Magnetic resonance imaging method, medical imaging scan control method, and medical imaging system

Abstract

This application relates to a magnetic resonance imaging method, a medical imaging scanning control method, and a medical imaging system. The method includes: acquiring a three-dimensional vascular image of an imaging object; the three-dimensional vascular image includes at least one of bright blood vessel images and dark blood vessel images; acquiring medical record information of the imaging object and / or other modalities of medical images of the imaging object; determining the location of a region of interest (ROI) in the three-dimensional vascular image based on the medical record information and / or other modalities of medical images, as well as the three-dimensional vascular image and a localization model; and scanning the imaging object based on the ROI location to determine a two-dimensional vascular image of the imaging object. Using the magnetic resonance imaging method provided in this application can improve the accuracy, consistency, and efficiency of locating the ROI, thereby improving the accuracy and efficiency of the determined two-dimensional vascular image of the imaging object.

Description

Technical Field

[0001] This application relates to the field of imaging technology, and in particular to a magnetic resonance imaging method, a medical imaging scanning control method, and a medical imaging system. Background Technology

[0002] When using magnetic resonance imaging (MRI) to scan blood vessel images, 3D imaging technology is first used to scan a large area of ​​3D images. Based on the 3D images, a preliminary assessment is made as to whether there is a region of interest in the blood vessel. If a region of interest is found, 2D imaging technology is then used to obtain a higher resolution 2D image. Based on the 2D image, the feature information of the region of interest is more clearly determined.

[0003] In traditional techniques, before acquiring 2D images using 2D imaging technology, scanners need to identify segments within blood vessels containing regions of interest from a large number of 3D thin-slice images obtained through scanning and then manually locate them. However, the localization of segments containing regions of interest within blood vessels using traditional techniques is inaccurate. Summary of the Invention

[0004] Therefore, it is necessary to provide a magnetic resonance imaging method, medical imaging scanning control method, and medical imaging system that can improve the accuracy of locating segments of interest in blood vessels, addressing the aforementioned technical problems.

[0005] In a first aspect, this application provides a magnetic resonance imaging method, the method comprising:

[0006] Acquire a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image;

[0007] Acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object;

[0008] Based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models, determine the location of the region of interest in the three-dimensional vascular image;

[0009] The imaging object is scanned based on the region of interest to determine a two-dimensional vascular image of the imaging object.

[0010] In one embodiment, the other modality of medical images is anatomical images. Based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and a localization model, the location of the region of interest is determined, including:

[0011] Input medical record information and / or other modalities of medical images, as well as 3D vascular images, into the localization model to determine the location of the region of interest;

[0012] or;

[0013] Medical records and / or other modalities of medical images, as well as three-dimensional vascular images, are fused to obtain fused data;

[0014] The fused data is input into the localization model to determine the location of the region of interest.

[0015] In one embodiment, the localization model includes a fusion sub-model and a localization sub-model. Medical record information and / or other modalities of medical images, as well as three-dimensional vascular images, are input into the localization model to determine the location of the region of interest, including:

[0016] Medical records and / or other modalities of medical images, as well as 3D vascular images, are input into the fusion sub-model to determine the fusion data;

[0017] The fused data is input into the localization sub-model to determine the location of the region of interest.

[0018] In one embodiment, the method further includes:

[0019] Determine if a region of interest exists in a 3D vascular image;

[0020] If a region of interest is determined to exist in the 3D vascular image, the process returns to the step of determining the location of the region of interest in the 3D vascular image based on medical records and / or other modal medical images, as well as the 3D vascular image input to the localization model.

[0021] If it is determined that there is no region of interest in the 3D vascular image, a first prompt message is sent.

[0022] In one embodiment, scanning the imaging object based on the region of interest location to determine a two-dimensional vascular image of the imaging object includes:

[0023] If multiple regions of interest exist in a defined 3D vascular image, display these regions on the display interface and send a second prompt message.

[0024] In response to the user's selection of multiple regions of interest based on the second prompt information, the location of the target region of interest is determined;

[0025] The scanning field of view of the imaging device is determined based on the location of the target region of interest, and the imaging object is scanned based on the scanning field of view to obtain a two-dimensional blood vessel image.

[0026] Secondly, this application provides a medical imaging scanning control method, the method comprising:

[0027] Acquire a pre-scanned image of the object being imaged;

[0028] Acquire historical medical text reports of the imaging object, including text reports of physiological examinations and / or text reports of imaging examinations; the historical medical text reports include natural language descriptions of at least one medical event;

[0029] Based on pre-scanned images and historical medical text reports, identify at least one region of interest in the imaging object;

[0030] Based on the region of interest, set the scanning parameters to generate the target scanning protocol;

[0031] Medical imaging scans are performed based on the target scanning protocol.

[0032] In one embodiment, the pre-scanned image is a 3D image, and the target scanning protocol corresponds to a 2D image.

[0033] Thirdly, this application provides a medical imaging system, including a scanner, a display, a memory, and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0034] Control the scanner to pre-scan the imaging object and control the display to show the pre-scanned image corresponding to the pre-scan;

[0035] Automatically mark at least one primary target tissue region on the pre-scanned image;

[0036] Acquire historical medical text reports of the imaging object, including text reports of physiological examinations and / or text reports of imaging examinations; the historical medical text reports include natural language descriptions of at least one medical event;

[0037] Automatically analyze historical medical text reports to identify the anatomical structures or secondary target tissue regions addressed in the historical medical text reports;

[0038] On a pre-scanned image of a first target tissue region that has been marked, mark at least one region of interest of the anatomical structure or the second target tissue region;

[0039] Based on at least one first target tissue region and at least one region of interest, set scanning parameters to generate a target scanning protocol;

[0040] Control the scanner to execute the target scanning protocol.

[0041] In one embodiment, the region of interest includes the plaque region of the blood vessel.

[0042] In one embodiment, scanning parameters are set to generate a target scanning protocol based on at least one first target tissue region and at least one region of interest, including:

[0043] Generate a selection list of at least one target organization region and at least one region of interest;

[0044] In response to a user's selection of at least one option in the selection list, imaging field of view parameters are set to generate a target scanning protocol.

[0045] Fourthly, this application provides a magnetic resonance imaging device, the device comprising:

[0046] The acquisition module is used to acquire a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image.

[0047] The acquisition module is also used to acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object;

[0048] The determination module is used to determine the location of the region of interest in the three-dimensional vascular image based on medical record information and / or other modal medical images, as well as the three-dimensional vascular image and localization model;

[0049] The scanning module is used to scan the imaging object based on the location of the region of interest to determine a two-dimensional vascular image of the imaging object.

[0050] Fifthly, one embodiment of this application provides a computer device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the methods provided in the first and second aspects described above.

[0051] In a sixth aspect, one embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the methods provided in the first and second aspects described above.

[0052] In a seventh aspect, one embodiment of this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the methods provided in the first and second aspects described above.

[0053] The aforementioned magnetic resonance imaging method, medical imaging scanning control method, and medical imaging system involve acquiring a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of bright blood images and dark blood images; acquiring medical record information and / or other modal medical images of the imaging object; determining the location of the region of interest (ROI) in the three-dimensional vascular image based on the medical record information and / or other modal medical images, as well as the three-dimensional vascular image and a positioning model; and scanning the imaging object based on the ROI location to determine a two-dimensional vascular image of the imaging object. In this embodiment, a trained positioning model is used to locate the three-dimensional vascular image of the imaging object and determine the location of the ROI. This eliminates the need for manual positioning by scanning personnel, avoiding time-consuming operations and inaccuracies and inconsistencies caused by varying experience among different scanning personnel. This improves the accuracy, consistency, and efficiency of the determined ROI location, thereby enhancing the accuracy and efficiency of subsequent scanning of the imaging object based on the ROI location to obtain a two-dimensional vascular image of the imaging object. Furthermore, the ROI location is obtained by locating the ROI based on the acquired medical record information and / or other modal medical images of the imaging object, as well as the three-dimensional vascular image and a positioning model. In this way, richer and more comprehensive information about the vascular images of the imaging object can be obtained through medical record information and other modalities of medical images. By combining the three-dimensional vascular images to locate the region of interest, the accuracy of the determined region of interest location can be improved. Attached Figure Description

[0054] Figure 1 This is a diagram illustrating the application environment of a magnetic resonance imaging method in one embodiment.

[0055] Figure 2 This is a schematic flowchart of a magnetic resonance imaging method in one embodiment;

[0056] Figure 3 This is a flowchart illustrating the steps of a magnetic resonance imaging method in another embodiment;

[0057] Figure 4 This is a flowchart illustrating the steps of a magnetic resonance imaging method in another embodiment;

[0058] Figure 5 This is a flowchart illustrating the steps of a magnetic resonance imaging method in another embodiment;

[0059] Figure 6 This is a flowchart illustrating the steps of a magnetic resonance imaging method in another embodiment;

[0060] Figure 7 This is a flowchart illustrating the steps of a magnetic resonance imaging method in another embodiment;

[0061] Figure 8 This is a flowchart illustrating the steps of a magnetic resonance imaging method in another embodiment;

[0062] Figure 9 This is a schematic diagram of the positioning image in one embodiment;

[0063] Figure 10 This is a schematic diagram of a bright blood vessel image in one embodiment;

[0064] Figure 11 This is a schematic diagram of a black blood vessel image in one embodiment;

[0065] Figure 12 This is a schematic diagram of a portion of a blood vessel segment containing the region of interest in one embodiment;

[0066] Figure 13 This is a schematic diagram of the scanning field of view in one embodiment;

[0067] Figure 14 This is a schematic diagram of a two-dimensional blood vessel image in one embodiment;

[0068] Figure 15 This is a flowchart illustrating the steps of a medical imaging scanning control method in one embodiment;

[0069] Figure 16 This is a flowchart illustrating the steps of a medical imaging scanning control method in another embodiment;

[0070] Figure 17 This is a flowchart illustrating the steps implemented by a processor executing a computer program in a medical imaging system according to one embodiment.

[0071] Figure 18 This is a flowchart illustrating the steps implemented by a processor executing a computer program in a medical imaging system according to another embodiment.

[0072] Figure 19 This is a schematic diagram of the structure of a magnetic resonance imaging device in one embodiment;

[0073] Figure 20 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0074] 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.

[0075] The serial numbers assigned to components in this article, such as "first" and "second", are used only to distinguish the objects being described and have no sequential or technical meaning.

[0076] First, before introducing the technical solutions of the embodiments disclosed in this application, the background technology or technological evolution on which the embodiments of this application are based will be introduced. In the field of imaging technology, when using magnetic resonance imaging equipment to scan vascular images, 3D imaging technology is first used to scan a large-scale 3D image, which can improve the overall overview of the blood vessel wall. Based on the 3D image, a preliminary assessment is made as to whether there is a region of interest on the blood vessel, that is, whether there is a lesion area on the blood vessel, such as atherosclerotic plaques; if a region of interest is found, 2D imaging technology is then used to obtain a higher resolution 2D image, and based on the 2D image, the feature information of the region of interest is more clearly determined, such as the shape, size, composition and other characteristics of the plaque.

[0077] In traditional techniques, before acquiring 2D images using 2D imaging technology, scanners need to identify and manually locate regions of interest (ROIs) from a large number of 3D thin-slice images obtained from scanning. However, traditional methods for locating ROIs within blood vessels are time-consuming. Furthermore, for structurally complex areas, such as intracranial vessels, manual localization struggles to accurately cover all ROI segments, especially for tortuous vessels. Additionally, manual localization relies on the scanner's experience, and the accuracy varies among different scanners, affecting image quality and diagnostic consistency. To address this, this application provides a magnetic resonance imaging (MRI) method.

[0078] The magnetic resonance imaging method provided in this embodiment can be as follows: Figure 1 The application environment shown includes a terminal 103 and an imaging device 104. The terminal 103 can communicate with the imaging device 104 via a network. The terminal 103 can be, but is not limited to, various personal computers, laptops, and tablets. The imaging device 104 is illustrated using a magnetic resonance (MR) device as an example.

[0079] The technical solution of this application and how the technical solution of this application solves the technical problem are described in detail below with specific embodiments.

[0080] In one embodiment, such as Figure 2 As shown, a magnetic resonance imaging method is provided. This embodiment illustrates the application of this method to a terminal. In this embodiment, the method includes the following steps:

[0081] Step 200: Obtain a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image.

[0082] The imaging subject can be an animal or a human body. A three-dimensional vascular image of the imaging subject refers to a three-dimensional vascular image obtained by scanning the imaging subject using a magnetic resonance imaging (MRI) device. The acquired three-dimensional vascular image of the imaging subject includes at least one of bright blood vessel images and dark blood vessel images. The bright blood vessel image is a three-dimensional image obtained by scanning the imaging subject using a time-of-flight (TOF) sequence with an MRI device. The obtained bright blood vessel images include transverse, coronal, sagittal, and maximum intensity projection (MIP) images. The dark blood vessel image is a three-dimensional image obtained by scanning the imaging subject using a T1-weighted image (T1WI) sequence with an MRI device. The obtained dark blood vessel images also include transverse, coronal, sagittal, and MIP images.

[0083] The terminal can acquire 3D vascular images of the imaging object from the post-processing workstation of the imaging equipment, or from a server such as a PACS (Picture Archiving and Communication Systems). Alternatively, the 3D vascular images of the imaging object can be pre-stored in the memory of a computer device, and the terminal can directly retrieve them from the memory when needed. The terminal can also control the magnetic resonance imaging equipment to scan the imaging object and obtain 3D vascular images in real time. This embodiment does not limit the specific method for acquiring 3D vascular images of the imaging object, as long as the function can be achieved.

[0084] In an optional embodiment, when the acquired three-dimensional vascular image of the imaging object includes both bright blood vessel images and dark blood vessel images, the bright blood vessel images can be used to determine whether there are stenotic segments in the blood vessels of the imaging object, while the dark blood vessel images facilitate observation of the vessel wall condition, thereby enabling plaque identification. Combining the bright and dark blood vessel images facilitates more accurate identification of regions of interest in the subsequent three-dimensional vascular image of the imaging object.

[0085] In an optional embodiment, before scanning the imaging object to obtain a three-dimensional vascular image, the magnetic resonance imaging (MRI) device can first scan the imaging object based on a gradient-recalled echo (GRE) sequence to obtain a localization image; then, based on the localization image, the imaging object is scanned to obtain a three-dimensional vascular image. This localization using the localization image before scanning improves the accuracy of the acquired three-dimensional vascular image.

[0086] Step 210: Input the three-dimensional blood vessel image into the localization model to determine the location of the region of interest in the three-dimensional blood vessel image.

[0087] The localization model can be pre-trained and stored in the terminal's memory. The localization model can be a machine learning model such as a support vector machine, random forest, or neural network. This embodiment does not limit the type or structure of the localization model, as long as it can achieve its function.

[0088] In an optional embodiment, the training method for the localization model includes: acquiring training samples; the training samples include three-dimensional blood vessel image samples; and training an initial network model using the training samples to obtain the localization model.

[0089] After acquiring a 3D vascular image, the terminal inputs it into a trained localization model. The model then performs localization processing on the 3D vascular image to determine the location of the region of interest (ROI). The ROI refers to the lesion area within the 3D vascular image. The location of the ROI determined by the localization model can include one or more regions.

[0090] In an optional embodiment, such as Figure 3 As shown, this involves inputting a three-dimensional blood vessel image into a localization model to determine the location of a region of interest in the three-dimensional blood vessel image. The steps of this implementation include:

[0091] Step 300: Obtain medical record information of the imaging object and / or medical images of other modalities of the imaging object.

[0092] Medical record information and other modalities of medical images of the imaging subject can be pre-stored in the imaging equipment post-processing workstation or PACS server. Medical record information can be text reports of physiological examinations and / or imaging examinations. It may include basic information about the imaging subject, medical history, physical examination information, auxiliary examination information, diagnostic information, and treatment information. Basic information about the imaging subject may include name, age, gender, contact information, and allergy history; medical history information may include current medical history, past medical history, and family history. Physical examination information may include general examination information and vital sign examination information. Auxiliary examination information may include laboratory tests, complete blood count, and biochemical tests. Other modalities of medical images of the imaging object can be computed tomography (CT) images, positron emission tomography (PET) images, single-photon emission computed tomography (SPECT) images, ultrasound (US) images, etc., obtained from previous scans of the imaging object, or vascular images obtained from the past of the imaging object.

[0093] The terminal can acquire medical record information of the imaging subject, as well as other modalities of medical images of the imaging subject. Other modalities of medical images may include anatomical images reflecting anatomical structures, such as CT images and US images, or molecular functional images such as PET and SPECT.

[0094] Step 310: Determine the location of the region of interest based on medical record information and / or other modal medical images, as well as three-dimensional vascular images and localization models.

[0095] The medical record information of the imaging object includes descriptive information about whether a region of interest exists in the blood vessels of the imaging object. When the medical record information is acquired by the terminal, it can be analyzed and processed first to extract the information describing the blood vessels of the imaging object; then, based on the medical record information, the three-dimensional blood vessel image, and a pre-trained localization model, the location of the region of interest can be determined.

[0096] Other modalities of medical images of the imaging object can be pre-annotated with relevant vascular features, or the terminal can identify the relevant vascular features by recognizing the other modalities of medical images of the imaging object. When the terminal acquires other modalities of medical images of the imaging object, the location of the region of interest can be determined based on the other modalities of medical images, the 3D vascular image, and a pre-trained localization model.

[0097] When the terminal acquires medical record information and other modalities of medical images of the imaging object, the location of the region of interest can be determined based on the medical record information, other modalities of medical images, three-dimensional vascular images, and a pre-trained localization model. This embodiment does not limit the specific method for determining the location of the region of interest based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and a localization model, as long as the function can be achieved.

[0098] Step 210: Scan the imaging object based on the region of interest to determine the two-dimensional blood vessel image of the imaging object.

[0099] After determining the location of the region of interest (ROI) in the 3D image, the terminal can determine the precise scanning position based on the ROI location. The terminal then sends a control signal to the imaging device based on the determined scanning position, causing the imaging device to scan the object and determine a two-dimensional vascular image of the object.

[0100] In an optional embodiment, the magnetic resonance imaging method further includes: performing identification processing on the two-dimensional vascular image to determine plaque feature information in the two-dimensional vascular image. The plaque feature information may include plaque type, size, shape, location, and plaque stability, etc.

[0101] The magnetic resonance imaging method provided in this application involves acquiring a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood image and a dark blood image; acquiring medical record information and / or other modal medical images of the imaging object; determining the location of the region of interest (ROI) in the three-dimensional vascular image based on the medical record information and / or other modal medical images, the three-dimensional vascular image, and a localization model; and scanning the imaging object based on the ROI location to determine a two-dimensional vascular image of the imaging object. In this embodiment, a trained localization model is used to locate the three-dimensional vascular image of the imaging object and determine the location of the ROI. This eliminates the need for manual localization by the user, avoiding time-consuming processes and inaccuracies and inconsistencies caused by different user experiences. This improves the accuracy, consistency, and efficiency of the determined ROI location, thereby enhancing the accuracy and efficiency of subsequent scanning of the imaging object based on the ROI location to obtain a two-dimensional vascular image of the imaging object. Furthermore, the ROI location is obtained by locating the ROI based on the acquired medical record information and / or other modal medical images of the imaging object, the three-dimensional vascular image, and the localization model. In this way, richer and more comprehensive information about the vascular images of the imaging object can be obtained through medical record information and other modalities of medical images. By combining the three-dimensional vascular images to locate the region of interest, the accuracy of the determined region of interest location can be improved.

[0102] In one embodiment, such as Figure 4 As shown, this involves two implementation methods for determining the location of a region of interest based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models. One implementation method includes the following steps:

[0103] Step 400: Input medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the localization model to determine the location of the region of interest.

[0104] After acquiring medical record information and / or other modalities of medical images of the imaging object, as well as three-dimensional vascular images, the terminal directly inputs the medical record information and / or other modalities of medical images, as well as the three-dimensional vascular images, into a pre-trained localization model. The localization model then analyzes the data to determine the location of the region of interest. During the training of this localization model, the training samples may also include medical record information samples and other modalities of medical image samples.

[0105] Another implementation method includes the following steps:

[0106] Step 410: Perform fusion processing on medical record information and / or other modal medical images, as well as three-dimensional vascular images, to obtain fused data.

[0107] After acquiring medical record information and / or other modalities of medical images of the imaging object, the terminal can fuse them with a three-dimensional vascular image to obtain fused data. This fusion can be achieved by fusing medical record information with a three-dimensional vascular image; by fusing other modalities of medical images with a three-dimensional vascular image; or by fusing medical record information with other modalities of medical images with a three-dimensional vascular image.

[0108] In an optional embodiment, when fusing medical record information with a 3D vascular image, the medical record information can be analyzed first to determine the vascular-related features within it; then, the determined vascular features are annotated into the 3D vascular image to obtain the fused 3D vascular image. When fusing other modalities of medical images with a 3D vascular image, the other modalities of medical images can be fused using an image fusion method. Image fusion methods can be, but are not limited to, principal component analysis, scale-invariant feature transformation fusion, and Bayesian decision fusion. When fusing medical record information with other modalities of medical images with a 3D vascular image, the medical record information can be fused with the 3D vascular image first, and then the fused 3D vascular image can be fused with other modalities of medical images; alternatively, other modalities of medical images can be fused with the 3D vascular image first, and then the fused vascular image can be fused with the medical record information.

[0109] Step 420: Input the fused data into the localization model to determine the location of the region of interest.

[0110] After acquiring medical record information and / or other modal medical images and 3D vascular images, the terminal inputs the fused data into the localization model. Through the localization analysis of the localization model, the location of the region of interest can be determined.

[0111] This embodiment provides two methods for determining the region of interest (ROI) location based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models. Users can choose any one method to determine the ROI location based on their actual application, or they can use both methods to obtain two ROI locations separately. By analyzing the two ROI locations, a more accurate and comprehensive ROI location can be obtained, thus improving the practicality of the magnetic resonance imaging method.

[0112] In one embodiment, the localization model includes a fusion sub-model and a localization sub-model. In this case, such as... Figure 5 As shown, another implementation method involves inputting medical record information and / or other modalities of medical images, as well as three-dimensional vascular images, into a localization model to determine the location of a region of interest. This implementation method includes the following steps:

[0113] Step 500: Input medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the fusion sub-model to determine the fusion data.

[0114] After acquiring the medical record information of the imaging object, the terminal can input the medical record information and the 3D vascular image into the fusion sub-model. The fusion sub-model then fuses the medical record information and the 3D vascular image to obtain fused data. Similarly, after acquiring other modalities of medical images of the imaging object, the terminal can input these other modalities of medical images and the 3D vascular image into the fusion sub-model. The fusion sub-model then performs the fusion processing to obtain fused data.

[0115] In an optional embodiment, the terminal uses training samples, including medical record information samples, medical image samples from other modalities, and three-dimensional vascular image samples, to train the network model and obtain a fusion sub-model.

[0116] Step 510: Input the fused data into the localization sub-model to determine the location of the region of interest.

[0117] After acquiring the fused data, the terminal inputs the fused data into the positioning sub-model. The positioning sub-model performs positioning processing to determine the location of the region of interest.

[0118] In an optional embodiment, the terminal trains the network model using training samples that include fused data samples to obtain a localization sub-model.

[0119] In this embodiment, medical record information and / or other modalities of medical images are first fused with three-dimensional vascular images using a fusion sub-model to obtain fused data. Then, a localization sub-model is used to locate the fused data and determine the region of interest. This improves the consistency, accuracy, and efficiency of determining the location of the fused data and the region of interest.

[0120] In one embodiment, such as Figure 6 As shown, the method further includes the following steps:

[0121] Step 600: Determine whether there is a region of interest in the three-dimensional blood vessel image.

[0122] After acquiring a three-dimensional vascular image of the imaging object, the terminal can first identify whether there is a region of interest in the three-dimensional vascular image.

[0123] In one optional embodiment, the terminal can input a three-dimensional vascular image into a pre-trained recognition model to identify whether a region of interest exists in the three-dimensional vascular image. The terminal can also input acquired medical record information and / or other modalities of medical images, along with the three-dimensional vascular image, into the pre-trained recognition model to identify whether a region of interest exists in the three-dimensional vascular image.

[0124] Step 610: If a region of interest is determined to exist in the three-dimensional vascular image, return to the step of inputting the three-dimensional vascular image into the localization model and determining the location of the region of interest in the three-dimensional vascular image.

[0125] If the terminal identifies a region of interest in the three-dimensional blood vessel image, it returns to step 210-211 to obtain a two-dimensional blood vessel image of the imaging object, which allows the user to more accurately determine the feature information of the region of interest based on the two-dimensional blood vessel image.

[0126] Step 620: If it is determined that there is no region of interest in the three-dimensional vascular image, send the first prompt message.

[0127] The first prompt message can be at least one of the following: a prompt bell, a prompt light, a prompt voice, and a prompt pop-up window on the display interface. If the terminal determines, through identification, that there is no region of interest in the three-dimensional vascular image, it will send the first prompt message. The first prompt message is used to inform the user that no region of interest has been identified in the three-dimensional vascular image. Based on this prompt message, the user can manually verify whether there is a region of interest in the three-dimensional vascular image; if the user determines that there is no region of interest in the three-dimensional vascular image, the current magnetic resonance scan will be stopped; if the user determines that there is a region of interest in the three-dimensional vascular image, the user can mark the location of the region of interest in the three-dimensional vascular image; after obtaining the three-dimensional vascular image marked by the user, the terminal executes step 220.

[0128] In this embodiment, it is first determined whether a region of interest exists in the three-dimensional vascular image. If a region of interest exists, steps 210 and 220 in the above embodiment are executed. If no region of interest exists, a first prompt message is sent to facilitate subsequent processing by the user. This avoids the need for subsequent localization processes when no region of interest exists in the three-dimensional vascular image, reducing resource waste. Furthermore, sending a first prompt message allows the user to perform subsequent processing in a timely manner, thereby improving the practicality of the magnetic resonance imaging method.

[0129] In one embodiment, such as Figure 7 As shown, this relates to an implementation method for scanning an imaging object based on the location of a region of interest to determine a two-dimensional vascular image of the imaging object. The steps of this implementation method include:

[0130] Step 700: If multiple regions of interest exist in the determined three-dimensional vascular image, display the multiple regions of interest on the display interface and send a second prompt message.

[0131] The terminal includes a display interface. The second prompt message can be at least one of a prompt bell, a prompt light, a prompt voice, and a prompt pop-up window on the display interface. If the terminal determines that there are multiple regions of interest in the three-dimensional vascular image, that is, multiple locations of the determined regions of interest, the terminal displays the three-dimensional vascular image on the display interface, marks the locations of the determined regions of interest in the three-dimensional vascular image, and sends the second prompt message. Specifically, the terminal can pop up a prompt window on the display interface, which displays "Identified the location of the region of interest at ×, please confirm the scanned area".

[0132] Step 710: In response to the user's selection of multiple regions of interest locations based on the second prompt information, determine the location of the target region of interest.

[0133] Based on the second prompt information obtained, the user selects a region of interest (ROI) location from multiple ROI locations. The terminal responds to the user's selection operation and determines the selected ROI location as the target ROI location.

[0134] Step 720: Determine the scanning field of view of the imaging device based on the location of the target region of interest, and scan the imaging object based on the scanning field of view to obtain a two-dimensional blood vessel image.

[0135] After acquiring the location of the target region of interest (ROI), the terminal determines the scanning field of view of the imaging device based on the ROI location. In other words, the size of the area that the imaging device needs to scan is determined based on the ROI location. Specifically, the scan start and end positions can be determined based on the ROI location, and the scanning field of view can be determined based on these positions.

[0136] After determining the scanning field of view of the imaging device, the terminal sends a control signal to the imaging device to control the imaging device to scan the imaging object based on the scanning field of view, thereby obtaining a two-dimensional vascular image of the imaging object. The terminal can repeat the above steps 710 and 720 to scan different regions of interest of the target to obtain multiple two-dimensional vascular images.

[0137] In this embodiment, when multiple regions of interest (ROIs) are determined to exist in a three-dimensional vascular image, these ROIs are displayed on the screen, and a second prompt is sent to the user. In response to the user's selection of ROIs based on the second prompt, the target ROI is determined. The scanning field of view of the imaging device is determined based on the target ROI, and the imaging object is scanned based on this field of view to obtain a two-dimensional vascular image. This human-computer interaction method for scanning the imaging object and obtaining a two-dimensional vascular image enhances the flexibility of the magnetic resonance imaging method.

[0138] In an optional embodiment, if the terminal determines that there are multiple regions of interest (ROIs) in the three-dimensional vascular image, the ROIs can be sorted in a preset order or randomly, and the corresponding scanning field of view is determined according to the sorting order. The terminal sends control signals to the imaging device to control the imaging device to scan the imaging object based on each scanning field of view, thereby obtaining multiple two-dimensional vascular images.

[0139] Please see Figure 8 One embodiment of this application provides a magnetic resonance imaging method, the steps of which include:

[0140] Step 800: Control the magnetic resonance imaging device to scan the imaging object to obtain a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image;

[0141] Step 810: Acquire medical record information and other modalities of medical images of the imaging object;

[0142] Step 820: Fuse medical record information, other modal medical images, and three-dimensional vascular images to obtain fused data;

[0143] Step 830: Input the fused data into the pre-trained localization model to determine the location of the region of interest in the three-dimensional blood vessel image;

[0144] Step 840: Determine the scanning field of view of the magnetic resonance imaging device based on the location of the target region of interest, and control the magnetic resonance imaging device to scan the imaging object based on the scanning field of view to obtain a two-dimensional vascular image of the imaging object.

[0145] In an optional embodiment, the acquired positioning image can be as follows: Figure 9 As shown. The localization image includes transverse, coronal, and sagittal images. The acquired bright blood vessel image is shown below. Figure 10 As shown, the bright blood vessel images include transverse, coronal, sagittal, and MIP images. The acquired dark blood vessel images are shown below. Figure 11As shown, the black blood vessel images include transverse, coronal, sagittal, and MIP images. Vascular segments with regions of interest were identified using medical record information, other modalities of medical images, and three-dimensional vascular images. Figure 12 As shown, Figure 12 The white area in the center represents the region of interest (ROI). The scanning field of view for imaging is determined based on the location of the ROI, such as... Figure 13 As shown, Figure 13 The rectangle in the image represents the scanning field of view. Controlling the imaging device to image the object based on this scanning field of view yields results such as... Figure 14 The image shown is a two-dimensional blood vessel image.

[0146] In one embodiment, such as Figure 15 As shown, a medical imaging scanning control method is provided. This embodiment illustrates the application of this method to a terminal. In this embodiment, the steps of the method include:

[0147] Step 150: Obtain a pre-scanned image of the imaging object.

[0148] The terminal sends a control signal to the scanning device, instructing the device to scan the object being imaged to obtain a pre-scanned image. Specifically, the terminal controls the scanning device to scan the target tissue region of the object, and the resulting pre-scanned image includes this target tissue region. The target tissue region can be the head vascular region, neck vascular region, chest vascular region, etc.

[0149] The pre-scanned image can be acquired in real time by scanning the imaging object, or it can be pre-stored in the terminal's storage device. The terminal acquires the pre-scanned image of the imaging object.

[0150] Step 151: Obtain the historical medical text report of the imaging object. The historical medical text report includes text reports of physiological tests and / or text reports of imaging tests; the historical medical text report includes a natural language description of at least one medical event.

[0151] Physiological detection text reports include text reports generated after detecting the physiological characteristics of the imaging subject. Physiological characteristics include, but are not limited to, the imaging subject's blood pressure, blood glucose, blood lipids, and cholesterol. Image detection text reports refer to one or more medical images of the imaging subject that have been scanned in the past. The medical images in the image detection text report may or may not be of the same modality as the pre-scanned images. When the image detection text report includes multiple medical images, the modalities of the multiple medical images may be the same or different. A medical event refers to an event in which a lesion exists in a certain tissue of the imaging subject. The historical medical document report includes text information describing the medical event using natural language. For example, the historical medical text report may include information about plaques in the blood vessels of the imaging subject's head. Historical medical text reports can be pre-stored in the terminal's storage device or in a server such as an imaging equipment post-processing workstation or PACS. The terminal retrieves the reports directly from its storage device, imaging equipment post-processing workstation, or PACS when needed.

[0152] Step 152: Based on the pre-scanned images and historical medical text reports, identify at least one region of interest in the imaging object.

[0153] After acquiring the pre-scanned image and historical medical text report of the imaging object, the terminal can determine at least one region of interest (ROI) within the imaging object based on the pre-scanned image and historical medical text report, thereby determining the location of the ROI. In other words, based on the pre-scanned image and historical medical text report, it can be determined that at least one lesion region exists within the target tissue region of the imaging object in the pre-scanned image. The description of determining at least one ROI within the imaging object based on the pre-scanned image and historical medical text report can be found in the detailed description in the above embodiments of determining the location of the ROI in a three-dimensional vascular image based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models, and will not be repeated here.

[0154] Step 153: Based on the region of interest, set the scanning parameters to generate the target scanning protocol.

[0155] After determining the region of interest (ROI), the terminal can adjust the imaging field of view (FPGA) parameters in the scanning parameters based on the location of the ROI. In other words, the FPGA parameters are adjusted to align the imaging field of view with the location of the ROI, thereby generating a target scanning protocol.

[0156] Step 154: Perform medical imaging scans based on the target scanning protocol.

[0157] After acquiring the target scanning protocol, the terminal performs a medical imaging scan based on that protocol. In other words, it controls the medical imaging device to scan the object to be imaged according to the target scanning protocol, thereby obtaining a target image of the object.

[0158] In this embodiment, at least one region of interest (ROI) is determined within the imaging object based on pre-scanned images and historical medical text reports. This eliminates the need for manual ROI location by scanning personnel, avoiding time-consuming processes and inaccuracies and inconsistencies caused by varying experience among different scanning personnel. Consequently, the accuracy, consistency, and efficiency of the determined ROI location are improved. Furthermore, this method yields richer and more comprehensive information about the imaging object, enhancing the accuracy of ROI identification and thus improving the practicality of the target scanning protocol. Ultimately, this leads to higher accuracy in the target images obtained from medical imaging scans performed based on the target scan.

[0159] In one embodiment, the pre-scanned image is a 3D image, and the target scanning protocol corresponds to a 2D image.

[0160] The target scanning protocol corresponds to a 2D image, indicating that the target image obtained by performing a medical imaging scan based on the target scanning protocol is a two-dimensional image. That is, in the embodiments of this application, a 3D image of the imaging object is first acquired. Through the 3D image and historical medical text reports, at least one region of interest of the imaging object is determined. Subsequently, a target scanning protocol is generated based on the region of interest, and a medical imaging scan is performed based on the target scanning protocol to obtain a more accurate two-dimensional image of the imaging object.

[0161] In one embodiment, such as Figure 16 As shown, a medical imaging scanning control method is provided. This embodiment illustrates the application of this method to a terminal. In this embodiment, the steps of the method include:

[0162] Step 160: Obtain a pre-scanned image of the imaging object.

[0163] The description of the pre-scanned object for acquiring the imaging object can be found in the detailed description of the above embodiments, and will not be repeated here.

[0164] Step 161: Automatically mark at least one first target tissue region on the pre-scanned image.

[0165] After acquiring the pre-scanned image, the terminal analyzes the image to identify and mark at least one target tissue region. The first target tissue region refers to the area in the pre-scanned image where a region of interest may exist. For example, the first target tissue region could be a blood vessel segment in the pre-scanned image where a region of interest may exist. This embodiment does not limit the specific method for determining the first target tissue region in the pre-scanned image, as long as the function can be achieved.

[0166] In an optional embodiment, the terminal may employ a thresholding method to determine at least one first target tissue region in the pre-scanned image. Alternatively, the terminal may input the pre-scanned image into a pre-trained region determination model to determine at least one first target tissue region in the pre-scanned image.

[0167] Step 162: Obtain historical medical text reports of the imaging object. The historical medical text reports include text reports of physiological tests and / or text reports of imaging tests; the historical medical text reports include natural language descriptions of at least one medical event.

[0168] The description of the historical medical text report of the acquired imaging object can be found in the detailed description of the above embodiments, and will not be repeated here.

[0169] Step 163: Automatically analyze historical medical text reports to determine the anatomical structures or secondary target tissue regions targeted by the historical medical text reports.

[0170] The terminal acquires historical medical text reports of the imaging object and analyzes these reports to determine the anatomical structures or secondary target tissue regions identified in the reports. In other words, by analyzing the historical medical text reports of the imaging object, it is possible to determine the anatomical structures or secondary target tissue regions where regions of interest were identified during previous image scans.

[0171] In an optional embodiment, the automatic analysis of historical medical text reports may enhance the key information in the historical medical text reports by determining the anatomical structure or secondary target tissue region targeted by the historical medical text reports based on relational information.

[0172] Step 164: On the pre-scanned image of the first target tissue region that has been marked, mark at least one region of interest of the anatomical structure or the second target tissue region.

[0173] After determining the anatomical structure or second target tissue region of the imaging object based on historical medical text reports, the terminal can determine at least one region of interest (ROI) of the imaging object based on the anatomical structure or second target tissue region. In other words, it can determine lesion areas that have historically existed on the imaging object. After determining at least one ROI of the imaging object, the terminal marks it in a pre-scan image. The current pre-scan marks the image with the first target tissue region of the imaging object and at least one ROI of the imaging object.

[0174] Step 165: Based on at least one first target tissue region and at least one region of interest, set scanning parameters to generate a target scanning protocol.

[0175] The terminal can set scanning parameters to generate a target scanning protocol based on the location of at least a first target tissue region and at least one region of interest marked in the pre-scanned image.

[0176] In an optional embodiment, the imaging field of view parameter in the scanning parameters can be set according to the location of the first target tissue region and the region of interest, so that the imaging field of view is consistent with the location of the region of interest.

[0177] In another optional embodiment, the region of interest corresponding to the first target tissue region is first determined, and the target region of interest of the imaging object is determined based on the region of interest corresponding to the first target tissue region and the region of interest corresponding to the second target tissue region; the imaging field of view parameter in the scanning parameters is set according to the position of the target region of interest so that the imaging field of view is consistent with the position of the region of interest.

[0178] Step 166: Perform medical imaging scans based on the target scanning protocol.

[0179] After determining the target scanning protocol, the terminal controls the medical imaging device to scan the object to be imaged based on that protocol. Scanning the object with the medical imaging device yields a target image of the object. The target image is a two-dimensional image.

[0180] In this embodiment, at least one first target tissue region of the imaging object is determined by the acquired pre-scan image; at least one region of interest corresponding to the anatomical structure or second target tissue region of the imaging object is determined by the acquired historical medical text report; and the field of view imaging in the target scanning protocol is determined based on the first target tissue region and at least one region of interest. This automatically determined field of view imaging can avoid time consumption and inaccuracies and inconsistencies in the determined field of view imaging caused by different scanning personnel's experience, thereby improving the accuracy of the target image obtained by performing medical imaging scans using the target scanning protocol.

[0181] Please see Figure 17One embodiment of this application provides a medical imaging system, which includes a scanner, a display, a memory, and a processor. The scanner, display, and memory are all communicatively connected to the processor. The scanner is used to scan an imaging object, and the display is used to display the scanned image. The memory stores a computer program, and the steps implemented by the processor when executing the computer program include:

[0182] Step 170: Control the scanner to pre-scan the imaging object and control the display to show the pre-scanned image.

[0183] The processor sends control signals to the scanner, which can then control the scanner to pre-scan the object being imaged, obtaining a pre-scanned image. After obtaining the pre-scanned image, the processor displays it on the monitor. A description of the pre-scanned image can be found in the detailed description of the above embodiments, and will not be repeated here.

[0184] Step 171: Automatically mark at least one first target tissue region on the pre-scanned image.

[0185] After acquiring the pre-scanned image, the processor analyzes the pre-scanned image, identifies at least one target tissue region in the pre-scanned image, and marks it. A description of automatically marking at least one first target tissue region on the pre-scanned image can be found in the detailed description of the above embodiments, and will not be repeated here.

[0186] Step 172: Obtain historical medical text reports of the imaging object. The historical medical text reports include text reports of physiological tests and / or text reports of imaging tests. The historical medical text reports include natural language descriptions of at least one medical event.

[0187] Step 173: Automatically analyze historical medical text reports to determine the anatomical structures or secondary target tissue regions targeted by the historical medical text reports.

[0188] Step 174: On the pre-scanned image of the first target tissue region that has been marked, mark at least one region of interest of the anatomical structure or the second target tissue region.

[0189] Optionally, if the acquired pre-scan image is a vascular image of the imaging object, at least one marked region of interest may be a plaque region in the blood vessel, i.e., a vascular plaque region.

[0190] Step 175: Based on at least one first target tissue region and at least one region of interest, set scanning parameters to generate a target scanning protocol.

[0191] The description of steps 172-175 can be found in the detailed description of the above embodiments, and will not be repeated here.

[0192] Step 176: Control the scanner to execute the target scanning protocol.

[0193] After determining the target scanning protocol, the processor sends a control signal to the scanner so that the scanner can execute the target scanning protocol to scan the imaging object and obtain the target image.

[0194] The processor in the medical imaging system provided in this embodiment determines at least one first target tissue region of the imaging object through the acquired pre-scanned image; determines at least one region of interest corresponding to the anatomical structure or second target tissue region of the imaging object through the acquired historical medical text report; and determines the field of view imaging in the target scanning protocol based on the first target tissue region and at least one region of interest. This automatically determined field of view imaging can avoid time consumption and inaccuracies and inconsistencies in the determined field of view imaging caused by different scanning personnel's experience, thereby improving the accuracy of the target image obtained by using the scanner to execute the target scanning protocol.

[0195] In one embodiment, such as Figure 18 As shown, an implementation method involves setting scanning parameters to generate a target scanning protocol based on at least one target tissue region and at least one region of interest. The steps of this implementation method include:

[0196] Step 180: Generate a selection list of at least one target organization region and at least one region of interest.

[0197] After obtaining at least one target tissue region and at least one region of interest of the imaging object, the processor generates a selection list based on the at least one target tissue region and at least one region of interest, and displays the selection list on the display interface. The order of the target tissue regions and regions of interest in the selection list can be randomized or arranged according to a preset rule; this embodiment does not impose any restrictions on this.

[0198] Step 181: In response to the user's selection of at least one option in the selection list, set the imaging field of view parameters to generate a target scanning protocol.

[0199] The user selects at least one option from the selection list on the display interface to either deselect or select it; that is, they select at least one of a target tissue region or a region of interest and deselect or select it. In response to the user's selection, the processor sets the imaging field of view parameters to align with the location of the selected first target tissue region or the selected region of interest. A target scanning protocol is then generated based on the set imaging field of view parameters.

[0200] In this embodiment, by generating a selection list of at least one target tissue region and at least one region of interest, and in response to a user's selection of at least one option in the selection list, imaging field of view parameters are set to generate a target scanning protocol. This human-computer interaction-based method of setting imaging field of view parameters and generating a target scanning protocol makes the medical imaging system more intelligent and improves its flexibility.

[0201] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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.

[0202] Based on the same inventive concept, this application also provides a magnetic resonance imaging apparatus for implementing the magnetic resonance imaging method described above, and a medical imaging scanning control apparatus for the medical imaging scanning control method. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the magnetic resonance imaging apparatus and medical imaging scanning control apparatus provided below can be found in the limitations of the magnetic resonance imaging method and medical imaging scanning control method described above, and will not be repeated here.

[0203] In one embodiment, such as Figure 19 As shown, a magnetic resonance imaging device 10 is provided, including: an acquisition module 11, a determination module 12, and a scanning module 13, wherein:

[0204] The acquisition module 11 is used to acquire a three-dimensional blood vessel image of the imaging object; the three-dimensional blood vessel image includes at least one of a bright blood vessel image and a dark blood vessel image.

[0205] The acquisition module 11 is also used to acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object.

[0206] The determination module 12 is used to determine the location of the region of interest in the three-dimensional vascular image based on medical record information and / or other modal medical images, as well as the three-dimensional vascular image and localization model;

[0207] The scanning module 13 is used to scan the imaging object based on the location of the region of interest to determine a two-dimensional vascular image of the imaging object.

[0208] In one embodiment, the determining module 12 is specifically used to input medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the localization model to determine the location of the region of interest; or; to perform fusion processing on the medical record information and / or other modal medical images, as well as the three-dimensional vascular images, to obtain fused data; and to input the fused data into the localization model to determine the location of the region of interest.

[0209] In one embodiment, the determining module 12 is further configured to input medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the fusion sub-model to determine the fusion data; and input the fusion data into the positioning sub-model to determine the location of the region of interest.

[0210] In one embodiment, the magnetic resonance imaging device 10 further includes a determination module, an execution module, and a transmission module. The determination module is used to determine whether a region of interest exists in the three-dimensional vascular image; if a region of interest is determined to exist in the three-dimensional vascular image, the determination module 12 is used to perform the step of determining the location of the region of interest in the three-dimensional vascular image based on medical record information and / or other modal medical images, as well as the three-dimensional vascular image and the localization model; if a region of interest is determined not to exist in the three-dimensional vascular image, a first prompt message is sent.

[0211] In one embodiment, the scanning module 13 is specifically used to display multiple regions of interest (ROIs) on a display interface and send a second prompt message when multiple ROIs exist in a determined three-dimensional vascular image; in response to a user's selection operation of multiple ROIs based on the second prompt message, determine the target ROI location; determine the scanning field of view of the imaging device based on the target ROI location, and scan the imaging object based on the scanning field of view to obtain a two-dimensional vascular image.

[0212] In one embodiment, a medical imaging scanning control device is provided, the device comprising:

[0213] The acquisition module is used to acquire a pre-scanned image of the imaging object;

[0214] The acquisition module is also used to acquire historical medical text reports of the imaging object, including text reports of physiological tests and / or text reports of image tests; the historical medical text reports include natural language descriptions of at least one medical event;

[0215] The determination module is used to determine at least one region of interest in the imaging object based on the pre-scanned image and historical medical text reports;

[0216] The configuration module is used to set scanning parameters based on the region of interest to generate a target scanning protocol;

[0217] The execution module is used to perform medical imaging scans based on the target scanning protocol.

[0218] Each module in the aforementioned magnetic resonance scanning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0219] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 20 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices 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 and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a magnetic resonance imaging method and a medical imaging scan control method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0220] Those skilled in the art will understand that Figure 20 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.

[0221] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0222] Acquire a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image;

[0223] Acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object;

[0224] Based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models, determine the location of the region of interest in the three-dimensional vascular image;

[0225] The imaging object is scanned based on the region of interest to determine a two-dimensional vascular image of the imaging object.

[0226] In one embodiment, when the processor executes the computer program, it further performs the following steps: inputting medical record information and / or other modal medical images, as well as three-dimensional vascular images, into a localization model to determine the location of the region of interest; or: performing fusion processing on the medical record information and / or other modal medical images, as well as the three-dimensional vascular images, to obtain fused data; and inputting the fused data into a localization model to determine the location of the region of interest.

[0227] In one embodiment, the processor, when executing the computer program, further performs the following steps: inputting medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the fusion sub-model to determine the fusion data; inputting the fusion data into the localization sub-model to determine the location of the region of interest.

[0228] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining whether a region of interest exists in the three-dimensional vascular image; if a region of interest is determined to exist in the three-dimensional vascular image, returning to the step of determining the location of the region of interest in the three-dimensional vascular image based on medical record information and / or other modal medical images, as well as the three-dimensional vascular image and the localization model; if a region of interest is determined not to exist in the three-dimensional vascular image, sending a first prompt message.

[0229] In one embodiment, when the processor executes the computer program, it further performs the following steps: if multiple regions of interest exist in the determined three-dimensional vascular image, display the multiple regions of interest locations on the display interface and send a second prompt message; in response to the user's selection operation of the multiple regions of interest locations based on the second prompt message, determine the target region of interest location; determine the scanning field of view of the imaging device based on the target region of interest location, and scan the imaging object based on the scanning field of view to obtain a two-dimensional vascular image.

[0230] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0231] Acquire a pre-scanned image of the object being imaged;

[0232] Acquire historical medical text reports of the imaging object, including text reports of physiological examinations and / or text reports of imaging examinations; the historical medical text reports include natural language descriptions of at least one medical event;

[0233] Based on pre-scanned images and historical medical text reports, identify at least one region of interest in the imaging object;

[0234] Based on the region of interest, set the scanning parameters to generate the target scanning protocol;

[0235] Medical imaging scans are performed based on the target scanning protocol.

[0236] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0237] Acquire a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image;

[0238] Acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object;

[0239] Based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models, determine the location of the region of interest in the three-dimensional vascular image;

[0240] The imaging object is scanned based on the location of the region of interest to determine a two-dimensional vascular image of the imaging object. In one embodiment, when the computer program is executed by a processor, it further performs the following steps: acquiring medical record information of the imaging object and / or other modalities of medical images of the imaging object; determining the location of the region of interest based on the medical record information and / or other modalities of medical images, as well as the three-dimensional vascular image and the localization model.

[0241] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: inputting medical record information and / or other modal medical images, as well as three-dimensional vascular images, into a localization model to determine the location of the region of interest; or: performing fusion processing on the medical record information and / or other modal medical images, as well as the three-dimensional vascular images, to obtain fused data; inputting the fused data into the localization model to determine the location of the region of interest.

[0242] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: inputting medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the fusion sub-model to determine the fusion data; inputting the fusion data into the localization sub-model to determine the location of the region of interest.

[0243] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining whether a region of interest exists in the three-dimensional vascular image; if a region of interest is determined to exist in the three-dimensional vascular image, returning to the step of determining the location of the region of interest in the three-dimensional vascular image based on medical record information and / or other modal medical images, as well as the three-dimensional vascular image and the localization model; if a region of interest is determined not to exist in the three-dimensional vascular image, sending a first prompt message.

[0244] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if multiple regions of interest exist in the determined three-dimensional vascular image, display the multiple regions of interest locations on the display interface and send a second prompt message; in response to the user's selection operation of the multiple regions of interest locations based on the second prompt message, determine the target region of interest location; determine the scanning field of view of the imaging device based on the target region of interest location, and scan the imaging object based on the scanning field of view to obtain a two-dimensional vascular image.

[0245] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0246] Acquire a pre-scanned image of the object being imaged;

[0247] Acquire historical medical text reports of the imaging object, including text reports of physiological examinations and / or text reports of imaging examinations; the historical medical text reports include natural language descriptions of at least one medical event;

[0248] Based on pre-scanned images and historical medical text reports, identify at least one region of interest in the imaging object;

[0249] Based on the region of interest, set the scanning parameters to generate the target scanning protocol;

[0250] Medical imaging scans are performed based on the target scanning protocol.

[0251] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0252] Acquire a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image;

[0253] Acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object;

[0254] Based on medical record information and / or other modalities of medical images, as well as three-dimensional vascular images and localization models, determine the location of the region of interest in the three-dimensional vascular image;

[0255] The imaging object is scanned based on the region of interest to determine a two-dimensional vascular image of the imaging object.

[0256] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring medical record information of the imaging object and / or medical images of other modalities of the imaging object; determining the location of the region of interest based on the medical record information and / or other medical images, as well as the three-dimensional vascular image and the localization model.

[0257] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: inputting medical record information and / or other modal medical images, as well as three-dimensional vascular images, into a localization model to determine the location of the region of interest; or: performing fusion processing on the medical record information and / or other modal medical images, as well as the three-dimensional vascular images, to obtain fused data; inputting the fused data into the localization model to determine the location of the region of interest.

[0258] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: inputting medical record information and / or other modal medical images, as well as three-dimensional vascular images, into the fusion sub-model to determine the fusion data; inputting the fusion data into the localization sub-model to determine the location of the region of interest.

[0259] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining whether a region of interest exists in the three-dimensional vascular image; if a region of interest is determined to exist in the three-dimensional vascular image, returning to the step of determining the location of the region of interest in the three-dimensional vascular image based on medical record information and / or other modal medical images, as well as the three-dimensional vascular image and the localization model; if a region of interest is determined not to exist in the three-dimensional vascular image, sending a first prompt message.

[0260] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if multiple regions of interest exist in the determined three-dimensional vascular image, display the multiple regions of interest locations on the display interface and send a second prompt message; in response to the user's selection operation of the multiple regions of interest locations based on the second prompt message, determine the target region of interest location; determine the scanning field of view of the imaging device based on the target region of interest location, and scan the imaging object based on the scanning field of view to obtain a two-dimensional vascular image.

[0261] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0262] Acquire a pre-scanned image of the object being imaged;

[0263] Acquire historical medical text reports of the imaging object, including text reports of physiological examinations and / or text reports of imaging examinations; the historical medical text reports include natural language descriptions of at least one medical event;

[0264] Based on pre-scanned images and historical medical text reports, identify at least one region of interest in the imaging object;

[0265] Based on the region of interest, set the scanning parameters to generate the target scanning protocol;

[0266] Medical imaging scans are performed based on the target scanning protocol.

[0267] 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, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0268] 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.

[0269] 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.

[0270] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A magnetic resonance imaging method, characterized by, The method includes: Acquire a three-dimensional vascular image of the imaging object; the three-dimensional vascular image includes at least one of a bright blood vessel image and a dark blood vessel image; Acquire medical record information of the imaging object and / or medical images of other modalities of the imaging object; Based on the medical record information and / or the other modal medical images, as well as the three-dimensional vascular image and the localization model, determine the location of the region of interest in the three-dimensional vascular image; The imaging object is scanned based on the location of the region of interest to determine a two-dimensional vascular image of the imaging object.

2. The method according to claim 1, characterized in that, The other modalities of medical images are anatomical images. Determining the location of the region of interest based on the medical record information and / or the other modalities of medical images, the three-dimensional vascular image, and the localization model includes: The medical record information and / or the other modal medical images, as well as the three-dimensional vascular image, are input into the localization model to determine the location of the region of interest; or; The medical record information and / or the other modal medical images, as well as the three-dimensional vascular image, are fused to obtain fused data; The fused data is input into the localization model to determine the location of the region of interest.

3. The method according to claim 2, characterized in that, The localization model includes a fusion sub-model and a localization sub-model. The step of inputting the medical record information and / or the medical images of other modalities, as well as the three-dimensional vascular image, into the localization model to determine the location of the region of interest includes: The medical record information and / or the medical images of other modalities, as well as the three-dimensional vascular image, are input into the fusion sub-model to determine the fusion data; The fused data is input into the localization sub-model to determine the location of the region of interest.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Determine whether a region of interest exists in the three-dimensional blood vessel image; If the region of interest is determined to exist in the three-dimensional vascular image, the process returns to the step of determining the location of the region of interest in the three-dimensional vascular image based on the medical record information and / or the other modal medical images, as well as the three-dimensional vascular image and the localization model. If it is determined that the region of interest does not exist in the three-dimensional vascular image, a first prompt message is sent.

5. The method according to any one of claims 1-3, characterized in that, The step of scanning the imaging object based on the region of interest location to determine a two-dimensional vascular image of the imaging object includes: If it is determined that there are multiple regions of interest in the three-dimensional vascular image, the multiple regions of interest are displayed on the display interface, and a second prompt message is sent. In response to the user's selection of multiple regions of interest locations based on the second prompt information, the location of the target region of interest is determined; The scanning field of view of the imaging device is determined based on the location of the target region of interest, and the imaging object is scanned based on the scanning field of view to obtain the two-dimensional blood vessel image.

6. A medical imaging scanning control method, characterized in that, The method includes: Acquire a pre-scanned image of the object being imaged; Obtain historical medical text reports of the imaging object, the historical medical text reports including text reports of physiological tests and / or text reports of image tests; the historical medical text reports include natural language descriptions of at least one medical event; Based on the pre-scanned image and the historical medical text report, at least one region of interest is determined in the imaging object; Based on the region of interest, scan parameters are set to generate a target scan protocol; Medical imaging scans are performed based on the target scanning protocol.

7. The method according to claim 6, characterized in that, The pre-scanned image is a 3D image, and the target scanning protocol corresponds to a 2D image.

8. A medical imaging system, comprising a scanner, a display, a memory, and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it performs the following steps: The scanner is controlled to pre-scan the imaging object, and the display is controlled to show the pre-scanned image corresponding to the pre-scan. At least one first target tissue region is automatically marked on the pre-scanned image; Obtain historical medical text reports of the imaging object, the historical medical text reports including text reports of physiological tests and / or text reports of image tests; the historical medical text reports include natural language descriptions of at least one medical event; The historical medical text report is automatically analyzed to determine the anatomical structure or second target tissue region to which the historical medical text report is targeted; On a pre-scanned image of the first target tissue region that has been marked, at least one region of interest of the anatomical structure or the second target tissue region is marked; Based on at least one first target tissue region and at least one region of interest, scanning parameters are set to generate a target scanning protocol; Control the scanner to execute the target scanning protocol.

9. The medical imaging system according to claim 8, characterized in that, The region of interest includes plaque areas of blood vessels.

10. The medical imaging system according to claim 8, characterized in that, The step of setting scanning parameters to generate a target scanning protocol based on the at least one first target tissue region and the at least one region of interest includes: Generate a selection list of at least one first target organization region and at least one region of interest; In response to a user's selection of at least one option in the selection list, imaging field of view parameters are set to generate the target scanning protocol.

Images