A PAE-guided method for magnetic resonance post-processing reconstruction of MIP images and interventional reconstruction

Abstract

The present invention provides a PAE-guided method for magnetic resonance post-processing reconstruction of MIP images and interventional reconstruction. An MIP image of the prostatic artery vessels is constructed by the MIP algorithm; at the same time, an interventional arterial image of the prostatic artery vessels is constructed; and then whether the characteristics of the prostatic artery vessels in the axial, coronal, and sagittal positions can be automatically matched successfully. The MIP image and the interventional arterial image can be automatically recognized and matched with each other. During clinical interventional surgery, the anatomy of each layer can be carried out on the thin layers of the axial, coronal, and sagittal multi-parameter scans of the magnetic resonance scan, which can provide detailed anatomical knowledge for the surgery. Therefore, it can avoid problems such as ambiguity and confusion caused by vascular variations, overlaps, and crossings, accurately guide the specific prostatic artery target vessels for doctors, greatly reduce the time consumed by doctors, and avoid affecting the preoperative preparation and the surgical efficiency of patients.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a method for guiding the MIP map of magnetic resonance post-processing reconstruction and the PAE of interventional reconstruction, a guiding device for prostate artery embolization, and an electronic device. Background Art

[0002] Prostate embolization surgery, also known as prostate artery embolization (PAE), is an emerging urological surgery mainly used to treat benign prostatic hyperplasia (BPH). This surgical method has the advantages of less trauma, good treatment effect, simple operation, and rapid postoperative recovery. The following is a detailed introduction to prostate embolization surgery:

[0003] 1. Surgical Principle

[0004] Prostate artery embolization is a procedure in which embolic agents are injected into the arteries that supply the prostate through interventional techniques, thereby embolizing these arteries and causing the prostate to gradually shrink due to lack of blood supply. This process can avoid the phenomena of prostate hyperplasia and compression of the urethral orifice, thereby improving the lower urinary tract symptoms of patients.

[0005] 2. Indications

[0006] Prostate artery embolization is mainly applicable to the following situations:

[0007] Patients with severe lower urinary tract symptoms caused by benign prostatic hyperplasia, and the drug treatment has poor effect or the patients cannot tolerate long-term drug treatment.

[0008] Patients with poor physical conditions who cannot tolerate the anesthesia or surgical risks of prostate surgery.

[0009] Patients who are unwilling to undergo cystostomy or long-term indwelling urinary catheter.

[0010] 3. Surgical Procedure

[0011] Prostate artery embolization is usually performed under local anesthesia or general anesthesia and guided by digital subtraction angiography (DSA). During the operation, the doctor will insert a catheter into the prostate blood supply artery through vascular puncture and then inject embolic agents to block the blood flow. The whole surgical process is relatively simple, with less trauma and less bleeding.

[0012] 4. Efficacy and Risks

[0013] The efficacy of prostate artery embolization is significant, and it can reduce the prostate volume to a certain extent and improve the lower urinary tract symptoms of patients. However, this surgery also has certain risks, such as possible symptoms of infection, fever, hematuria, etc. during the embolization process. In addition, due to the rich blood supply of the prostate, it may not be possible to achieve complete embolization, and the prostate may hyperplasia again after the operation.

[0014] However, when performing prostate embolization surgery in the hospital currently, it is necessary to observe the anatomical position of the prostate artery and whether there are variations, etc. For this reason, all patients need to undergo magnetic resonance prostate artery MIP scanning.

[0015] As shown in the Figure 1 attachment, it is a magnetic resonance image of prostate artery MIP scanning. Although the prostate artery image collected under magnetic resonance scanning can show the direction of the prostate artery to the doctor, the obtained prostate artery MRI image still has problems such as blurring and confusion caused by vascular variations, overlaps, and intersections, and cannot accurately guide the doctor to the specific target blood vessels of the prostate artery. It requires the doctor to spend a lot of time, affecting the preoperative preparation and the surgical efficiency of the patient, with low efficiency.

[0016] In addition, if the prostate artery is observed based on interventional radiology images, the above problems will also exist. Summary of the Invention

[0017] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0018] On the one hand, a method for guiding PAE by magnetic resonance post-processing reconstruction MIP map and interventional reconstruction is provided. This method is implemented by an electronic device and includes:

[0019] S1. Obtain the original blood vessel image of the prostate artery through magnetic resonance scanning and perform anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostate artery blood vessel;

[0020] S2. Based on the MIP algorithm, perform image MIP reconstruction on the pelvic MRI post-processing image. After reconstruction, obtain the MIP image of the prostate artery blood vessel, including:

[0021] Analyze the MRI post-processing image of the prostate artery blood vessel to obtain MRI scan data in different scanning directions;

[0022] Traverse the MRI scan data, read the MRI scan data of the prostate artery blood vessel in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostate artery blood vessel;

[0023] Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate the MIP projection data set of the prostate artery blood vessel;

[0024] In the same scanning direction, fuse each MIP projection image in the MIP projection data set to reconstruct and obtain the MIP image of the prostate artery blood vessel;

[0025] S3. Obtain an interventional radiography scan image of the prostatic artery through magnetic resonance scanning, and construct an interventional arterial image of the prostatic artery based on three-dimensional reconstruction and vascular segmentation techniques;

[0026] S4. Identify and determine whether the prostatic artery vascular features of the MIP image and the interventional arterial image can be successfully automatically matched in the axial, coronal, and sagittal positions respectively:

[0027] If so, proceed to S5;

[0028] If not, proceed to S6;

[0029] S5. Output the MIP image and display it on the front-end page of the operating room for guiding prostatic artery embolization;

[0030] S6. Use a preset prostatic artery recognition AI model to identify the prostatic artery image features in the interventional arterial image, locate and fuse them on the MIP image, and output and display the MIP image after location and fusion on the front-end page of the operating room for guiding prostatic artery embolization.

[0031] As a preferred implementation scheme of the present invention, preferably, S6. Use a preset prostatic artery recognition AI model to identify the prostatic artery image features in the interventional arterial image, locate and fuse them on the MIP image, and output and display the MIP image after location and fusion on the front-end page of the operating room for guiding prostatic artery embolization, including:

[0032] S600. Perform image enhancement processing on the interventional arterial image to obtain an interventional enhanced image of the arterial vessel, and import the interventional enhanced image of the arterial vessel into the preset prostatic artery recognition AI model. The prostatic artery recognition AI model identifies and marks the prostatic artery image features in the axial, coronal, and sagittal positions of the interventional enhanced image of the arterial vessel;

[0033] S601. Based on the image registration and fusion method, locate and fuse the prostatic artery image features on the MIP image, form contrast features in the axial, coronal, and sagittal positions between the prostatic artery image features and the original prostatic artery vessels on the MIP image, and generate a contrast feature of the vascular tomographic scan of the prostatic artery vessels after location and fusion on the MIP image;

[0034] S602. Output and display the interventional arterial image of the prostatic artery vessels after location and fusion on the front-end page of the operating room for guiding prostatic artery embolization.

[0035] As a preferred embodiment of the present invention, preferably, S3: Obtain the interventional radiology scan images of the prostatic arteries through magnetic resonance scanning, and construct the interventional arterial images of the prostatic arteries based on three-dimensional reconstruction and vascular segmentation techniques, including:

[0036] Perform MRI scanning on the prostatic arteries to obtain MRI scan data corresponding to the prostatic arteries;

[0037] Label the vascular contour data of the MRI scan data of the prostatic arteries, and convert and generate the two-dimensional original scan images of the prostatic arteries obtained under MRI scanning;

[0038] Combine the volume rendering three-dimensional reconstruction algorithm to perform three-dimensional conversion on the two-dimensional original scan images under each scan sequence, reconstruct the prostatic arteries, and generate the corresponding three-dimensional model of the prostatic arteries;

[0039] Use the preset prostatic artery segmentation model to perform image segmentation processing on the three-dimensional model of the prostatic arteries in the axial, coronal, and sagittal positions respectively, obtain the prostatic artery images of the three-dimensional model of the prostatic arteries in the axial, coronal, and sagittal positions, and obtain the magnetic resonance artery MIP images of the prostatic arteries.

[0040] As a preferred embodiment of the present invention, preferably, the method for generating the prostatic artery segmentation model includes:

[0041] Collect the sets of MRI images of the prostatic arteries in the axial, coronal, and sagittal positions respectively;

[0042] Perform preprocessing on the sets of MRI images of the prostatic arteries in the axial, coronal, and sagittal positions respectively;

[0043] Perform annotation processing on the MRI images of the prostatic arteries in the axial, coronal, and sagittal positions in the set of MRI images of the prostatic arteries, and determine the boundary positions of the prostatic arteries in the axial, coronal, and sagittal positions respectively;

[0044] After the annotation is completed, obtain the training set and import it into the preset convolutional neural network model for training and learning of the annotation data to train the prostatic artery segmentation model;

[0045] Use the validation sets of the prostatic artery images in the axial, coronal, and sagittal positions respectively to perform segmentation verification on the prostatic artery segmentation model;

[0046] If the verification is passed, deploy the prostatic artery segmentation model on the background server.

[0047] As a preferred embodiment of the present invention, preferably, S4: identify and determine whether the prostate artery vessel features of the MIP image and the interventional arterial image can be successfully automatically matched in the axial, coronal, and sagittal positions, including:

[0048] Extract the first prostate artery vessel features of the MIP image in the axial, coronal, and sagittal positions respectively;

[0049] Extract the second prostate artery vessel features of the prostate artery vessel images of the prostate artery vessel three-dimensional model in the axial, coronal, and sagittal positions respectively;

[0050] Automatic matching judgment:

[0051] (1) Compare the first prostate artery vessel features in the axial position with the second prostate artery vessel features;

[0052] (2) Compare the first prostate artery vessel features in the coronal position with the second prostate artery vessel features;

[0053] (3) Compare the first prostate artery vessel features in the sagittal position with the second prostate artery vessel features;

[0054] If the feature comparisons in (1)-(3) are all successful, it is considered that the prostate artery vessel features of the MIP image and the interventional arterial image can be successfully automatically matched in the axial, coronal, and sagittal positions;

[0055] Otherwise, it fails.

[0056] On the other hand, a prostate artery embolization guiding device is provided. The prostate artery embolization guiding device is used to implement the method for guiding the MIP map reconstructed by magnetic resonance post-processing and the PAE by interventional reconstruction. The device includes:

[0057] (1) An MRI image processing system, which is used to obtain the original vessel image of the prostate artery through magnetic resonance scanning and perform anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostate artery;

[0058] (2) An MIP image processing system, which is used to perform MIP reconstruction on the pelvic MRI post-processing image based on the MIP algorithm. After reconstruction, an MIP image of the prostate artery is obtained, including:

[0059] Analyze the MRI post-processing image of the prostate artery to obtain MRI scan data in different scanning directions;

[0060] Traverse the MRI scan data, read the MRI scan data of the prostatic artery vessels in different scan directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostatic artery vessels;

[0061] Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scan directions to generate the MIP projection data set of the prostatic artery vessels;

[0062] In the same scan direction, fuse each MIP projection image in the MIP projection data set to reconstruct the MIP image of the prostatic artery vessels;

[0063] (3) An interventional arterial image processing system for obtaining an interventional radiology scan image of the prostatic artery vessels through magnetic resonance scanning and constructing an interventional arterial image of the prostatic artery vessels based on three-dimensional reconstruction and vascular segmentation techniques;

[0064] (4) An arterial feature recognition system for identifying and determining whether the prostatic artery vessel features of the MIP image and the interventional arterial image in the axial, coronal, and sagittal positions can be automatically matched successfully:

[0065] If so, output the MIP image and display it on the front-end page of the operating room for guiding prostatic artery embolization;

[0066] If not, enter the use of a preset prostatic artery recognition AI model to identify the prostatic artery image features in the interventional arterial image and locate and fuse them on the MIP image, and output and display the located and fused MIP image on the front-end page of the operating room for guiding prostatic artery embolization;

[0067] (5) The front end of the operating room for displaying the MIP image;

[0068] The MRI image processing system is communicatively connected to the MIP image processing system;

[0069] The MIP image processing system and the interventional arterial image processing system are respectively communicatively connected to the arterial feature recognition system;

[0070] The arterial feature recognition system is communicatively connected to the front end of the operating room.

[0071] On the other hand, an electronic device is provided, and the electronic device includes: a processor; a memory, and a computer-readable instruction is stored on the memory. When the computer-readable instruction is executed by the processor, any one of the methods in the above-mentioned magnetic resonance post-processing reconstruction MIP map and interventional reconstruction PAE guidance method is implemented.

[0072] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for magnetic resonance post-processing reconstruction of MIP images and PAE-guided method for interventional reconstruction.

[0073] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0074] Based on the implementation of the present invention, the present invention reconstructs the MRI images of the prostatic artery vessels based on the MIP algorithm to construct MIP images of the prostatic artery vessels; at the same time, the interventional radiography scan images of the prostatic artery vessels are obtained through magnetic resonance scanning, and based on three-dimensional reconstruction and vascular segmentation techniques, the interventional arterial images of the prostatic artery vessels are constructed; then, whether the characteristics of the prostatic artery vessels in the axial, coronal, and sagittal positions can be automatically matched successfully: if the automatic matching is successful, the MIP image is output and displayed on the front-end page of the operating room for guiding the prostatic artery embolization; if it is not successful, the preset prostatic artery recognition AI model is used to identify the characteristics of the prostatic artery images in the interventional arterial images and locate and fuse them on the MIP image, and the MIP image after the positioning and fusion is output and displayed on the front-end page of the operating room for guiding the prostatic artery embolization.

[0075] Therefore, the present invention performs automatic comparison after reconstructing all the original data of magnetic resonance scans and the original data during interventional radiology procedures to meet the automatic comparison between the two. If the two are successfully compared, the arterial vessels can be directly embolized during the operation to meet the diagnosis of clinical operations. By performing maximum intensity projection on the original data after scanning using post-processing software, the origin and course of the arteries between the prostate can be clearly seen on the post-processed images, and whether there are any variations. With the above solution, if the MIP image and the interventional arterial image can be automatically recognized and matched with each other, during clinical interventional operations, the axial, coronal, and sagittal thin slices of the multi-parameter scans of magnetic resonance can be used for anatomical analysis at each level, providing detailed anatomical knowledge for the operation. Therefore, it can avoid problems such as ambiguity and confusion caused by vascular variations, overlaps, and crossings, accurately guide the specific prostatic artery target vessels for doctors, greatly reduce the time consumed by doctors, and avoid affecting the preoperative preparation and the surgical efficiency of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0077] Figure 1 is the nuclear magnetic resonance image of the traditional prostate artery MIP scan;

[0078] Figure 2 is the flow chart of the magnetic resonance post - processing reconstruction MIP map and the interventional reconstruction PAE guidance method provided by the embodiment of the present invention;

[0079] Figure 3 is the block diagram of the prostate artery embolization guidance device provided by the embodiment of the present invention;

[0080] Figure 4 is the schematic structural diagram of an electronic device provided by the embodiment of the present invention. Detailed Embodiments

[0081] The following will describe the technical solutions in the present invention with reference to the accompanying drawings.

[0082] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0083] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when not emphasizing their differences, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when not emphasizing their differences, the meanings they express are the same.

[0084] In the embodiments of the present invention, sometimes subscripts such as W1 may be miswritten as non - subscript forms such as W1. When not emphasizing their differences, the meanings they express are the same.

[0085] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0086] An embodiment of the present invention provides a PAE-guided method for magnetic resonance post-processing reconstruction of MIP images and interventional reconstruction. This method can be implemented by an electronic device, which can be a terminal or a server. As Figure 2 shown in the flowchart of the PAE-guided method for magnetic resonance post-processing reconstruction of MIP images and interventional reconstruction, the processing flow of this method can include the following steps:

[0087] On the one hand, a PAE-guided method for magnetic resonance post-processing reconstruction of MIP images and interventional reconstruction is provided. This method is implemented by an electronic device and includes:

[0088] S1. Obtain the original vascular image of the prostatic artery through magnetic resonance scanning and perform anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostatic artery;

[0089] S2. Based on the MIP algorithm, perform MIP reconstruction on the pelvic MRI post-processing image. After reconstruction, obtain the MIP image of the prostatic artery, including:

[0090] Analyze the MRI post-processing image of the prostatic artery to obtain MRI scan data in different scanning directions;

[0091] Traverse the MRI scan data, read the MRI scan data of the prostatic artery in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostatic artery;

[0092] Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate the MIP projection data set of the prostatic artery;

[0093] Fuse the individual MIP projection images in the MIP projection data set in the same scanning direction to reconstruct and obtain the MIP image of the prostatic artery;

[0094] S3. Obtain the interventional radiology scan image of the prostatic artery through magnetic resonance scanning, and based on three-dimensional reconstruction and vascular segmentation technology, construct the interventional arterial image of the prostatic artery;

[0095] S4. Identify and determine whether the prostatic artery vascular features of the MIP image and the interventional arterial image can be successfully automatically matched in the axial, coronal, and sagittal positions:

[0096] If so, go to S5;

[0097] If not, go to S6;

[0098] S5. Output and display the MIP image on the front-end page of the operating room for guiding prostate artery embolization;

[0099] S6. Use a preset prostate artery recognition AI model to identify the prostate artery image features in the interventional artery image and locate and fuse them on the MIP image, and output and display the MIP image after location and fusion on the front-end page of the operating room for guiding prostate artery embolization.

[0100] When performing prostate embolization surgery in a traditional hospital, it is necessary to observe the anatomical position of the prostate artery and whether there are variations, etc. For this reason, all patients need to undergo magnetic resonance imaging of the prostate artery. However, relying solely on magnetic resonance, it is impossible to clearly distinguish information such as the context, direction, and origin of the prostate artery vessels.

[0101] The advantages of interventional scan MIP (maximum intensity projection) technology in arterial vessel imaging include:

[0102] 1). Display of vascular structure: MIP can clearly display the three-dimensional structure of blood vessels, helping doctors better understand the direction and distribution of blood vessels.

[0103] 2). Enhancement of contrast: By enhancing the contrast agent signal in blood vessels, MIP technology can increase the contrast between blood vessels and surrounding tissues, making the blood vessel image more prominent.

[0104] 3). Reduction of image noise: MIP technology reduces the noise in the image by selectively projecting the strongest signals in the image, thereby improving the image quality.

[0105] 4). Fast imaging: MIP technology can complete the imaging of a large range of blood vessels in a short time, improving the examination efficiency.

[0106] 5). Diagnostic assistance: For the diagnosis of vascular diseases such as atherosclerosis, vascular stenosis, and hemangioma, MIP technology can provide important auxiliary information.

[0107] 6). Treatment planning: Before interventional treatment, MIP imaging can help doctors plan the surgical path, evaluate the condition of the diseased blood vessels, and provide precise anatomical information for the surgery.

[0108] 7). Non-invasiveness: Compared with traditional angiography, MIP technology is a non-invasive imaging method, reducing the discomfort and potential risks of patients.

[0109] Therefore, the present invention automatically compares the original data of all magnetic resonance scans with the original data after reconstruction during interventional radiology procedures. This is done to satisfy the automatic comparison between the two. If the comparison is successful, during surgery, the arterial blood vessels can be directly embolized to meet the diagnostic requirements of clinical surgery.

[0110] First, it is necessary to: S1. Obtain the original vascular image of the prostatic artery through magnetic resonance scanning and perform anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostatic artery.

[0111] The acquisition and preprocessing of the original MRI image can be handled by the administrator himself / herself to obtain the corresponding original MRI image as shown in the appendix. Figure 1 as shown in the original MRI image.

[0112] Next, MIP image reconstruction of the prostatic artery will be performed:

[0113] S2. Based on the MIP algorithm, perform MIP image reconstruction on the pelvic MRI post-processing image. After reconstruction, obtain the MIP image of the prostatic artery, including:

[0114] Analyze the pelvic MRI post-processing image of the prostatic artery to obtain MRI scan data in different scanning directions;

[0115] Traverse the MRI scan data, read the MRI scan data of the prostatic artery in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostatic artery;

[0116] Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate the MIP projection data set of the prostatic artery;

[0117] In the same scanning direction, fuse each MIP projection image in the MIP projection data set to reconstruct the MIP image of the prostatic artery.

[0118] The MIP algorithm, that is, Maximum Intensity Projection, is a three-dimensional reconstruction technology commonly used in medical image processing. Its steps are as follows:

[0119] 1. Data acquisition: First, obtain two-dimensional tomographic image data of blood vessels through imaging devices such as MRI or CT.

[0120] 2. Image preprocessing: Perform preprocessing operations such as denoising and enhancing contrast on the acquired images to improve the accuracy of subsequent processing.

[0121] 3. Vessel segmentation: Using image segmentation techniques such as threshold segmentation and edge detection, extract the vessel region from the preprocessed image.

[0122] 4. Voxel intensity calculation: Calculate the intensity value of each voxel (3D pixel), usually taking the maximum intensity value of the region where the voxel is located.

[0123] 5. Projection calculation: Starting from the perspective specified by the user, project the 3D data, only retaining the voxel value with the maximum intensity along the line of sight direction, and ignoring other voxel values.

[0124] 6. Image reconstruction: Combine the 2D images obtained by projection to form the final 3D vessel image.

[0125] The advantages of the MIP algorithm in vessel image reconstruction include:

[0126] 1. Simple and efficient: The MIP algorithm is relatively simple and has high computational efficiency, making it suitable for quickly reconstructing vessel images.

[0127] 2. Display of vessel structure: It can clearly display the 3D structure of the vessels, facilitating doctors to observe the direction and morphology of the vessels.

[0128] 3. Contrast enhancement: Since only the maximum intensity value is displayed, the MIP algorithm can enhance the contrast between the vessels and the surrounding tissues, making the vessels more prominent.

[0129] 4. Diagnostic assistance: It helps doctors diagnose vascular diseases such as vascular stenosis and aneurysms.

[0130] 5. Non-invasiveness: As a non-invasive imaging technique, the MIP algorithm does not cause additional harm to patients.

[0131] Therefore, the present invention uses the MIP algorithm to construct the MIP image (3D vessel image) of the prostatic arteries, thereby obtaining a high-definition choroid map of the prostatic artery vasculature and using it for the next image-guided contrast study.

[0132] First, it is necessary to read the MRI scan data of the prostatic artery vessels in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostatic artery vessels. Then, based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate the MIP projection data set of the prostatic artery vessels. Finally, in accordance with the same scanning direction, fuse each MIP projection image in the MIP projection data set to reconstruct the MIP image of the prostatic artery vessels. Specifically: it is necessary to preprocess the MRI vascular scan data, including steps such as denoising, correction, and normalization, to ensure data quality. Next, apply the Maximum Intensity Projection (MIP) algorithm to process the preprocessed data. The specific steps are as follows:

[0133] 1. Select an appropriate threshold to distinguish blood vessels from other tissues.

[0134] 2. Traverse the three-dimensional data set and calculate the maximum intensity value of each voxel along the preset projection direction (such as coronal, sagittal, or axial).

[0135] 3. Generate a two-dimensional MIP image based on the calculation results, which shows the maximum intensity values of all voxels along the projection direction.

[0136] 4. Post-process the generated MIP image, including contrast adjustment, edge enhancement, etc., to improve image quality.

[0137] 5. Finally, analyze and interpret the MIP image to reconstruct the three-dimensional structure of the blood vessels.

[0138] In order to clearly project the blood vessel images in each scanning direction, the present invention adopts MIP projection imaging in the axial, coronal, and sagittal scanning directions, and finally fuses the two-dimensional images and generates a three-dimensional arterial blood vessel image:

[0139] A single-direction MIP image may not be sufficient to comprehensively display the vascular structure. Therefore, MIP projections can be performed along multiple directions (such as the X, Y, Z axes and their combinations) to generate a series of MIP images. These images can provide detailed information about the blood vessels from different angles, helping doctors or researchers to more comprehensively understand the structure and orientation of the blood vessels. By fusing the MIP images in multiple directions, a more comprehensive three-dimensional view can be created. This usually involves using professional medical image processing software or visualization tools. The fused image can be interactively viewed through operations such as rotation, scaling, and translation, enabling the observer to view the vascular structure from different angles and distances. In addition to visual evaluation, quantitative analysis can also be performed on the MIP images. For example, parameters such as the diameter, length, and volume of the blood vessels can be measured. These can be completed by the administrator to facilitate subsequent prostate vascular diagnosis and evaluation and the formulation of corresponding treatment plans. These parameters are of great significance for evaluating the health status and lesion degree of the blood vessels and formulating treatment plans.

[0140] After the reconstruction and analysis of the MIP images are completed, a detailed report needs to be prepared. The report should include the patient's basic information, scanning parameters, image processing process, MIP image results, and analysis conclusions, etc. The report should clearly and accurately convey information so that doctors or researchers can quickly understand the patient's vascular condition and make corresponding decisions. The processed MIP images and their related data are stored in a secure and reliable system for future review or sharing with other medical institutions.

[0141] As a preferred implementation of the present invention, preferably, in S3, an interventional radiology scan image of the prostatic artery is obtained through magnetic resonance scanning, and based on three-dimensional reconstruction and vascular segmentation techniques, an interventional artery image of the prostatic artery is constructed, including:

[0142] Perform an MRI scan on the prostatic artery to obtain MRI scan data corresponding to the prostatic artery;

[0143] Label the vascular contour data of the MRI scan data of the prostatic artery and convert it to generate a two-dimensional original scan image of the prostatic artery obtained under MRI scan;

[0144] Combined with the volume rendering three-dimensional reconstruction algorithm, perform three-dimensional conversion on the two-dimensional original scan images in each scan sequence to reconstruct the prostatic artery and generate a corresponding three-dimensional model of the prostatic artery;

[0145] Using a preset prostate artery segmentation model, perform image segmentation processing on the three-dimensional model of the prostate artery blood vessels in the axial, coronal, and sagittal planes respectively, obtain the prostate artery blood vessel images of the three-dimensional model of the prostate artery blood vessels in the axial, coronal, and sagittal planes, and obtain the magnetic resonance artery MIP image of the prostate artery blood vessels.

[0146] Here, interventional scanning technology is adopted to perform angiographic interventional scanning on the prostate artery blood vessels, and intelligent image processing is performed on the interventional scanning images to identify and extract the two-dimensional scanning images of the prostate artery blood vessels.

[0147] Next, using three-dimensional reconstruction technology, perform three-dimensional synthesis on the two-dimensional images in different scanning directions to construct a three-dimensional model of the prostate artery blood vessels. Then, use the prostate artery segmentation model to perform image segmentation processing on the three-dimensional model of the prostate artery blood vessels in the axial, coronal, and sagittal planes respectively, so as to obtain the interventional artery images of the prostate artery blood vessels. Therefore, here, the interventional artery images of the prostate artery blood vessels are obtained from three scanning directions on the three-dimensional image, which are used for image contrast calibration to avoid the defects of unclear part contrast and inaccurate position caused by single image contrast.

[0148] After obtaining the interventional radiology scanning images, image preprocessing is first required, including steps such as denoising and enhancing contrast to improve the image quality. Next, apply three-dimensional reconstruction technology to convert the two-dimensional scanning images into a three-dimensional model. Then, use vascular segmentation technology to accurately extract the structure of the artery blood vessels from the three-dimensional model. This usually involves threshold segmentation, edge detection, or model-based segmentation methods. Finally, through these steps, a clear three-dimensional model of the artery blood vessels can be constructed for further diagnosis or surgical planning.

[0149] In the three-dimensional reconstruction stage, various algorithms can be adopted, such as volume rendering or surface rendering. The volume rendering method can display the details in the entire volume data, while the surface rendering focuses more on extracting and displaying the outer surface of the data. For the three-dimensional reconstruction of artery blood vessels, the surface rendering method may be more applicable because it can more clearly outline the contour of the blood vessels.

[0150] In the vascular segmentation stage, since arterial blood vessels may appear as complex network structures in images, and their shapes, sizes, and positions may vary significantly among different individuals, it is crucial to select an appropriate segmentation method. A commonly used method is the region-based segmentation method, such as the Region Growing or LevelSet method. These methods can start from one or more seed points and iteratively expand the segmentation region according to the similarity of pixels or voxels (such as gray values, textures, etc.) until the entire arterial blood vessel is covered.

[0151] In addition, deep learning techniques can be used to improve the accuracy and efficiency of vascular segmentation. For example, a convolutional neural network (CNN) can be used to automatically identify and segment arterial blood vessels in images. By training a large amount of labeled data, the CNN can learn the feature representation of arterial blood vessels and accurately identify arterial blood vessels in new images.

[0152] Finally, after constructing the three-dimensional model of the arterial blood vessel, visualization tools can be used for further analysis and processing. For example, parameters such as the diameter, length, and branching angle of the blood vessel can be calculated to evaluate its morphological and functional status. In addition, the three-dimensional model can be combined with clinical information to provide more comprehensive diagnostic basis and surgical guidance for doctors.

[0153] Compared with the traditional method that only relies on prostate artery MRI images for PAE guidance, the present invention can accurately extract the arterial blood vessel structure from the three-dimensional model by using vascular segmentation technology, and can construct a clear three-dimensional model of the arterial blood vessel for further diagnosis or surgical planning. When implementing PAE, doctors can clearly observe the three-dimensional orientation and structure of the target blood vessels of the prostate artery, avoiding problems such as ambiguity and confusion caused by vascular variations, overlaps, and crossings, accurately guiding doctors to the specific target blood vessels of the prostate artery, and saving time for doctors to implement PAE.

[0154] As a preferred implementation scheme of the present invention, preferably, the method for generating the prostate artery segmentation model includes:

[0155] Collect the prostate artery blood vessel MRI image sets of the prostate artery blood vessels in the axial, coronal, and sagittal positions respectively;

[0156] Preprocess the prostate artery blood vessel MRI image sets in the axial, coronal, and sagittal positions respectively;

[0157] Perform annotation processing on the prostate artery blood vessel MRI images in the prostate artery blood vessel MRI image sets in the axial, coronal, and sagittal positions respectively to determine the boundary positions of the prostate artery blood vessels in the axial, coronal, and sagittal positions respectively;

[0158] After annotation is completed, a training set is obtained and imported into a preset convolutional neural network model for training and learning of the annotated data, and the prostate artery segmentation model is obtained through training;

[0159] Use the validation sets of the prostate artery vessel images in the axial, coronal, and sagittal planes respectively to perform segmentation verification on the prostate artery segmentation model;

[0160] If the verification is passed, deploy the prostate artery segmentation model on the background server.

[0161] The prostate artery vessel MRI image sets in the axial, coronal, and sagittal planes can be obtained by an administrator from the background database of the diagnosis and treatment system (the diagnosis data of a large number of prostate patients in daily life includes these data).

[0162] The specific method for constructing the prostate artery segmentation model includes the following steps:

[0163] 1. Data preparation: Collect medical image data of the prostate artery, such as MRI or MRI scan images, and ensure that the data has sufficient quality and diversity.

[0164] 2. Preprocessing: Preprocess the collected image data, including denoising, normalization, contrast enhancement, etc., to improve the accuracy and efficiency of subsequent processing.

[0165] 3. Annotation: Manually annotate the image data by professional radiologists or medical imaging experts to determine the accurate location of the prostate artery.

[0166] 4. Model training: Use deep learning algorithms, such as convolutional neural networks (CNNs), to train the prostate artery segmentation model based on the annotated data. The U-Net architecture can be adopted because it performs well in medical image segmentation tasks.

[0167] 5. Model verification: Use the validation set to test the trained model, evaluate its segmentation performance, and adjust and optimize the model if necessary.

[0168] 6. Model deployment: Deploy the trained model into actual applications for automatic segmentation of the prostate artery.

[0169] After the model is deployed, the steps for performing image segmentation processing on the three-dimensional model of the prostate artery vessels include:

[0170] 1. Input the three-dimensional model: Input the three-dimensional model of the prostate artery vessels into the trained segmentation model.

[0171] 2. Segmentation processing: The model automatically identifies and segments the prostate artery vessels according to the learned features.

[0172] 3. Result Output: The model outputs the segmented images, which respectively correspond to the prostate artery vessel images on the axial, coronal, and sagittal planes.

[0173] 4. Post - processing: Post - process the segmentation results, such as smoothing the edges, filling holes, etc., to improve the image quality.

[0174] Specifically, it is understood in combination with the above - mentioned image segmentation method.

[0175] Traditional vascular image segmentation techniques mainly rely on manual or semi - automatic methods, including threshold segmentation, edge detection, region growing, level set methods, active contour models, etc. When processing vascular images, these techniques usually require pre - processing the images, such as denoising, enhancing contrast, etc., to improve the accuracy of segmentation. Although these methods can provide good segmentation results in some cases, they often have high requirements for image quality and may not be robust enough when dealing with complex vascular structures.

[0176] In the training of the present invention, deep learning methods are used to achieve automatic segmentation of vascular images. By respectively performing feature annotation at the boundary positions of the prostate artery vessels on the axial, coronal, and sagittal planes, the trained prostate artery segmentation model can perform image segmentation processing on the three - dimensional model of the prostate artery vessels on the axial, coronal, and sagittal planes respectively, and obtain the prostate artery vessel images (prostate artery vessel images constructed by vascular boundaries) of the three - dimensional model of the prostate artery vessels on the axial, coronal, and sagittal planes.

[0177] Therefore, by using the above - mentioned model for segmentation, it is possible to improve the rapid positioning, boundary recognition, and rapid image segmentation of the prostate artery vessel images on the axial, coronal, and sagittal planes, and improve the processing efficiency.

[0178] As a preferred embodiment of the present invention, preferably, in S4, it is identified and determined whether the prostate artery vessel features of the MIP image and the interventional artery image can be automatically matched successfully on the axial, coronal, and sagittal planes respectively, including:

[0179] Respectively extract the first prostate artery vessel features of the MIP image on the axial, coronal, and sagittal planes;

[0180] Respectively extract the second prostate artery vessel features of the prostate artery vessel images of the three - dimensional model of the prostate artery vessels on the axial, coronal, and sagittal planes;

[0181] Automatic matching judgment:

[0182] (1)Compare the first prostate artery vessel features on the axial plane with the second prostate artery vessel features in terms of features;

[0183] (2)Compare the first prostate artery vessel features on the coronal plane with the second prostate artery vessel features in terms of features;

[0184] (3)Compare the first prostate artery vessel features on the sagittal plane with the second prostate artery vessel features in terms of features;

[0185] If the feature comparison in (1)-(3) is successful, it is considered that the prostate artery vessel features of the MIP image and the interventional artery image on the axial plane, coronal plane and sagittal plane can be automatically matched successfully;

[0186] Otherwise, it fails.

[0187] The present invention performs automatic comparison after reconstructing all the original data of magnetic resonance scans and the original data during interventional radiology to meet the automatic matching between the two. If the two are successfully matched, the artery vessels can be directly embolized during the operation to meet the diagnosis of clinical operations.

[0188] Therefore, it is necessary to compare the MIP image with the interventional artery image. The specific comparison criteria are: comparison of the prostate artery vessel features on the axial plane, coronal plane and sagittal plane on the MIP image and the interventional artery image respectively (the above (1)-(3)).

[0189] The steps to extract the prostate artery vessel features on the prostate artery vessel image can be as follows:

[0190] 1. Image preprocessing: First, perform preprocessing operations such as denoising and enhancing contrast on the image to improve the visibility of vessel features.

[0191] 2. Vessel segmentation: Use image segmentation techniques such as threshold segmentation, region growing, edge detection or model-based methods to identify and separate the prostate artery vessels.

[0192] 3. Feature extraction: Apply feature extraction algorithms to the segmented vessel image, such as morphological features (vessel width, length, number of branches, etc.), texture features (texture patterns on the vessel surface) and geometric features (vessel curvature, angle, etc.).

[0193] 4. Analysis and recognition: Use machine learning or deep learning methods to analyze the extracted features to identify and classify different vessel features, such as normal vessels and abnormal vessels.

[0194] The image feature comparison method can perform feature comparison in the following way:

[0195] 1. Feature extraction: First, extract key feature points or regions from two images. This can be achieved through algorithms such as edge detection, corner detection, SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), etc.

[0196] 2. Feature description: Describe the extracted feature points for easy comparison. The descriptor can be in vector form, such as the SIFT feature descriptor.

[0197] 3. Feature matching: Match the feature points in one image with those in another image. This is usually done by calculating the similarity between feature descriptors, such as using Euclidean distance or Hamming distance (feature image similarity, or cosine similarity).

[0198] 4. Confirm matching: Eliminate incorrect matches by setting thresholds or using algorithms such as RANSAC (Random Sample Consensus) to retain correct matching point pairs.

[0199] 5. Geometric transformation estimation: Calculate the geometric transformation relationship between two images using the matching point pairs, such as affine transformation or homography matrix.

[0200] 6. Image alignment: Transform one image according to the estimated geometric transformation to align it with another image.

[0201] 7. Result evaluation: Evaluate the comparison effect by comparing the similarity between the transformed image and the target image. Metrics such as mean squared error (MSE), structural similarity index (SSIM), etc. can be used.

[0202] Specifically, the administrator can randomly select the above methods for feature comparison. If the first prostate artery vessel feature and the second prostate artery vessel feature in the axial, coronal, and sagittal positions of the MIP image have feature image matching (for example, the similarity meets more than 95%), it is considered that the comparison between the two is successful (all the judgment conditions in (1)-(3) above are met). Otherwise, it is unsuccessful.

[0203] If the authentication is successful, the MIP image (using the MIP algorithm to construct the MIP image of the prostate artery vessels (three-dimensional vascular image), obtaining a high-definition vascular map of the prostate artery vessel course and used for the next image intervention comparison study) will be output and displayed on the front-end page of the operating room to guide the prostate artery embolization. The MIP image shown here will be a three-dimensional vascular image of the prostate artery vessels reconstructed based on the MIP algorithm. Therefore, it is displayed on the front-end page of the operating room (usually the display page of the PC terminal in the operating room) to guide the doctor to perform prostate surgery and facilitate seeing the prostate vasculature of the patient.

[0204] As a preferred embodiment of the present invention, preferably, in S6, using a preset prostate artery recognition AI model, the prostate artery image features in the interventional artery image are recognized and located and fused on the MIP image, and the MIP image after the location and fusion is output and displayed on the front-end page of the operating room for guiding prostate artery embolization, including:

[0205] S600. Perform image enhancement processing on the interventional artery image to obtain an interventional enhanced image of the arterial blood vessels, and import the interventional enhanced image of the arterial blood vessels into the preset prostate artery recognition AI model. The prostate artery recognition AI model recognizes and marks the prostate artery image features on the axial, coronal, and sagittal planes in the interventional enhanced image of the arterial blood vessels;

[0206] S601. Based on the image registration and fusion method, locate and fuse the prostate artery image features on the MIP image, and form contrast features on the axial, coronal, and sagittal planes between the prostate artery image features and the original prostate artery blood vessels on the MIP image, and generate a tomographic scan contrast feature of the prostate artery blood vessels after the location and fusion on the MIP image;

[0207] S602. Output and display the interventional artery image of the prostate artery blood vessels after the location and fusion on the front-end page of the operating room for guiding prostate artery embolization.

[0208] If it is found that the feature comparison between the interventional image and the MIP image fails, the prostate artery image features in the interventional artery image (in the same scanning direction, such as the axial plane) are used to enhance and supplement the prostate artery blood vessel image at the corresponding position in the MIP image, so as to combine the image advantages of the interventional image to form an image complementary feature for the MIP image, and perform automatic comparison after reconstructing all the original data of the magnetic resonance scan and the original data during the intervention in the interventional radiology department to meet the automatic comparison between the two, so as to make the prostate choroid more clear, facilitate the doctor to understand the patient's blood vessel trend and other conditions, and facilitate the implementation of the operation.

[0209] Image enhancement processing usually includes:

[0210] 1. Edge enhancement: Highlight the blood vessel edges through edge detection algorithms (such as Sobel, Canny, Prewitt, etc.) to better identify the contours of the blood vessels.

[0211] 2. Multi-scale and multi-modal fusion: If there are multi-modal images (such as MRI, MRI, etc.), image fusion can be performed to obtain more comprehensive blood vessel information.

[0212] 3. Deep learning method: Use deep learning models such as convolutional neural networks (CNNs) to automatically learn the features of image enhancement (the administrator prepares the corresponding artificially enhanced interventional arterial images in advance) and enhance the images.

[0213] The construction method of the prostate artery recognition AI model here can be understood in combination with the generation method of the above-mentioned "prostate artery segmentation model", except that the training data set to be prepared is: interventional enhanced images of arterial blood vessels in the axial, coronal, and sagittal positions respectively. Its model training steps can be trained and learned in combination with the application principle of, for example, CNN (convolutional neural network model), which will not be elaborated in this embodiment.

[0214] Both the MIP image and the interventional image can be benchmarked in the same coordinate system, and the prostate artery image features in the axial, coronal, and sagittal positions in the extracted interventional enhanced images of arterial blood vessels are fused at the corresponding positions on the corresponding MIP image according to the preset positioning benchmark, so as to cover and replace the original prostate artery blood vessel feature images in the axial, coronal, and sagittal positions on the MIP image, realizing the interventional replacement and coverage of the corresponding blood vessel features and enhancing the visibility of the choroid.

[0215] Through the above processing, the vascular tomographic contrast features of the prostate artery blood vessels after positioning and fusion are generated on the MIP image, which can enable the doctor to clearly see the prostate artery choroid on the MIP image. Therefore, the MIP image of the prostate artery blood vessels after positioning and fusion at this time can be output and displayed on the front-end page of the operating room for guiding prostate artery embolization.

[0216] In actual operation, image enhancement processing is usually completed by professional medical imaging software or image processing software, such as MATLAB, ImageJ, Fiji, etc. In some cases, dedicated medical imaging workstations can also be used, which usually integrate a variety of image processing and analysis tools.

[0217] On the other hand, a guiding device for prostate artery embolization is provided.

[0218] Figure 3 It is a block diagram of a guiding device for prostate artery embolization shown according to an exemplary embodiment. This device is used for the PAE guiding method of magnetic resonance post-processing reconstruction of MIP maps and interventional reconstruction. Refer to Figure 3 The guiding device for prostate artery embolization is used to implement the PAE guiding method of magnetic resonance post-processing reconstruction of MIP maps and interventional reconstruction. The device includes:

[0219] (1)An MRI image processing system 310, which is used to obtain the original vascular image of the prostatic artery through magnetic resonance scanning and perform anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostatic artery;

[0220] (2)A MIP image processing system 320, which is used to perform MIP reconstruction on the pelvic MRI post-processing image based on the MIP algorithm. After reconstruction, a MIP image of the prostatic artery is obtained, including:

[0221] Analyze the MRI post-processing image of the prostatic artery to obtain MRI scan data in different scanning directions;

[0222] Traverse the MRI scan data, read the MRI scan data of the prostatic artery in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostatic artery;

[0223] Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate a MIP projection data set of the prostatic artery;

[0224] Fuse each MIP projection image in the MIP projection data set in the same scanning direction to reconstruct a MIP image of the prostatic artery;

[0225] (3)An interventional artery image processing system 330, which is used to obtain the interventional radiology scan image of the prostatic artery through magnetic resonance scanning, and construct an interventional artery image of the prostatic artery based on three-dimensional reconstruction and vascular segmentation technology;

[0226] (4)An artery feature recognition system 340, which is used to identify and judge whether the prostatic artery vessel features of the MIP image and the interventional artery image in the axial, coronal, and sagittal positions can be automatically matched successfully:

[0227] If so, output the MIP image and display it on the front-end page of the operating room for guiding prostatic artery embolization;

[0228] If not, enter the use of a preset prostatic artery recognition AI model to identify the prostatic artery image features in the interventional artery image and locate and fuse them on the MIP image, and output and display the located and fused MIP image on the front-end page of the operating room for guiding prostatic artery embolization;

[0229] (5)The front-end of the operating room 350, which is used to display the MIP image;

[0230] The MRI image processing system 310 is communicatively connected to the MIP image processing system 320;

[0231] The MIP image processing system 320 and the interventional artery image processing system 330 are respectively communicatively connected to the artery feature recognition system 340;

[0232] The artery feature recognition system 340 is communicatively connected to the front end 350 of the operating room.

[0233] For the functions and interactions of the above-mentioned various systems or front ends, please refer to the corresponding steps in the above method for understanding, and will not be elaborated in this embodiment.

[0234] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, as Figure 4 shown, the electronic device may include the above-mentioned Figure 3 prostatic artery embolization guiding device shown. Optionally, the electronic device 410 may include a first processor 2001.

[0235] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003.

[0236] Among them, the first processor 2001, the memory 2002 and the transceiver 2003 may be connected through a communication bus, for example.

[0237] Next, Figure 4 specific introductions will be made to the respective components of the electronic device 410:

[0238] Among them, the first processor 2001 is the control center of the electronic device 410, which may be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be a specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0239] Optionally, the first processor 2001 may execute various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0240] In a specific implementation, as an example, the first processor 2001 may include one or more CPUs, such as Figure 4 the CPU0 and CPU1 shown in

[0241] In a specific implementation, as an example, the electronic device 410 may also include multiple processors, such as Figure 4 the first processor 2001 and the second processor 2004 shown in

[0242] Among them, the memory 2002 is used to store the software program for executing the solution of the present invention and is controlled by the first processor 2001 to execute. The specific implementation manner can refer to the above method embodiments and will not be elaborated here.

[0243] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or exist independently and is coupled to the first processor 2001 through the interface circuit ( Figure 4 not shown in

[0244] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0245] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 4 not separately shown in

[0246] Optionally, the transceiver 2003 may be integrated with the first processor 2001 or exist independently, and is coupled to the first processor 2001 through an interface circuit (not shown) of the electronic device 410. The embodiments of the present invention do not make specific limitations thereto. Figure 4 It should be noted that

[0247] the structure of the electronic device 410 shown in Figure 4 does not constitute a limitation to the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0248] In addition, the technical effects of the electronic device 410 may refer to the technical effects of the magnetic resonance post-processing reconstruction MIP map and the PAE-guided method for interventional reconstruction described in the above method embodiments, which will not be elaborated herein.

[0249] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0250] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0251] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0252] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0253] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0254] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0255] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0256] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0257] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0258] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0259] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0260] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0261] As described above, the above are only specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for guiding PAE in magnetic resonance post - processing reconstruction of MIP map and interventional reconstruction, characterized in that, The method includes: S1. Obtain the original vascular image of the prostatic artery through magnetic resonance scanning and perform anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostatic artery; S2. Based on the MIP algorithm, perform image MIP reconstruction on the pelvic MRI post-processing image. After reconstruction, obtain the MIP image of the prostatic artery, including: Analyze the MRI post-processing image of the prostatic artery to obtain MRI scan data in different scanning directions; Traverse the MRI scan data, read the MRI scan data of the prostatic artery in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostatic artery; Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate the MIP projection data set of the prostatic artery; In the same scanning direction, fuse each MIP projection image in the MIP projection data set and reconstruct to obtain the MIP image of the prostatic artery; S3. Obtain the interventional radiology scan image of the prostatic artery through magnetic resonance scanning, and based on three-dimensional reconstruction and vascular segmentation techniques, construct the interventional artery image of the prostatic artery; S4. Identify and judge whether the prostatic artery vessel features of the MIP image and the interventional artery image can be automatically matched successfully in the axial, coronal, and sagittal positions respectively: If so, enter S5; If not, enter S6; S5. Output the MIP image and display it on the front-end page of the operating room, which is used to guide the prostatic artery embolization. The anatomy of each layer can be performed on the thin layers of the axial, coronal, and sagittal multi-parameter scans of the magnetic resonance, providing detailed anatomical knowledge for the operation; S6. Use the preset prostatic artery recognition AI model to identify the prostatic artery image features in the interventional artery image and locate and fuse them on the MIP image, and output and display the located and fused MIP image on the front-end page of the operating room for guiding the prostatic artery embolization; S3. Obtain the interventional radiology scan image of the prostatic artery through magnetic resonance scanning, and based on three-dimensional reconstruction and vascular segmentation techniques, construct the interventional artery image of the prostatic artery, including: Perform MRI scanning on the prostatic artery to obtain the MRI scan data corresponding to the prostatic artery; Label the vascular contour data of the MRI scan data of the prostatic artery and convert it to generate the two-dimensional original scan image obtained by the prostatic artery under MRI scanning; Combined with the volume rendering three-dimensional reconstruction algorithm, perform three-dimensional conversion on the two-dimensional original scan images under each scanning sequence to reconstruct the prostatic artery and generate the corresponding three-dimensional model of the prostatic artery; Using a preset prostate artery segmentation model, perform image segmentation processing on the three-dimensional model of the prostate artery blood vessels in the axial, coronal, and sagittal positions respectively, obtain the prostate artery blood vessel images of the three-dimensional model of the prostate artery blood vessels in the axial, coronal, and sagittal positions, and obtain the magnetic resonance artery MIP image of the prostate artery blood vessels; S4. Identify and determine whether the prostate artery blood vessel features of the MIP image and the interventional artery image can be automatically matched successfully in the axial, coronal, and sagittal positions respectively, including: Extract the first prostate artery blood vessel features of the MIP image in the axial, coronal, and sagittal positions respectively; Extract the second prostate artery blood vessel features of the prostate artery blood vessel images of the three-dimensional model of the prostate artery blood vessels in the axial, coronal, and sagittal positions respectively; Automatic matching judgment: (1) Compare the first prostate artery blood vessel features in the axial position with the second prostate artery blood vessel features; (2) Compare the first prostate artery blood vessel features in the coronal position with the second prostate artery blood vessel features; (3) Compare the first prostate artery blood vessel features in the sagittal position with the second prostate artery blood vessel features; If (1)-(3) can all be successfully matched in features, it is considered that the prostate artery blood vessel features of the MIP image and the interventional artery image can be automatically matched successfully in the axial, coronal, and sagittal positions respectively; Otherwise, it fails; S6. Use a preset prostate artery recognition AI model to recognize the prostate artery image features in the interventional artery image and locate and fuse them on the MIP image, and output and display the located and fused MIP image on the front-end page of the operating room for guiding prostate artery embolization, including: S600. Perform image enhancement processing on the interventional artery image to obtain an interventional enhanced image of the artery blood vessels, and import the interventional enhanced image of the artery blood vessels into the preset prostate artery recognition AI model, and the prostate artery recognition AI model recognizes and marks the prostate artery image features in the axial, coronal, and sagittal positions of the interventional enhanced image of the artery blood vessels; S601. Based on the image registration and fusion method, locate and fuse the prostate artery image features on the MIP image to form comparison features in the axial, coronal, and sagittal positions between the prostate artery blood vessels on the MIP image and the original prostate artery blood vessels on the MIP image, and generate tomographic scan comparison features of the prostate artery blood vessels after location and fusion on the MIP image, specifically including: Both the MIP image and the interventional image can be benchmarked in the same coordinate system, and the prostate artery image features on the axial, coronal, and sagittal planes of the extracted interventional enhanced image of the arterial blood vessels are fused at the corresponding positions on the corresponding MIP image according to the preset positioning benchmark, so as to cover and replace the feature images of the original prostate artery blood vessels on the MIP image on the axial, coronal, and sagittal planes, realizing the interventional replacement and coverage of the corresponding blood vessel features and enhancing the visibility of its context; S602. Output the interventional artery image of the positioned and fused prostate artery blood vessels and display it on the front-end page of the operating room for guiding the prostate artery embolization.

2. The PAE-guided method for magnetic resonance post-processing reconstruction of MIP images and interventional reconstruction according to claim 1, characterized in that The method for generating the prostate artery segmentation model includes: Collect the MRI image sets of the prostate artery blood vessels on the axial, coronal, and sagittal planes respectively; Preprocess the MRI image sets of the prostate artery blood vessels on the axial, coronal, and sagittal planes respectively; Perform annotation processing on the MRI images of the prostate artery blood vessels in the MRI image sets on the axial, coronal, and sagittal planes respectively to determine the boundary positions of the prostate artery blood vessels on the axial, coronal, and sagittal planes respectively; After the annotation is completed, obtain the training set and import it into the preset convolutional neural network model for training and learning of the annotated data to train the prostate artery segmentation model; Use the validation sets of the prostate artery blood vessel images on the axial, coronal, and sagittal planes respectively to perform segmentation verification on the prostate artery segmentation model; If the verification is passed, deploy the prostate artery segmentation model on the background server.

3. A guiding device for prostate artery embolization, which is used to implement the method for guiding PAE by magnetic resonance post-processing reconstruction of MIP map and interventional reconstruction as described in claim 1 or 2, characterized in that, The device includes: (1) An MRI image processing system for obtaining the original blood vessel image of the prostate artery through magnetic resonance scanning and performing anatomical preprocessing to obtain the pelvic MRI post-processing image of the prostate artery blood vessels; (2) A MIP image processing system for performing MIP reconstruction on the pelvic MRI post-processing image based on the MIP algorithm. After reconstruction, the MIP image of the prostate artery blood vessels is obtained, including: Analyze the MRI post-processing image of the prostate artery blood vessels to obtain MRI scan data in different scanning directions; Traverse the MRI scan data, read the MRI scan data of the prostate artery blood vessels in different scanning directions, calculate the maximum three-dimensional pixel value, and save it to obtain the MRI scan data set of the prostate artery blood vessels; Based on the MIP algorithm, perform MIP projection imaging on the MRI scan data set in the axial, coronal, and sagittal scanning directions to generate the MIP projection data set of the prostate artery blood vessels; Fuse each MIP projection image in the MIP projection data set in the same scanning direction to reconstruct the MIP image of the prostate artery blood vessels; (3) An interventional artery image processing system for obtaining the interventional radiology scan image of the prostate artery blood vessels through magnetic resonance scanning and constructing the interventional artery image of the prostate artery blood vessels based on three-dimensional reconstruction and blood vessel segmentation technology; (4) An arterial feature recognition system for identifying and determining whether the prostate artery vessel features of the MIP image and the interventional arterial image can be successfully automatically matched in the axial, coronal, and sagittal planes: If so, output and display the MIP image on the front-end page of the operating room for guiding prostate artery embolization; If not, enter the use of a preset prostate artery recognition AI model to identify the prostate artery image features in the interventional arterial image and locate and fuse them on the MIP image, and output and display the MIP image after the location and fusion on the front-end page of the operating room for guiding prostate artery embolization; (5) The front end of the operating room for displaying the MIP image; The MRI image processing system is communicatively connected to the MIP image processing system; The MIP image processing system and the interventional arterial image processing system are respectively communicatively connected to the arterial feature recognition system; The arterial feature recognition system is communicatively connected to the front end of the operating room.

4. An electronic device, characterized in that, The electronic device includes: A processor; A memory, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor, the method described in claim 1 or 2 is implemented.

5. A computer-readable storage medium, characterized in that, Program code is stored in the computer-readable storage medium, and the program code can be called by the processor to execute the method described in claim 1 or 2.

Images