Surgical position positioning and navigation method, device and equipment for vascular surgical operation
The method constructs a pure vascular topology model by removing abnormal regions and incorporating physiological data, enhancing surgical planning accuracy and safety in vascular surgery.
Patent Information
- Application Number
- CN202510582383.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2025-07-15
AI Technical Summary
The prior art is difficult to provide detailed and accurate vascular surgical position and path planning, affecting the accuracy and safety of the surgery.
By obtaining human vascular images and physiological characteristic data, removing abnormal areas, building a pure human vascular topological model, and combining physiological characteristic data for lesion labeling, a general human vascular topological model is generated, and finally registering with the images of the patient to be operated, marking the surgical location and path.
It improves the accuracy and safety of vascular surgery, reduces the risk of overfitting, ensures the accuracy and stability of the model, and adapts to pathological deformation needs.
Smart Images
Figure CN120304950A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical technology, and particularly to a surgical position positioning and navigation method, device and equipment for vascular surgery. Background Art
[0002] Vascular surgery is mainly for the prevention, diagnosis and treatment of peripheral vascular diseases other than cerebrovascular and cardiovascular diseases. At present, vascular surgery is generally divided into two categories: direct surgery and indirect intervention. Due to its advantages of minimally invasive and quick recovery, the indirect intervention surgery of inserting a guide wire or catheter through the distal blood vessel and navigating it to the lesion site is the preferred choice for modern vascular surgery. In the indirect intervention surgery of vascular surgery, in order to improve the accuracy and safety of the surgery, in addition to real-time image guidance during the operation, the surgical position and surgical path are generally planned before the operation, and the detail and accuracy of vascular imaging are the most core basis for preoperative surgical position and surgical path planning. Therefore, how to provide a method to construct the human vascular structure in detail and accurately and perform accurate preoperative surgical position and surgical path planning has become an urgent problem to be solved. Summary of the Invention
[0003] For this reason, to solve the above problems, the present invention provides a surgical position positioning and navigation method, device and equipment for vascular surgery.
[0004] For this reason, according to the first aspect, the present invention provides a surgical position positioning and navigation method for vascular surgery, including the following steps:
[0005] Obtain multiple human vascular images, and obtain the physiological characteristic data and disease characteristic data of the individuals corresponding to each human vascular image;
[0006] According to the disease characteristic data, eliminate the abnormal areas in the corresponding human vascular images to obtain multiple first input images;
[0007] Input the multiple first input images and the corresponding physiological characteristic data into a semantic segmentation model with multi-modal input to obtain a pure human vascular topology structure model;
[0008] According to the disease characteristic data, perform lesion annotation on the corresponding human vascular images to obtain multiple second input images;
[0009] Input the multiple second input images into the pure human vascular topology structure model to obtain a general human vascular topology structure model;
[0010] Obtain the vascular detection image and physiological characteristic detection data of the patient to be operated, and register the vascular detection image and physiological characteristic detection data with the general human vascular topology structure to obtain the vascular topology structure of the patient to be operated;
[0011] Mark the position to be operated on the vascular topology of the patient to be operated, and generate a number of operable positions and corresponding surgical paths according to the vascular topology and the position to be operated of the patient to be operated.
[0012] Optionally, the surgical position positioning and navigation method for vascular surgery further includes the following steps:
[0013] Obtain the difficulty score values of a number of surgical paths based on a preset surgical difficulty scoring standard, and obtain the optimal surgical position among a number of operable positions according to the difficulty score values.
[0014] Optionally, the surgical difficulty scoring standard includes any two or more of a path length scoring standard, a path width scoring standard, a path narrowest width scoring standard, a path node number scoring standard, a path vascular wall thickness scoring standard, a path vascular dynamics scoring standard, and a surgical prognosis scoring standard.
[0015] Optionally, the physiological characteristic data includes multiple of height and body type characteristic data, age characteristic data, gender characteristic data, blood pressure characteristic data, blood volume and cardiac output characteristic data, and angiogenesis-related gene characteristic data; the physiological characteristic detection data is correspondingly set with the physiological characteristic data.
[0016] Optionally, the step of performing lesion annotation on the corresponding human blood vessel image according to the disease characteristic data to obtain a plurality of second input images specifically includes:
[0017] Perform lesion area annotation and set lesion type labels on the corresponding human blood vessel image according to the disease characteristic data to obtain a second input image.
[0018] Optionally, the step of inputting a plurality of second input images into a pure human blood vessel topology model to obtain a general human blood vessel topology model specifically includes:
[0019] Input a plurality of second input images into a pure human blood vessel topology model to obtain a general human blood vessel topology model; there is a loss function layer in the pure blood vessel topology model.
[0020] Optionally, the step of inputting a plurality of second input images into a pure human blood vessel topology model to obtain a general human blood vessel topology model specifically includes:
[0021] Obtain the blood flow hydrodynamics simulation data of each individual corresponding to the human blood vessel image;
[0022] Input a plurality of second input images and the corresponding blood flow hydrodynamics simulation data into a pure human blood vessel topology model to obtain a general human blood vessel topology model; there is a loss function layer in the pure blood vessel topology model.
[0023] According to a second aspect, an embodiment of the present invention provides a surgical position positioning and navigation device for vascular surgery, including:
[0024] A first data acquisition module, configured to acquire multiple human vascular images, and acquire physiological characteristic data and disease characteristic data of the individuals corresponding to the respective human vascular images;
[0025] A first image processing module, configured to remove abnormal regions in the corresponding human vascular images according to the disease characteristic data to obtain a plurality of first input images;
[0026] A first model construction module, configured to input the plurality of first input images and the corresponding physiological characteristic data into a semantic segmentation model with multi-modal input to obtain a pure human vascular topological structure model;
[0027] A second image processing module, configured to perform lesion annotation on the corresponding human vascular images according to the disease characteristic data to obtain a plurality of second input images;
[0028] A second model construction module, configured to input the plurality of second input images into the pure human vascular topological structure model to obtain a general human vascular topological structure model;
[0029] A second data acquisition module, configured to acquire vascular detection images and physiological characteristic detection data of a patient to be operated on, and register the vascular detection images and the physiological characteristic detection data with the general human vascular topological structure model to obtain the vascular topological structure of the patient to be operated on;
[0030] A surgical position navigation module, configured to mark the position to be operated on the vascular topological structure of the patient to be operated on, and generate a plurality of operable positions and corresponding surgical paths according to the vascular topological structure and the position to be operated on of the patient to be operated on.
[0031] According to a third aspect, an embodiment of the present invention provides a surgical position positioning and navigation device for vascular surgery, including: at least one processor; and a memory communicatively connected to the at least one processor; computer instructions are stored in the memory, and the processor executes the computer instructions to execute the method described in the first aspect or any one of the embodiments of the first aspect.
[0032] According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, and computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method described in the first aspect or any one of the embodiments of the first aspect.
[0033] The technical solution provided by the present invention has the following advantages:
[0034] The surgical position positioning and navigation method for vascular surgery provided by the present invention uses a human vascular image (i.e., the first input image) with abnormal diseased areas removed when constructing a pure human vascular topological structure model. This can avoid interference of the overall vascular topological structure by diseased characteristics, avoid learning completely from noise, reduce the risk of overfitting, and can provide anatomical constraints for the reconstruction of diseased blood vessels (preventing the problem of obtaining a structural model that does not conform to anatomy that may occur when directly constructing a model based on a human vascular image containing diseased characteristics). At the same time, when constructing a pure human vascular topological structure model, the physiological characteristic data corresponding to the human vascular image is also input into the model as a channel data, incorporating the influence of physiological characteristic data on the vascular topological structure, and further improving the accuracy of the constructed pure human vascular topological structure model. Then, after lesion annotation of the human vascular image to obtain the second input image, the pure human vascular topological structure model is fine-tuned for case characteristics, so that the obtained general human vascular topological structure model can not only adapt to pathological deformation to meet the needs of preoperative surgical position and surgical path planning, but also ensure its stability and accuracy. Finally, by obtaining the vascular detection image and physiological characteristic detection data of the patient to be operated on, and registering the vascular detection image and physiological characteristic detection data with the general human vascular topological structure to obtain the vascular topological structure of the patient to be operated on, and then planning the operable position and corresponding surgical path of the patient to be operated on accordingly, the accuracy of the preoperative planning can be improved, thereby improving the precision and safety of vascular surgery. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0036] Figure 1 It is a flowchart of a method for the surgical position positioning and navigation method for vascular surgery provided by an embodiment of the present invention;
[0037] Figure 2 It is another flowchart of a method for the surgical position positioning and navigation method for vascular surgery provided by an embodiment of the present invention;
[0038] Figure 3 It is a schematic block diagram of the principle of a surgical position positioning and navigation device for a vascular surgery provided by an embodiment of the present invention;
[0039] Figure 4 It is a schematic hardware structure diagram of a surgical position positioning and navigation device for a vascular surgery provided by an embodiment of the present invention. Detailed implementation manners
[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0041] In the description of the present invention, it should be noted that the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.
[0042] Embodiment 1
[0043] Figure 1 The flowchart of a method for positioning and navigating the surgical position of a vascular surgery in the embodiments of the present invention is shown. Specifically, as Figure 1 shown, the method may include the following steps:
[0044] S100: Obtain multiple human vascular images, and obtain the physiological characteristic data and disease characteristic data of the individuals corresponding to the respective human vascular images.
[0045] In this embodiment, the physiological characteristic data may include multiple of height and body type characteristic data, age characteristic data, gender characteristic data, blood pressure characteristic data, blood volume and cardiac output characteristic data, blood vessel generation-related gene characteristic data; it may further include one or more of blood pressure fluctuation characteristic data, blood lipid characteristic data, blood glucose characteristic data, etc.
[0046] Specifically, the height and body type characteristic data may include one or more of height data, limb dimension data, limb length data, body fat percentage data, and bone mass data; the blood vessel generation-related gene characteristic data may include the characteristic data of whether blood vessel generation-related genes such as VEGF, PDGF, and ANGPT are mutated. Specifically, the blood vessel generation-related gene characteristic data can be detected by methods such as sequencing, expression analysis, and protein detection.
[0047] In this embodiment, the disease characteristic data may be the disease type; specifically, the disease type is used to characterize the lesion location and lesion type. For example, lower limb arteriosclerosis characterizes that the lesion location is the lower limb artery (specifically, the left lower limb or the right lower limb in specific applications), and the lesion type is arteriosclerosis (specifically, stenosis or occlusion in specific applications).
[0048] Those skilled in the art should understand that the setting of disease characteristic data does not mean that the human vascular image obtained in this step must be from the image of a sick person. When the human vascular image is of a healthy person (the healthy person here does not mean that he is completely disease-free, but just does not suffer from vascular surgical diseases), it is only necessary to set the disease characteristic data to "no disease" or directly to the empty value "null". Correspondingly, there is no need to remove abnormal areas from the human vascular image of the healthy person in the following step S200.
[0049] S200: Eliminate abnormal areas in the corresponding human blood vessel image according to the disease characteristic data to obtain a plurality of first input images.
[0050] In specific implementation, when the number of first input images is small, or there are few images of healthy people in the human blood vessel images, that is, most of the first input images are images with abnormal areas removed, a generative model (such as a deep learning model such as CycleGAN) can be further used to synthesize healthy blood vessels to replace the abnormal areas, and the image after the healthy blood vessels are replaced can be used as the first input image.
[0051] S300: Inputting a plurality of first input images and corresponding physiological feature data into a multimodal input semantic segmentation model to obtain a pure human vascular topological structure model.
[0052] In specific implementation, the semantic segmentation model of multimodal input can be a Unet model, an MM-Unet model, etc., or a UNet+Transformer hybrid architecture model. In specific implementation, the physiological feature data can be converted into a matrix with the same spatial size as the input image to form newly added channel data, and the newly added channel data and the original input image channel data can be spliced to obtain the model input data; the physiological data can also be encoded into a feature vector through a fully connected layer, and then the vector is copied to each spatial position in the model, and spliced with the intermediate feature map of the encoder (downsampling path) in the model to achieve model training based on the first input image and the corresponding physiological feature data.
[0053] S400: Annotating corresponding human blood vessel images for lesions according to the disease characteristic data to obtain a plurality of second input images.
[0054] In this embodiment, the lesion annotation may include lesion region annotation, and specifically, the lesion region annotation may be to generate a lesion region mask. In specific implementation, the lesion region mask may be generated by manual marking or by threshold segmentation combined with morphological processing.
[0055] As an optional specific implementation of this embodiment, step S400 may specifically include the following steps:
[0056] S410: Label the lesion area on the corresponding human blood vessel image according to the disease feature data and set the lesion type label to obtain a second input image.
[0057] In this embodiment, it can be set that the disease feature data in step S100 includes not only the disease type but also the lesion grade; specifically, the lesion grade is set corresponding to the lesion type. For example, if it is a stenosis lesion, it corresponds to the stenosis grade, and the specific grade can be set to include mild, severe, and very severe, or can be set to small, medium, large, and extra-large, or can be set to include level one, level two, level three, and level four, etc.
[0058] Correspondingly, the lesion grade label can be set corresponding to the lesion grade in the disease feature data. For example, the lesion grade label can be "stenosis grade - severe", "aneurysm grade - small", etc.
[0059] S500: Input multiple second input images into the pure human blood vessel topological structure model to obtain a general human blood vessel topological structure model.
[0060] As an optional specific embodiment of this embodiment, it can be set that there is a loss function level in the pure blood vessel topological structure model to focus on the lesion site and improve the accuracy of the general human blood vessel topological structure model constructed in step S500.
[0061] As an optional specific embodiment of this embodiment, in order to further improve the accuracy of the constructed general human blood vessel model, it can also be set that step S500 specifically includes the following steps:
[0062] S510: Obtain the blood flow hydrodynamics simulation data of each individual corresponding to the human blood vessel image.
[0063] Specifically, the blood flow hydrodynamics simulation data can be constructed based on medical imaging data such as four-dimensional flow magnetic resonance imaging, ultrasound Doppler, etc.
[0064] S520: Input multiple second input images and the corresponding blood flow hydrodynamics simulation data into the pure human blood vessel topological structure model to obtain a general human blood vessel topological structure model.
[0065] In specific implementation, the hemodynamic simulation data can also be converted into a matrix with the same spatial size as the input image to form new channel data. Then, the new channel data and the original input image channel data are spliced to obtain the model input data, thereby realizing model training based on the second input image and the corresponding hemodynamic simulation data. Alternatively, the hemodynamic simulation data can be encoded into a feature vector through a fully connected layer, and then this vector is copied to each spatial position in the model and spliced with the intermediate feature map of the encoder (downsampling path) in the model, thereby realizing model training based on the second input image and the corresponding hemodynamic simulation data.
[0066] Similarly, a loss function layer can also be set in the pure blood vessel topological structure model.
[0067] S600: Obtain the blood vessel detection image and physiological feature detection data of the patient to be operated on, and register the general human blood vessel topological structure model using the blood vessel detection image and physiological feature detection data to obtain the blood vessel topological structure of the patient to be operated on.
[0068] Specifically, the physiological feature detection data of the patient to be operated on is set corresponding to the physiological feature data in the above step S100.
[0069] S700: Mark the position to be operated on the blood vessel topological structure of the patient to be operated on, and generate a number of operable positions and corresponding surgical paths according to the blood vessel topological structure and the position to be operated on of the patient to be operated on.
[0070] Specifically, the marking of the position to be operated on can be the lesion position marked by the general human blood vessel topological structure model according to the input blood vessel detection image, or can be manually marked by medical staff according to the generated blood vessel topological structure of the patient to be operated on.
[0071] As an optional specific implementation manner of this embodiment, in order to further improve the preoperative planning guidance effect of the surgical position positioning and navigation method for vascular surgery in this embodiment, as shown in the figure, it can be set that the surgical position positioning and navigation method for vascular surgery further includes the following steps:
[0072] S800: Obtain the difficulty score values of a number of surgical paths based on a preset surgical difficulty scoring standard, and obtain the optimal surgical position among a number of operable positions according to the difficulty score values.
[0073] Specifically, the surgical difficulty scoring criteria include any two or more of the path length scoring criteria, path width scoring criteria, narrowest path width scoring criteria, path node number scoring criteria, path blood vessel wall thickness scoring criteria, path blood vessel dynamics scoring criteria, and surgical prognosis scoring criteria. In specific implementation, weights can also be set for each scoring criteria, and the difficulty score value is the weighted sum of the scores under each scoring criteria.
[0074] An embodiment of the present invention further provides a surgical position positioning and navigation device for vascular surgery, as Figure 3 shown. The device includes: a first data acquisition module 100, a first image processing module 200, a first model construction module 300, a second image processing module 400, a second model construction module 500, a second data acquisition module 600, and a surgical position navigation module 700; wherein,
[0075] The first data acquisition module 100 is configured to acquire multiple human blood vessel images, and acquire the physiological characteristic data and disease characteristic data of the individuals corresponding to each human blood vessel image;
[0076] The first image processing module 200 is configured to remove abnormal regions in the corresponding human blood vessel images according to the disease characteristic data, and obtain a plurality of first input images;
[0077] The first model construction module 300 is configured to input the plurality of first input images and the corresponding physiological characteristic data into a semantic segmentation model with multi-modal input, and obtain a pure human blood vessel topological structure model;
[0078] The second image processing module 400 is configured to perform lesion annotation on the corresponding human blood vessel images according to the disease characteristic data, and obtain a plurality of second input images;
[0079] The second model construction module 500 is configured to input the plurality of second input images into the pure human blood vessel topological structure model, and obtain a general human blood vessel topological structure model;
[0080] The second data acquisition module 600 is configured to acquire the blood vessel detection image and physiological characteristic detection data of the patient to be operated on, and register the general human blood vessel topological structure model with the blood vessel detection image and physiological characteristic detection data, so as to obtain the blood vessel topological structure of the patient to be operated on;
[0081] The surgical position navigation module 700 is configured to mark the surgical position to be operated on the blood vessel topological structure of the patient to be operated on, and generate a plurality of operable positions and corresponding surgical paths according to the blood vessel topological structure of the patient to be operated on and the surgical position.
[0082] The specific functions of each module in the device can be understood with reference to the content in the above method, and will not be elaborated here.
[0083] In the surgical position positioning and navigation method and device for vascular surgery in this embodiment, by using the human vascular image (i.e., the first input image) with the diseased and abnormal areas removed to construct a pure human vascular topological structure model, it is possible to avoid the overall vascular topological structure being interfered by diseased features, avoid learning completely from noise, reduce the risk of overfitting, and provide anatomical constraints for the reconstruction of diseased blood vessels (preventing the problem of obtaining a structural model that does not conform to anatomy that may occur when directly constructing a model based on the human vascular image containing diseased features); at the same time, when constructing the pure human vascular topological structure model, the physiological feature data corresponding to the human vascular image is also input into the model as a channel data, incorporating the influence of physiological feature data on the vascular topological structure, further improving the accuracy of the constructed pure human vascular topological structure model; then, after performing lesion annotation on the human vascular image to obtain the second input image, the pure human vascular topological structure model is fine-tuned for case characteristics, so that the obtained general human vascular topological structure model can not only adapt to pathological deformation to meet the needs of preoperative surgical position and surgical path planning, but also ensure its stability and accuracy; finally, by acquiring the vascular detection image and physiological feature detection data of the patient to be operated on, and using the vascular detection image and physiological feature detection data to register the general human vascular topological structure, the vascular topological structure of the patient to be operated on is obtained, and then the operable position and the corresponding surgical path of the patient to be operated on are planned accordingly, which can improve the accuracy of the preoperative planning, thereby improving the precision and safety of vascular surgery.
[0084] Embodiment 2
[0085] The embodiment of the present invention also provides a surgical position positioning and navigation device for vascular surgery, as Figure 4 shown. The device may include a processor 41 and a memory 42, where the processor 41 and the memory 42 may be connected by a bus or other means, Figure 4 taking the connection by bus as an example.
[0086] The processor 41 may be a central processing unit (CPU). The processor 41 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. chips, or a combination of the above various types of chips.
[0087] The memory 42 serves as a non-transitory computer-readable storage medium and can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the surgical position positioning and navigation method for vascular surgery in Embodiment 1 of the present invention. The processor 41 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory 42, that is, implements the surgical position positioning and navigation method for vascular surgery in Embodiment 1 of the above method.
[0088] The memory 42 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor 41 and the like. In addition, the memory 42 may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 42 may optionally include a memory remotely set relative to the processor 41, and these remote memories can be connected to the processor 41 through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.
[0089] The one or more modules are stored in the memory 42 and, when executed by the processor 41, execute the surgical position positioning and navigation method for vascular surgery in Embodiment 1 as Figure 1 - Figure 2 shown.
[0090] Specific details of the above surgical position positioning and navigation device for vascular surgery can be understood by referring to the corresponding relevant descriptions and effects in Embodiment 1 shown Figures 1 to 2 and will not be elaborated here.
[0091] Those skilled in the art can understand that to implement all or part of the processes in the above embodiment methods, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (abbreviation: HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.
[0092] Obviously, the above embodiments are merely examples for clear illustration and not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation manners here. And the obvious changes or modifications derived therefrom still fall within the protection scope of the present invention.
Claims
1. A surgical position positioning and navigation method for vascular surgery, characterized in that, It includes the following steps: Obtain multiple human vascular images, and obtain the physiological characteristic data and disease characteristic data of the individuals corresponding to each of the human vascular images; Remove the abnormal regions in the corresponding human vascular images according to the disease characteristic data to obtain multiple first input images; Input the multiple first input images and the corresponding physiological characteristic data into a semantic segmentation model with multi-modal input to obtain a pure human vascular topological structure model; Perform lesion annotation on the corresponding human vascular images according to the disease characteristic data to obtain multiple second input images; Input the multiple second input images into the pure human vascular topological structure model to obtain a general human vascular topological structure model; Obtain the vascular detection image and physiological characteristic detection data of the patient to be operated on, and register the vascular detection image and the physiological characteristic detection data with the general human vascular topological structure model to obtain the vascular topological structure of the patient to be operated on; Mark the position to be operated on of the patient to be operated on on the vascular topological structure of the patient to be operated on, and generate several operable positions and corresponding surgical paths according to the vascular topological structure of the patient to be operated on and the position to be operated on.
2. The surgical position positioning and navigation method for vascular surgery according to claim 1, wherein It further includes the following steps: Obtain the difficulty score values of several of the surgical paths based on a preset surgical difficulty scoring standard, and obtain the optimal surgical position among several of the operable positions according to the difficulty score values.
3. The surgical position positioning and navigation method for vascular surgery according to claim 2, characterized in that, The surgical difficulty scoring standard includes any two or more of a path length scoring standard, a path width scoring standard, a path narrowest width scoring standard, a path node number scoring standard, a path vascular wall thickness scoring standard, a path vascular dynamics scoring standard, and a surgical prognosis scoring standard.
4. The surgical position positioning and navigation method for vascular surgery according to claim 1, characterized in that, The physiological characteristic data includes multiple of height and body type characteristic data, age characteristic data, gender characteristic data, blood pressure characteristic data, blood volume and cardiac output characteristic data, and vascular generation related gene characteristic data; the physiological characteristic detection data is set corresponding to the physiological characteristic data.
5. The surgical position positioning and navigation method for vascular surgery according to any one of claims 1-4, characterized in that, The step of performing lesion annotation on the corresponding human vascular images according to the disease characteristic data to obtain multiple second input images specifically includes: Perform lesion region annotation on the corresponding human vascular images according to the disease characteristic data and set lesion type labels to obtain the second input images.
6. The surgical position positioning and navigation method for vascular surgery according to claim 5, characterized in that, The step of inputting the multiple second input images into the pure human vascular topological structure model to obtain a general human vascular topological structure model specifically includes: Input the multiple second input images into the pure human vascular topological structure model to obtain the general human vascular topological structure model; the pure vascular topological structure model has a loss function level.
7. The surgical position positioning and navigation method for vascular surgery according to claim 5, characterized in that, The step of inputting the multiple second input images into the pure human vascular topological structure model to obtain a general human vascular topological structure model specifically includes: Obtain the blood flow hydrodynamics simulation data of the individuals corresponding to each of the human vascular images; Input multiple of the second input images and the corresponding hemodynamic simulation data into the pure human blood vessel topological structure model to obtain the general human blood vessel topological structure model; there is a loss function level in the pure blood vessel topological structure model.
8. A surgical position positioning and navigation device for vascular surgery, characterized in that, It includes: A first data acquisition module, configured to acquire multiple human blood vessel images, and acquire the physiological characteristic data and disease characteristic data of the individuals corresponding to the respective human blood vessel images; A first image processing module, configured to remove abnormal regions in the corresponding human blood vessel images according to the disease characteristic data to obtain multiple first input images; A first model construction module, configured to input multiple of the first input images and the corresponding physiological characteristic data into a semantic segmentation model with multi-modal input to obtain a pure human blood vessel topological structure model; A second image processing module, configured to perform lesion annotation on the corresponding human blood vessel images according to the disease characteristic data to obtain multiple second input images; A second model construction module, configured to input multiple of the second input images into the pure human blood vessel topological structure model to obtain a general human blood vessel topological structure model; A second data acquisition module, configured to acquire the blood vessel detection image and physiological characteristic detection data of the patient to be operated on, and register the general human blood vessel topological structure model with the blood vessel detection image and the physiological characteristic detection data to obtain the blood vessel topological structure of the patient to be operated on; A surgical position navigation module, configured to mark the surgical position of the patient to be operated on on the blood vessel topological structure of the patient to be operated on, and generate a number of surgically accessible positions and corresponding surgical paths according to the blood vessel topological structure of the patient to be operated on and the surgical position.
9. A surgical position positioning and navigation device for vascular surgery, characterized in that, It includes: At least one processor; And a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-7 above.
10. A computer-readable storage medium having computer instructions stored thereon, characterized in that, When the instructions are executed by the processor, the steps of the method according to any one of claims 1-7 above are implemented.