Method, device, electronic device and storage medium for forming microcatheter shaping needle

Abstract

The present invention discloses a method, device, electronic device, and storage medium for forming a microcatheter shaping needle. The method comprises: determining the morphological data of a target blood vessel in a medical image; simulating the shape data of a microcatheter entering the target blood vessel according to the morphological data; inputting the shape data into a pre-trained shaping needle morphological model, and determining the morphological data of the shaping needle according to the shaping needle morphological model. The present invention simulates the shape data of a microcatheter entering the target blood vessel according to the morphological data of the target blood vessel in a medical image, and combines the shaping needle morphological model obtained based on deep learning, which can assist in quickly and accurately planning the morphological data of a shaping needle that matches the target blood vessel, and then can achieve accurate microcatheter shaping based on the shaping needle.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a method, device, electronic equipment and storage medium for forming a microcatheter molding needle. Background Art

[0002] Intracranial aneurysms are local bulging of intracranial blood vessels caused by vascular endothelial damage, with a prevalence of about 5%-8% in the adult population. Subarachnoid hemorrhage (SAH) caused by rupture of intracranial aneurysms is one of the important causes of hemorrhagic stroke, with a very high disability and mortality rate. Interventional embolization refers to entering the aneurysm through the blood vessels and using a microcatheter to fill the aneurysm with special materials (such as spring coils) to prevent blood from entering the aneurysm, thereby occluding the aneurysm and preventing it from rupture. Interventional embolization has become an important means of clinically treating unruptured aneurysms due to its characteristics of low trauma, fast recovery and good effect. When performing interventional embolization of intracranial aneurysms, the operator must bend the shaping needle according to the location and angle of the aneurysm, the shape of the parent artery and the material properties of the microcatheter, and then put the microcatheter on the periphery of the shaping needle and perform shaping. Good microcatheter shaping is more conducive to the appropriate distribution of the coil in the aneurysm, which is the key and difficulty of interventional embolization of intracranial aneurysms and is also the research direction of neurointerventional doctors.

[0003] In the prior art, microcatheter shaping is performed with the aid of a shaping needle, and the position of the shaping needle mainly depends on the rich knowledge and experience of clinicians. There is a lack of accurate and effective auxiliary design solutions, so accurate microcatheter shaping cannot be achieved. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the above-mentioned defects in the prior art and to provide a method, device, electronic device and storage medium for forming a microcatheter shaping needle.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] In a first aspect, a method for forming a microcatheter shaping needle is provided, comprising:

[0007] determining morphological data of a target blood vessel in a medical image;

[0008] Simulating the shape data of the microcatheter entering the target blood vessel according to the morphological data;

[0009] The shape data is input into a pre-trained shaping needle morphology model, and the morphology data of the shaping needle is determined according to the shaping needle morphology model.

[0010] Optionally, determining morphological data of a target blood vessel in a medical image includes:

[0011] Performing image segmentation processing on the medical image to determine a region where a target blood vessel in the medical image is located;

[0012] The morphological data is determined according to the image segmentation result.

[0013] Optionally, performing image segmentation processing on the medical image includes:

[0014] determining a centerline of a blood vessel in the medical image;

[0015] Densely sampling the medical image along the center line to obtain a number of candidate frames, and removing redundant candidate frames;

[0016] The target blood vessels in the candidate frame after removing redundancy are segmented based on the trained segmentation model.

[0017] Optionally, performing image segmentation processing on the medical image includes:

[0018] Acquire a first endpoint and a second endpoint marked on a blood vessel in the medical image; the target blood vessel is located between the first endpoint and the second endpoint;

[0019] determining a centerline of a target blood vessel between the first endpoint and the second endpoint;

[0020] The region where the target blood vessel is located is segmented according to the center line and based on the trained segmentation model.

[0021] Optionally, the morphological data includes a three-dimensional model and an inflow angle of the target blood vessel; simulating the shape data of the microcatheter entering the target blood vessel according to the morphological data includes:

[0022] determining a target center point in the three-dimensional model of the target blood vessel;

[0023] Extending in the reverse direction from the target center point along the inflow angle direction, and sequentially determining a plurality of contact points where the extension curve contacts the blood vessel wall represented by the three-dimensional model;

[0024] When the multiple contact points include a target contact point or the distance between the extension curve and the marking point on the centerline of the target blood vessel is less than a first distance threshold, the shape data of the microcatheter is determined according to the three-dimensional coordinates of the multiple contact points.

[0025] Optionally, determining the movement data according to the three-dimensional coordinates of the multiple contact points includes:

[0026] Fitting the three-dimensional coordinates of the multiple contact points to obtain a spline curve;

[0027] Performing smoothing on the spline curve;

[0028] The shape data is determined according to the smoothed spline curve.

[0029] Optionally, the shaping needle morphology model includes a feature extraction sub-model and a shaping simulation sub-model; inputting the shape data into a pre-trained shaping needle morphology model, and determining the morphology data of the shaping needle according to the shaping needle morphology model, including:

[0030] Inputting the shape-shifting data into the feature extraction sub-model, so that the feature extraction sub-model performs feature extraction on the shape-shifting data;

[0031] The feature extraction result output by the feature extraction sub-model is input into the shaping simulation sub-model to determine the morphological data of the shaping needle.

[0032] Optionally, the method further comprises:

[0033] Generate a mesh model of the shaping needle according to the morphological data of the shaping needle;

[0034] Sculpt the pins to match the mesh model.

[0035] In a second aspect, a device for forming a microcatheter shaping needle is provided, comprising:

[0036] A first determination module, used to determine morphological data of a target blood vessel in a medical image;

[0037] A simulation module, used for simulating the shape data of the microcatheter entering the target blood vessel according to the morphological data;

[0038] The second determination module is used to input the shape data into a pre-trained shaping needle morphology model, and determine the morphology data of the shaping needle according to the shaping needle morphology model.

[0039] Optionally, the first determining module includes:

[0040] a segmentation unit, configured to perform image segmentation processing on the medical image to determine a region where a target blood vessel in the medical image is located;

[0041] A determination unit is used to determine the morphological data according to the image segmentation result.

[0042] Optionally, the segmentation unit is specifically used for:

[0043] determining a centerline of a blood vessel in the medical image;

[0044] Densely sampling the medical image along the center line to obtain a number of candidate frames, and removing redundant candidate frames;

[0045] Based on the trained segmentation model, the candidate boxes after redundant removal are detected and segmented.

[0046] Optionally, the segmentation unit is specifically used for:

[0047] Acquire a first endpoint and a second endpoint marked on a blood vessel in the medical image; the target blood vessel is located between the first endpoint and the second endpoint;

[0048] determining a centerline of a target blood vessel between the first endpoint and the second endpoint;

[0049] The region where the target blood vessel is located is segmented according to the center line and based on the trained segmentation model.

[0050] Optionally, the simulation module is specifically used for:

[0051] a point determination unit, configured to determine a target center point in the three-dimensional model of the target blood vessel, and to extend from the target center point in the reverse direction along the inflow angle direction, and to sequentially determine a plurality of contact points where the extension curve contacts the blood vessel wall represented by the three-dimensional model;

[0052] The shape determination unit is used to determine the shape data of the microcatheter according to the three-dimensional coordinates of the multiple contact points when the multiple contact points include a target contact point or the distance between the extension curve and the marking point on the center line of the target blood vessel is less than a first distance threshold.

[0053] Optionally, the walking shape determining unit is specifically used for:

[0054] Fitting the three-dimensional coordinates of the multiple contact points to obtain a spline curve;

[0055] Performing smoothing on the spline curve;

[0056] The shape data is determined according to the smoothed spline curve.

[0057] Optionally, the shaping needle morphology model includes a feature extraction sub-model and a shaping simulation sub-model; the shaping data is input into a pre-trained shaping needle morphology model, and the second determination module includes:

[0058] An input unit, used for inputting the shape-shifting data into the feature extraction sub-model, so that the feature extraction sub-model performs feature extraction on the shape-shifting data;

[0059] A determination unit is used to input the feature extraction result output by the feature extraction sub-model into the shaping simulation sub-model to determine the morphological data of the shaping needle.

[0060] Optionally, the device further comprises:

[0061] A generating module, used for generating a mesh model of the shaping needle according to the morphological data of the shaping needle;

[0062] The shaping module is used to shape the shaping pins to match the mesh model.

[0063] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for forming a microcatheter molding needle as described in any one of the above items is implemented.

[0064] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for forming a microcatheter molding needle as described in any one of the above items is implemented.

[0065] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0066] The positive progressive effect of the present invention is that the present invention simulates the path data of the microcatheter entering the target blood vessel according to the morphological data of the target blood vessel in the medical image, and combined with the shaping needle morphological model obtained based on deep learning, it can assist in quickly and accurately planning the morphological data of the shaping needle that is compatible with the target blood vessel, and then accurate microcatheter shaping can be achieved based on the shaping needle. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A flow chart of a method for forming a microcatheter molding needle provided by an exemplary embodiment of the present invention;

[0068] Figure 2 for Figure 1 A flowchart of an implementation method of step 101;

[0069] Figure 3a for Figure 1 A flowchart of another implementation of step 101;

[0070] Figure 3b for Figure 1 A flowchart of another implementation of step 101;

[0071] Figure 4 for Figure 1 A flowchart of an implementation method of step 102;

[0072] Figure 5 A schematic diagram of the effect of determining the shape data in a method for forming a micro-catheter shaping needle provided by an exemplary embodiment of the present invention;

[0073] Figure 6aA schematic diagram of a morphological curve represented by morphological data of a shaping needle obtained by a method for forming a microcatheter shaping needle provided by an exemplary embodiment of the present invention;

[0074] Figure 6b A schematic diagram of a network architecture of a shaping needle morphology model used in a method for forming a microcatheter shaping needle provided by an exemplary embodiment of the present invention;

[0075] Figure 6c A schematic diagram of a network architecture of an RNN sub-model provided for an exemplary embodiment of the present invention;

[0076] Figure 7 A schematic diagram of a module of a device for forming a microcatheter shaping needle provided by an exemplary embodiment of the present invention;

[0077] Figure 8 The present invention is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0078] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0079] Figure 1 A flowchart of a method for forming a microcatheter molding needle provided by an exemplary embodiment of the present invention, the method comprising the following steps:

[0080] Step 101: Determine morphological data of a target blood vessel in a medical image.

[0081] Among them, the medical image is an image containing a target blood vessel, which can be a medical image of various modalities, including but not limited to CTA (CTangiography) images, MRA (MR angiography) images, DSA (Digital subtraction angiography) images, DR (Digital Radiography) images, etc., and the embodiment of the present invention does not specifically limit this.

[0082] In one embodiment, see Figure 2 , step 101 comprises:

[0083] Step 101 - 1 : performing image segmentation processing on the medical image to determine the region where the target blood vessel in the medical image is located.

[0084] The so-called target blood vessel may be a section of a blood vessel containing a lesion, such as a section of a blood vessel containing an aneurysm; the target blood vessel may also be an arbitrarily designated section of a blood vessel.

[0085] In one embodiment, a first image segmentation process is performed on the medical image to determine the region where the blood vessel is located, and then a second image segmentation process is performed on the region where the blood vessel is located to determine the region where the target blood vessel is located.

[0086] Different image segmentation algorithms can be used for medical images of different modalities. For example, for 3D-DSA medical images, threshold segmentation and Hessian enhancement algorithms can be used to determine the area where the blood vessels are located. Image segmentation can also be achieved using a trained model. For example, the medical image is input into a pre-trained image segmentation model to determine the area where the blood vessels are located, where the image segmentation model is obtained by training a neural network using training samples labeled with blood vessel area information.

[0087] In one embodiment, the region where the target blood vessel is located is determined based on automatic segmentation. For details, see Figure 3a Based on the segmentation result of the first image segmentation processing of the medical image, the three-dimensional model of the blood vessel in the medical image is determined, and the three-dimensional model of the blood vessel in the medical image is refined, and the center line L of the blood vessel in the medical image is determined, and the medical image is densely sampled along the center line L to obtain a plurality of candidate frames 31, and the redundant candidate frames are removed, and the target blood vessel in the candidate frame after the redundant removal is segmented based on the trained segmentation model, and the region where the target blood vessel in the medical image is located is determined to obtain the three-dimensional model of the target blood vessel. Among them, the segmentation model can be, but is not limited to, based on deep learning and using training samples annotated with information about the region where the target blood vessel is located to train a neural network (such as a V-Net network). The V-Net network can output the three-dimensional model of the target blood vessel based on the image segmentation result.

[0088] In one embodiment, redundant candidate boxes are removed based on a non-maximum suppression (NMS) algorithm, which can effectively remove redundant candidate boxes with high accuracy, thereby improving the accuracy of image segmentation.

[0089] In one embodiment, redundant candidate boxes are removed based on a k-means clustering algorithm. The algorithm is simple to implement and highly efficient, thereby improving the efficiency of image segmentation.

[0090] In one embodiment, the region where the target blood vessel is located is determined based on user input. For details, see Figure 3b, obtain a first endpoint B and a second endpoint C marked on a blood vessel in a medical image, a target blood vessel A on the blood vessel is located between the first endpoint B and the second endpoint C, determine the centerline of the target blood vessel between the first endpoint B and the second endpoint C, refine the three-dimensional model of the blood vessel between the first endpoint B and the second endpoint C to determine the centerline of the target blood vessel, segment the target blood vessel according to the centerline and based on a trained segmentation model, and determine the region where the target blood vessel is located in the medical image. The segmentation model can be, but is not limited to, trained based on deep learning and using training samples marked with information about the region where the target blood vessel is located to train a neural network (e.g., a V-Net network). The V-Net network can output a three-dimensional model of the target blood vessel based on the image segmentation result.

[0091] Step 101 - 2: Determine morphological data according to the image segmentation result.

[0092] According to the image segmentation results, the three-dimensional model of the target blood vessel, the centerline of the target blood vessel, and the morphological data such as the morphological parameters required for clinical use can be determined. Among them, the morphological parameters include at least one of the following parameters: tumor neck, maximum diameter, tumor height, tumor width, inflow angle, etc.

[0093] Step 102: Simulate the path data of the microcatheter entering the target blood vessel according to the morphological data.

[0094] In one embodiment, see Figure 4 , step 102 comprises the following steps:

[0095] Step 102 - 1 : Determine a target center point in the three-dimensional model of the target blood vessel.

[0096] The target center point may be the center point of a lesion on the blood vessel, or the center point of an arbitrarily designated area on the blood vessel.

[0097] In one embodiment, the point marked by the user in the three-dimensional model can be determined as the lesion center point (aneurysm anchor point), see Figure 5 Point A in .

[0098] In one embodiment, a pre-trained lesion center determination model is used to identify the lesion center; the lesion center determination model is obtained by training a neural network using training samples marked with the lesion center.

[0099] Step 102-2: Extending from the target center point in the reverse direction along the inflow angle direction, and sequentially determining a plurality of contact points where the extension curve contacts the blood vessel wall represented by the three-dimensional model.

[0100] Step 102-2 simulates the movement of the microcatheter after entering the target blood vessel. During the simulation of the movement, the contact points need to be determined in sequence in combination with the microcatheter material and relevant requirements of clinical treatment. For example, the extension direction of the extension curve is adjusted based on the microcatheter material and relevant requirements of clinical treatment.

[0101] Step 102-3: when the multiple contact points include the target contact point or the distance between the extension curve and the marking point on the centerline of the target blood vessel is less than a first distance threshold, determine the microcatheter shape data according to the three-dimensional coordinates of the multiple contact points.

[0102] The target contact point is a contact point whose distance from the marked point on the centerline is less than the second distance threshold; the marked point is a point marked by the user on the centerline of the target blood vessel. The first distance threshold and the second distance threshold can be set according to actual conditions, and the first distance threshold and the second distance threshold can be set to be the same or different.

[0103] See also Figure 5 , taking point A as the center point of the lesion and point B as the marking point on the center line as an example, the process of determining the contact point is explained, extending from point A in the reverse direction along the inflow angle until the extension curve S contacts the blood vessel wall represented by the three-dimensional model, and determining contact point 1; extending from contact point 1 in the reverse direction along the inflow angle until the extension curve S contacts the blood vessel wall represented by the three-dimensional model, and determining contact point 2; extending from contact point 2 in the reverse direction along the inflow angle until the extension curve S contacts the blood vessel wall represented by the three-dimensional model, and determining contact point 3; extending from contact point 3 in the reverse direction along the inflow angle, when the distance between the extension curve S and point B is less than the first distance threshold, and the extension curve S almost passes through point B, then stop extending, and determine the shape data of the microcatheter according to the three-dimensional coordinates of point A, contact points 1 to 3, and point B.

[0104] In one embodiment, when determining the displacement data according to the three-dimensional coordinates of multiple contact points, the three-dimensional coordinates of the multiple contact points are first fitted to obtain a spline curve, the spline curve is smoothed, and the displacement data is determined according to the smoothed spline curve. After the smoothing process, the smoothness of the spline curve is ensured, thereby improving the reliability of the displacement data. The displacement data includes the three-dimensional coordinates of each sampling point on the spline curve.

[0105] Step 103, input the shape data into the pre-trained shaping needle morphology model, and determine the morphology data of the shaping needle according to the shaping needle morphology model.

[0106] Among them, the shaping needle morphology model is obtained by deep learning training of the neural network using multiple groups of data samples, and each group of data samples includes the morphology data of the shaping needle and the shape data of the microcatheter obtained based on the shaping needle.

[0107] The present invention simulates the trajectory data of a microcatheter entering a target blood vessel according to the morphological data of the target blood vessel in a medical image, and combined with the shaping needle morphological model obtained based on deep learning, can assist in quickly and accurately planning the morphological data of a shaping needle that matches the target blood vessel, thereby achieving precise microcatheter shaping based on the shaping needle and providing a microcatheter trajectory with individualized patient characteristics.

[0108] In one embodiment, the shaping needle morphology model includes a feature extraction submodel and a shaping simulation submodel, and the deformation data is input into the feature extraction submodel of the shaping needle morphology model, so that the deformation data is resampled by the feature extraction submodel to extract the characteristics of each sampling point and the image characteristics at the corresponding position. The characteristics of the sampling point include at least one of the following: the three-dimensional coordinates of the sampling point, the curvature of the spline curve at the sampling point, the distance from the sampling point to point A (Euclidean distance and / or the distance from the spline curve to point A), the shortest distance from the sampling point to the center line, the three-dimensional coordinates of the center point closest to the sampling point on the center line, the curvature of the center line corresponding to the sampling point, the angle between the line segment composed of the sampling point and the center point and the center line, the microcatheter and the shaping needle model and elastic coefficient. The image features include a candidate frame (e.g., 25*25*25 pixels) intercepted in the area where the target blood vessel is located in the medical image with the center point closest to the sampling point on the center line as the center and / or a candidate frame (e.g., 25*25*25 pixels) intercepted on the three-dimensional model of the target blood vessel. The output of the feature extraction sub-model (feature extraction result) is used as the input of the shaping simulation sub-model. The morphological data of the shaping needle is determined according to the output result of the shaping simulation sub-model. Figure 6a , showing the morphological data of the shaping needle.

[0109] See also Figure 6b In the figure, MLNN (Multi-Layer Neural Network) and CNN (Convolutional Neural Network) are used as the network architecture of the feature extraction sub-model, and RNN (Recurrent Neural Network) is used as the network architecture of the shaping simulation sub-model. The characteristics of the sampling points of the deformation data and the image features at the corresponding positions are extracted using the MLNN sub-model and the CNN sub-model respectively. Taking the number of sampling points as N as an example, the feature extraction results X0~X corresponding to the N sampling nodes are obtained. N , and use it as the input of the RNN sub-model. Where N is a positive integer.

[0110] See also Figure 6c , the RNN sub-model includes N nodes, X0~X N As the input of each node, the coordinates H0~H of each sampling point on the morphological curve of the shaping needle are determined by the RNN sub-model. N, the coordinates H0~H N Characterize the morphological data of the shaping needle. Then, a mesh model of the shaping needle can be generated according to the morphological data of the shaping needle, and a shaping needle matching the mesh model can be manufactured.

[0111] In one embodiment, a mesh model of the shaping needle is generated based on the morphological data and using a Marching Cube method.

[0112] In one embodiment, a shaping needle matching the mesh model is shaped by 3D printing.

[0113] The molded shaping needle is used to shape the microcatheter, and can achieve precise and effective microcatheter shaping.

[0114] Corresponding to the aforementioned embodiment of the method for forming a microcatheter shaping needle, the present invention also provides an embodiment of an apparatus for forming a microcatheter shaping needle.

[0115] Figure 7 A schematic diagram of a module of a device for forming a microcatheter shaping needle provided in an exemplary embodiment of the present invention, the device comprising:

[0116] A first determination module 71, configured to determine morphological data of a target blood vessel in a medical image;

[0117] A simulation module 72, used for simulating the shape data of the microcatheter entering the target blood vessel according to the morphological data;

[0118] The second determination module 73 is used to input the shape data into a pre-trained shaping needle morphology model, and determine the morphology data of the shaping needle according to the shaping needle morphology model; wherein the shaping needle morphology model is obtained by training a neural network using multiple groups of data samples, and each group of data samples includes the morphology data of the shaping needle and the shape data of the microcatheter obtained based on the shaping needle.

[0119] Optionally, the first determining module includes:

[0120] a segmentation unit, configured to perform image segmentation processing on the medical image to determine a region where a target blood vessel in the medical image is located;

[0121] A determination unit is used to determine the morphological data according to the image segmentation result.

[0122] Optionally, the segmentation unit is specifically used for:

[0123] determining a centerline of a blood vessel in the medical image;

[0124] Densely sampling the medical image along the center line to obtain a number of candidate frames, and removing redundant candidate frames;

[0125] The target blood vessels in the candidate frame after removing redundancy are segmented based on the trained segmentation model.

[0126] Optionally, the segmentation unit is specifically used for:

[0127] Acquire a first endpoint and a second endpoint marked on a blood vessel in the medical image; the target blood vessel is located between the first endpoint and the second endpoint;

[0128] determining a centerline of a target blood vessel between the first endpoint and the second endpoint;

[0129] The region where the target blood vessel is located is segmented according to the center line and based on the trained segmentation model.

[0130] Optionally, the simulation module is specifically used for:

[0131] a point determination unit, configured to determine a target center point in the three-dimensional model of the target blood vessel, and to extend from the target center point in the reverse direction along the inflow angle direction, and to sequentially determine a plurality of contact points where the extension curve contacts the blood vessel wall represented by the three-dimensional model;

[0132] The shape determination unit is used to determine the shape data of the microcatheter according to the three-dimensional coordinates of the multiple contact points when the multiple contact points include a target contact point or the distance between the extension curve and the marking point on the center line of the target blood vessel is less than a first distance threshold.

[0133] The target contact point is a contact point whose distance from the marked point on the center line of the diseased blood vessel is less than or equal to a second distance threshold.

[0134] Optionally, the walking shape determining unit is specifically used for:

[0135] Fitting the three-dimensional coordinates of the multiple contact points to obtain a spline curve;

[0136] Performing smoothing on the spline curve;

[0137] The shape data is determined according to the smoothed spline curve.

[0138] Optionally, the shaping needle morphology model includes a feature extraction sub-model and a shaping simulation sub-model; the shaping data is input into a pre-trained shaping needle morphology model, and the second determination module includes:

[0139] An input unit, used for inputting the shape-shifting data into the feature extraction sub-model, so that the feature extraction sub-model performs feature extraction on the shape-shifting data;

[0140] A determination unit is used to input the feature extraction result output by the feature extraction sub-model into the shaping simulation sub-model to determine the morphological data of the shaping needle.

[0141] Optionally, the device further comprises:

[0142] A generation model is used to generate a mesh model of the shaping needle according to the morphological data of the shaping needle;

[0143] The shaping module is used to shape the shaping pins to match the mesh model.

[0144] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of the present invention. Ordinary technicians in this field can understand and implement it without paying creative work.

[0145] Figure 8 The schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present invention shows a block diagram of an exemplary electronic device 80 suitable for implementing the embodiment of the present invention. Figure 8 The electronic device 80 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0146] like Figure 8 As shown, the electronic device 80 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 80 may include, but are not limited to: at least one processor 81, at least one memory 82, and a bus 83 connecting different system components (including the memory 82 and the processor 81).

[0147] The bus 83 includes a data bus, an address bus, and a control bus.

[0148] The memory 82 may include a volatile memory, such as a random access memory (RAM) 821 and / or a cache memory 822 , and may further include a read-only memory (ROM) 823 .

[0149] The memory 82 may also include a program tool 825 (or utility) having a set (at least one) of program modules 824, such program modules 824 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0150] The processor 81 executes various functional applications and data processing by running the computer program stored in the memory 82, such as the method provided in any of the above embodiments.

[0151] The electronic device 80 may also communicate with one or more external devices 84 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 85. Furthermore, the model-generated electronic device 80 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 86. As shown, the network adapter 86 communicates with other modules of the model-generated electronic device 80 via a bus 83. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the model-generated electronic device 80, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0152] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0153] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method provided by any of the above embodiments is implemented.

[0154] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0155] In a possible implementation manner, the embodiment of the present invention may also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute a method for implementing any of the above embodiments.

[0156] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on a user device, partially on a user device, as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0157] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for forming a microcatheter shaping needle, characterized in that: include: determining morphological data of a target blood vessel in a medical image; Simulating the shape data of the microcatheter entering the target blood vessel according to the morphological data; Inputting the shape data into a pre-trained shaping needle morphology model, and determining the morphology data of the shaping needle according to the shaping needle morphology model; The shaping needle morphology model comprises a feature extraction sub-model and a shaping simulation sub-model; the step of inputting the shape data into the pre-trained shaping needle morphology model and determining the morphology data of the shaping needle according to the shaping needle morphology model comprises: The displacement data is input into the feature extraction sub-model, so that the feature extraction sub-model performs feature extraction on the displacement data; the feature extraction result includes the characteristics of each sampling point of the resampled displacement data and the image features at the corresponding position; The feature extraction result output by the feature extraction sub-model is input into the shaping simulation sub-model to determine the morphological data of the shaping needle.

2. The method for forming a microcatheter molding needle according to claim 1, characterized in that: The step of determining the morphological data of the target blood vessel in the medical image comprises: Performing image segmentation processing on the medical image to determine a region where a target blood vessel in the medical image is located; The morphological data is determined according to the image segmentation result.

3. The method for forming a microcatheter molding needle according to claim 2, characterized in that: The performing image segmentation processing on the medical image comprises: Determine the center line of the blood vessel in the medical image; densely sample the medical image along the center line to obtain a plurality of candidate frames, and remove redundant candidate frames; and segment the target blood vessel in the candidate frames from which the redundant frames have been removed based on the trained segmentation model; Alternatively, a first endpoint and a second endpoint marked on a blood vessel in the medical image are obtained; the target blood vessel is located between the first endpoint and the second endpoint; a centerline of the target blood vessel between the first endpoint and the second endpoint is determined; and an area where the target blood vessel is located is segmented according to the centerline and based on a trained segmentation model.

4. The method for forming a microcatheter shaping needle according to claim 1, characterized in that: The morphological data includes a three-dimensional model and an inflow angle of the target blood vessel; the data for simulating the movement of the microcatheter into the target blood vessel according to the morphological data includes: determining a target center point in the three-dimensional model of the target blood vessel; Extending in the reverse direction from the target center point along the inflow angle direction, and sequentially determining a plurality of contact points where the extension curve contacts the blood vessel wall represented by the three-dimensional model; When the multiple contact points include a target contact point or the distance between the extension curve and the marking point on the centerline of the target blood vessel is less than a first distance threshold, the shape data of the microcatheter is determined according to the three-dimensional coordinates of the multiple contact points.

5. The method for forming a microcatheter shaping needle according to claim 4, characterized in that: The determining the movement data according to the three-dimensional coordinates of the multiple contact points includes: Fitting the three-dimensional coordinates of the multiple contact points to obtain a spline curve; Performing smoothing on the spline curve; The shape data is determined according to the smoothed spline curve.

6. The method for forming a microcatheter molding needle according to any one of claims 1 to 5, characterized in that: Also includes: Generate a mesh model of the shaping needle according to the morphological data of the shaping needle; Sculpt the pins to match the mesh model.

7. A device for forming a microcatheter shaping needle, characterized in that: include: A first determination module, used to determine morphological data of a target blood vessel in a medical image; A simulation module, used for simulating the shape data of the microcatheter entering the target blood vessel according to the morphological data; A second determination module is used to input the shape data into a pre-trained shaping needle morphology model, and determine the morphology data of the shaping needle according to the shaping needle morphology model; The shaping needle morphology model includes a feature extraction sub-model and a shaping simulation sub-model; the shape data is input into the pre-trained shaping needle morphology model, and the second determination module includes: An input unit, used for inputting the displacement data into the feature extraction sub-model, so that the feature extraction sub-model performs feature extraction on the displacement data; the feature extraction result includes the characteristics of each sampling point of the resampled displacement data and the image features at the corresponding position; A determination unit is used to input the feature extraction result output by the feature extraction sub-model into the shaping simulation sub-model to determine the morphological data of the shaping needle.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for forming the microcatheter molding needle according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for forming a microcatheter molding needle according to any one of claims 1 to 6 is implemented.

Images