Surgical navigation method, system, medium and electronic device based on dsa images

Abstract

The application provides a surgery navigation method and system based on DSA images, a medium and an electronic device, comprising: acquiring DSA images in real-time surgery; constructing a data set and preprocessing, and dividing into a training set and a test set according to a preset proportion; establishing a mathematical model, training the mathematical model through the training set, and verifying the feasibility of the mathematical model on the test set; deploying an Unet segmentation model, and segmenting the blood vessels under the current frame image in real time in the subtraction stage; image fusion is performed on the blood vessels segmented in the subtraction stage and the perspective view, so as to realize the blood vessel path navigation in the DSA image. The application segments the DSA image blood vessels in the subtraction stage through the model, and fuses the blood vessels in the perspective stage, thereby providing navigation for the interventional medical instrument working in the blood vessels, improving the marching accuracy of the interventional medical instrument to the detection site, and further improving the success rate of the surgery.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, in particular to a surgery navigation method and system based on DSA images, a medium and an electronic device. BACKGROUND

[0002] In the field of modern medicine, interventional surgery has developed into the best treatment for complex conditions such as vascular obstruction due to its small trauma and accurate positioning. Interventional surgery uses X-ray, puncture catheter and guide wire, and other interventional medical devices to treat diseases. Due to the overlapping of various tissues and organs in the test site, blood vessels are difficult to identify, and early non-subtraction angiography cannot be used for accurate clinical diagnosis. With the development of interventional surgery, DSA devices are constantly evolving, and intelligentization will be the inevitable trend of future DSA development. Providing accurate navigation for doctors or surgical robots during interventional surgery can provide comprehensive assistance throughout the surgery, which is an essential technology.

[0003] Patent document CN115170912A discloses a method for training an image processing model, a method for generating an image, and related products. The method for training an image processing model includes obtaining a blood vessel segmentation map of an original medical image; preprocessing the original medical image to obtain an intermediate medical image with a blood vessel morphology inconsistent with the original medical image; generating a training image based on the intermediate medical image and the blood vessel segmentation map; and training the image processing model using the training image to restore the training image to the original medical image.

[0004] Although patent document CN115170912A can achieve minor feature changes, it cannot guarantee segmentation accuracy; the addition of an intermediate medical image makes the steps further complicated, and it cannot segment blood vessels in a perspective view.

[0005] Patent document CN115239744A discloses a blood vessel segmentation method, device, equipment, and storage medium. The blood vessel segmentation method includes: inputting an original medical image into a first blood vessel segmentation model to obtain a first blood vessel segmentation prediction result of a target blood vessel, and obtaining a blood vessel trunk positioning result of the target blood vessel from the first blood vessel segmentation prediction result; cutting the original medical image into multiple local image blocks, and according to the position of each local image block in the original medical image and the blood vessel trunk positioning result, cutting out a global region of the target blood vessel from the original medical image; inputting the global region into the first blood vessel segmentation model to obtain a global intermediate feature map generated in an intermediate stage; inputting the multiple local image blocks into a second blood vessel segmentation model, and introducing the global intermediate feature map as reference information for blood vessel segmentation prediction into the second blood vessel segmentation model in a data interaction manner to obtain a second blood vessel segmentation prediction result of the target blood vessel.

[0006] However, the patent document CN115239744A cannot segment blood vessels in a perspective view. SUMMARY

[0007] In view of the defects in the prior art, the purpose of the present application is to provide a surgery navigation method, system, medium and electronic equipment based on DSA images.

[0008] According to the surgery navigation method based on DSA images provided by the present application, the following steps are included:

[0009] Step S1: Obtain DSA images in real-time surgery;

[0010] Step S2: Construct a data set and pre-process it, and divide it into a training set and a test set according to a preset ratio;

[0011] Step S3: Use a neural network algorithm to establish a Unet segmentation model, train the Unet segmentation model through the training set, and verify the feasibility of the Unet segmentation model on the test set;

[0012] Step S4: Deploy the Unet segmentation model and segment the blood vessels under the current frame image in real time in the subtraction stage;

[0013] Step S5: Image fusion of the blood vessels segmented in the subtraction stage and the perspective view, realizing blood vessel path navigation in DSA images.

[0014] Preferably, the data set includes original images in the contrast agent injection stage in the subtraction process, wherein the contrast agent flow direction and the blood flow direction are consistent;

[0015] The pre-processing includes labeling the main blood vessels in the original images in the data set to generate corresponding mask images;

[0016] The Unet segmentation model includes an encoding part and a decoding part, the encoding part includes a down-sampling module to change the image pixel resolution from high to low; the decoding part includes an up-sampling module to change the image resolution from low to high.

[0017] Preferably, the step S4 includes:

[0018] Step S4.1: Deploy the Unet segmentation model in the DSA image display;

[0019] Step S4.2: Segment the blood vessels under the current frame image in real time in the subtraction stage through the Unet segmentation model to obtain a segmented blood vessel path image;

[0020] Step S4.3: Smooth the segmented vascular path map to eliminate the segmented capillaries and retain the main blood vessels on the pathway from the interventional medical device to the site to be examined.

[0021] The main blood vessels include arteries and veins.

[0022] Preferably, step S5 includes:

[0023] Step S5.1: Save and record the blood vessel images segmented in real time during the subtraction stage;

[0024] Step S5.2: Record the position of the feature point in the image as the first position, and the position of the feature point in the fluoroscopic stage image as the second position. Record the pixel coordinates of the first position and the second position respectively, and perform position matching on the pixel coordinates so that the blood vessel image segmented in real time during the subtraction stage coincides with the fluoroscopic stage image.

[0025] Step S5.3: Layer the image within the current DSA image range. The segmented blood vessel and fluoroscopic images are designated as the first layer and the second layer, respectively. Weights are assigned to the gray values ​​of the first and second layers at the same pixel points. The weights are then added together to obtain the gray value of the fused image. This results in a fused image of the blood vessel image segmented in real time during the subtraction stage and the fluoroscopic image, thereby enabling blood vessel path navigation in DSA images under low-dose angiography radiation.

[0026] A surgical navigation system based on DSA images provided by the present invention includes:

[0027] Module M1: Acquires real-time DSA images during surgery;

[0028] Module M2: Constructs and preprocesses the dataset, and divides it into training and test sets according to a preset ratio;

[0029] Module M3: Utilizes a neural network algorithm to establish a Unet segmentation model, trains the Unet segmentation model using the training set, and verifies the feasibility of the Unet segmentation model on the test set;

[0030] Module M4: Deploys the Unet segmentation model and segments blood vessels in the current frame image in real time during the subtraction stage;

[0031] Module M5: Performs image fusion between the blood vessels segmented in the subtraction stage and the perspective view to achieve vascular path navigation in DSA images.

[0032] Preferably, the dataset includes original images of the contrast agent injection stage during the subtraction angiography process, wherein the contrast agent flow direction and the blood flow direction are consistent;

[0033] The preprocessing includes labeling the main blood vessels in the original images of the dataset and generating corresponding mask images.

[0034] Preferably, the module M4 includes:

[0035] Module M4.1: Deploy the Unet segmentation model in a DSA image display;

[0036] Module M4.2: The Unet segmentation model is used to segment blood vessels in the current frame image in real time during the subtraction stage to obtain the segmented blood vessel path map;

[0037] Module M4.3: Smooths the segmented vascular path map, eliminates the segmented capillaries, and preserves the main blood vessels on the pathway from the interventional medical device to the site to be examined;

[0038] The main blood vessels include arteries and veins.

[0039] Preferably, the module M5 includes:

[0040] Module M5.1: Saves and records the blood vessel images segmented in real time during the subtraction stage;

[0041] Module M5.2: Record the position of the feature point in the image as the first position, and the position of the feature point in the fluoroscopic stage image as the second position. Record the pixel coordinates of the first position and the second position respectively, and perform position matching on the pixel coordinates so that the blood vessel image segmented in real time during the subtraction stage coincides with the fluoroscopic stage image.

[0042] Module M5.3: Layers are created within the current DSA image range. The segmented blood vessel and fluoroscopic images are designated as the first layer and the second layer, respectively. Weights are assigned to the grayscale values ​​of the first and second layers at the same pixel points. The weights are then summed to obtain the grayscale value of the fused image, resulting in a fused image of the blood vessel image segmented in real time during the subtraction stage and the fluoroscopic image. This enables blood vessel path navigation in DSA images under low-dose angiography radiation.

[0043] According to the present invention, a computer-readable storage medium storing a computer program is provided, wherein when the computer program is executed by a processor, the steps of the surgical navigation method based on DSA images are implemented.

[0044] An electronic device according to the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the surgical navigation method based on DSA images.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. This invention segments blood vessels in DSA images during the subtraction stage by building a model. By smoothing the segmented blood vessel path map, clear blood vessel images can be obtained, improving the accuracy of the obtained blood vessel-related information, reducing the number of angiography sessions and lowering radiation levels.

[0047] 2. This invention can display the relationship between interventional devices and blood vessel positions in real time in perspective images through image fusion, realizing DSA image vascular path navigation under low-dose angiography radiation.

[0048] 3. This invention segments blood vessels in DSA images during the subtraction phase by building a model, and simultaneously fuses the blood vessels during the fluoroscopy phase to provide navigation for interventional medical devices to operate in blood vessels, thereby improving the accuracy of the interventional medical devices in the process of reaching the examination site and thus improving the success rate of the surgery. Attached Figure Description

[0049] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0050] Figure 1 This is a schematic diagram of the workflow of the present invention.

[0051] Figure 2 This is a subtraction angiography image of blood vessels in this invention.

[0052] Figure 3 This is a segmented blood vessel diagram from the present invention.

[0053] Figure 4 This is a vascular pathway navigation map of DSA images under low-dose radiation in this invention. Detailed Implementation

[0054] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0055] According to the present invention, a surgical navigation method based on DSA images is provided, such as... Figure 1 As shown, it includes:

[0056] Step S1: Acquire real-time DSA images during surgery. Acquisition methods include accurately acquiring real-time DSA images during surgery using a DSA image display that conforms to the DICOM Part 14 standard.

[0057] Step S2: Construct and preprocess the dataset, dividing it into training and test sets according to a preset ratio. For example, assuming the selected dataset contains 7000 images, it can be divided into training and test sets at a 6:1 ratio. This dataset includes original images of the contrast agent injection stage during subtraction angiography, where the contrast agent flow direction is consistent with the blood flow direction. Specifically, the required case data can be collected from an interventional surgery case database system to create the applicable dataset. Preprocessing includes labeling the main blood vessels in the original images of the dataset and generating corresponding mask images.

[0058] Step S3: Utilizing a neural network algorithm, establish a Unet segmentation model. The model consists of an encoding part and a decoding part. The encoding part comprises a downsampling module, which reduces the image pixel resolution from high to low; the decoding part comprises an upsampling module, which increases the image resolution from low to high. Train the mathematical model using the training set, iteratively assigning weights between neurons using the error gradient descent algorithm, and verify the segmentation accuracy on the test set using MeanIOU parameters to demonstrate the feasibility of the mathematical model.

[0059] Step S4: Deploy the Unet segmentation model and segment blood vessels in the current frame image in real time during the subtraction stage. Step S4 includes:

[0060] Step S4.1: Deploy the Unet segmentation model in the DSA image display.

[0061] Step S4.2: The blood vessels in the current frame image are segmented in real time during the subtraction stage using the Unet segmentation model to obtain the segmented blood vessel path map.

[0062] Step S4.3: Smooth the segmented vascular pathway map to eliminate segmented capillaries and retain the main blood vessels along the pathway from the interventional medical device to the site of examination. The main blood vessels include arteries and veins. The subtraction image before segmentation is shown below. Figure 2 As shown, the segmented blood vessel image after smoothing is as follows: Figure 3 As shown.

[0063] Step S5: The blood vessels segmented in the subtraction stage and the perspective image are fused to achieve vascular path navigation in the DSA image. Step S5 includes:

[0064] Step S5.1: Save and record the blood vessel images segmented in real time during the subtraction stage.

[0065] Step S5.2: Record the position of the feature point in the image as the first position, and the position of the feature point in the fluoroscopic stage image as the second position. Record the pixel coordinates of the first position and the second position respectively, and perform position matching on the pixel coordinates so that the blood vessel image segmented in real time during the subtraction stage coincides with the fluoroscopic stage image.

[0066] Step S5.3: Layer the image within the current DSA image range. The segmented blood vessel and fluoroscopic images are designated as the first layer and the second layer, respectively. Weights are assigned to the gray values ​​of the first and second layers at the same pixel points. The weights are then added together to obtain the gray value of the fused image. This results in a fused image of the blood vessel image segmented in real time during the subtraction stage and the fluoroscopic image, thereby enabling blood vessel path navigation in DSA images under low-dose angiography radiation.

[0067] Specifically, such as Figure 4 As shown, the position of feature points in the subtraction phase image is recorded as the first position, and the position of the iliac joint in the fluoroscopic phase image is recorded as the second position. The pixel coordinates (x1, y1) of the first position in the subtraction phase image and the pixel coordinates (x2, y2) of the second position in the fluoroscopic phase image are recorded respectively. The pixel coordinates are matched to ensure that the subtraction phase image and the fluoroscopic phase image overlap. After the subtraction phase image and the fluoroscopic phase image overlap, layering is performed within the current DSA image range. The transparency of the segmented blood vessel information is enhanced, serving as the first layer within the current DSA image range. The fluoroscopic phase image is used as the second layer within the current DSA image range. Based on the grayscale information of the first and second layers, weights are assigned to the grayscale values ​​of the first and second layers at the same pixel points. The weighted sum of the grayscale values ​​of the first and second layers is used as the grayscale value of the fused image, resulting in a fused image of the blood vessels segmented in the subtraction phase and the fluoroscopic view, thus achieving image fusion. Through image fusion, the relationship between the interventional device and the blood vessel position can be displayed in real time in the fluoroscopic view, enabling vascular path navigation in DSA images under low-dose angiography radiation.

[0068] The present invention also provides a surgical navigation system based on DSA images. Those skilled in the art can implement the surgical navigation system based on DSA images by executing the steps of the surgical navigation method based on DSA images. That is, the surgical navigation method based on DSA images can be understood as a preferred embodiment of the surgical navigation system based on DSA images.

[0069] A surgical navigation system based on DSA images provided by the present invention includes:

[0070] Module M1: Acquires real-time DSA images during surgery.

[0071] Module M2: Constructs and preprocesses the dataset, dividing it into training and test sets according to a preset ratio. For example, assuming the selected dataset contains 7000 images, it can be divided into training and test sets in a 6:1 ratio. Specifically, the dataset includes original images from the contrast agent injection stage of the subtraction angiography process, where the contrast agent flow direction is consistent with the blood flow direction. The preprocessing includes labeling the main blood vessels in the original images of the dataset and generating corresponding mask images.

[0072] Module M3: Utilizes a neural network algorithm to establish a Unet segmentation model. The model consists of an encoding part and a decoding part. The encoding part comprises a downsampling module, which reduces the image pixel resolution from high to low; the decoding part comprises an upsampling module, which increases the image resolution from low to high. The mathematical model is trained using the training set, and the weights between neurons are iteratively adjusted using the error gradient descent algorithm. The segmentation accuracy is verified on the test set using MeanIOU parameters, demonstrating the feasibility of the mathematical model.

[0073] Module M4: Deploys the Unet segmentation model and segments blood vessels in the current frame image in real time during the subtraction stage. Module M4 includes: Module M4.1: Deploys the Unet segmentation model on the DSA image display. Module M4.2: Segments blood vessels in the current frame image in real time during the subtraction stage using the Unet segmentation model, obtaining a segmented blood vessel path map. Module M4.3: Smooths the segmented blood vessel path map, eliminating segmented capillaries and retaining the main blood vessels along the pathway from the interventional medical device to the examination site. The main blood vessels include arteries and veins.

[0074] Module M5: This module fuses the blood vessels segmented during the subtraction phase and the fluoroscopic image to achieve vascular path navigation in DSA images. Module M5 includes: Module M5.1: Saving and recording the blood vessel images segmented in real-time during the subtraction phase. Module M5.2: Recording the positions of feature points in the image as the first position and the positions of feature points in the fluoroscopic image as the second position, recording the pixel coordinates of the first and second positions respectively, and matching these pixel coordinates to ensure that the blood vessel images segmented in real-time during the subtraction phase and the fluoroscopic images overlap. Module M5.3: Layering within the current DSA image area, recording the segmented blood vessels and the fluoroscopic images as the first layer and the second layer respectively, assigning weights to the grayscale values ​​of the first and second layers at the same pixel points, and summing these weights to obtain the grayscale value of the fused image. This results in a fused image of the blood vessel images segmented in real-time during the subtraction phase and the fluoroscopic images, thereby achieving vascular path navigation in DSA images under low-dose angiography.

[0075] According to the present invention, a computer-readable storage medium storing a computer program is provided, wherein when the computer program is executed by a processor, the steps of the surgical navigation method based on DSA images are implemented.

[0076] Step 1: Acquire real-time DSA images during surgery.

[0077] Step 2: Construct the dataset and preprocess it, then divide it into training and test sets according to a preset ratio.

[0078] Step 3: Using a neural network algorithm, a Unet segmentation model is established. The model consists of an encoding part and a decoding part. The encoding part consists of a downsampling module, which reduces the image pixel resolution from high to low; the decoding part consists of an upsampling module, which increases the image resolution from low to high. The mathematical model is trained using the training set, and the weights between neurons are iteratively adjusted according to the error gradient descent algorithm. The segmentation accuracy is verified on the test set using MeanIOU parameters, proving the feasibility of the mathematical model.

[0079] Step 4: Deploy the Unet segmentation model and segment blood vessels in the current frame image in real time during the subtraction stage.

[0080] Step 5: The blood vessels segmented in the subtraction stage and the perspective view are fused to achieve vascular path navigation in DSA images.

[0081] In addition, an electronic device provided by the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the surgical navigation method based on DSA images.

[0082] Those skilled in the art will understand that, in addition to implementing the system, apparatus, and their modules provided by this invention in purely computer-readable program code, the same program can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system, apparatus, and their modules provided by this invention can be considered a hardware component, and the modules included therein for implementing various programs can also be considered structures within the hardware component; alternatively, modules for implementing various functions can be considered both software programs implementing the method and structures within the hardware component.

[0083] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method of surgical navigation based on DSA images, characterized in that, The application relates to a method for realizing DSA image blood vessel path navigation under low-dose contrast radiation. The method comprises the following steps: Step S1: acquiring a DSA image in real-time surgery; Step S2: constructing a data set and performing pretreatment, and dividing the data set into a training set and a test set according to a preset proportion; Step S3: establishing an Unet segmentation model by using a neural network algorithm, training the Unet segmentation model by using the training set, and verifying the feasibility of the Unet segmentation model on the test set; Step S4: deploying the Unet segmentation model and segmenting blood vessels under a current frame image in a subtraction stage in real time; Step S5: performing image fusion on the blood vessels segmented in the subtraction stage and a perspective view, and realizing blood vessel path navigation in the DSA image. The step S5 comprises the following steps: Step S5.1: saving and recording the blood vessel image segmented in the subtraction stage in real time; Step S5.2: recording the position of a feature point in the image as a first position, recording the position of the feature point in the perspective stage image as a second position, recording the pixel coordinates of the first position and the second position respectively, and performing position matching on the pixel coordinates, so that the blood vessel image segmented in the subtraction stage in real time and the perspective stage image are overlapped; 2. The DSA image-based surgery navigation method according to claim 1, characterized in that, Step S5.3: performing layer stratification in the current DSA image range, recording the segmented blood vessels and the perspective stage image as a first layer and a second layer respectively, assigning a weight value to the gray values of the first layer and the second layer at the same pixel point, and adding the weight values to obtain the gray value of the fusion image, thereby obtaining the fusion image of the blood vessel image segmented in the subtraction stage in real time and the perspective stage image, and realizing DSA image blood vessel path navigation under low-dose contrast radiation. The data set comprises an original image in a contrast agent injection stage in a subtraction process, wherein the contrast agent flow direction is consistent with the blood flow direction. The pretreatment comprises marking main blood vessels in the original image in the data set to generate a corresponding mask image.

3. The DSA image-based surgery navigation method of claim 1, wherein, The Unet segmentation model comprises an encoding part and a decoding part, the encoding part comprises a down-sampling module for reducing the image pixel resolution from high to low, and the decoding part comprises an up-sampling module for increasing the image resolution from low to high. The step S4 comprises the following steps: Step S4.1: deploying the Unet segmentation model in a DSA image display; Step S4.2: segmenting blood vessels under a current frame image in a subtraction stage in real time by using the Unet segmentation model, and obtaining a segmented blood vessel path image; Step S4.3: performing smoothing processing on the segmented blood vessel path image, eliminating the segmented capillary blood vessels, and retaining the main blood vessels on the access path of the interventional medical instrument to the detection site.

4. A surgical navigation system based on DSA images, characterized by The main blood vessels comprise arterial blood vessels and venous blood vessels. The application further discloses a method for realizing DSA image blood vessel path navigation under low-dose contrast radiation. The method comprises the following steps: Module M1: acquiring a DSA image in real-time surgery; Module M2: constructing a data set and performing pretreatment, and dividing the data set into a training set and a test set according to a preset proportion; Module M3: establishing an Unet segmentation model by using a neural network algorithm, training the Unet segmentation model by using the training set, and verifying the feasibility of the Unet segmentation model on the test set; Module M4: deploying the Unet segmentation model and segmenting blood vessels under a current frame image in a subtraction stage in real time; Module M5: performing image fusion on the blood vessels segmented in the subtraction stage and a perspective view, and realizing blood vessel path navigation in the DSA image. Module M5: image fusion of the blood vessels segmented by the subtraction stage and the fluoroscopy image, to realize blood vessel path navigation in the DSA image; The module M5 comprises: Module M5.1: save and record the blood vessel image segmented in real time by the subtraction stage; Module M5.2: record the position of the feature point in the image as a first position, and record the position of the feature point in the fluoroscopy image as a second position, record the pixel coordinates of the first position and the second position respectively, and perform position matching on the pixel coordinates, so that the blood vessel image segmented in real time by the subtraction stage and the fluoroscopy image are overlapped; Module M5.3: layering in the current DSA image range, the segmented blood vessels and the fluoroscopy image are recorded as a first layer and a second layer respectively, and the gray values of the first layer and the second layer at the same pixel point are respectively assigned a weight value, and the weight values are added as the gray value of the fusion image, to obtain the fusion image of the blood vessel image segmented in real time by the subtraction stage and the fluoroscopy image, and to realize DSA image blood vessel path navigation under low-dose contrast radiation.

5. The DSA image-based surgery navigation system according to claim 4, wherein, The data set comprises an original image in the contrast agent injection stage in the subtraction process, wherein the contrast agent flow direction and the blood flow direction are consistent; The preprocessing comprises labeling the main blood vessels in the original image in the data set to generate a corresponding mask image; The Unet segmentation model comprises an encoding part and a decoding part, the encoding part comprises a down-sampling module to reduce the image pixel resolution from high to low, and the decoding part comprises an up-sampling module to increase the image resolution from low to high.

6. The DSA image-based surgery navigation system according to claim 4, wherein, The module M4 comprises: Module M4.1: deploy the Unet segmentation model in the DSA image display; Module M4.2: segment the blood vessels in the current frame image in real time by the Unet segmentation model in the subtraction stage to obtain a segmented blood vessel path image; Module M4.3: smooth the segmented blood vessel path image to eliminate the segmented capillary blood vessels and retain the main blood vessels on the access path of the interventional medical instrument to the detection site; The main blood vessels comprise arterial blood vessels and venous blood vessels.

7. A computer readable storage medium storing a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the surgical navigation method based on the DSA image according to any one of claims 1 to 3.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The computer program, when executed by a processor, implements the steps of the surgical navigation method based on the DSA image according to any one of claims 1 to 3.

Images