Image Analysis Method, System, Device, and Medium

Abstract

The present application discloses an image analysis method, system, device, and medium. The image analysis method includes: performing target area analysis on a target image containing blood vessels to obtain an analysis result of the target image, where the analysis result includes the positions of at least one target area in the blood vessels; and determining the degree of blood vessel stenosis corresponding to each target area by using the blood vessel size information at at least two target positions corresponding to each target area. The above solution can improve the efficiency of target area analysis.

Description

Technical Field

[0001] This application relates to the field of image processing technologies, and particularly to an image analysis method, system, device, and medium. Background Art

[0002] Early detection of the degree of vascular stenosis is very important for preventing ischemic diseases. Generally, the narrower the blood vessel, the higher the likelihood of developing the disease. Therefore, in vascular analysis, it is generally necessary to analyze the degree of vascular stenosis and the stenotic site of the blood vessel.

[0003] However, currently, generally, doctors judge the degree of vascular stenosis and the stenotic site where the degree of vascular stenosis is located based on their experience on the scanned images of patients. The problems with this method include that it takes a long time for doctors to perform manual analysis and the analysis efficiency is not high. Summary of the Invention

[0004] This application provides at least an image analysis method, system, device, and medium.

[0005] This application provides an image analysis method, including: performing target region analysis on a target image containing blood vessels to obtain an analysis result of the target image, where the analysis result includes the positions of at least one target region in the blood vessel; and determining the degree of vascular stenosis corresponding to each target region by using the blood vessel size information at at least two target positions corresponding to each target region.

[0006] Therefore, after performing target region analysis on the target image, and then obtaining the degree of vascular stenosis corresponding to each target region, it realizes automatic target region analysis of the target image without manual participation, improving the efficiency of target region analysis. Moreover, by using the blood vessel size information at at least two target positions to determine the degree of vascular stenosis corresponding to the target region, the accuracy of the obtained degree of vascular stenosis is improved.

[0007] Wherein, the at least two target positions are the positions at both ends of the target region in the blood vessel; and / or, the blood vessel size information is the blood vessel diameter; and / or, the target region includes the region where the target plaque is located.

[0008] Therefore, by using the blood vessel size information corresponding to the positions at both ends of the target region to determine the degree of vascular stenosis corresponding to the target region, it can reduce the calculation error caused by the sudden decrease in blood vessel size. In addition, the method of obtaining the blood vessel diameter is simple, so the process of determining the degree of vascular stenosis corresponding to the target region by the blood vessel diameter is also relatively simple. In addition, by performing plaque analysis on the target image to obtain the position of the target plaque in the blood vessel, the degree of vascular stenosis corresponding to each target plaque can be determined.

[0009] Among them, determining the degree of vascular stenosis corresponding to each target area by using the vascular size information of at least two target positions corresponding to each target area includes: for each target area, respectively determining the first vascular stenosis rate of the target area with respect to each target position based on the vascular size information of each target position corresponding to the target area; and obtaining the degree of vascular stenosis corresponding to the target area by using the first vascular stenosis rate of the target area with respect to each target position.

[0010] Therefore, by obtaining the degree of vascular stenosis corresponding to the target area by using the first vascular stenosis rate of the target area with respect to each target position, the accuracy of the obtained degree of vascular stenosis can be improved.

[0011] Among them, obtaining the degree of vascular stenosis corresponding to the target area by using the first vascular stenosis rate of the target area with respect to each target position includes: counting the first vascular stenosis rate of the target area with respect to each target position to obtain the second vascular stenosis rate corresponding to the target area; and determining the degree of vascular stenosis corresponding to the target area based on the second vascular stenosis rate, where the degree of vascular stenosis includes the second vascular stenosis rate and / or the preset degree description corresponding to the second vascular stenosis rate.

[0012] Therefore, by counting the first vascular stenosis rate of the target area with respect to each target position to obtain the second vascular stenosis rate corresponding to the target area, the determined second vascular stenosis rate is more accurate.

[0013] Among them, respectively determining the first vascular stenosis rate of the target area with respect to each target position based on the vascular size information of each target position corresponding to the target area includes: in response to the user's first selection instruction, selecting at least one target vascular stenosis rate determination method from several vascular stenosis rate determination methods; and for each target position, processing the vascular size information of the target position by using at least one target vascular stenosis rate determination method to obtain the first vascular stenosis rate of the target area with respect to the target position.

[0014] Therefore, by responding to the user's first selection instruction, selecting at least one target vascular stenosis rate from several vascular stenosis rate determination methods, and obtaining the corresponding first vascular stenosis rate according to the target vascular stenosis rate determination method, the user can determine the corresponding target vascular stenosis rate determination method according to the specific application scenario, improving the flexibility of the image analysis method.

[0015] Among them, using at least one target blood vessel stenosis rate determination method to process the blood vessel size information of the target position to obtain the first blood vessel stenosis rate of the target area with respect to the target position includes: using each target blood vessel stenosis rate determination method to process the blood vessel size information of the target position respectively to obtain the candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method; performing a preset operation on the candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method to obtain the first blood vessel stenosis rate of the target area with respect to the target position.

[0016] Therefore, by performing a preset operation on the candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method to obtain the first blood vessel stenosis rate of the target area with respect to the target position, the obtained first blood vessel stenosis rate is more accurate.

[0017] Among them, performing target area analysis on the target image containing blood vessels to obtain the analysis result of the target image includes: using the region classification model to perform target area analysis on the target image to obtain the analysis result of the target image, and the analysis result also includes the category of the target object contained in each target area.

[0018] Therefore, by using the region classification model to perform target area analysis on the target image and obtaining the category of the target object contained in the target area, so that the doctor can formulate a corresponding surgical plan according to the category of the target object contained in the target area subsequently, which greatly improves the doctor's work efficiency.

[0019] Among them, before performing target area analysis on the target image containing blood vessels to obtain the analysis result of the target image, the method further includes: performing image reconstruction on the scan image containing at least one blood vessel to obtain the blood vessel reconstruction map corresponding to each blood vessel, where the blood vessel reconstruction map is used as the target image.

[0020] Therefore, by reconstructing the scan image to obtain the blood vessel reconstruction map and using the blood vessel reconstruction map as the target image, compared with directly performing target area analysis on the scan image, the accuracy of the analysis result can be improved.

[0021] Among them, the analysis result includes the category of the target object contained in each target area. After determining the blood vessel stenosis degree corresponding to each target area by using the blood vessel size information of at least two target positions corresponding to each target area, the method further includes: displaying the blood vessel identifier corresponding to each blood vessel contained in the scan image; in response to the user's second selection instruction, selecting the target blood vessel from each blood vessel identifier; displaying the first area information of each target area in the target blood vessel, where the first area information includes the blood vessel stenosis degree and / or category.

[0022] Therefore, by selecting a target blood vessel from each blood vessel identification based on the user's second selection instruction and displaying the first region information of each target region in the target blood vessel, the interaction with the user can be improved.

[0023] Among them, the degree of blood vessel stenosis includes the second blood vessel stenosis rate corresponding to the target region; after determining the degree of blood vessel stenosis corresponding to each target region by using the blood vessel size information of at least two target positions corresponding to each target region, the method further includes: displaying a target image and displaying second region information on the target image, where the second region information includes the analysis result of the target image and / or the second blood vessel stenosis rate corresponding to each target region.

[0024] Therefore, by displaying the target image and displaying the second region information on the target image, the user can intuitively observe the regional distribution on the target image and check the analysis result of the region.

[0025] Among them, after displaying the target image and displaying the second region information on the target image, the method further includes: in response to a moving instruction for the target image, moving the target image and adjusting the display position of the second region information; and / or, the target image is obtained by reconstructing a scanned image, and displaying the target image includes: adjusting the scan value of the target image according to the type of the target region to increase the contrast between the blood vessel region of the target image containing the target region and the blood vessel region not containing the target region.

[0026] Therefore, by receiving a moving instruction for the target image, moving the target image and adjusting the display position of the second region information, the user can check the region information on the target image from multiple angles. In addition, by adjusting the scan value of the target image according to the type of the target region, the contrast between the blood vessel region of the target image containing the target region and the blood vessel region not containing the target region can be increased, thereby facilitating the user to check the analysis result of the target image.

[0027] This application provides an image analysis system, including: an analysis module for performing target region analysis on a target image containing blood vessels to obtain an analysis result of the target image, where the analysis result includes the position of at least one target region in the blood vessel; a blood vessel stenosis degree determination module for determining the blood vessel stenosis degree corresponding to each target region by using the blood vessel size information of at least two target positions corresponding to each target region.

[0028] This application provides an electronic device, including a memory and a processor, where the processor is configured to execute program instructions stored in the memory to implement the above image analysis method.

[0029] This application provides a computer-readable storage medium, on which program instructions are stored, and when the program instructions are executed by a processor, the above image analysis method is implemented.

[0030] In the above solution, after analyzing the target regions of the target image, the degree of vascular stenosis corresponding to each target region is obtained, realizing the automated analysis of the target regions of the target image without manual participation, which improves the efficiency of the target region analysis. Moreover, by using the vascular size information at at least two target positions, the degree of vascular stenosis corresponding to the target region is determined, which improves the accuracy of the obtained degree of vascular stenosis.

[0031] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification. These drawings illustrate embodiments consistent with this application and, together with the specification, are used to explain the technical solutions of this application.

[0033] Figure 1 is a schematic flowchart of an embodiment of the image analysis method of this application;

[0034] Figure 2 is a schematic sub - flowchart showing step S12 in an embodiment of the image analysis method of this application;

[0035] Figure 3 is another schematic flowchart of an embodiment of the image analysis method of this application;

[0036] Figure 4 is a schematic interface diagram showing a vascular list in an embodiment of the image analysis method of this application;

[0037] Figure 5 is a schematic structural diagram of an embodiment of the image analysis system of this application;

[0038] Figure 6 is a schematic structural diagram of an embodiment of the electronic device of this application;

[0039] Figure 7 is a schematic structural diagram of an embodiment of the computer - readable storage medium of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The following will describe the solutions of the embodiments of this application in detail with reference to the drawings in the specification.

[0041] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures, interfaces, and technologies are presented in order to thoroughly understand this application.

[0042] As used herein, the term "and / or" merely describes the associated relationship of associated objects and indicates that there can be three relationships. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " in this text generally indicates that the associated objects before and after are in an "or" relationship. Furthermore, "plurality" in this text means two or more than two. Additionally, the term "at least one" in this text means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0043] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an embodiment of the image analysis method of the present application. Specifically, the following steps may be included:

[0044] Step S11: Perform target region analysis on a target image containing blood vessels to obtain an analysis result of the target image, where the analysis result includes the positions of at least one target region in the blood vessels.

[0045] Among them, there are various ways to perform target region analysis on a target image containing blood vessels. For example, according to a pre-trained network model for target region analysis, perform target region analysis on a target image containing blood vessels to obtain an analysis result of the target image.

[0046] The target image containing blood vessels can be a scanned image containing blood vessels or an image obtained by performing image processing on the scanned image. The blood vessels can be blood vessels in the human head and neck, such as the internal carotid artery, vertebral artery, etc. In some application scenarios, the blood vessels include the left carotid artery, right carotid artery, left vertebral artery, and right vertebral artery.

[0047] Step S12: Determine the degree of blood vessel stenosis corresponding to each target region by using the blood vessel size information at at least two target positions corresponding to each target region.

[0048] The blood vessel size information at at least two target positions corresponding to each target region can specifically be the blood vessel size information at at least two target positions corresponding to each target region respectively. The target position can specifically be the blood vessel region in the blood vessel where the target region is located without the target region. The degree of blood vessel stenosis corresponding to the target region is the degree of blood vessel stenosis at the position of the blood vessel where the target region is located. For example, if the target region is at position a in the vertebral artery, the degree of blood vessel stenosis corresponding to the target region is specifically the degree of blood vessel stenosis at position a in the vertebral artery, that is, the degree of blood vessel stenosis of this blood vessel.

[0049] In the above solution, after analyzing the target regions of the target image, the degree of vascular stenosis corresponding to each target region is obtained, realizing the automated analysis of the target regions of the target image without manual participation, and improving the efficiency of the target region analysis. Moreover, by using the vascular size information at at least two target positions, the degree of vascular stenosis corresponding to the target region is determined, improving the accuracy of the obtained degree of vascular stenosis.

[0050] In some disclosed embodiments, the target region is a region containing the target object. The target object may be a target plaque. Exemplarily, the target region includes the region where the target plaque is located. By performing target plaque analysis on the target image containing blood vessels, the analysis result of the target image is obtained. Among them, the analysis result includes the position of at least one target plaque in the blood vessel. By performing target image plaque analysis, the position of the target plaque in the blood vessel can be obtained to determine the degree of vascular stenosis corresponding to each target plaque.

[0051] In some disclosed embodiments, the at least two target positions are positions at both ends of the target region in the blood vessel. Both ends of the target region can be considered as the two ends along the extending direction of the blood vessel. For example, if the target region is in the middle of the blood vessel, the two target positions can be the blood vessel positions separated from the target region by a preset distance. The calculation method of the distance from the target region can be the distance from the center point of the target region in the blood vessel length direction, or the distance from any other position in the target region. For example, the target position can specifically be a blood vessel region 5 cm away from the target region in the blood vessel. Among them, the preset distance can be user-defined or the default setting can be selected.

[0052] The vascular size information includes the blood vessel diameter. Specifically, the blood vessel diameter refers to the diameter of the blood vessel channel surrounded by the inner wall of the blood vessel. In some other disclosed embodiments, the blood vessel diameter can also be the diameter corresponding to the outer wall of the blood vessel. Of course, the vascular size can also include the blood vessel radius. The vascular size information of the target position can be the size information of the blood vessel at this target position, or the average vascular size information, the maximum vascular size information or the minimum vascular size information of a blood vessel region centered on the target position and not containing any target regions. For example, the vascular size information of the target position can be the average blood vessel diameter of a blood vessel region centered on the target position and not containing any detected target regions.

[0053] By using the vascular size information corresponding to the positions at both ends of the target region to determine the degree of vascular stenosis corresponding to the target region, the calculation error caused by the sudden decrease in the vascular size can be reduced. In addition, the method for obtaining the blood vessel diameter is simple, so the process of determining the degree of vascular stenosis corresponding to the target region through the blood vessel diameter is also relatively simple.

[0054] Please also refer to Figure 2 ,Figure 2 This is a schematic diagram of the sub - process showing step S12 in an embodiment of the image analysis method of this application. As Figure 2 shown, the above - mentioned step S12 includes the following steps:

[0055] Step S121: For each target region, based on the blood - vessel size information of each target position corresponding to the target region, respectively determine the first blood - vessel stenosis rate of the target region with respect to each target position.

[0056] In some application scenarios, if the blood vessels are the blood vessels in the head and neck, including the carotid artery and the vertebral artery, since the blood - vessel sizes of the carotid artery and the vertebral artery will face the problem of sudden changes, the embodiments of this disclosure utilize the blood - vessel size information of two target positions to obtain the degree of blood - vessel stenosis corresponding to the position where the target region is located, which can improve the accuracy of the obtained degree of blood - vessel stenosis.

[0057] Specifically, for each target region, it is also necessary to obtain the blood - vessel size information of the position where the target region is located. Among them, the blood - vessel size information of the position where the target region is located is specifically the difference between the diameter of the blood vessel and the thickness of the region in the blood - vessel width direction. Of course, if the shape of the target region is irregular, the length in the blood - vessel length direction is long, the thickness is uneven, and there may be multiple differences between the diameter of the blood vessel and the thickness of the target region in the blood - vessel width direction. The embodiments of this disclosure select the minimum thickness difference as the final difference between the diameter of the blood vessel and the thickness of the region in the blood - vessel width direction. Exemplarily, the diameter of the blood vessel at the position where the target region is located is 2 cm, and the thickness of the target region in the blood - vessel width direction is 1.5 cm, then the difference between the diameter of the blood vessel and the thickness of the target region in the blood - vessel width direction is 0.5 cm.

[0058] Among them, the first blood - vessel stenosis rate of the target region with respect to each target position is specifically the blood - vessel stenosis rate of the position where the target region is located determined based on the blood - vessel size information of this target position. For example, the target region is at position a of the blood vessel. If the target positions include the first target position and the second target position, the first target position is on the left side of the target region, and the second target position is on the right side of the target region. The first blood - vessel stenosis rate of the target region with respect to the first target position is the blood - vessel stenosis rate at position a of the blood vessel determined based on the blood - vessel size information of the first target position. The first blood - vessel stenosis rate of the target region with respect to the second target position is the blood - vessel stenosis rate at position a of the blood vessel determined based on the blood - vessel size information of the second target position.

[0059] The method for obtaining the first vascular stenosis rate can be the NASCET (Symptomatic Carotid Endarterectomy Trial, ultrasonic parameter method), the ECST (European Carotid Surgery Trial) method, or the CC (Common Carotid) method. Taking the NASCET method as an example, if the vascular diameter at one target position is 2 cm, the first vascular stenosis rate of the target area corresponding to this target position is (2 - 0.5) / 2 = 0.75. If the vascular diameter at another target position is 3 cm, the first vascular stenosis rate of the target area corresponding to this target position is (3 - 1.5) / 3 = 0.5. Among them, in some disclosed embodiments, the vascular stenosis rate can also be expressed as a percentage. For example, the percentages of the above two vascular stenosis rates 0.75 and 0.5 are expressed as 75% and 50%. There are no excessive limitations on the specific manifestation form of the vascular stenosis rate here.

[0060] By using the vascular size information corresponding to the positions at both ends of the target area to determine the degree of vascular stenosis corresponding to the target area, it is possible to reduce the calculation error caused by the sudden decrease in vascular size. In addition, the method for obtaining the vascular diameter is simple, so the process of determining the degree of vascular stenosis corresponding to the target area based on the vascular diameter is also relatively simple.

[0061] In some other disclosed embodiments, in response to the user's first selection instruction, at least one target vascular stenosis rate determination method is selected from several vascular stenosis rate determination methods. For example, the vascular stenosis rate determination methods available for the user to select include the above three. The user's selection instruction for one or more of them is received so as to obtain the corresponding first vascular stenosis rate according to the target vascular stenosis rate determination method selected by the user.

[0062] Then, for each target position, at least one target vascular stenosis rate determination method is used to process the vascular size information of the target position to obtain the first vascular stenosis rate of the target area corresponding to the target position.

[0063] By responding to the user's first selection instruction, selecting at least one target vascular stenosis rate from several vascular stenosis rate determination methods, and obtaining the corresponding first vascular stenosis rate according to the target vascular stenosis rate determination method, the user can determine the corresponding target vascular stenosis rate determination method according to the specific application scenario, which improves the flexibility of target area analysis.

[0064] Specifically, using each method for determining the target blood vessel stenosis rate, the blood vessel size information at the target position is processed respectively to obtain the candidate blood vessel stenosis rates corresponding to each method for determining the target blood vessel stenosis rate. Continuing with the above example, in the case where the method for determining the target blood vessel stenosis rate is the NASCET method, the candidate blood vessel stenosis rate corresponding to the target area with respect to the target position is obtained. Similarly, when the target blood vessel stenosis rate is determined by other methods, the candidate blood vessel stenosis rate corresponding to the target area with respect to the target position is obtained. Then, a preset operation is performed on the candidate blood vessel stenosis rates corresponding to each method for determining the target blood vessel stenosis rate to obtain the first blood vessel stenosis rate of the target control with respect to the target position. Specifically, the preset operation can specifically be to calculate the average value. That is, the average value of the candidate blood vessel stenosis rates corresponding to all methods for determining the target blood vessel stenosis rate with respect to a target position is calculated to obtain the first blood vessel stenosis rate of the target area at this target position. By performing a preset operation on the candidate blood vessel stenosis rates corresponding to each method for determining the target blood vessel stenosis rate, the first blood vessel stenosis rate of the target area with respect to the target position is obtained, making the obtained first blood vessel stenosis rate more accurate.

[0065] Step S122: Using the first blood vessel stenosis rate of the target area with respect to each target position, obtain the degree of blood vessel stenosis corresponding to the target area.

[0066] In some disclosed embodiments, the first blood vessel stenosis rates of the target area with respect to each target position are statistically analyzed to obtain the second blood vessel stenosis rate corresponding to the target area.

[0067] Specifically, the average value of the first blood vessel stenosis rates of the target with respect to each target position is calculated to obtain the second blood vessel stenosis rate corresponding to the target area. Continuing with the above example, the target positions corresponding to the target area include the first target position and the second target position. Then, there is a first blood vessel stenosis rate with respect to the first target position and a first blood vessel stenosis rate with respect to the second target position in the target area. Then, these two first blood vessel stenosis rates are statistically analyzed to obtain the second blood vessel stenosis rate corresponding to the target area. That is, the second blood vessel stenosis rate corresponding to the target area is used as the final blood vessel stenosis rate of the blood vessel position where the target area is located.

[0068] In some other disclosed embodiments, corresponding weights can also be set for the first blood vessel stenosis rates of the target area with respect to each target position first, and then a weighted average is performed on the first blood vessel stenosis rates of the target area with respect to each target position to obtain the corresponding second blood vessel stenosis rate. Among them, the specific method for setting the weights for each first blood vessel stenosis rate can be to determine the predicted blood vessel diameter when the position where the target area is located does not include the target area, determine the difference between the blood vessel diameters of each target position and the predicted blood vessel diameter, and based on this difference, determine the corresponding weights for the first blood vessel stenosis rates of each target position. Optionally, the weights of the first blood vessel stenosis rates of each target position are negatively correlated with the corresponding difference, that is, the larger the difference, the smaller the weight.

[0069] Then, based on the second blood vessel stenosis rate, determine the blood vessel stenosis degree corresponding to the target region. The blood vessel stenosis degree corresponding to the target region is the blood vessel stenosis degree at the blood vessel position where the target region is located. The blood vessel stenosis degree includes the second blood vessel stenosis rate and / or a preset degree description corresponding to the second blood vessel stenosis rate. This blood vessel stenosis degree can be the stenosis degree of the blood vessel or the smoothness of the blood vessel. For example, in the case where the blood vessel stenosis degree includes a preset degree description corresponding to the second blood vessel stenosis rate, an association relationship between the second blood vessel stenosis rate and the preset degree description is pre-constructed. For example, the second blood vessel stenosis rate is divided into grades, and each grade corresponds to a preset degree description. For example, if the second blood vessel stenosis rate is distributed between 0 and 1, the second blood vessel stenosis rate of 0 - 1 can be divided into 6 grades, namely no stenosis, minimal stenosis, mild stenosis, moderate stenosis, severe stenosis, and occlusion. For example, when the second blood vessel stenosis rate is 0, it indicates no stenosis, and when the second blood vessel stenosis rate is 1, it indicates occlusion. The division of specific preset degree descriptions can be customized by the user or select the default setting. By statistically analyzing the first blood vessel stenosis rate of the target region with respect to each target position, the second blood vessel stenosis rate corresponding to the target region is obtained, making the determined second blood vessel stenosis rate more accurate.

[0070] In some disclosed embodiments, the above step S11 includes:

[0071] Use the target region analysis model to perform target region analysis on the target image to obtain the analysis result of the target image. Among them, the analysis result also includes the category of the target object included in each target region. The category of the target object included in the target region is obtained by dividing based on the composition of the target object included in the target region. Exemplarily, the target object included in the target region can be a target plaque. Use the target plaque analysis model to perform target plaque analysis on the target image to obtain the analysis result of the target image. Among them, the analysis result includes the position of at least one target plaque in the blood vessel and the category of each target plaque. For example, the category of the target plaque includes calcified plaque, non-calcified plaque, and mixed plaque. That is, the target region analysis model is a multi-classification model. By using the region classification model to perform target region analysis on the target image and obtaining the category of the target object included in the target region, subsequent doctors can formulate corresponding surgical plans according to the category of the target object included in the target region, greatly improving the doctor's work efficiency.

[0072] Among them, before performing step S11, the following steps are also included:

[0073] Image reconstruction is performed on a scanned image containing at least one blood vessel to obtain a blood vessel reconstruction map corresponding to each blood vessel. The blood vessel reconstruction map is used as the target image. Generally, after a patient completes a CT scan, the obtained scanned image is only a sectional view of the human body, which is not sufficient to directly observe the conditions in each region of the blood vessels. Therefore, post-processing reconstruction of the scanned image is required to generate a multi-dimensional image. Then, blood vessel segmentation is performed on the multi-dimensional image to obtain a volume rendering map (VR map) of the blood vessels. For example, volume rendering maps corresponding to the left carotid artery, right carotid artery, left vertebral artery, and right vertebral artery are segmented. After determining these four blood vessel paths, the centerline of the blood vessels is determined based on the volume rendering map of the blood vessels, and a curved surface reconstruction map is obtained through the determined centerline of the blood vessels. Then, the centerline of the blood vessels in the curved surface reconstruction map (CPR map) is corrected to obtain a complete blood vessel reconstruction map. It can be considered that the blood vessel reconstruction map is a curved surface reconstruction map after being straightened. By reconstructing the scanned image to obtain a blood vessel reconstruction map and using this blood vessel reconstruction map as the target image, the accuracy of the analysis result can be improved compared to directly analyzing the target region of the scanned image.

[0074] In some disclosed embodiments, the analysis result includes the category of the target object in each target region. Please also refer to Figure 3 , Figure 3 which is another schematic flowchart of an implementation of the image analysis method of the present application. As Figure 3 shown, after performing step S12, the following steps are further included:

[0075] Step S13: Display the blood vessel identifiers corresponding to each blood vessel included in the scanned image.

[0076] For example, if the scanned image includes the left carotid artery, right carotid artery, left vertebral artery, and right vertebral artery. Then, display the blood vessel identifiers corresponding to these blood vessels. The blood vessel identifiers can specifically be the blood vessel names, pre-set serial numbers used to represent each blood vessel, image identifiers corresponding to each blood vessel, or any other identifier that can distinguish each blood vessel.

[0077] The specific display method can be to display in the form of a blood vessel list.

[0078] Step S14: Select a target blood vessel from the blood vessel identifiers in response to the user's second selection instruction.

[0079] Specifically, the second selection instruction can be a voice instruction or a click instruction on each blood vessel identifier in the blood vessel list. Regarding the specific form of the second selection instruction, no excessive limitation is imposed here.

[0080] Step S15: Display the first region information of each target region in the target blood vessel. The first region information includes the degree of blood vessel stenosis and / or category.

[0081] Among them, the degree of vascular stenosis here can be at least one of the second vascular stenosis rate of the target area and the preset degree description corresponding to the second vascular stenosis rate. The categories included in the first area information include the category of the target object, for example, including the category of the target plaque.

[0082] Exemplarily, if the target blood vessel is the left vertebral artery, at least one of the degree of vascular stenosis corresponding to each detected target area in the left vertebral artery and the category of the target object included in the target area is displayed in the blood vessel list. Optionally, in the case where there are multiple target areas in the target blood vessel, the one with the maximum degree of vascular stenosis is preferentially displayed, for example, the most severe one among the preset degree descriptions corresponding to each target area is displayed. Exemplarily, if there are 2 target areas in the target blood vessel, and the preset degree description corresponding to one target area is mild stenosis, while the preset degree description corresponding to the other target area is moderate stenosis, then moderate stenosis is preferentially displayed. In this way, the user can intuitively see the severity of stenosis of each blood vessel. Please also refer to Figure 4 , Figure 4 is a schematic diagram of the interface showing the blood vessel list in an embodiment of the image analysis method of the present application. As Figure 4 shown, the left carotid artery L-ICA, right carotid artery R-ICA, left vertebral artery L-VA, and right vertebral artery R-VA are shown on the left. On the right side of the left carotid artery L-ICA, right carotid artery R-ICA, left vertebral artery L-VA, and right vertebral artery R-VA, the one with the most severe degree of vascular stenosis in the corresponding blood vessel is shown. No stenosis can indicate that the target area in the corresponding area has little effect on the blood flow of the blood vessel. By receiving the second selection instruction of the user for the right vertebral artery R-VA, the target areas detected in the right vertebral artery R-VA are displayed. As Figure 4 shown, a total of two target areas are detected in the right vertebral artery R-VA. The type of the first target area is a calcified area, its corresponding second vascular stenosis rate is 49.6%, and its corresponding preset degree description is mild stenosis. The type of the second target area is also a calcified area, its corresponding second vascular stenosis rate is 20.3%, and its corresponding preset degree description is mild stenosis. Therefore, the one with the most severe degree of vascular stenosis - mild stenosis is preferentially displayed on the right side of the right vertebral artery R-VA. After receiving the selection instruction of the user for the target area, the preset degree description corresponding to the target area is continuously displayed.

[0083] By selecting the target blood vessel from each blood vessel identifier based on the second selection instruction of the user and displaying the first area information of each target area in the target blood vessel, the interaction with the user can be improved.

[0084] In some other disclosed embodiments, the degree of vascular stenosis includes the second vascular stenosis rate corresponding to the target area. After performing step S12, the following steps may further be included:

[0085] The target image is displayed, and second region information is displayed on the target image. The second region information includes the analysis result of the target image and / or the second blood vessel stenosis rate corresponding to the target region. Specifically, according to the positions of the target regions detected in the target image, the category of the target object included in the target region and the second blood vessel stenosis rate corresponding to the target region are displayed at the corresponding positions on the target image. Among them, the way of including the category of the target object in the target region can be represented by different colors or in the form of characters. In some other disclosed embodiments, the second region information further includes a preset degree description corresponding to the target region. By displaying the target image and displaying the second region information on the target image, the user can intuitively observe the regional distribution on the target image and check the analysis result of the region.

[0086] Among them, the target image is obtained by reconstructing the scanned image. During the process of displaying the target image, according to the type of the target region, the scan value of the target image is adjusted to increase the contrast between the blood vessel region including the target region and the blood vessel region not including the target region in the target image. That is, the contrast between the image region where the target region is located and the blood vessel region is increased. The scan value can specifically be the HU value. That is, according to the HU value corresponding to the target region, the HU value of the target image is adjusted to increase the contrast between the target region and the blood vessel, so that the user can better observe the content related to the target region. By adjusting the scan value of the target image according to the type of the target region, the contrast between the blood vessel region including the target region and the blood vessel region not including the target region in the target image can be increased, thereby facilitating the user to check the analysis result of the target image.

[0087] In some other disclosed embodiments, after the target image is displayed, the following steps can also be executed:

[0088] In response to a movement instruction for the target image, the target image is moved and the display position of the second region information is adjusted. The movement instruction can be a translation instruction for the target image or a rotation instruction, etc. For example, the user adjusts the observation position of the target image by dragging or the like, that is, adjusts the display positions of the second region information on the display interface, so as to observe the situations of the target regions in the target image in all directions. By receiving the movement instruction for the target image, moving the target image, and adjusting the display position of the second region information, the user can check the region information on the target image from multiple angles.

[0089] In some disclosed embodiments, the target image with the second region information displayed and the scanned image corresponding to the target image are saved to the medical imaging system.

[0090] In the above solution, after analyzing the target regions of the target image, the degree of vascular stenosis corresponding to each target region is obtained, realizing the automated analysis of the target regions of the target image without manual participation, and improving the efficiency of the target region analysis. Moreover, by using the vascular size information at at least two target positions, the degree of vascular stenosis corresponding to the target region is determined, improving the accuracy of the obtained degree of vascular stenosis.

[0091] In some application scenarios, after a patient completes the scan of the head and neck CT angiography image (CTA image), based on the image analysis method provided in the embodiments of the present disclosure, the position detection of plaques, the determination of plaque types, and the degree of vascular stenosis corresponding to the positions where the plaques are located can be quickly performed. It reduces the time for doctors to search for plaques and classify their types, improves the diagnosis efficiency of doctors, is more conducive to assisting doctors in diagnosis, and greatly reduces the problems of missed diagnosis of plaques and incorrect type classification.

[0092] Moreover, usually doctors need to evaluate the risk of plaque detachment and the surgical plan for plaque stripping according to the vascular stenosis rate and type corresponding to the plaque. The fully automated and multi-calculation method of plaque stenosis measurement can better assist doctors in formulating surgical plans.

[0093] In addition, by displaying the information corresponding to the plaque on the straightened vascular reconstruction image, it is visualized for doctors to view and diagnose. The head and neck CTA diagnosis does not require a plain scan before injecting the contrast agent. After the image scan is completed, doctors can quickly obtain the position, composition, and vascular stenosis rate of each plaque. The analysis results and visualization reports provided by the image analysis method can improve the efficiency of doctors' film reading and diagnosis.

[0094] Among them, the execution subject of the image analysis method can be an image analysis system. For example, the image analysis system can be a medical system. The image analysis system can be set in a terminal device, a server, or other processing devices. Among them, the terminal device can be a medical device, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the image analysis method can be implemented by a processor calling computer-readable instructions stored in a memory.

[0095] Please refer to Figure 5 , Figure 5It is a schematic structural diagram of an embodiment of the image analysis system of the present application. The image analysis system 50 includes an analysis module 51 and a blood vessel stenosis degree determination module 52. The analysis module 51 is used to perform target area analysis on a target image including blood vessels to obtain an analysis result of the target image. The analysis result includes the positions of at least one target area in the blood vessel. The blood vessel stenosis degree determination module 52 is used to determine the blood vessel stenosis degree corresponding to each target area by using the blood vessel size information of at least two target positions corresponding to each target area.

[0096] In the above solution, after performing target area analysis on the target image, the blood vessel stenosis degree corresponding to each target area is obtained, realizing automatic target area analysis of the target image without manual participation, and improving the efficiency of target area analysis. Moreover, by using the blood vessel size information of at least two target positions to determine the blood vessel stenosis degree corresponding to the target area, the accuracy of the obtained blood vessel stenosis degree is improved.

[0097] In some disclosed embodiments, the at least two target positions are the positions at both ends of the target area in the blood vessel; and / or, the blood vessel size information is the blood vessel diameter; and / or, the target area includes the area where the target plaque is located.

[0098] In the above solution, by using the blood vessel size information corresponding to the positions at both ends of the target area to determine the blood vessel stenosis degree corresponding to the target area, the calculation error caused by the sudden decrease in blood vessel size can be reduced. In addition, the method of obtaining the blood vessel diameter is simple, so the process of determining the blood vessel stenosis degree corresponding to the target area by the blood vessel diameter is also relatively simple. In addition, by performing plaque analysis on the target image to obtain the position of the target plaque in the blood vessel, the blood vessel stenosis degree corresponding to each target plaque can be determined.

[0099] In some disclosed embodiments, the blood vessel stenosis degree determination module 52 determines the blood vessel stenosis degree corresponding to each target area by using the blood vessel size information of at least two target positions corresponding to each target area, including: for each target area, respectively determining the first blood vessel stenosis rate of the target area with respect to each target position based on the blood vessel size information of each target position corresponding to the target area; and obtaining the blood vessel stenosis degree corresponding to the target area by using the first blood vessel stenosis rate of the target area with respect to each target position.

[0100] In the above solution, by using the first blood vessel stenosis rate of the target area with respect to each target position to obtain the blood vessel stenosis degree corresponding to the target area, the accuracy of the obtained blood vessel stenosis degree can be improved.

[0101] In some disclosed embodiments, the blood vessel stenosis degree determination module 52 obtains the blood vessel stenosis degree corresponding to the target area by using the first blood vessel stenosis rate of the target area with respect to each target position, including: counting the first blood vessel stenosis rate of the target area with respect to each target position to obtain the second blood vessel stenosis rate corresponding to the target area; determining the blood vessel stenosis degree corresponding to the target area based on the second blood vessel stenosis rate, where the blood vessel stenosis degree includes the second blood vessel stenosis rate and / or the preset degree description corresponding to the second blood vessel stenosis rate.

[0102] In the above solution, by counting the first blood vessel stenosis rate of the target area with respect to each target position to obtain the second blood vessel stenosis rate corresponding to the target area, the determined second blood vessel stenosis rate is more accurate.

[0103] In some disclosed embodiments, the blood vessel stenosis degree determination module 52 respectively determines the first blood vessel stenosis rate of the target area with respect to each target position based on the blood vessel size information of each target position corresponding to the target area, including: in response to the user's first selection instruction, selecting at least one target blood vessel stenosis rate determination method from several blood vessel stenosis rate determination methods; for each target position, using at least one target blood vessel stenosis rate determination method to process the blood vessel size information of the target position to obtain the first blood vessel stenosis rate of the target area with respect to the target position.

[0104] In the above solution, by responding to the user's first selection instruction, selecting at least one target blood vessel stenosis rate from several blood vessel stenosis rate determination methods, and obtaining the corresponding first blood vessel stenosis rate according to the target blood vessel stenosis rate determination method, the user can determine the corresponding target blood vessel stenosis rate determination method according to the specific application scenario, improving the flexibility of the image analysis method.

[0105] In some disclosed embodiments, the blood vessel stenosis degree determination module 52 uses at least one target blood vessel stenosis rate determination method to process the blood vessel size information of the target position to obtain the first blood vessel stenosis rate of the target area with respect to the target position, including: using each target blood vessel stenosis rate determination method to process the blood vessel size information of the target position respectively to obtain the candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method; performing a preset operation on the candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method to obtain the first blood vessel stenosis rate of the target area with respect to the target position.

[0106] In the above solution, by performing a preset operation on the candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method to obtain the first blood vessel stenosis rate of the target area with respect to the target position, the obtained first blood vessel stenosis rate is more accurate.

[0107] In some disclosed embodiments, the analysis module 51 performs target area analysis on a target image containing blood vessels to obtain the analysis result of the target image, including: performing target area analysis on the target image by using a region classification model to obtain the analysis result of the target image, and the analysis result further includes the category of the target object included in each target area.

[0108] In the above solution, by using a region classification model to perform target area analysis on the target image and obtaining the category of the target object included in the target area, so that the doctor can subsequently formulate a corresponding surgical plan according to the category of the target object included in the target area, which greatly improves the doctor's work efficiency.

[0109] In some disclosed embodiments, before performing target area analysis on a target image containing blood vessels to obtain the analysis result of the target image, the analysis module 51 is further configured to: perform image reconstruction on a scanned image containing at least one blood vessel to obtain a blood vessel reconstruction map corresponding to each blood vessel, where the blood vessel reconstruction map is used as the target image.

[0110] In the above solution, by reconstructing the scanned image to obtain a blood vessel reconstruction map and using the blood vessel reconstruction map as the target image, compared with directly performing target area analysis on the scanned image, the accuracy of the analysis result can be improved.

[0111] In some disclosed embodiments, the image analysis system 50 includes a display module (not shown in the figure). The analysis result includes the category of the target object included in each target area. After determining the blood vessel stenosis degree corresponding to each target area by using the blood vessel size information at at least two target positions corresponding to each target area, the display module is configured to: display a blood vessel identifier corresponding to each blood vessel included in the scanned image; in response to a second selection instruction of the user, select a target blood vessel from each blood vessel identifier; display first area information of each target area in the target blood vessel, where the first area information includes the blood vessel stenosis degree and / or category.

[0112] In the above solution, by selecting a target blood vessel from each blood vessel identifier based on the second selection instruction of the user and displaying the first area information of each target area in the target blood vessel, the interaction with the user can be improved.

[0113] In some disclosed embodiments, the blood vessel stenosis degree includes a second blood vessel stenosis rate corresponding to the target area; after determining the blood vessel stenosis degree corresponding to each target area by using the blood vessel size information at at least two target positions corresponding to each target area, the display module is further configured to: display the target image and display second area information on the target image, where the second area information includes the analysis result of the target image and / or the second blood vessel stenosis rate corresponding to each target area.

[0114] In the above solution, by displaying the target image and the second region information on the target image, the user can visually observe the regional distribution on the target image and check the analysis results of the regions.

[0115] In some disclosed embodiments, after displaying the target image and the second region information on the target image, the display module is further configured to: in response to a movement instruction for the target image, move the target image and adjust the display position of the second region information; and / or, the target image is obtained by reconstructing a scanned image, and displaying the target image includes: adjusting the scan value of the target image according to the type of the target region to increase the contrast between the blood vessel region of the target image including the target region and the blood vessel region not including the target region.

[0116] In the above solution, by receiving a movement instruction for the target image, moving the target image, and adjusting the display position of the second region information, the user can check the region information on the target image from multiple angles. Additionally, by adjusting the scan value of the target image according to the type of the target region, the contrast between the blood vessel region of the target image including the target region and the blood vessel region not including the target region can be increased, thereby facilitating the user to check the analysis results of the target image.

[0117] In the above solution, after performing target region analysis on the target image, the degree of blood vessel stenosis corresponding to each target region is obtained, realizing automated target region analysis of the target image without manual participation, and improving the efficiency of target region analysis. Moreover, by using the blood vessel size information at at least two target positions to determine the degree of blood vessel stenosis corresponding to the target region, the accuracy of the obtained degree of blood vessel stenosis is improved.

[0118] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of an embodiment of an electronic device according to the present application. The electronic device 60 includes a memory 61 and a processor 62. The processor 62 is configured to execute program instructions stored in the memory 61 to implement the steps in any of the above embodiments of the image analysis method. In a specific implementation scenario, the electronic device 60 may include, but is not limited to: medical devices, microcomputers, desktop computers, servers. In addition, the electronic device 60 may also include mobile devices such as laptop computers and tablet computers, which are not limited herein.

[0119] Specifically, the processor 62 is used to control itself and the memory 61 to implement the steps in any of the above image analysis method embodiments. The processor 62 can also be referred to as a CPU (Central Processing Unit). The processor 62 may be an integrated circuit chip with signal processing capabilities. The processor 62 can also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. Additionally, the processor 62 can be implemented jointly by integrated circuit chips.

[0120] In the above solution, after performing target area analysis on the target image, the degree of vascular stenosis corresponding to each target area is obtained, realizing automated target area analysis of the target image without manual participation, and improving the efficiency of target area analysis. Moreover, by using the vascular size information at at least two target positions, the degree of vascular stenosis corresponding to the target area is determined, improving the accuracy of the obtained degree of vascular stenosis.

[0121] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. The computer-readable storage medium 70 stores program instructions 71 thereon, and when the program instructions 71 are executed by the processor, they are used to implement the steps in any of the above image analysis method embodiments.

[0122] In the above solution, after performing target area analysis on the target image, the degree of vascular stenosis corresponding to each target area is obtained, realizing automated target area analysis of the target image without manual participation, and improving the efficiency of target area analysis. Moreover, by using the vascular size information at at least two target positions, the degree of vascular stenosis corresponding to the target area is determined, improving the accuracy of the obtained degree of vascular stenosis.

[0123] In some embodiments, the functions or modules included in the system provided by the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be elaborated here.

[0124] The descriptions of the above embodiments tend to emphasize the differences between the embodiments. For the same or similar parts, reference can be made to each other. For the sake of brevity, they will not be elaborated herein again.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system implementation described above is only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the system or unit can be in electrical, mechanical or other forms.

[0126] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes.

Claims

1. An image analysis method, characterized in that, Including: Performing target region analysis on a target image including blood vessels to obtain an analysis result of the target image, where the analysis result includes the positions of at least one target region in the blood vessels; Determining the degree of blood vessel stenosis corresponding to each target region by using the blood vessel size information at at least two target positions corresponding to each target region; The determining the degree of blood vessel stenosis corresponding to each target region by using the blood vessel size information at at least two target positions corresponding to each target region includes: for each target region, respectively determining a first blood vessel stenosis rate of the target region with respect to each target position based on the blood vessel size information at each target position corresponding to the target region; statistically calculating the first blood vessel stenosis rates of the target region with respect to each target position to obtain a second blood vessel stenosis rate corresponding to the target region; and determining the degree of blood vessel stenosis corresponding to the target region based on the second blood vessel stenosis rate, where the degree of blood vessel stenosis includes the second blood vessel stenosis rate and / or a preset degree description corresponding to the second blood vessel stenosis rate; Wherein, the blood vessel size information includes blood vessel diameter, and the statistically calculating the first blood vessel stenosis rates of the target region with respect to each target position to obtain a second blood vessel stenosis rate corresponding to the target region includes: determining a predicted blood vessel diameter at the position where the target region is located without including the target region, and determining the difference between the blood vessel diameter at each target position and the predicted blood vessel diameter; based on each difference, determining a corresponding weight for the first blood vessel stenosis rate at each target position, where the weight of the first blood vessel stenosis rate at each target position is negatively correlated with the difference corresponding to each target position; and performing weighted averaging on each first blood vessel stenosis rate according to the weight of each first blood vessel stenosis rate to obtain the second blood vessel stenosis rate.

2. The method according to claim 1, wherein The at least two target positions are the positions at both ends of the target region in the blood vessel; And / or, the blood vessel size information is blood vessel diameter; And / or, the target region includes the region where the target plaque is located.

3. The method according to claim 1, wherein The respectively determining a first blood vessel stenosis rate of the target region with respect to each target position based on the blood vessel size information at each target position corresponding to the target region includes: In response to a first selection instruction of the user, selecting at least one target blood vessel stenosis rate determination method from several blood vessel stenosis rate determination methods; For each target position, using the at least one target blood vessel stenosis rate determination method to process the blood vessel size information at the target position to obtain a first blood vessel stenosis rate of the target region with respect to the target position.

4. The method according to claim 3, wherein The using the at least one target blood vessel stenosis rate determination method to process the blood vessel size information at the target position to obtain a first blood vessel stenosis rate of the target region with respect to the target position includes: Using each target blood vessel stenosis rate determination method to process the blood vessel size information at the target position respectively to obtain a candidate blood vessel stenosis rate corresponding to each target blood vessel stenosis rate determination method; Perform a preset operation on the candidate blood vessel stenosis rates corresponding to each target blood vessel stenosis rate determination method to obtain a first blood vessel stenosis rate of the target region with respect to the target position.

5. The method according to any one of claims 1-4, characterized in that, The performing of target region analysis on a target image including blood vessels to obtain an analysis result of the target image includes: Performing target region analysis on the target image by using a region classification model to obtain an analysis result of the target image, where the analysis result further includes the categories of target objects included in each of the target regions.

6. The method according to any one of claims 1 to 4, characterized in that, Before the performing of target region analysis on a target image including blood vessels to obtain an analysis result of the target image, the method further includes: Performing image reconstruction on a scanned image including at least one blood vessel to obtain a blood vessel reconstruction map corresponding to each blood vessel, where the blood vessel reconstruction map serves as the target image.

7. The method according to claim 6, wherein After the analysis result includes the categories of target objects included in each of the target regions and the determining of the blood vessel stenosis degree corresponding to each of the target regions by using blood vessel size information of at least two target positions corresponding to each of the target regions, the method further includes: Displaying blood vessel identifiers corresponding to each blood vessel included in the scanned image; In response to a second selection instruction of a user, selecting a target blood vessel from each of the blood vessel identifiers; Displaying first region information of each of the target regions in the target blood vessel, where the first region information includes the blood vessel stenosis degree and / or the category.

8. The method according to any one of claims 1 to 4, characterized in that The blood vessel stenosis degree includes a second blood vessel stenosis rate corresponding to the target region; after the determining of the blood vessel stenosis degree corresponding to each of the target regions by using blood vessel size information of at least two target positions corresponding to each of the target regions, the method further includes: Displaying the target image and displaying second region information on the target image, where the second region information includes the analysis result of the target image and / or the second blood vessel stenosis rate corresponding to each of the target regions.

9. The method according to claim 8, wherein After the displaying of the target image and the displaying of second region information on the target image, the method further includes: In response to a moving instruction for the target image, moving the target image and adjusting a display position of the second region information; And / or, the target image is obtained by reconstructing a scanned image, and the displaying of the target image includes: Adjusting a scanned value of the target image according to a type of the target region to increase a contrast between a blood vessel region of the target image including the target region and a blood vessel region not including the target region.

10. An image analysis system, characterized in that, including: An analysis module, configured to perform target region analysis on a target image including blood vessels to obtain an analysis result of the target image, where the analysis result includes positions of at least one target region in the blood vessel; A blood vessel stenosis degree determination module, configured to determine a blood vessel stenosis degree corresponding to each of the target regions by using blood vessel size information of at least two target positions corresponding to each of the target regions; The method for determining the degree of vascular stenosis of each target region by using the vascular size information of at least two target positions corresponding to each target region includes: for each target region, based on the vascular size information of each target position corresponding to the target region, respectively determining a first vascular stenosis rate of the target region with respect to each target position; counting the first vascular stenosis rates of the target region with respect to each target position to obtain a second vascular stenosis rate corresponding to the target region; and determining the degree of vascular stenosis corresponding to the target region based on the second vascular stenosis rate, where the degree of vascular stenosis includes the second vascular stenosis rate and / or a preset degree description corresponding to the second vascular stenosis rate. Wherein, the vascular size information includes the vascular diameter. The method for the vascular stenosis degree determination module to count the first vascular stenosis rates of the target region with respect to each target position to obtain the second vascular stenosis rate corresponding to the target region includes: determining a predicted vascular diameter at the position where the target region is located without including the target region, and determining the difference between the vascular diameter of each target position and the predicted vascular diameter; based on each difference, determining a corresponding weight for the first vascular stenosis rate of each target position, where the weight of the first vascular stenosis rate of each target position is negatively correlated with the difference corresponding to each target position; and performing weighted averaging on each first vascular stenosis rate according to the weight of each first vascular stenosis rate to obtain the second vascular stenosis rate.

11. An electronic device, characterized in that, It includes a memory and a processor, and the processor is configured to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, the method according to any one of claims 1 to 9 is implemented.

Images