chart of a hemorrhagic brain stem cell injury imaging detection method provided in Example 1 of the present invention;

[0049] Figure 8 A flow chart of a hemorrhagic brain stem cell injury imaging detection system provided in Embodiment 2 of the present invention;

[0050] Fig. 9 A flowchart of a storage medium provided in Embodiment 3 of the present invention.

[0051] Labels: grayscale point module 100; grayscale data module 200; brain result module 300.

[0052] Processor 1110 ; communication interface 1120 ; memory 1130 ; computer storage medium 1140 . DETAILED DESCRIPTION

[0053] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] The present invention is further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0055] Embodiment 1

[0056] like Figure 1 , Figure 2 As shown, the present invention proposes a method for imaging detection of hemorrhagic brain stem cell damage, comprising the following steps:

[0057] S1: obtaining a medical image of the brain to be tested (an image of brain stem cells); graying the medical image to be tested to obtain a grayscale image of the brain to be tested, and determining a brain grayscale point according to the grayscale value of each pixel in the grayscale image of the brain to be tested;

[0058] S2: Divide the brain grayscale image to be detected according to the brain grayscale points and record the grayscale point data; obtain the brain blood area contour of the brain grayscale image to be detected according to the edge detection algorithm; and determine whether there is cerebral hemorrhage in the brain medical image to be detected according to each of the grayscale point data and the brain blood area contour.

[0059] It should be noted that the brain medical image to be detected is grayed to obtain a gray image of the brain to be detected, and the brain gray points are determined by calculating the gray values ​​of each pixel of the brain gray image to be detected; the brain blood area contour of the brain gray image to be detected is obtained by clustering the gray values ​​of the brain gray points through an edge detection algorithm, so that the area of ​​internal brain bleeding can be accurately known, thereby improving the detection speed; and then the gray point data of brain bleeding, blood circulation of the retina, and short-term congestion of the brain caused by rapid blood circulation in the brain after human exercise are obtained by clustering the brain gray points, so as to know the factors affecting the judgment of whether the brain is bleeding, thereby accurately judging whether the brain is bleeding; whether the brain is bleeding can be accurately and quickly detected based on the judgment of the gray point data and the brain blood area contour;

[0060] Specifically, Figure 3 , Figure 4 , Figure 5 As shown, Figure 4 It is a schematic diagram of the brain blood accumulation area of ​​the first level brain gray point cluster; Figure 5 A schematic diagram of the outline of the brain blood area where the brain blood accumulates;

[0061] like Figure 3 As shown, in step S2, the grayscale image of the brain to be detected is divided according to the brain grayscale points to record the grayscale point data; the brain blood area contour of the grayscale image of the brain to be detected is obtained according to the edge detection algorithm, and whether there is cerebral hemorrhage in the medical image of the brain to be detected is judged according to each of the grayscale point data and the brain blood area contour. The specific operation steps are as follows:

[0062] S21: Calculate the grayscale value of each pixel of the grayscale image of the brain to be detected, and determine it as a brain grayscale point by judging the grayscale value; if the grayscale value of each pixel is greater than a preset grayscale value threshold o, retain the pixel that is greater than the preset grayscale value threshold o, and determine the retained pixel as a brain grayscale point; if the grayscale value of each pixel is less than or equal to the preset grayscale value threshold o, perform subsequent operations on the pixel that is less than or equal to the preset grayscale value threshold o (i.e., continue the operation in step S22);

[0063] Clustering the same grayscale value of each brain grayscale point to obtain different first-level brain grayscale point clusters; and recording grayscale point data through the first-level brain grayscale point clusters;

[0064] The gray point data include: brain hemorrhage, blood circulation of the blood retina, and rapid blood circulation in the brain after human exercise, resulting in short-term congestion of the brain;

[0065] It should be noted that the grayscale value of the pixel is used for judgment, and the pixel points with a grayscale value greater than the preset grayscale value threshold o are retained. Whether the brain is bleeding can be determined by the change of the grayscale value, and the blood state of the brain can be determined by the grayscale value of the relatively high pixel points. The brain is a sulcus structure, and there is a layer of blood retina on the surface of the sulcus structure; therefore, when the brain is bleeding, the blood flowing in the blood retina will show different grayscale value changes, so the grayscale value of the pixel point with a higher grayscale value is retained to be determined as the brain grayscale point (that is, it can also be called the brain blood point); and when the brain is bleeding, the final brain grayscale point is presented in the brain sulcus structure or the blood retina bleeding flows into the brain sulcus structure through the instrument scanning, so that the brain grayscale point cannot be fully presented, therefore, the first-level brain grayscale point cluster (that is, the blood gathering area) is connected in a range by using the subsequent brain grayscale contour points to form the brain blood area contour;

[0066] By clustering each brain grayscale point with the same grayscale value, we can get blood accumulation areas of different areas (i.e., the first-level brain grayscale point clusters). The blood accumulation areas have different shape structures or areas due to the special structure of the sulcus structure and the blood retina, resulting in different blood states, so the grayscale point data are recorded; the grayscale point data include: cerebral hemorrhage, blood circulation in the blood retina, and rapid blood circulation in the brain after human exercise, which leads to temporary congestion of the brain.

[0067] S22: The grayscale image of the brain to be detected is used to form the outline of the brain blood area through an edge detection algorithm; the pixel points with the grayscale value less than or equal to the preset grayscale value threshold o are clustered with the same grayscale value to obtain the second-level brain grayscale point cluster; the second-level brain grayscale point cluster is judged to be less than the preset brain grayscale contour point threshold t; if the second-level brain grayscale point cluster is less than the preset brain grayscale contour point threshold t, the second-level brain grayscale point cluster is judged to be the brain grayscale contour point, and the brain grayscale contour points are connected to form the brain blood area outline of the brain grayscale points; if the second-level brain grayscale point cluster is greater than or equal to the preset brain grayscale contour point threshold t, the second-level brain grayscale point cluster is eliminated;

[0068] It should be noted that the pixel points whose grayscale values ​​are less than or equal to the preset grayscale value threshold value o in step S21 are also clustered in the same manner, and it is determined whether the second-level brain grayscale point cluster is less than the preset brain grayscale contour point threshold value t. If it is less than, the second-level brain grayscale point cluster is determined to be a brain grayscale contour point; the medical image of the brain to be detected is obtained by a scanning instrument to detect whether the brain is bleeding, and the brain grayscale points (i.e., brain blood points) are connected with the brain grayscale contour points by an edge detection algorithm during the scanning process to form the brain blood area contour of the first-level brain grayscale point cluster (i.e., blood aggregation area);

[0069] Because, after clustering, the pixel points with grayscale values ​​greater than the preset grayscale value threshold o form the first-level brain grayscale point cluster. There will be discrete pixel points with grayscale values ​​less than or equal to the preset grayscale value threshold o around the first-level brain grayscale point cluster (i.e., brain grayscale points). These discrete pixel points are clustered again to form the second-level brain grayscale point cluster (i.e., brain grayscale contour points). By judging that the pixel points are less than the preset brain grayscale contour point threshold t, the first-level brain grayscale point cluster (i.e., brain grayscale points) are connected to form the brain blood area contour of the first-level brain grayscale point cluster (i.e., blood accumulation area). The brain blood area contour and the grayscale point data of the brain grayscale points are used to judge whether there is brain hemorrhage.

[0070] S23: judging whether there is brain bleeding based on the brain blood area contour and gray point data;

[0071] It should be noted that the area of ​​the blood accumulation area is judged by the brain blood area contour of the first-level brain grayscale point cluster (i.e., the blood accumulation area), and there is also grayscale point data (i.e., the grayscale point data includes: brain hemorrhage, blood circulation in the blood retina, and the rapid blood circulation in the brain after human exercise, which leads to temporary congestion of the brain); when the brain is hemorrhaged, the grayscale value of the brain grayscale point is high (i.e., the grayscale value of the first-level brain grayscale point cluster is high), which will also affect the enlargement of the brain blood area contour, thereby affecting the accuracy of judging whether the brain is bleeding.

[0072] Specifically, Figure 6 As shown, in step S23, the brain blood area contour and gray point data are used to determine whether the brain is bleeding. The specific operation steps are as follows:

[0073] S231: Determine whether the brain blood area contour is bleeding through the grayscale point data; determine the contour grayscale level of the brain blood area contour through the range between the preset first threshold W and the second threshold N (the contour grayscale level includes a low contour grayscale level, a medium contour grayscale level, and a high contour grayscale level); the "contour grayscale level" of the above-mentioned brain blood area contour refers to the grayscale ratio of the current contour grayscale to the current overall brain grayscale image to be detected; the above-mentioned first threshold W and the second threshold N are also a proportional value.

[0074] It should be noted that the outline of the brain blood area is judged by the range between the first threshold W and the second threshold N; the outline grayscale level is set for the outline of the brain blood area, when the outline grayscale level of the brain blood area outline is within the range of the first threshold W and the second threshold N, and based on the grayscale point data (combined with the grayscale point data of brain hemorrhage, blood circulation of the retina, and rapid blood circulation in the brain after human exercise leading to temporary congestion of the brain), it is proved that the brain blood area outline is a hemorrhage area of ​​the brain, and the brain is in a hemorrhage state.

[0075] S232: When the brain blood area contour is greater than the first threshold W and less than the second threshold N (i.e., the first threshold W<brain blood area contour<second threshold), the brain blood area contour is a medium contour grayscale level, and the brain blood area contour at the brain position is judged to be cerebral hemorrhage according to the grayscale point data; if the brain blood area contour is less than the first threshold W or greater than the second threshold N, the brain blood area contour is determined to be a high contour grayscale level or a low contour grayscale level, and no cerebral hemorrhage is found in the brain blood area contour at the brain position according to the grayscale point data.

[0076] It should be noted that by judging the grayscale level of the contour of the brain blood area, and then judging the state of the brain blood area contour according to the brain hemorrhage of the grayscale point data, the change of the blood grayscale value of the blood retinal circulation, and the short-term congestion of the brain caused by the rapid blood circulation in the brain after human exercise (that is, when the contour grayscale level of the brain blood area contour is large, it means that the grayscale value of the first-level brain grayscale point cluster will also be high, and the grayscale value of the first-level brain grayscale point cluster changes with the change of the contour grayscale level of the brain blood area contour, so as to judge whether the brain is bleeding according to the grayscale point data)

[0077] The study also found that in many cases the outline of the brain blood area identified by clustering may be an irregular shape. In this case, the maximum bounding box method can be used to obtain a regular shape (i.e., a circle), and the area of ​​the minimum circle outside the brain blood area outline is used as the area of ​​the brain blood area outline (wherein the maximum bounding box method is to encircle the minimum circle obtained after including all points of the brain blood area outlines of all clusters, and determine its radius and the area of ​​the minimum circle).

[0078] By comparison, when it is found that the contour area of ​​the brain blood region (i.e., the contour grayscale level) is greater than the first threshold W and less than the second threshold N (i.e., the first threshold W < brain blood region contour < second threshold), the brain blood region contour is of a medium contour grayscale level, and the brain can be accurately judged to be in a bleeding state within a certain threshold range; if a threshold is set, when the threshold is set too large, the result of the brain blood region contour will become rigorous, and if combined with the grayscale point data, the blood circulation of the blood retina will become the result of brain hemorrhage judgment, causing an error in judgment; when the threshold is set too small, the result of the brain blood region contour will become loose, and if combined with the grayscale point data, the rapid blood circulation in the brain after human exercise will cause a short-term congestion of the brain to become the result of brain hemorrhage judgment, causing an error in judgment; therefore, it is of great significance to use two thresholds to judge the contour grayscale level of the brain blood region contour.

[0079] Specifically, Figure 7 As shown, in step S231, the gray point data is used to determine whether the brain blood area contour is bleeding; the brain blood area contour is determined by a range between a preset first threshold W and a second threshold N to determine the contour gray level of the brain blood area contour, and the specific operation steps are as follows:

[0080] S2311: Determine the first threshold W and the second threshold N using the grayscale values ​​of the brain grayscale contour points of the brain blood area contour and the average grayscale value of the entire grayscale image to be detected; when the contour grayscale level of the brain blood area contour of the first-level brain grayscale point cluster (i.e., the blood aggregation area) is less than the first threshold W (i.e., the contour grayscale level of the brain blood area contour < the first threshold W), the brain blood area contour of the first-level brain grayscale point cluster is relatively small, and the brain blood area contour of the first-level brain grayscale point cluster is of a low contour grayscale level, and it is determined that the blood circulation is in the blood retina, and there is no brain bleeding;

[0081] It should be noted that the first-level brain grayscale point cluster is a blood aggregation area, and the brain grayscale contour points confirmed by the second-level brain grayscale point cluster form the brain blood area contour of the first-level brain grayscale point cluster; therefore, when the contour grayscale level of the brain blood area contour of the first-level brain grayscale point cluster (i.e., the blood aggregation area) is relatively small, it is determined that it is the blood circulation of the blood retina on the surface of the brain; because the blood retina has small blood vessels, the grayscale value of the first-level brain grayscale point cluster is relatively small, so the brain blood area contour of the blood aggregation area is relatively small, and combined with the grayscale point data, it does not meet the brain hemorrhage condition;

[0082] S2312: When the contour grayscale level of the brain blood region contour is greater than the second threshold W (i.e., the contour grayscale level of the brain blood region contour> the second threshold N), the brain blood region contour of the first-level brain grayscale point cluster (i.e., the blood aggregation area) is relatively large, and the brain blood region contour of the first-level brain grayscale point cluster is of a high contour grayscale level, and it is determined that the rapid blood circulation in the brain after human exercise leads to temporary congestion of the brain, and there is no brain bleeding;

[0083] It should be noted that when the outline of the brain blood area of ​​the first-level brain grayscale point cluster (i.e., blood accumulation area) is too large, it is determined that the rapid blood circulation in the brain after human exercise causes temporary brain congestion. When the human body is in strenuous exercise or emotional tension or excitement, the brain will be temporarily congested. When resting and calming, it will gradually recover. Therefore, the grayscale point data does not meet the brain hemorrhage condition;

[0084] S2313: When the contour grayscale level of the brain grayscale contour is greater than the first threshold W and less than the second threshold N (i.e., the first threshold W<contour grayscale level of the brain blood area contour<the second threshold), the brain blood area contour of the first-level brain grayscale point cluster is a medium contour grayscale level, and brain hemorrhage is judged based on the current grayscale point data.

[0085] It should be noted that, according to the above explanations, only when the grayscale contour of the brain is greater than the first threshold W and less than the second threshold N (that is, the first threshold W < brain blood area contour < second threshold N), the contour grayscale level of the brain grayscale contour is within the range of the two thresholds, there will be no recognition errors after blood retina and human body movement. Therefore, brain hemorrhage is judged in combination with the grayscale point data.

[0086] Specifically, in step S2311, the first threshold W and the second threshold N are determined by using the grayscale values ​​of the brain grayscale contour points of the brain blood area contour and the average grayscale value of the entire grayscale image to be detected, which specifically includes the following operation steps:

[0087] S23111: First, the average grayscale value De of the entire grayscale image to be detected and the grayscale value of the brain grayscale contour point (i.e., the second-level brain grayscale point cluster) are obtained through an adaptive threshold algorithm to calculate the first threshold W formula:

[0088]

[0089] Wherein, H is the first proportional coefficient, (Ro1, Ro2, Ro3, ..., Ron) are the grayscale values ​​of the brain grayscale contour points of the brain blood area contour (brain grayscale contour points on the brain blood area contour line); at the same time, the above-mentioned brain blood area contour is composed of n brain grayscale contour points; De is the average grayscale value of the entire grayscale image to be detected; K is the basic threshold (i.e., reference threshold);

[0090] The second threshold N is calculated by the proportionality coefficient of the first threshold W, and the calculation formula is:

[0091]

[0092] Wherein, B is the second proportional coefficient, and the second proportional coefficient B is greater than the first proportional coefficient H;

[0093] It should be noted that the first proportionality coefficient H is a parameter in the adaptive threshold algorithm, which is used to adjust the value of the first threshold W; the basic threshold K is a fixed value, and in the adaptive threshold algorithm, the basic threshold K can be considered as a starting point; the average gray value of the contour of the brain blood area is calculated, and the smaller H is, the smaller the first threshold W will be; the average gray value De of the current entire gray image to be detected is used to compare with the average gray value of the number of brain gray contour points Ro and the basic threshold K to calculate the first threshold W, and by analyzing the average gray value De of the current entire gray image to be detected and the average gray value of the number of brain gray contour points Ro and the basic threshold K, a medium threshold can be obtained (the medium threshold is a single threshold within a certain threshold range, and the single threshold, whether the threshold is too large or too small, will affect the detection of the contour gray level of the brain blood area contour, so the medium single threshold is multiplied by a certain proportion of the first proportionality coefficient H to obtain the first threshold W), and the medium threshold is multiplied by the first proportionality coefficient to accurately obtain the first threshold W;

[0094] The second threshold N is calculated using the first threshold W, the basic threshold K and the second proportional coefficient B (in the dual threshold, the first threshold W is smaller than the second threshold N. Therefore, the first threshold W will be calculated again using a certain proportion of the second proportional coefficient B, and the second proportional coefficient B will be greater than the first proportional coefficient H).

[0095] S23112: Determine the contour grayscale level of the brain blood area contour by using the first threshold W and the second threshold N, and determine whether there is brain bleeding by using the contour grayscale level of the brain blood area contour.

[0096] It should be noted that the values ​​of the two thresholds can be quickly calculated by calculating the adaptive threshold algorithm, and the contour grayscale level of the brain blood area contour can be accurately and quickly detected through the two thresholds, so as to quickly determine whether the brain is bleeding.

[0097] Compared with the prior art, it is of great significance to study the grayscale values ​​of the brain grayscale contour points on the contour line of the brain blood region. The prior art mainly analyzes the grayscale values ​​of a large number of pixel points in the region, which has a large amount of calculation and is not very targeted. However, this embodiment believes that studying the grayscale values ​​of the brain grayscale contour points on the contour line of the brain blood region can better understand the boundary characteristics of the brain blood region and realize the detection of cerebral hemorrhage.

[0098] At the same time, after determining that the contour of the brain blood area of ​​the first-level brain grayscale point cluster is a medium contour grayscale level, brain hemorrhage is judged based on the current grayscale point data; this can further verify the detection by analyzing the grayscale values ​​of the grayscale contour points on the contour line of the brain blood area, and finally determine whether there is brain hemorrhage, thereby realizing lesion detection and analysis.

[0099] Judging that there is brain hemorrhage based on the current grayscale point data is an auxiliary detection condition, and judging that there is brain hemorrhage based on the current grayscale point data is further verified.

[0100] Specifically, in step S23112, the grayscale level of the outline of the brain blood region is determined by the first threshold W and the second threshold N, and whether the brain is bleeding is determined by the grayscale level of the outline of the brain blood region, which specifically includes the following operation steps:

[0101] S231121: obtaining the middle grayscale level of the grayscale contour of the brain through the range between the first threshold W and the second threshold N, and further determining whether there is brain bleeding based on the middle grayscale level of the grayscale contour of the brain and the grayscale point data;

[0102] S231122: Preset the boundary grayscale threshold c through the adaptive threshold algorithm (that is, the grayscale point data is clustered according to the brain grayscale points to obtain the first-level brain grayscale point cluster to confirm the state division of the grayscale point data. Therefore, the role of confirming the division boundary of the first-level brain grayscale point cluster through the adaptive threshold algorithm preset threshold c is to determine the range of the three states). If the grayscale value of the first-level brain grayscale point cluster is greater than or less than the preset boundary grayscale threshold c, it is determined that the proportion of grayscale point data belonging to the brain hemorrhage state is greater than the proportion threshold of grayscale point data belonging to the brain non-hemorrhage state (that is, the blood circulation of the blood retina, the rapid blood circulation of the brain after human exercise leads to temporary congestion of the brain); if the grayscale value of the first-level brain grayscale point cluster is equal to the preset boundary grayscale threshold c, it is determined that the proportion of grayscale point data belonging to the brain hemorrhage state is less than the proportion threshold of grayscale point data belonging to the brain non-hemorrhage state, and the subsequent steps are performed;

[0103] It should be noted that the grayscale point data are obtained by clustering the brain grayscale points to obtain the first-level brain grayscale point clusters, and then recording the obtained grayscale point data; the grayscale point data include three states: cerebral hemorrhage, retinal blood circulation, and rapid blood circulation in the brain after human exercise leading to temporary congestion of the brain; the grayscale point data are divided by a boundary based on these three states, and the grayscale point data are confirmed by the first-level brain grayscale point clusters. Therefore, the role of confirming the division boundary by using the adaptive threshold algorithm to preset the threshold c for the first-level brain grayscale point clusters is to determine the range of the three states, so as to further analyze the grayscale point data, and by setting the threshold c, determine which data states belong to cerebral hemorrhage, retinal blood circulation, or temporary congestion of the brain due to rapid blood circulation in the brain after human exercise, and different states can be classified data proportion grouping; if it is greater than or less than the limit grayscale threshold c, it is determined that the grayscale point data belonging to the brain non-bleeding state accounts for less than 1 / 3 of the total grayscale point data (i.e., the proportion of grayscale point data belonging to the brain non-bleeding state) ("1 / 3" is just a reference constant value, or the proportion is low), the probability of brain hemorrhage is relatively small, or there are other influencing factors that lead to a low proportion of bleeding state, and it indicates that the blood aggregation area of ​​the grayscale point data (i.e., the first-level brain grayscale point cluster) is the blood circulation of the blood retina or the rapid blood circulation of the brain after human exercise, resulting in a short-term congestion state of the brain; if it is equal to the limit grayscale threshold c, it is determined that the grayscale point data belonging to the brain non-bleeding state accounts for more than 2 / 3 of the total grayscale point data, the probability of brain hemorrhage is relatively high, or brain hemorrhage has already occurred.

[0104] S231123: Calculate the average grayscale value (i.e. the average grayscale value of all brain grayscale contour points on the brain blood area contour line) of the grayscale values ​​of the brain grayscale contour points of the middle contour grayscale level of the brain grayscale contour (i.e. the second-level brain grayscale point cluster, the brain grayscale contour points on the brain blood area contour line); compare the average grayscale value of the brain grayscale contour points of the middle contour grayscale level of the brain grayscale contour with the grayscale value of the grayscale point data (i.e. the grayscale point data is confirmed by the first-level brain grayscale point cluster, therefore, the grayscale point data can be calculated with grayscale values ​​or compared with other grayscale values) by using a preset contrast threshold z; if the average grayscale value of the brain grayscale contour points of the middle contour grayscale level of the brain grayscale contour and the grayscale value of the grayscale point data are both greater than the preset contrast threshold z, then There is cerebral hemorrhage in the medical image of the brain to be detected; if the average grayscale value of the brain grayscale contour points of the medium contour grayscale level of the brain grayscale contour is less than or equal to the preset contrast threshold z (that is, the grayscale value of the grayscale point data is greater than the preset contrast threshold z), the comparison between the two fails, and the first threshold W and the second threshold N are recalculated by the adaptive threshold algorithm, and the contour grayscale level of the brain grayscale contour is detected within the range between the first threshold W and the second threshold N; if the grayscale value of the grayscale point data is less than or equal to the preset contrast threshold z (that is, the average grayscale value of the brain grayscale contour points of the medium contour grayscale level of the brain grayscale contour is greater than the preset contrast threshold z), the comparison between the two fails, and the preset boundary grayscale threshold c is iterated by the adaptive threshold algorithm until the comparison between the two is successful and both are greater than the preset contrast threshold z;

[0105] It should be noted that, when the two are compared, only when the average grayscale value of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour and the grayscale value of the grayscale point data are all greater than the preset comparison threshold z, can it be explained that there is brain hemorrhage in the brain medical image to be detected; when one or all of the average grayscale value of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour or the grayscale value of the grayscale point data is less than or equal to the preset comparison threshold z, the brain hemorrhage state is not detected; and the first threshold W and the second threshold N are recalculated by the adaptive threshold algorithm (that is, the dual thresholds are calculated by re-adjusting the proportional coefficient) or the preset limit grayscale threshold c is iterated until the conditions are met;

[0106] By recalculating or iterating the threshold, the brain hemorrhage status can be judged more accurately, the misdiagnosis rate and missed diagnosis rate can be reduced, and the accuracy and reliability of diagnosis can be improved; at the same time, the threshold can be dynamically adjusted through the adaptive threshold algorithm, making the detection algorithm of brain hemorrhage status more flexible, accurate and applicable, which helps to improve the accuracy and efficiency of medical image analysis.

[0107] Embodiment 2

[0108] like Figure 8 As shown, accordingly, the present invention also proposes a hemorrhagic brain stem cell injury imaging detection system, including: a gray point module 100, a gray data module 200, and a brain result module 300;

[0109] The grayscale point module 100 is used to obtain a medical image of the brain to be detected; grayscale the medical image to be detected to obtain a grayscale image of the brain to be detected, and determine the brain grayscale point according to the grayscale value of each pixel in the grayscale image of the brain to be detected;

[0110] The grayscale data module 200 is used to obtain the brain grayscale points to divide the grayscale image of the brain to be detected and record the grayscale point data; obtain the brain blood area contour of the grayscale image of the brain to be detected according to the edge detection algorithm;

[0111] The brain result module 300 is used to determine whether there is cerebral hemorrhage in the brain medical image to be detected based on each of the grayscale point data and the brain blood area contour.

[0112] Embodiment 3

[0113] like Fig. 9 As shown, on the other hand, this embodiment 3 is based on the hemorrhagic brain stem cell injury imaging detection method provided in the invention embodiment 1, and further provides a computer storage medium 1140 (hereinafter referred to as storage medium). It is a schematic diagram of the computer storage medium structure framework provided in the invention embodiment 3, which includes:

[0114] A memory 1130, used for storing computer programs;

[0115] The communication interface 1120 is used to connect the memory 1130 to the processor 1110;

[0116] The processor 1110 is used to execute a computer program to implement an imaging detection method for hemorrhagic brain stem cell damage involved in an embodiment disclosed in combination with any of the above-mentioned implementation modes.

[0117] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application specific integrated circuits, digital signal processors, digital signal processing devices, programmable logic devices, field programmable gate arrays, general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0118] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0119] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] In summary, the imaging detection method for hemorrhagic brain stem cell damage proposed in the example of the present invention determines the brain grayscale points by the grayscale values ​​of each pixel point of the grayscale image of the brain to be detected, and the brain blood area contour and grayscale point data can be further determined by clustering the brain grayscale points according to the same grayscale value; the brain blood area contour can be used to quickly know the blood accumulation area of ​​the brain, and the accurate brain hemorrhage analysis of the brain blood accumulation area can be obtained by the grayscale point data, thereby improving the efficiency and accuracy of detection;

[0122] Furthermore, the brain grayscale points are clustered by preset grayscale value thresholds to form a first-level brain grayscale point cluster, through which the outline of the brain blood area can be obtained, and through different grayscale value changes, the brain sulcus structure can present the brain blood detection area, thereby reducing the detection difficulty and improving the detection speed;

[0123] Furthermore, by clustering the brain grayscale points to form a second-level brain grayscale point cluster, grayscale point data is obtained, and the blood status of the brain is determined based on the grayscale point data, such as the blood retina on the surface of the sulcus structure of the brain and the speed of blood flow in the brain after human exercise. The second-level brain grayscale point cluster with different grayscale value changes reflects whether the brain is bleeding, thereby improving the detection accuracy and judging whether there is actual bleeding in the brain.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. A person skilled in the art may modify the technical solutions described in the above embodiments, or replace part or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting hemorrhagic brain stem cell damage by imaging, characterized in that: The steps are as follows: Acquire a medical image of the brain to be detected; grayscale the medical image to be detected to obtain a grayscale image of the brain to be detected, and determine the brain grayscale point according to the grayscale value of each pixel in the grayscale image of the brain to be detected; Dividing the grayscale image of the brain to be detected according to the brain grayscale points and recording the grayscale point data; obtaining the brain blood area contour of the grayscale image of the brain to be detected according to the edge detection algorithm; and judging whether there is cerebral hemorrhage in the medical image of the brain to be detected according to each of the grayscale point data and the brain blood area contour; The grayscale image of the brain to be detected is divided according to the brain grayscale points to record the grayscale point data; the brain blood area contour of the grayscale image of the brain to be detected is obtained according to the edge detection algorithm, and whether there is cerebral hemorrhage in the medical image of the brain to be detected is judged according to each of the grayscale point data and the brain blood area contour. The specific operation steps are as follows: Calculate the grayscale value of each pixel of the grayscale image of the brain to be detected, and determine it as a brain grayscale point by judging it according to the grayscale value; if the grayscale value of each pixel is greater than a preset grayscale value threshold o, retain the pixel that is greater than the preset grayscale value threshold o, and determine the retained pixel as a brain grayscale point; if the grayscale value of each pixel is less than or equal to the preset grayscale value threshold o, perform subsequent operations on the pixel that is less than or equal to the preset grayscale value threshold o; Clustering the same grayscale value of each brain grayscale point to obtain different first-level brain grayscale point clusters; and recording grayscale point data through the first-level brain grayscale point clusters; The grayscale image of the brain to be detected forms the outline of the brain blood area through an edge detection algorithm; the pixel points with the grayscale value less than or equal to the preset grayscale value threshold o are clustered with the same grayscale value to obtain a second-level brain grayscale point cluster; Determining whether the second-level brain grayscale point cluster is smaller than a preset brain grayscale contour point threshold t; If the second-level brain grayscale point cluster is smaller than the preset brain grayscale contour point threshold t, the second-level brain grayscale point cluster is determined to be a brain grayscale contour point, and the brain grayscale contour points are connected to form a brain blood area contour of the brain grayscale points; If the second-level brain grayscale point cluster is greater than or equal to the preset brain grayscale contour point threshold t, the second-level brain grayscale point cluster is eliminated; Whether there is brain bleeding is determined by the brain blood area contour and gray point data.

2. The imaging detection method for hemorrhagic brain stem cell damage according to claim 1, characterized in that: The gray point data include: brain hemorrhage, blood circulation in the retina, and rapid blood circulation in the brain after human exercise, which leads to short-term congestion of the brain.

3. The imaging detection method for hemorrhagic brain stem cell damage according to claim 2, characterized in that: The specific operation steps of judging whether the brain is bleeding by the brain blood area contour and gray point data are as follows: Determine whether the brain blood area contour is bleeding by using the gray point data; determine the contour gray level of the brain blood area contour by a range between a preset first threshold W and a second threshold N; When the brain blood area contour is greater than the first threshold W and less than the second threshold N, the brain blood area contour is a medium contour grayscale level, and the brain blood area contour at the brain position is judged to be cerebral hemorrhage according to the grayscale point data; if the brain blood area contour is less than the first threshold W or greater than the second threshold N, the brain blood area contour is determined to be a high contour grayscale level or a low contour grayscale level, and no cerebral hemorrhage is found in the brain blood area contour at the brain position according to the grayscale point data.

4. A method for detecting hemorrhagic brain stem cell damage by imaging according to claim 3, characterized in that: The brain blood area contour determines the contour gray level of the brain blood area contour by a range between a preset first threshold value W and a second threshold value N, and the specific operation steps are as follows: The first threshold W and the second threshold N are determined by using the grayscale values ​​of the brain grayscale contour points of the brain blood area contour and the average grayscale value of the entire grayscale image to be detected; when the contour grayscale level of the brain blood area contour of the first-level brain grayscale point cluster is less than the first threshold W, the brain blood area contour of the first-level brain grayscale point cluster is too small, and the brain blood area contour of the first-level brain grayscale point cluster is of a low contour grayscale level, and it is determined that the blood circulation of the blood retina is good, and there is no brain bleeding; When the contour gray level of the brain blood region contour is greater than the second threshold value W, the brain blood region contour of the first-level brain gray point cluster is larger, and the brain blood region contour of the first-level brain gray point cluster is of a high contour gray level, and it is determined that the rapid blood circulation in the brain after human exercise leads to temporary congestion of the brain, and there is no brain bleeding; When the contour grayscale level of the brain grayscale contour is greater than the first threshold W and less than the second threshold N, the brain blood area contour of the first-level brain grayscale point cluster is a medium contour grayscale level, and brain hemorrhage is determined based on the current grayscale point data.

5. A method for detecting hemorrhagic brain stem cell damage by imaging according to claim 4, characterized in that: The first threshold W and the second threshold N are determined by using the grayscale value of the brain grayscale contour point of the brain blood area contour and the average grayscale value of the entire grayscale image to be detected, which specifically includes the following operation steps: The formula for calculating the first threshold W by obtaining the average grayscale value De of the entire grayscale image to be detected and the grayscale value of the brain grayscale contour point through the adaptive threshold algorithm is: Wherein, H is the first proportional coefficient, (Ro1, Ro2, Ro3, ..., Ron) are the grayscale values ​​of the brain grayscale contour points of the brain blood area contour; at the same time, the above-mentioned brain blood area contour is composed of n brain grayscale contour points; De is the average grayscale value of the entire grayscale image to be detected; K is the basic threshold; The second threshold N is calculated by the proportionality coefficient of the first threshold W, and the calculation formula is: Wherein, B is the second proportional coefficient, and the second proportional coefficient B is greater than the first proportional coefficient H; The contour grayscale level of the brain blood region contour is determined by the first threshold W and the second threshold N, and whether the brain is bleeding is determined by the contour grayscale level of the brain blood region contour.

6. A method for detecting hemorrhagic brain stem cell damage by imaging according to claim 5, characterized in that: The step of judging the grayscale level of the contour of the brain blood region by using the first threshold W and the second threshold N, and judging whether the brain is bleeding by using the grayscale level of the contour of the brain blood region, specifically includes the following steps: Obtaining the middle contour gray level of the brain gray contour through the range between the first threshold W and the second threshold N, and further determining whether the brain is bleeding based on the middle contour gray level of the brain gray contour and the gray point data; A grayscale threshold c is preset by an adaptive threshold algorithm. If the grayscale value of the first-level brain grayscale point cluster is greater than or less than the preset grayscale threshold c, it is determined that the grayscale point data ratio of the brain hemorrhage state is greater than the grayscale point data ratio threshold of the brain non-hemorrhage state; If the gray value of the first-level brain gray point cluster is equal to the preset gray threshold c, it is determined that the gray point data ratio of the brain hemorrhage state is less than the gray point data ratio threshold of the brain non-hemorrhage state, and subsequent steps are performed; The average grayscale value of the grayscale values ​​of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour is calculated; the average grayscale value of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour is compared with the grayscale value of the grayscale point data through a preset contrast threshold z; if the average grayscale value of the brain grayscale contour points of the medium grayscale level of the brain grayscale contour and the grayscale value of the grayscale point data are both greater than the preset contrast threshold z, then there is cerebral hemorrhage in the brain medical image to be detected; if the medium grayscale level of the brain grayscale contour is When the average grayscale value of the grayscale contour points of the grayscale level of the brain is less than or equal to the preset contrast threshold z, the comparison between the two fails, and the first threshold W and the second threshold N are recalculated through the adaptive threshold algorithm, and the contour grayscale level of the brain grayscale contour is detected in the range between the first threshold W and the second threshold N; if the grayscale value of the grayscale point data is less than or equal to the preset contrast threshold z, the comparison between the two fails, and the preset boundary grayscale threshold c is iterated through the adaptive threshold algorithm until the comparison between the two is successful and greater than the preset contrast threshold z.

7. A hemorrhagic brain stem cell injury imaging detection system, characterized in that: Used to implement a method for detecting hemorrhagic brain stem cell damage imaging as described in any one of claims 1 to 6, the system comprising: a gray point module, a gray data module, and a brain result module; The grayscale point module is used to obtain a medical image of the brain to be detected; grayscale the medical image to be detected to obtain a grayscale image of the brain to be detected, and determine the brain grayscale point according to the grayscale value of each pixel in the grayscale image of the brain to be detected; The grayscale data module is used to obtain the brain grayscale points to divide the grayscale image of the brain to be detected and record the grayscale point data; obtain the brain blood area contour of the grayscale image of the brain to be detected according to the edge detection algorithm; The brain result module is used to determine whether there is cerebral hemorrhage in the brain medical image to be detected based on each of the grayscale point data and the brain blood area contour.

8. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the imaging detection method for hemorrhagic brain stem cell damage described in any one of claims 1 to 6 are implemented.

Images