Marker positioning method and apparatus

Abstract

This application relates to a marker localization method and apparatus. The method includes: acquiring a head structure localization image of a target object; determining a vascular localization image of the target object based on the head structure localization image; locating the head planar imaging range of the target object based on the head structure localization image; and locating the vascular marker band of the target object based on the vascular localization image. This method enables automatic localization of arterial spin marker imaging without the need for manual repositioning of the head planar imaging range and vascular marker band, thus improving the accuracy of the placement of the head planar imaging range and vascular marker band.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a marker positioning method and apparatus. Background Technology

[0002] With the development of medical imaging technology, arterial spin labeling (ASL) has emerged. It is a non-invasive magnetic resonance imaging (MRI) method for measuring cerebral blood flow without the use of contrast agents, and it has a wide range of applications in screening, grading, evaluating regions of interest of target subjects, as well as in scientific research.

[0003] Traditional arterial spin labeling has two methods. The first method fixes the distance and orientation of the imaging area and the vascular marker band, requiring manual positioning of the head-plane imaging range. The second method requires manual adjustment of both the position and orientation of the imaging area and the vascular marker band. Figure 11 As shown. Due to the limitations of manually locating the head planar imaging range or the vascular marker band, the accuracy of placing the head planar imaging range and the vascular marker band is relatively low. Summary of the Invention

[0004] Therefore, it is necessary to provide a marking and positioning method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of the head planar imaging range and the placement position of the vascular marker band in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a marker localization method. The method includes: acquiring a head structure localization image of a target object; determining a vascular localization image of the target object based on the head structure localization image; locating the head planar imaging range of the target object based on the head structure localization image; and locating a vascular marker band of the target object based on the vascular localization image.

[0006] Secondly, this application also provides a marker positioning device. The device includes: a structural positioning image acquisition module for acquiring a head structural positioning image of a target object; a vascular positioning image determination module for determining a vascular positioning image of the target object based on the head structural positioning image; and an arterial spin marker positioning module for positioning the head planar imaging range of the target object based on the head structural positioning image, and positioning the vascular marker band of the target object based on the vascular positioning image.

[0007] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program, performs the following steps: acquiring a head structure localization image of a target object; determining a vascular localization image of the target object based on the head structure localization image; locating the head planar imaging range of the target object based on the head structure localization image; and locating the vascular marker band of the target object based on the vascular localization image.

[0008] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps: acquiring a head structure localization image of a target object; determining a vascular localization image of the target object based on the head structure localization image; locating the head planar imaging range of the target object based on the head structure localization image; and locating the vascular marker band of the target object based on the vascular localization image.

[0009] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps: acquiring a head structure localization image of a target object; determining a vascular localization image of the target object based on the head structure localization image; locating the head planar imaging range of the target object based on the head structure localization image; and locating the vascular marker band of the target object based on the vascular localization image.

[0010] The aforementioned marker positioning method, apparatus, computer equipment, storage medium, and computer program product acquire a head structure positioning image of a target object; determine a vascular positioning image of the target object based on the head structure positioning image; locate the head planar imaging range of the target object based on the head structure positioning image; and locate the vascular marker band of the target object based on the vascular positioning image.

[0011] By using the head structure localization image of the target object to scan and obtain the vascular localization image of the target object, and further using the head structure localization image to locate the head planar imaging range of the target object, and using the vascular localization image to locate the vascular marker band of the target object, it is possible to realize the automatic localization of arterial spin labeling (ASL) imaging without the need for manual movement of the head planar imaging range and vascular marker band, which is beneficial to improving the accuracy of the placement of the head planar imaging range and vascular marker band. Attached Figure Description

[0012] Figure 1 This is an application environment diagram of a marker localization method in one embodiment;

[0013] Figure 2 This is a flowchart illustrating a marker localization method in one embodiment;

[0014] Figure 3 This is a flowchart illustrating a blood vessel localization image localization method in one embodiment;

[0015] Figure 4 This is a flowchart illustrating a method for determining the head plane imaging range in one embodiment;

[0016] Figure 5 This is a flowchart illustrating a method for obtaining head tissue recognition results in one embodiment;

[0017] Figure 6 This is a flowchart illustrating a method for obtaining the localization center through planar imaging in one embodiment;

[0018] Figure 7 This is a flowchart illustrating a method for determining vascular marker bands in one embodiment;

[0019] Figure 8 This is a flowchart illustrating the method for determining vascular marker bands in another embodiment;

[0020] Figure 9 This is a flowchart illustrating the method for determining the vascular marker band in yet another embodiment;

[0021] Figure 10 This is a flowchart illustrating the method for determining vascular marker bands in another embodiment;

[0022] Figure 11 This is a schematic diagram of the results of manual arterial spin labeling in one embodiment;

[0023] Figure 12 This is a schematic diagram illustrating the implementation logic of a marker positioning method in one embodiment;

[0024] Figure 13 This is a schematic diagram of the results of automatic arterial spin labeling in one embodiment;

[0025] Figure 14 This is a structural block diagram of a marking and positioning device in one embodiment;

[0026] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0028] The marker positioning method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Server 104 obtains a head structure localization image of the target object from terminal 102; determines the vascular localization image of the target object based on the head structure localization image; locates the head planar imaging range of the target object based on the head structure localization image; and locates the vascular marker band of the target object based on the vascular localization image. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0029] In one embodiment, such as Figure 2 As shown, a marker localization method is provided, which can be applied to... Figure 1 Taking the server in the example, the following steps are included:

[0030] Step 202: Obtain the head structure localization image of the target object.

[0031] The target object can be a person or an animal, and the target object contains a region of interest, such as the head structure and blood vessels in the head and neck of the human body.

[0032] Among them, the head structure localization image can be an image obtained by scanning with magnetic resonance imaging (MRI) technology that uses non-invasive measurement of cerebral blood flow, and is used for automatic localization of the head plane imaging range for subsequent arterial spin labeling (ASL) imaging.

[0033] Specifically, in response to the automatic localization command for arterial spin labeling imaging from terminal 102, server 104 acquires a localization image of the head structure of the target object from terminal 102. This head structure localization image includes regions of interest that require further understanding of the target object, such as the distribution of blood vessels in the head and neck.

[0034] Step 204: Determine the vascular localization image of the target object based on the head structure localization image.

[0035] Among them, the vascular localization image can be an image obtained by using non-invasive magnetic resonance imaging (MRI) technology to measure cerebral blood flow, guided by the head structure localization image, and used for automatic localization of vascular markers for subsequent arterial spin labeling (ASL) imaging.

[0036] Specifically, server 104 uses an image recognition algorithm to identify at least one target positioning structure (e.g., vertebral body) of the target object from the head structure positioning image of the target object. With the target tissue structure as the planar imaging positioning center, terminal 102 scans the target object to obtain the vascular positioning image of the target object. The head structure positioning image and the vascular positioning image can be at the same scanning angle or at different scanning angles.

[0037] Step 206: Based on the head structure localization image, locate the head planar imaging range of the target object, and based on the blood vessel localization image, locate the blood vessel marker band of the target object.

[0038] Among them, the head plane imaging range can be the field of view range of the head plane imaging, and the size of the field of view angle (FOV) of the head plane imaging determines the field of view range of the head plane imaging.

[0039] Among them, the vascular marker band can be used to obtain vascular perfusion information of the skull. Generally, the vascular marker band mainly marks the internal carotid artery.

[0040] Specifically, server 104 uses image segmentation algorithms (including but not limited to deep learning algorithms, such as traditional image segmentation algorithms) to segment at least one target localization structure (e.g., vertebral body) of the target object from the head structure localization image of the target object. When the target tissue structure is used as the planar imaging localization center, server 104 uses image feature extraction algorithms to extract at least one target tissue structure (e.g., corpus callosum, anterior and posterior commissure, etc.) of the target object from the head structure localization image of the target object, and further realizes automatic localization of the head planar imaging range based on each target tissue structure.

[0041] Server 104 uses an image segmentation algorithm to segment at least one head and carotid artery from the target object's vascular localization image, and further uses the distance and angle between the segmentation information of each head and carotid artery to automatically locate the vascular marker band.

[0042] In one embodiment, such as Figure 12 As shown, where, Figure 12 Image 1 in the image is a head structure localization image, while Figure 12Positioning image 2 in the image is a blood vessel positioning image, which is obtained by scanning with the positioning center of the planar imaging of positioning image 1. Figure 12 The right side shows the head planar imaging range determined based on positioning image 1, and the vascular marker band determined based on positioning image 2.

[0043] In the above-mentioned marker localization method, the following steps are taken: acquiring a head structure localization image of the target object; determining a blood vessel localization image of the target object based on the head structure localization image; locating the head planar imaging range of the target object based on the head structure localization image; and locating the blood vessel marker band of the target object based on the blood vessel localization image.

[0044] By using the head structure localization image of the target object to scan and obtain the vascular localization image of the target object, and further using the head structure localization image to locate the head planar imaging range of the target object, and using the vascular localization image to locate the vascular marker band of the target object, it is possible to realize the automatic localization of arterial spin labeling (ASL) imaging without the need for manual movement of the head planar imaging range and vascular marker band, which is beneficial to improving the accuracy of the placement of the head planar imaging range and vascular marker band.

[0045] In one embodiment, such as Figure 3 As shown, based on the head structure localization image, the blood vessel localization image of the target object is determined, including:

[0046] Step 302: Determine the planar imaging positioning center based on the head structure positioning image.

[0047] The planar imaging positioning center can be the geometric center of the field of view of the head planar imaging, and is generally determined by the vertebral body in the head structure positioning image.

[0048] Specifically, firstly, server 104 executes the first scanning protocol and further uses an automatic positioning algorithm to segment at least one vertebra of the target object from the head structure positioning image of the target object; server 104 executes the second scanning protocol and further identifies the first vertebra and the second vertebra as the planar imaging positioning center from each vertebra of the target object.

[0049] Step 304: Locate the blood vessel localization image based on the planar imaging localization center.

[0050] Specifically, once the planar imaging positioning center is determined, the server 104 controls the terminal 102 to adjust the scanning angle. Furthermore, after the server 104 obtains information from the terminal 102 regarding the completion of the scanning angle adjustment, the control terminal 102 scans the target object with the planar imaging positioning center as a reference to obtain a vascular positioning image of the target object.

[0051] In this embodiment, by using the planar imaging positioning center in the head structure positioning image, the blood vessel positioning image of the target object can be located. This enables the mutual constraint between the head structure positioning image and the blood vessel marker band, which is beneficial to improving the positioning accuracy in subsequent automatic positioning.

[0052] In one embodiment, such as Figure 4 As shown, based on the head structure localization image, the head planar imaging range of the target object is located, including:

[0053] Step 402: Determine the planar imaging positioning center based on the head structure positioning image.

[0054] Specifically, firstly, server 104 executes the first scanning protocol and further uses an automatic positioning algorithm to segment at least one vertebra of the target object from the head structure positioning image of the target object; server 104 executes the second scanning protocol and further identifies the first vertebra and the second vertebra as the planar imaging positioning center from each vertebra of the target object.

[0055] Step 404: Based on the planar imaging positioning center, perform feature recognition on the head structure positioning image to obtain the recognition results of each head tissue.

[0056] The head tissue recognition result can be that the server 104 identifies part of the head tissue structure of the target object in the head structure localization image, such as the corpus callosum, anterior and posterior commissure, etc.

[0057] Specifically, when executing the Arterial Spin Labeling (ASL) imaging localization protocol, the field of view bounding box used for locating the head plane imaging will perform feature recognition on the head structure localization image based on the information of the head structure localization image, and automatically identify head tissues such as the corpus callosum and the anterior and posterior commissures.

[0058] Step 406: Determine the head planar imaging range based on the identification results of each head tissue.

[0059] Specifically, once the identification results of each head tissue are determined, the server 104 controls the terminal 102 to adjust the scanning angle. Furthermore, after the server 104 obtains information from the terminal 102 regarding the completion of the scanning angle adjustment, the control terminal 102 uses the identification results of each head tissue as a reference to locate the head planar imaging range.

[0060] In this embodiment, by using the planar imaging positioning center in the head structure positioning image, each head tissue of the target object is identified, and the planar imaging positioning range is further determined based on each head tissue. The planar imaging positioning range in the region of interest can be automatically and reasonably confirmed by referring to each head tissue. This not only eliminates the error of manual positioning, but also improves the accuracy of the positioning planar imaging positioning range.

[0061] In one embodiment, such as Figure 5 As shown, based on the planar imaging positioning center, feature recognition is performed on the head structure positioning image to obtain the recognition results of each head tissue, including:

[0062] Step 502: Determine the planar imaging positioning range based on the planar imaging positioning center.

[0063] The planar imaging positioning range can be the recognition range of the head planar imaging, which is determined by the field of view (FOV) range of the head planar imaging.

[0064] Specifically, when the planar imaging positioning center is determined, the server 104 uses the planar imaging positioning center as the geometric center of the field of view (FOV) range of the head planar imaging, and adjusts the field of view (FOV) range of the head planar imaging as the planar imaging positioning range for identifying head tissue structures.

[0065] Step 504: Under the planar imaging positioning range, perform feature recognition on the head structure positioning image to obtain the recognition results of each head tissue.

[0066] Specifically, given a defined planar imaging positioning range, server 104 employs an image recognition algorithm to identify the various head tissue structure features of the target object within the planar imaging positioning range, and further determines the identification results of each head tissue of the target object based on these features.

[0067] In this embodiment, by using an image recognition algorithm to identify each head tissue in the head structure localization image within the planar imaging localization range, the recognition accuracy and efficiency of the artificial intelligence model can be utilized to improve the processing efficiency of the head structure localization image.

[0068] In one embodiment, such as Figure 6 As shown, the planar imaging positioning center is determined based on the head structure localization image, including:

[0069] Step 602: Segment the first vertebra and the second vertebra from the head structure localization image.

[0070] The first vertebral body and the second vertebral body can be the cervical vertebral body numbered first and the cervical vertebral body numbered second in the head structure localization image.

[0071] Specifically, server 104 executes the first scanning protocol, inputting the head structure localization image into the automatic localization algorithm. By selecting a segmentation method that matches the head structure localization image from threshold segmentation methods, region-based segmentation methods, edge-based segmentation methods, and theory-based segmentation methods, each vertebra is segmented from the head structure localization image. Server 104 executes the second scanning protocol, inputting the images of each vertebra into the image recognition algorithm. By selecting a recognition method that matches each vertebra from depth-first search, breadth-first search, residual shrinkage network, directional FAST feature point detection, and rotation BRIEF description algorithm (ORB algorithm), the first and second vertebrae of the target object's neck position are identified from each vertebra.

[0072] Step 604: Use the first vertebral body and the second vertebral body as the localization center for planar imaging.

[0073] Specifically, based on the position information of the first vertebra and the position information of the second vertebra, the planar imaging positioning center for adjusting the field of view (FOV) range of the head planar imaging is calculated.

[0074] In this embodiment, by using the first and second vertebrae in the head structure positioning image to determine the planar imaging positioning center, the data of the planar imaging positioning center can be accurately calculated by utilizing the characteristics of the first and second vertebrae.

[0075] In one embodiment, such as Figure 7 As shown, based on the vascular localization image, the vascular marker bands of the target object are located, including:

[0076] Step 702: Perform image segmentation on the blood vessel localization image to obtain vertebral artery segmentation information and carotid artery segmentation information.

[0077] The vertebral artery segmentation information can include the location and direction information of the vertebral artery.

[0078] Among them, the carotid artery segmentation information can be the location information and direction information of the carotid artery.

[0079] Specifically, the blood vessel localization image is input into the image segmentation algorithm. By selecting a segmentation method that matches the blood vessel localization image from threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and segmentation methods based on specific theories, the vertebral artery and carotid artery are segmented from the blood vessel localization image. The corresponding vertebral artery segmentation information (position and orientation information of the vertebral artery) is extracted from the vertebral artery, and the corresponding carotid artery segmentation information (position and orientation information of the carotid artery) is extracted from the carotid artery.

[0080] Step 704: Determine the vascular marker band based on the difference in direction between the vertebral artery segmentation information and the carotid artery segmentation information.

[0081] The difference in direction can be the difference in distance between the vertebral artery and the carotid artery in their respective directions.

[0082] Specifically, based on the vertebral artery segmentation information (position and direction information of the vertebral artery) and the carotid artery segmentation information (position and direction information of the carotid artery), the difference in orientation between the vertebral artery and the carotid artery in the same coordinate system is calculated. For example, in the same coordinate system, any point on the vertebral artery is selected, and the position and direction information of the vertebral artery at that point are extracted. By finding the tangent line of the carotid artery parallel to that vertebral artery point, and then calculating the distance between the point and the line as the distance between the vertebral artery and the carotid artery, the same solution method is applied to each vertebral artery point to obtain the difference in orientation between the vertebral artery segmentation information and the carotid artery segmentation information. Furthermore, the vertebral artery point and the carotid artery point with the minimum orientation difference are selected to place vascular marker bands, wherein the vascular marker bands are as perpendicular as possible to the vertebral artery and the carotid artery.

[0083] In this embodiment, the directional difference is calculated using the segmentation information of the vertebral artery and the segmentation information of the carotid artery to locate the vascular landmark, which can ensure the positioning effect of the vascular landmark in the vascular positioning image and improve the placement accuracy of the vascular landmark.

[0084] In one embodiment, such as Figure 8 As shown, based on the difference in direction between the vertebral artery segmentation information and the carotid artery segmentation information, vascular marker bands are determined, including:

[0085] Step 802: Traverse the vertebral artery segmentation information and carotid artery segmentation information to obtain the vessel course information and vessel angle information.

[0086] Among them, the vascular course information can be a measure of the complexity of the course of the vertebral artery or carotid artery at any location.

[0087] Among them, the vascular angle information can be the angle value between the vertebral artery and the carotid artery.

[0088] Specifically, by traversing the vertebral artery segmentation information (position and direction information) at each point of the vertebral artery, the vascular course information of the vertebral artery with its position information determined can be obtained; similarly, by traversing the carotid artery segmentation information (position and direction information) at each point of the carotid artery, the vascular course information of the carotid artery with its position information determined can be obtained; by integrating the vascular course information of the vertebral artery and the carotid artery, the vascular course information is obtained.

[0089] By using the vertebral artery direction information in the vertebral artery segmentation information and the carotid artery direction information in the carotid artery segmentation information, the angle between any point on the vertebral artery and the carotid artery is calculated as the vascular angle information.

[0090] Step 804: If the vascular course information and vascular angle information both meet the conditions for placing the vascular marker band, search for the marker band placement position based on the vertebral artery segmentation information and the carotid artery segmentation information.

[0091] Among them, the conditions for placing the marker band can be that the vascular course information does not exceed the maximum value of the course complexity, the vascular angle information does not exceed the maximum value of the vascular angle, and the vascular marker band is not parallel to the vertebral artery and carotid artery.

[0092] The placement location of the marker band can be the coordinate information used to place the vascular marker band.

[0093] Specifically, if the vessel course information and vessel angle information both meet the conditions for placing the vessel marker band, that is, if the vessel course information is not greater than the maximum value of the course complexity and the vessel angle information is not greater than the maximum value of the vessel angle, then based on the vertebral artery segmentation information (vertebral artery position and direction information) and the carotid artery segmentation information (carotid artery position and direction information) at each point, the minimum value of the course difference between the vertebral artery and the carotid artery is searched, that is, the minimum distance between the vertebral artery and the carotid artery; finally, using the vertebral artery point and the carotid artery point with the minimum course difference, the specific information of the marker band placement position is calculated.

[0094] Step 806: Determine the vascular marker band based on the placement position of the marker band.

[0095] Specifically, server 104 places vascular markers on the vascular localization image based on the specific information of the marker placement location.

[0096] In this embodiment, by utilizing the difference in orientation between the vertebral artery segmentation information and the carotid artery segmentation information to determine the placement position of the vascular marker band when both the vascular course information and the vascular angle information meet the conditions for the placement of the vascular marker band, it is possible to ensure that the placement position of the vascular marker band is as perpendicular as possible to the carotid and vertebral arteries, thereby improving the effect of subsequent scanning images of the region of interest of the target object.

[0097] In one embodiment, such as Figure 9 As shown, based on the difference in direction between the vertebral artery segmentation information and the carotid artery segmentation information, vascular marker bands are determined, including:

[0098] Step 902: If the vascular course information is not satisfied but the vascular angle information satisfies the labeling conditions for the vascular labeling band, search for the labeling position and labeling direction based on the vertebral artery segmentation information and the carotid artery segmentation information.

[0099] The direction in which the marker band is placed can be the direction of the long side or the short side of the vascular marker band.

[0100] Specifically, if the vessel course information does not meet the placement conditions for the vessel marker band, but the vessel angle information does, meaning the vessel course information is greater than the maximum course complexity, but the vessel angle information is not greater than the maximum vessel angle, then this location is considered to have a complex vessel course and is unsuitable for placing a marker band. When encountering a complex vessel course scenario, based on the vertebral artery segmentation information (position and direction information) and the carotid artery segmentation information (position and direction information) at each point, using the position above the cervical cruciate vertebra as a constraint, the minimum difference in the course between the vertebral artery and the carotid artery is searched, i.e., the minimum distance between them. Using the vertebral artery point and the carotid artery point with the minimum course difference, the specific information for the marker band placement position is calculated; and the placement direction of the vessel marker band is searched, where the placement direction is neither parallel to the vertebral artery nor parallel to the carotid artery.

[0101] Step 904: Determine the vascular marker band based on the placement position and orientation of the marker band.

[0102] Specifically, server 104 places vascular markers on the vascular positioning image based on the specific information of the marker placement location and the placement direction of the markers corresponding to the long or short side of the vascular markers.

[0103] In this embodiment, by adjusting the placement position and direction of the marker band when the blood vessel course information is not satisfied but the blood vessel angle information satisfies the marker band placement conditions, it is possible to ensure that the blood vessel marker band can be positioned in a standard position even in scenarios with complex blood vessel course, thereby improving the effect of subsequent scanning images of the region of interest of the target object.

[0104] In one embodiment, such as Figure 10 As shown, the method also includes:

[0105] Step 1002: If the placement direction of the marker band does not meet the placement conditions of the vascular marker band, determine the vascular marker band according to the default placement position of the marker band.

[0106] The default placement position of the marker band can be the default position set for the vascular marker band.

[0107] Specifically, if the placement direction of the marker band does not meet the placement conditions of the vascular marker band, that is, the placement direction of the marker band can only be selected to be parallel to the vertebral artery or the carotid artery, the server 104 places the vascular marker band on the vascular positioning image according to the specific information of the default placement position of the marker band.

[0108] Alternatively, in step 1004, if the vessel angle information does not meet the labeling conditions for the vessel labeling band, the vessel labeling band is determined according to the default placement position of the labeling band.

[0109] Specifically, if the vessel angle information does not meet the conditions for placing the vessel marker, that is, if the vessel angle information can only be selected to be greater than the maximum value of the vessel angle, the server 104 places the vessel marker on the vessel positioning image according to the specific information of the default placement position of the marker.

[0110] In this embodiment, by placing the vascular marker in the default marker placement position when the marker placement direction or vascular angle information does not meet the marker placement conditions, it can be ensured that the subsequent scanning images of the region of interest of the target object meet the minimum requirements.

[0111] In one embodiment, such as Figure 13 The diagram shows a schematic of a marker positioning operation interface according to an embodiment of this application. The first row, from left to right, displays a sagittal plane structural image, a coronal plane TOF (Time of Flight) image, and a sagittal plane TOF image. The sagittal plane structural image confirms that the FOV (Field of View) can encompass the brain region, and that the FOV is placed parallel to the brain. The coronal and sagittal plane TOF images determine the position of the marker band. The second row includes a scanning protocol list and a selected protocol parameter display area. The scanning protocol list includes scanned protocols and protocols to be scanned; the selected protocol parameter display area displays the set pulse parameters, position parameters, etc.

[0112] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0113] Based on the same inventive concept, this application also provides a marker positioning device for implementing the marker positioning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more marker positioning device embodiments provided below can be found in the limitations of the marker positioning method described above, and will not be repeated here.

[0114] In one embodiment, such as Figure 14 As shown, a marker positioning device is provided, including: a structural positioning image acquisition module 1402, a blood vessel positioning image determination module 1404, and an arterial spin marker positioning module 1406, wherein:

[0115] The structural localization image acquisition module 1402 is used to acquire the head structural localization image of the target object;

[0116] The vascular localization image determination module 1404 is used to determine the vascular localization image of the target object based on the head structure localization image;

[0117] The artery spin marker localization module 1406 is used to locate the head plane imaging range of the target object based on the head structure localization image, and to locate the vascular marker band of the target object based on the vascular localization image.

[0118] In one embodiment, the blood vessel localization image determination module 1404 is further configured to determine the planar imaging localization center based on the head structure localization image; and locate the blood vessel localization image based on the planar imaging localization center.

[0119] In one embodiment, the arterial spin marker localization module 1406 is further configured to determine the planar imaging localization center based on the head structure localization image; perform feature recognition on the head structure localization image based on the planar imaging localization center to obtain the recognition results of each head tissue; and determine the head planar imaging range based on the recognition results of each head tissue.

[0120] In one embodiment, the arterial spin marker localization module 1406 is further configured to determine the planar imaging localization range based on the planar imaging localization center; and to perform feature recognition on the head structure localization image within the planar imaging localization range to obtain the recognition results of each head tissue.

[0121] In one embodiment, the vascular localization image determination module 1404 or the arterial spin marker localization module 1406 is further used to segment the first vertebral body and the second vertebral body from the head structure localization image; and to use the first vertebral body and the second vertebral body as the planar imaging localization center.

[0122] In one embodiment, the arterial spin marker localization module 1406 is further used to perform image segmentation on the vascular localization image to obtain vertebral artery segmentation information and carotid artery segmentation information; and to determine the vascular marker band based on the directional difference between the vertebral artery segmentation information and the carotid artery segmentation information.

[0123] In one embodiment, the arterial spin marker localization module 1406 is further configured to traverse the vertebral artery segmentation information and the carotid artery segmentation information to obtain vascular course information and vascular angle information; when the vascular course information and vascular angle information both meet the marker placement conditions of the vascular marker band, the marker band placement position is searched according to the vertebral artery segmentation information and the carotid artery segmentation information; and the vascular marker band is determined according to the marker band placement position.

[0124] In one embodiment, the arterial spin marker positioning module 1406 is further configured to, when the blood vessel course information is not satisfied but the blood vessel angle information satisfies the marker placement conditions of the blood vessel marker, search for the marker placement position and the marker placement direction based on the vertebral artery segmentation information and the carotid artery segmentation information; and determine the blood vessel marker based on the marker placement position and the marker placement direction.

[0125] In one embodiment, the arterial spin marker positioning module 1406 is further configured to determine the vascular marker band based on the default placement position of the marker band when the placement direction of the marker band does not meet the placement conditions of the vascular marker band; or, to determine the vascular marker band based on the default placement position of the marker band when the vascular angle information does not meet the placement conditions of the vascular marker band.

[0126] The modules in the aforementioned marking and positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0127] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 15 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores server data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a marker-based localization method.

[0128] Those skilled in the art will understand that Figure 15 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0129] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0130] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0131] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0132] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0133] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0134] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A marker-based localization method, characterized in that, The method includes: Obtain the head structure localization image of the target object; Based on the head structure localization image, the blood vessel localization image of the target object is determined; wherein, based on the head structure localization image, the planar imaging localization center is determined; and based on the planar imaging localization center, the blood vessel localization image is located. Based on the head structure localization image, the planar imaging range of the target object's head is located, and based on the blood vessel localization image, the blood vessel marker band of the target object is located; wherein, based on the head structure localization image, the planar imaging localization center is determined; based on the planar imaging localization center, feature recognition is performed on the head structure localization image to obtain the identification results of each head tissue; based on the identification results of each head tissue, the planar imaging range of the head is determined; image segmentation is performed on the blood vessel localization image to obtain vertebral artery segmentation information and carotid artery segmentation information; based on the directional difference between the vertebral artery segmentation information and the carotid artery segmentation information, the blood vessel marker band is determined.

2. The method according to claim 1, characterized in that, The step of performing feature recognition on the head structure localization image based on the planar imaging localization center to obtain the recognition results of each head tissue includes: The planar imaging positioning range is determined based on the planar imaging positioning center; Within the planar imaging positioning range, feature recognition is performed on the head structure positioning image to obtain the identification results of each head tissue.

3. The method according to any one of claims 1 to 2, characterized in that, The step of determining the planar imaging positioning center based on the head structure positioning image includes: The first vertebra and the second vertebra are segmented from the head structure localization image; The first vertebra and the second vertebra are used as the positioning centers for the planar imaging.

4. The method according to claim 1, characterized in that, The step of determining the vascular marker band based on the difference in orientation between the vertebral artery segmentation information and the carotid artery segmentation information includes: By traversing the vertebral artery segmentation information and the carotid artery segmentation information, the vessel course information and vessel angle information are obtained; If both the vessel course information and the vessel angle information meet the labeling conditions of the vessel labeling band, the labeling band placement position is searched based on the vertebral artery segmentation information and the carotid artery segmentation information; The vascular marker band is determined based on the placement position of the marker band.

5. The method according to claim 4, characterized in that, The step of determining the vascular marker band based on the difference in orientation between the vertebral artery segmentation information and the carotid artery segmentation information includes: If the vessel course information is not satisfied and the vessel angle information satisfies the labeling conditions of the vessel labeling band, the labeling position and labeling direction are searched based on the vertebral artery segmentation information and the carotid artery segmentation information. The vascular marker band is determined based on the placement position and orientation of the marker band.

6. The method according to claim 5, characterized in that, The method further includes: If the placement direction of the marker band does not meet the placement conditions of the vascular marker band, the vascular marker band is determined according to the default placement position of the marker band; or, If the vessel angle information does not meet the labeling conditions of the vessel labeling band, the vessel labeling band is determined according to the default placement position of the labeling band.

7. A marking and positioning device, characterized in that, The device includes: The structural localization image acquisition module is used to acquire the head structural localization image of the target object; A blood vessel localization image determination module is used to determine the blood vessel localization image of the target object based on the head structure localization image; wherein, a planar imaging localization center is determined based on the head structure localization image; and the blood vessel localization image is located based on the planar imaging localization center. An artery spin marker localization module is used to locate the planar imaging range of the head of the target object based on the head structure localization image, and to locate the vascular marker band of the target object based on the vascular localization image; wherein, based on the head structure localization image, a planar imaging localization center is determined; based on the planar imaging localization center, feature recognition is performed on the head structure localization image to obtain the recognition results of each head tissue; the planar imaging range of the head is determined based on the recognition results of each head tissue; image segmentation is performed on the vascular localization image to obtain vertebral artery segmentation information and carotid artery segmentation information; and the vascular marker band is determined based on the directional difference between the vertebral artery segmentation information and the carotid artery segmentation information.

Images