Carbon fiber guide wire positioning method and device for interventional operation

Abstract

The invention provides a carbon fiber guide wire positioning method and device for an interventional operation, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining multi-source data in the interventional operation in real time; performing time synchronization processing on the multi-source data to obtain synchronous image data and synchronous electromagnetic positioning data; performing feature extraction on the synchronous image data to obtain a first position feature; the spatial position of the carbon fiber guide wire is updated through the synchronous electromagnetic positioning data, and a second position feature is obtained; performing multi-source fusion through the first position feature and the second position feature to obtain a final position feature; and constructing a carbon fiber guide wire positioning network through the final position features, and positioning a carbon fiber guide wire in an interventional operation through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result. The problems that an existing carbon fiber guide wire positioning method is not clear enough in imaging, low in positioning precision and insufficient in real-time performance are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a method and device for positioning a carbon fiber guidewire used in interventional surgery. Background Art

[0002] Carbon fiber guidewire positioning plays a vital role in interventional surgery. It has high flexibility, small size and excellent mechanical properties, but due to its unique properties, positioning errors are prone to occur in electromagnetic positioning.

[0003] Due to the size of the carbon fiber guidewire, it is difficult to locate using electromagnetic sensors. Although electromagnetic markers can be fixed inside the carbon fiber guidewire using nano-adhesives or embedded designs, the signals generated by magnetic markers are weak due to the small diameter of the carbon nanowire, which makes accurate positioning more difficult. At the same time, external electromagnetic fields and other medical devices may interfere with the signal and affect positioning accuracy.

[0004] On the other hand, carbon fiber guide wires are usually made of carbon fiber or carbon nanomaterials, which themselves have low radioactive contrast under CT or X-rays. The X-ray absorption coefficient of carbon itself is much lower than that of metal materials. Therefore, in conventional X-ray or CT scans, carbon nano guide wires may be difficult to display clearly, resulting in unclear imaging and affecting positioning accuracy. And carbon nano guide wires may bend or deform during surgery. When using X-rays or CT for positioning, the three-dimensional morphology of the guide wire (especially the curved part) may be difficult to display accurately. Especially when passing through curved blood vessels or tortuous passages, the morphology of the guide wire will make its positioning more difficult. Therefore, there is an urgent need for a high-precision, real-time carbon fiber guide wire positioning method. Summary of the invention

[0005] The purpose of the present invention is to provide a method and device for positioning a carbon fiber guidewire in interventional surgery to improve the above-mentioned problem. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present application provides a carbon fiber guidewire positioning method for interventional surgery, comprising:

[0007] Acquire multi-source data in interventional surgery in real time, wherein the multi-source data includes image data and electromagnetic positioning data;

[0008] Performing time synchronization processing on the image data and the electromagnetic positioning data to obtain synchronized multi-source data, wherein the synchronized multi-source data includes synchronized image data and synchronized electromagnetic positioning data;

[0009] Performing feature extraction on the synchronous image data to obtain a first position feature;

[0010] The spatial position of the carbon fiber guide wire is updated by using the synchronous electromagnetic positioning data to obtain a second position feature;

[0011] Obtaining a final position feature by performing multi-source fusion of the first position feature and the second position feature;

[0012] A carbon fiber guide wire positioning network is constructed through the final position feature, and the carbon fiber guide wire in the interventional surgery is positioned through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result.

[0013] In a second aspect, the present application also provides a carbon fiber guidewire positioning device for use in interventional surgery, comprising:

[0014] An acquisition unit, used for acquiring multi-source data in interventional surgery in real time, wherein the multi-source data includes image data and electromagnetic positioning data;

[0015] A synchronization unit, used for performing time synchronization processing on the image data and the electromagnetic positioning data to obtain synchronized multi-source data, wherein the synchronized multi-source data includes synchronized image data and synchronized electromagnetic positioning data;

[0016] A first feature extraction unit, used for performing feature extraction on the synchronous image data to obtain a first position feature;

[0017] A second feature extraction unit is used to update the spatial position of the carbon fiber guide wire through the synchronous electromagnetic positioning data to obtain a second position feature;

[0018] a fusion unit, configured to perform multi-source fusion of the first position feature and the second position feature to obtain a final position feature;

[0019] The positioning unit is used to construct a carbon fiber guide wire positioning network through the final position feature, and to position the carbon fiber guide wire in the interventional surgery through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result.

[0020] The beneficial effects of the present invention are as follows: the present invention uses time synchronization processing of image data and electromagnetic positioning data through multi-source data fusion to ensure the temporal consistency of different data sources and reduce positioning errors. Secondly, combined with multi-resolution dense convolution submodules, the network can effectively capture the detailed information of the guide wire at different scales, improve the expression ability of image data, suppress background noise, enhance the signal quality of image features, and thus improve positioning accuracy. The electromagnetic positioning data compensates for the shortcomings of electromagnetic navigation in deep or obscured areas through the carbon fiber guide wire positioning network. In addition, by fusing the position features of multiple sources, the network can learn richer and more accurate spatial information, which improves the positioning accuracy and real-time performance of carbon fiber guide wires in complex anatomical environments.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a schematic flow chart of a method for positioning a carbon fiber guidewire used in an interventional surgery according to an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of the structure of the carbon fiber guide wire positioning network described in an embodiment of the present invention;

[0025] Figure 3 Schematic diagram of the structure of the first feature extraction branch described in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, 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 in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a carbon fiber guidewire positioning method for use in interventional surgery.

[0030] See also Figure 1 , the figure shows that the method includes step S100, step S200, step S300, step S400, step S500 and step S600.

[0031] Step S100: acquiring multi-source data in the interventional surgery in real time, wherein the multi-source data includes image data and electromagnetic positioning data;

[0032] In this embodiment, the image data may be real-time X-ray or CT images, and the electromagnetic positioning data is obtained through the magnetic markers on the carbon nanowires and an external paired electromagnetic sensor device. Specifically, by combining X-ray or CT images with electromagnetic positioning data, the deficiency of a single data source is made up.

[0033] Step S200: performing time synchronization processing on the image data and the electromagnetic positioning data to obtain synchronized multi-source data, wherein the synchronized multi-source data includes synchronized image data and synchronized electromagnetic positioning data;

[0034] In this embodiment, the image data and electromagnetic positioning data come from different devices, and the sampling frequencies and time points may be different. If time synchronization is not performed, there will be problems such as data mismatch, delayed or inaccurate real-time positioning, and multi-source data needs to be input as input for feature fusion at the same time. If the time steps of different modal data are not synchronized, it will make it difficult for the network to capture effective spatiotemporal correlation characteristics.

[0035] The step S200 includes:

[0036] Step S201: respectively obtaining timestamps of the image data and the electromagnetic positioning data;

[0037] Step S202: performing nearest neighbor matching on the image data and the electromagnetic positioning data based on the timestamp to obtain preliminary alignment data;

[0038] Step S203: performing time compensation on the preliminary aligned data by interpolation to obtain synchronized multi-source data.

[0039] In this embodiment, the nearest neighbor matching preliminary alignment can quickly find the closest value between the electromagnetic data and image data time points, control the data error within the time resolution range, and avoid significant misalignment problems caused by large differences in time points. The interpolation method can make fine adjustments to the preliminary aligned data, further reduce the residual error at the time point, and ensure high synchronization of the data. Compatible with different sampling frequencies, the low-frequency data is supplemented and seamlessly integrated with the high-frequency data, which helps to capture effective features during feature extraction and fusion, thereby improving positioning performance.

[0040] Step S300: extracting features from the synchronous image data to obtain a first position feature;

[0041] In this embodiment, a carbon fiber guide wire positioning network is constructed as follows: Figure 2 As shown, the carbon fiber guide wire positioning network includes two feature extraction branches, namely a first feature extraction branch and a second feature extraction branch, wherein the first feature extraction branch is used to extract the first position feature of the synchronized image data, and the second feature extraction branch is used to extract the second position feature of the synchronized electromagnetic positioning data, and ⊕ represents an addition operation.

[0042] The step S300 includes:

[0043] Step S301: constructing a feature extraction module, a feature fusion module and a timing module based on the synchronous image data;

[0044] like Figure 3 As shown, it is a structural diagram of the first feature extraction branch, where UP represents upsampling and ⊕ represents addition operation.

[0045] Step S302: extracting features from the synchronous image data by the feature extraction module to obtain preliminary position features;

[0046] The step S302 includes:

[0047] Step A100: extracting features from the synchronized image data through a convolution submodule to obtain a first extracted feature;

[0048] In this embodiment, due to the high transparency of the carbon fiber guide wire, some auxiliary technologies are used in interventional surgery to enhance the visibility of the guide wire, such as adding fluorescence or other special markers or embedding trace radioactive imaging materials to enhance visibility in low-contrast images, which appear as linear structures in the image. Therefore, this local characteristic is effectively captured by convolution operation. The convolution submodule can clearly extract the guide wire features, including extracting low-level information such as the edge and brightness gradient of the carbon fiber guide wire. At the same time, background interference can be reduced, and the interference of background structures (such as bones and soft tissues) can be preliminarily filtered.

[0049] Step A200: extracting the first extracted features through a plurality of dense convolution submodules in sequence to obtain a plurality of dense features of different resolutions, wherein every two adjacent dense convolution submodules are connected by a sampling submodule, and the sampling submodule includes a batch normalization, a convolution layer, and an average pooling layer connected in sequence;

[0050] In this step, each dense convolution submodule contains a different number of fused convolution layers. In this embodiment, for lightweight design, the number of fused convolution layers in multiple dense convolution submodules is set to 4, 8, 12 and 8. At the same time, the sampling submodule is used to reduce the number of feature channels and further downsample the feature map.

[0051] Step A300: taking a plurality of dense features of different resolutions together as preliminary position features output by the feature extraction module.

[0052] In step S302, the dense convolution submodule performs feature extraction steps as follows:

[0053] Step B100: Obtaining input features of the dense convolution submodule;

[0054] Step B200: performing multi-scale perception on the input features of the dense convolution submodule through a plurality of sequentially connected fused convolution layers to obtain a first convolution feature, wherein the fused convolution layer comprises sequentially connected dimensionality reduction convolution blocks and fused convolution blocks;

[0055] Step B300: enhancing the global perception capability of the first convolution feature through a shared perceptron to obtain the output feature of the dense convolution submodule.

[0056] In this embodiment, since the features of the carbon fiber guide wire are relatively small in the image data and the importance of information at different scales varies, the overall position information needs to be considered during positioning, and simple local features are prone to cause positioning errors. Therefore, a dense convolution submodule is constructed for feature extraction.

[0057] The input of each fused convolution layer in the dense convolution submodule comes from the output of all previous layers, and the output of each layer is also passed to all subsequent layers, which enhances the propagation and reuse of features, reduces feature redundancy, and can extract information from all previous layers, improving feature diversity. Since each layer only needs to learn a small number of new features, most of the features can be reused from the previous layers, reducing the number of parameters, and the output of each layer contains the feature information of all previous layers, forming a multi-level feature fusion.

[0058] At the same time, each fused convolution layer sets a dimension reduction convolution block, which is a 1x1 convolution, to reduce the number of channels of the input feature map and reduce the amount of calculation.

[0059] The expression of the fused convolutional layer is:

[0060] F i =SE(α1·f dilated (X di )+α2·f depthwise (X di )+α3·f adaptive (X di ))

[0061] X di =Conv(f li ([F1,F2,…,F i-1 ]))

[0062] In the formula, F n represents the output feature of the nth fused convolutional layer, n = 1, 2, …, i, n represents the number of fused convolutional layers, i represents the index parameter of the fused convolutional layer, SE(·) represents the channel attention mechanism, α1, α2 and α3 all represent weight factors, and f dilated (·) represents the dilated convolution, f depthwise (·) represents depthwise separable convolution, f adaptive (·) represents adaptive convolution, X di represents the input feature of the i-th fused convolutional layer, f li (·) represents the transformation function of the i-th fused convolutional layer, and Conv(·) represents the dimension reduction convolution operation.

[0063] In this embodiment, the fused convolution block includes dilated convolution, depthwise separable convolution and adaptive convolution. These three convolution methods can effectively capture multi-scale features, and their respective characteristics can complement each other, thereby enhancing the perception ability of the network, especially in processing tasks with multi-scale features such as carbon fiber guide wire positioning, which can significantly improve the positioning performance.

[0064] Step S303: fusing the preliminary position features through the feature fusion module to obtain fused position features;

[0065] The step S303 includes:

[0066] Step C100: upsampling and fusion of multiple dense features in turn according to the resolution, to obtain preliminary fusion features containing low-level details and high-level semantic information;

[0067] In this embodiment, the high-resolution features contain more spatial details, and the low-resolution features have stronger global semantic information. The upsampling operation can restore the low-resolution features to a higher resolution, aligning them with the high-resolution features, thereby achieving better fusion. Multi-level feature fusion helps to capture both the detail information (such as edge information) and context information (such as surrounding tissue structure) of the carbon fiber guide wire.

[0068] In guidewire positioning, high-resolution features help identify the boundaries and shapes of carbon fiber guidewires, while low-resolution features provide overall spatial position and semantic clues. Through fusion, the position of carbon fiber guidewires in complex backgrounds can be accurately located.

[0069] Step C200: suppressing background noise of the preliminary fusion feature through a self-attention mechanism to obtain a weighted fusion feature;

[0070] In this embodiment, the carbon fiber guide wire is usually small and easily disturbed by the surrounding complex background (such as blood vessels, soft tissues, etc.). The self-attention mechanism can adaptively give a higher weight to the area where the carbon fiber guide wire is located. By focusing on the relevant features of the carbon fiber guide wire, the useless interference in the complex background is reduced, and the carbon fiber guide wire is effectively distinguished from the background, such as the contrast agent flowing in the blood vessel, the reflection of the surgical instrument, etc., to improve the accuracy of the positioning of the carbon fiber guide wire.

[0071] Step C300: performing nonlinear mapping processing on the weight fusion feature through a shared perceptron to obtain a fused position feature.

[0072] In this embodiment, in the carbon fiber guide wire positioning task, complex structures may lead to nonlinear relationships between features, and the shared perceptron can learn these complex relationships and improve the expressiveness of the features, while reducing the computational cost through parameter sharing while retaining the global perception capability.

[0073] Step S304: learning the context information of the fused position feature through the timing module to obtain a first position feature, wherein the timing module adopts a gated recurrent unit.

[0074] In this embodiment, during interventional surgery, the position and movement of the carbon fiber guidewire are continuously changing, and timing information is crucial for the positioning of the carbon fiber guidewire. The timing module can effectively learn the dynamic information of the position characteristics changing over time, and can predict the current position of the carbon fiber guidewire based on the historical positioning information, thereby improving the positioning accuracy and stability, especially during rapid operations.

[0075] Step S400: updating the spatial position of the carbon fiber guide wire through the synchronous electromagnetic positioning data to obtain a second position feature;

[0076] In this embodiment, electromagnetic positioning can provide the real-time position of the carbon fiber guide wire in three-dimensional space, but due to the influence of factors such as electromagnetic interference, the position may drift. Therefore, by updating the spatial position and filtering out noise, a more accurate spatial position feature is obtained to ensure the accuracy and stability of the carbon fiber guide wire position update.

[0077] Specifically, through Figure 2 The second feature extraction branch obtains the second position feature, updates the spatial position through the updating module, and encodes the spatial position through the spatial position encoding module, and finally obtains the second position feature through the shared perceptron.

[0078] The step S400 includes:

[0079] Step S401: updating the position of the synchronous electromagnetic positioning data by Kalman filtering to obtain an updated spatial position of the carbon fiber guide wire;

[0080] In this embodiment, during interventional surgery, the position of the carbon fiber guide wire needs to be updated with high frequency and low latency. Kalman filtering can filter out noise in the synchronous electromagnetic positioning data to ensure the accuracy and stability of the carbon fiber guide wire position update.

[0081] Step S402: performing spatial position coding on the updated spatial position of the carbon fiber guide wire to obtain a position coding feature;

[0082] In this embodiment, after obtaining the updated spatial position, the information must be converted into a feature representation suitable for further processing. Spatial position encoding can provide more effective information for subsequent network processing by converting position data into features suitable for neural network processing.

[0083] At the same time, spatial position encoding can fuse the guidewire position information with other features to enhance the network's understanding of spatial information.

[0084] Step S403: performing feature mapping on the position encoding feature through a shared perceptron to obtain a second position feature.

[0085] In this embodiment, the shared perceptron processes input features by sharing parameters, thereby enhancing the perception capability of the entire spatial environment and avoiding local overfitting.

[0086] Step S500: performing multi-source fusion of the first position feature and the second position feature to obtain a final position feature;

[0087] In this embodiment, in the task of positioning the carbon fiber guidewire in interventional surgery, the data sources come from different modalities, such as image data and electromagnetic positioning data. In order to ensure that the information of each data source can be fully utilized, these multi-source data are effectively fused to improve the accuracy and stability of the final positioning result.

[0088] The step S501 includes:

[0089] Step S502: normalizing the first position feature and the second position feature to obtain a first normalized feature and a second normalized feature;

[0090] In this embodiment, the first position feature and the second position feature come from different modes, and their value ranges and scales are different. Normalization processing can unify these features to the same scale, thereby reducing the deviation caused by scale differences. And after normalization, the features can be smoother in the subsequent fusion and learning process, avoiding a certain feature from having too much influence on network training.

[0091] Step S503: performing feature concatenation on the first normalized feature and the second normalized feature to obtain a position vector;

[0092] Step S504: cross-fusion the position vectors through a cross-attention mechanism to obtain a cross-position vector;

[0093] In this embodiment, the cross-attention mechanism can weight different features in a feature space in an adaptive manner, and use the relationship between each feature to select the most important information for fusion. The cross-attention mechanism is more effective than a simple weighted average or concatenation method because it can learn the relevance of different features in a specific task and automatically adjust the fusion weight.

[0094] Step S505: performing feature mapping on the cross position vector through a shared perceptron to obtain a final position feature.

[0095] In this embodiment, the cross position vector is further processed by a shared perceptron, mapped to a higher dimensional space through nonlinear transformation, and potential complex relationships are mined to generate the final high-quality position feature, i.e., the final position feature. At the same time, the generalization ability of the network is enhanced by sharing parameters, and it has good adaptability and stability between different input data.

[0096] Step S600: constructing a carbon fiber guide wire positioning network through the final position feature, and positioning the carbon fiber guide wire in the interventional surgery through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result.

[0097] In this embodiment, different branches in the carbon fiber guide wire positioning network are shared for training, that is, different tasks are shared for training, and information is transferred between different tasks, thereby improving the comprehensive ability of the network. At the same time, a joint loss function is set to balance the learning objectives between different tasks.

[0098] In summary, the present invention aims to solve the problems of high flexibility, small size, low contrast and weak electromagnetic signal of carbon fiber guidewires during positioning in interventional surgery by using technologies such as time synchronization, feature extraction, noise suppression, multi-source fusion and timing modeling to solve the problems of unclear imaging, low positioning accuracy and insufficient real-time performance of carbon nano guidewires during positioning in interventional surgery.

[0099] Specifically, the present invention fuses multi-source data, learns the position features of different data sources through the carbon fiber guidewire positioning network, and uses the cross-attention mechanism to optimize the interaction between the two data sources during the feature fusion process, so that the network can learn richer and more accurate spatial information. It improves the positioning accuracy and real-time performance of carbon fiber guidewires in interventional surgery, and can make precise adjustments during dynamic surgery, providing doctors with more reliable positioning support.

[0100] Embodiment 2:

[0101] This embodiment provides a carbon fiber guidewire positioning device for use in interventional surgery, the device comprising:

[0102] An acquisition unit, used for acquiring multi-source data in interventional surgery in real time, wherein the multi-source data includes image data and electromagnetic positioning data;

[0103] A synchronization unit, used for performing time synchronization processing on the image data and the electromagnetic positioning data to obtain synchronized multi-source data, wherein the synchronized multi-source data includes synchronized image data and synchronized electromagnetic positioning data;

[0104] A first feature extraction unit, used for performing feature extraction on the synchronous image data to obtain a first position feature;

[0105] A second feature extraction unit is used to update the spatial position of the carbon fiber guide wire through the synchronous electromagnetic positioning data to obtain a second position feature;

[0106] a fusion unit, configured to perform multi-source fusion of the first position feature and the second position feature to obtain a final position feature;

[0107] The positioning unit is used to construct a carbon fiber guide wire positioning network through the final position feature, and to position the carbon fiber guide wire in the interventional surgery through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result.

[0108] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0110] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A carbon fiber guidewire positioning method for interventional surgery, characterized in that: include: Acquire multi-source data in interventional surgery in real time, wherein the multi-source data includes image data and electromagnetic positioning data; Performing time synchronization processing on the image data and the electromagnetic positioning data to obtain synchronized multi-source data, wherein the synchronized multi-source data includes synchronized image data and synchronized electromagnetic positioning data; Performing feature extraction on the synchronous image data to obtain a first position feature; The spatial position of the carbon fiber guide wire is updated by using the synchronous electromagnetic positioning data to obtain a second position feature; Obtaining a final position feature by performing multi-source fusion of the first position feature and the second position feature; A carbon fiber guide wire positioning network is constructed through the final position feature, and the carbon fiber guide wire in the interventional surgery is positioned through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result.

2. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 1, characterized in that , the said performing time synchronization processing on the said image data and electromagnetic positioning data to obtain synchronized multi-source data, comprises: respectively obtaining time stamps of the image data and the electromagnetic positioning data; Performing nearest neighbor matching on the image data and the electromagnetic positioning data based on the timestamp to obtain preliminary alignment data; The preliminary aligned data are time compensated by interpolation to obtain synchronized multi-source data.

3. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 1, characterized in that , said extracting features from the synchronous image data to obtain a first position feature, including: Constructing a feature extraction module, a feature fusion module and a timing module based on the synchronous image data; Extracting features from the synchronized image data by the feature extraction module to obtain preliminary position features; The preliminary position features are subjected to feature fusion by the feature fusion module to obtain fused position features; The context information of the fused position feature is learned through the timing module to obtain the first position feature, and the timing module adopts a gated recurrent unit.

4. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 3, characterized in that , said extracting features from the synchronous image data by the feature extraction module to obtain preliminary position features, including: Performing feature extraction on the synchronized image data through a convolution submodule to obtain a first extracted feature; The first extracted features are sequentially subjected to a plurality of dense convolution submodules for feature extraction to obtain a plurality of dense features of different resolutions, wherein every two adjacent dense convolution submodules are connected by a sampling submodule, and the sampling submodule includes a batch normalization layer, a convolution layer, and an average pooling layer connected in sequence; A plurality of dense features of different resolutions are used together as preliminary position features output by the feature extraction module.

5. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 4, characterized in that ,The steps of feature extraction by the dense convolution submodule are: Obtaining input features of the dense convolution submodule; The input features of the dense convolution submodule are subjected to multi-scale perception through a plurality of sequentially connected fused convolution layers to obtain a first convolution feature, wherein the fused convolution layer comprises sequentially connected dimensionality reduction convolution blocks and fused convolution blocks; The global perception capability of the first convolution feature is enhanced by a shared perceptron to obtain the output feature of the dense convolution submodule.

6. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 5, characterized in that , the expression of the fused convolutional layer is: F i =SE(α1·f dilated (X di )+α2·f depthwise (X di )+α3·f adaptive (X di )) X di =Conv(f li ([F1,F2,…,F i-1 ])) In the formula, F n represents the output feature of the nth fused convolutional layer, n = 1, 2, …, i, n represents the number of fused convolutional layers, i represents the index parameter of the fused convolutional layer, SE(·) represents the channel attention mechanism, α1, α2 and α3 all represent weight factors, and f dilated (·) represents the dilated convolution, f depthwise (·) represents depthwise separable convolution, f adaptive (·) represents adaptive convolution, X di represents the input feature of the i-th fused convolutional layer, f li (·) represents the transformation function of the i-th fused convolutional layer, and Conv(·) represents the dimension reduction convolution operation.

7. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 4, characterized in that , said fusing the preliminary position features through the feature fusion module to obtain fused position features, including: Upsample and fuse multiple dense features in turn according to the resolution to obtain preliminary fused features containing low-level details and high-level semantic information; Suppressing background noise of the preliminary fusion feature through a self-attention mechanism to obtain a weighted fusion feature; The weight fusion feature is subjected to nonlinear mapping processing through a shared perceptron to obtain a fused position feature.

8. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 1, characterized in that , the spatial position of the carbon fiber guide wire is updated by the synchronous electromagnetic positioning data to obtain a second position feature, including: The synchronous electromagnetic positioning data is updated by Kalman filtering to obtain an updated spatial position of the carbon fiber guide wire; Performing spatial position encoding on the updated spatial position of the carbon fiber guide wire to obtain a position encoding feature; The position encoding feature is feature mapped through a shared perceptron to obtain a second position feature.

9. The method for positioning a carbon fiber guidewire in an interventional surgery according to claim 1, characterized in that , the multi-source fusion of the first position feature and the second position feature to obtain the final position feature includes: Normalizing the first position feature and the second position feature to obtain a first normalized feature and a second normalized feature; Perform feature concatenation on the first normalized feature and the second normalized feature to obtain a position vector; Cross-fusion is performed on the position vectors through a cross-attention mechanism to obtain a cross-position vector; The cross position vector is feature mapped through a shared perceptron to obtain a final position feature.

10. A carbon fiber guidewire positioning device for use in interventional surgery, characterized in that: include: An acquisition unit, used for acquiring multi-source data in interventional surgery in real time, wherein the multi-source data includes image data and electromagnetic positioning data; A synchronization unit, used for performing time synchronization processing on the image data and the electromagnetic positioning data to obtain synchronized multi-source data, wherein the synchronized multi-source data includes synchronized image data and synchronized electromagnetic positioning data; A first feature extraction unit, used for performing feature extraction on the synchronous image data to obtain a first position feature; A second feature extraction unit is used to update the spatial position of the carbon fiber guide wire through the synchronous electromagnetic positioning data to obtain a second position feature; a fusion unit, configured to perform multi-source fusion of the first position feature and the second position feature to obtain a final position feature; The positioning unit is used to construct a carbon fiber guide wire positioning network through the final position feature, and to position the carbon fiber guide wire in the interventional surgery through the carbon fiber guide wire positioning network to obtain a carbon fiber guide wire positioning result.

Images