Cardiovascular hemangioma embolism spring coil parameter control method and device and storage medium

Abstract

A cardiovascular hemangioma embolism spring coil parameter control method and device and a storage medium relate to the technical field of medical instruments, and the method comprises the following steps: acquiring multi-modal image data of hemangioma, and constructing a hemangioma three-dimensional model based on the multi-modal image data; identifying a target anchoring area of the tumor embolism spring by using the hemangioma three-dimensional model; dividing the inner cavity of the hemangioma three-dimensional model into a target anchoring area and a filling area by using the recognition result; according to the method, the multi-modal image data is obtained and analyzed, the parameters corresponding to the embolism spring ring are obtained according to the form of hemangioma, filling can be completed through a single spring ring, meanwhile, better anchoring performance is achieved, and the method is suitable for being used in the field of hemangioma filling. The intraoperative time is effectively shortened; and the safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a method, device, and storage medium for controlling the parameters of a cardiovascular hemangioma embolization coil. Background Art

[0002] A cardiovascular embolization coil is a spiral device made of a metal material. It is soft and has good compliance, and can be precisely delivered to the lesion site through a catheter, such as into an aneurysm cavity or an abnormal blood vessel passage. By filling and inducing thrombus formation, it can achieve the purpose of embolizing blood vessels and blocking blood flow.

[0003] The history of embolization coils can be traced back to the 1970s, when scientists began to explore the use of physical devices such as coils to occlude blood vessels. With the continuous development of materials science and interventional techniques, the design and materials of embolization coils have also been greatly improved. Modern embolization coils are usually made of metal materials such as platinum, nitinol alloy, and chromium alloy, and have good biocompatibility, flexibility, and stability. However, despite the continuous progress of its technology, there are still some problems that need to be solved urgently.

[0004] 1. The filling process takes too long

[0005] When filling a cardiovascular hemangioma, due to the different shapes and sizes of hemangiomas, sometimes multiple coils need to be used to achieve an ideal embolization effect. This not only increases the operation time and difficulty, but also increases the surgical risk and pain of the patient. At the same time, when using multiple coils, the risk of detachment is also increased.

[0006] 2. In some cases, doctors need to break the coil according to the filling degree to achieve an ideal embolization effect. However, the breaking operation is not only difficult to control the breaking position, but also may cause the cross-section of the broken part to be rough, with the risk of scratching the inner wall of the hemangioma. This not only increases the surgical risk, but also may affect the embolization effect and the prognosis of the patient.

[0007] As an advanced interventional medical device, the cardiovascular hemangioma embolization coil plays an important role in the treatment of cardiovascular hemangiomas. However, the existing embolization coils still have the above-mentioned defects. Therefore, how to optimize the coil design to improve the performance and safety of the embolization coil needs to be solved. Summary of the Invention

[0008] The embodiments of the present invention provide a method, device, and storage medium for controlling the parameters of a cardiovascular hemangioma embolization coil. By acquiring and analyzing multi-modal image data, the parameters corresponding to the embolization coil can be obtained according to the morphology of the hemangioma, so that a single coil can complete the filling, and at the same time, it has better anchoring performance, effectively shortening the intraoperative time and improving the safety.

[0009] Parameter control method for cardiovascular hemangioma embolization coil, comprising:

[0010] Obtain multi-modal image data of the hemangioma, and construct a three-dimensional model of the hemangioma based on the multi-modal image data;

[0011] Use the three-dimensional model of the hemangioma to identify the target anchoring area of the embolization coil;

[0012] Use the above recognition result to divide the inner cavity of the three-dimensional model of the hemangioma into a target anchoring area and a filling area;

[0013] Calculate the parameters of the embolization coil according to the shape characteristics of the target anchoring area and the filling area respectively.

[0014] Further, the multi-modal image data includes CT, MRI, and DSA image data, and the obtained image data has the same resolution.

[0015] Further, the process of constructing the three-dimensional model of the hemangioma includes:

[0016] Preprocess the obtained multi-modal image data;

[0017] Align the image data of different modalities to the same spatial coordinate system for multi-modal image registration;

[0018] Use a deep learning model to segment the hemangioma area;

[0019] Generate a three-dimensional model of the hemangioma.

[0020] Further, the parameters of the embolization coil include anchoring section parameters and filling section parameters.

[0021] Further, the process of identifying the target anchoring area includes the following steps:

[0022] Extract geometric features from the inner cavity model of the hemangioma to identify at least one anchoring area;

[0023] When the number of anchoring areas is greater than one, score the anchoring areas;

[0024] Output the marked high-score anchoring area as the target anchoring area;

[0025] When the number of anchoring areas is one, output it as the target anchoring area.

[0026] Further, the calculation process of the anchoring section parameters of the embolization coil includes:

[0027] Identify the shape characteristics of the target anchoring area;

[0028] Calculate the shape structure of the anchoring section of the embolization coil adapted to its shape characteristics according to the shape characteristics of the target anchoring area;

[0029] Perform simulation calculations using the shape structure of the anchoring section of the embolization coil obtained;

[0030] When the anchoring force provided by the anchoring section of the embolization coil reaches the set threshold, output the shape structure of the anchoring section of the embolization coil.

[0031] Furthermore, the shape structure of the anchoring section of the embolization coil is the length shape feature of the anchoring section of the embolization coil.

[0032] Furthermore, the calculation process of the parameters of the filling section of the embolization coil includes:

[0033] Calculate the length of the filling section of the embolization coil based on the shape features of the filling area;

[0034] Evaluate the rupture risk and the risk of insufficient filling, and adjust the length of the filling section of the embolization coil according to the evaluation results until there is no rupture risk and no risk of insufficient filling in the filling section of the embolization coil.

[0035] A computer device includes: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the above method by executing the computer instructions.

[0036] A computer-readable storage medium stores computer instructions thereon, and the computer instructions are used to cause a computer to execute the above method.

[0037] The beneficial effects of the above technical solutions provided by the embodiments of the present invention at least include:

[0038] 1. By analyzing the morphology of the hemangioma, after identifying the target anchoring area therein, the parameters of the anchoring section of the embolization coil are obtained according to the shape features of the target anchoring area, so that the parameters of the anchoring section match the shape features of the target anchoring area, enabling it to provide better anchoring force, avoiding the risk of the embolization coil falling off, and at the same time, since it matches the shape features of the target anchoring area, it can also prevent mechanical force from damaging the inner wall of the hemangioma during the anchoring process.

[0039] 2. The embolization coil is an integral whole composed of an anchoring section and a filling section. During the filling process, only one embolization coil is needed to complete the filling, avoiding the problem in the prior art that multiple spring coils need to be pushed back and forth, resulting in an increase in the operation time and operation difficulty.

[0040] 3. The length of the integral embolization coil matches the volume of the hemangioma, and no breaking operation is required. Not only is the operation difficulty reduced, but there is also no cross-section, which can avoid causing additional harm to the patient.

[0041] Other features and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. The objectives and other advantages of the present invention may be realized and attained by the structure particularly pointed out in the written description, claims as well as the drawings.

[0042] The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments. Description of the Drawings

[0043] The drawings are used to provide a further understanding of the present invention, and constitute a part of the description. Together with the embodiments of the present invention, they are used to explain the present invention, but do not constitute a limitation to the present invention. In the drawings:

[0044] Figure 1 It is a flowchart of the method for controlling the parameters of a cardiovascular hemangioma embolization coil disclosed in the embodiment of the present invention. Detailed Embodiments

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art.

[0046] Figure 1 A method for controlling the parameters of a cardiovascular hemangioma embolization coil is shown, including the following steps:

[0047] Step 1: Obtain multi-modal image data of the hemangioma, and construct a three-dimensional model of the hemangioma based on the multi-modal image data.

[0048] Among them, the multi-modal image data includes CT, MRI, and DSA image data, and the resolution of the obtained image data needs to be kept consistent.

[0049] Step 1.1: Preprocess the obtained multi-modal image data, including denoising and gray normalization of the above-obtained image data to eliminate the influence of equipment differences.

[0050] Step 1.2: Align the images of different modalities to the same spatial coordinate system for multi-modal image registration.

[0051] Align the images through affine transformation:

[0052] T(x) = R·x + t

[0053] Optimization objective (minimize the difference):

[0054]

[0055] Wherein, R: 3×3 rotation matrix (degree of freedom: 3), t: 3×1 translation vector (degree of freedom: 3), x: three-dimensional coordinate point, I CT , I MRI : Gray values of CT and MRI images.

[0056] Step 1.3, use a deep learning model to segment the hemangioma region.

[0057] Use a deep learning model (such as 3D U-Net) to segment the hemangioma region;

[0058] The model outputs a probability map P(x), representing the probability that a voxel belongs to the hemangioma:

[0059] P(x) = σ(U-Net(I(x)))

[0060] The segmentation mask M(x) is obtained by thresholding:

[0061]

[0062] Wherein, I(x): voxel value of the input image, σ: Sigmoid activation function, P(x): probability that a voxel belongs to the hemangioma (range [0,1]).

[0063] Step 1.4, generate an implicit surface model to convert the binary segmentation mask into a continuous implicit surface representation.

[0064] Define the surface using the Signed Distance Function (SDF):

[0065]

[0066] Calculation steps:

[0067] Calculate the Euclidean distance field: Calculate the distance from each voxel to the surface for the binary mask M(x).

[0068] Sign assignment: Assign a sign to the distance field according to the mask value (0 or 1).

[0069] Wherein, sign(x): position attribute of point x relative to the hemangioma region Ω, where sign(x) = 1: point x is outside the hemangioma; sign(x) = -1: point x is inside the hemangioma, the shortest distance from point x to the surface boundary of the hemangioma of the inner cavity surface of the hemangioma.

[0070] Step 1.5, Surface Optimization and Smoothing, to eliminate segmentation noise and generate a smooth implicit surface.

[0071] Optimize φ(x) through Laplacian smoothing:

[0072]

[0073] where is the Laplacian operator (the second derivative of the surface, reflecting the curvature change), and λ is the smoothing coefficient (usually taken as 0.1 - 0.3).

[0074] Step 1.6, Implicit Surface Reconstruction, to extract the isosurface φ(x) = 0 and generate a triangular mesh model.

[0075] Extract the surface from the SDF using the Marching Cubes algorithm:

[0076] Traverse the voxel grid to detect the edges with sign changes;

[0077] Generate triangular patches according to the preset pattern.

[0078] Step 2, Use the three-dimensional model of the hemangioma to identify the target anchoring area of the embolization spring.

[0079] The process of anchoring area identification includes the following steps:

[0080] Step 2.1, Extract geometric features from the hemangioma lumen model to identify at least one anchoring area.

[0081] Shape feature extraction:

[0082] Quantify the shape characteristics of the lumen surface through local geometric descriptors and define the following two types of features:

[0083] Narrow area: The part where the lumen diameter is significantly smaller than the surrounding area.

[0084] Convex and concave structure: The area where there are obvious protrusions or depressions on the surface, providing mechanical anchor points.

[0085] Definition of local geometric descriptors:

[0086] Identify the narrow area by calculating the local diameter change rate of the hemangioma lumen.

[0087]

[0088] where D local : The local diameter along the lumen axis centered at point x, and D avg : The average diameter of the hemangioma lumen.

[0089] Narrow condition: ΔD(x) < γ (γ is preset according to requirements, e.g., γ = 0.7).

[0090] Recognition of concave-convex structure:

[0091] Quantify the degree of concavity and convexity through the Surface Concavity-Convexity Index (SCCI).

[0092]

[0093] In the formula, n(x): the surface normal vector at point x, x i : other points within the neighborhood of point x, N: the total number of points within the neighborhood.

[0094] Concave-convex condition:

[0095] |SCCI(x)| > δ

[0096] In the formula, δ: the concave-convex threshold, a positive value indicates a convexity, and a negative value indicates a concavity.

[0097] Step 2.2, when the number of anchorage areas is greater than one, score the anchorage areas, and output the marked high-score anchorage area as the target anchorage area.

[0098] Comprehensive scoring of the anchoring position, combining the narrow and concave-convex features, calculate the anchoring fitness of the area:

[0099] Anchoring score S(x):

[0100] S(x) = w1·(1 - ΔD(x)) + w2·|SCCI(x)|

[0101] In the formula, w1, w2: weight coefficients (e.g., w1 = 0.6, w2 = 0.4).

[0102] Anchoring condition:

[0103] S(x) > θ

[0104] In the formula, θ: the comprehensive scoring threshold (e.g., θ = 0.5).

[0105] Step 2.3, when the number of anchorage areas is one, output it as the target anchorage area.

[0106] Step 3, use the above recognition results to divide the inner cavity of the three-dimensional model of the hemangioma into the target anchorage area and the filling area.

[0107] Among them, the parameters of the embolization coil include the parameters of the anchoring section and the filling section. The embolization coil is an integral body composed of the anchoring section and the filling section. The anchoring section of the embolization coil is made of shape memory alloy such as nitinol, and the filling section is made of platinum or chromium alloy or platinum-tungsten alloy, etc.

[0108] The anchoring section is used to fill the target anchoring area, and after combining with the target anchoring area, it fixes the embolization coil. The filling section is used to fill the remaining filling area.

[0109] Step 4: Calculate the parameters of the embolization coil according to the shape characteristics of the target anchoring area and the filling area respectively.

[0110] The calculation process of the parameters of the anchoring section of the embolization coil includes:

[0111] Step 41a: Identify the shape characteristics of the target anchoring area.

[0112] Extract the following characteristics from the identified anchoring area:

[0113] Local curvature κ(x): The maximum value of the principal curvature of the surface.

[0114] Anchoring area size L anchor : The axial length of the anchoring area (along the axis of the hemangioma lumen).

[0115] Concavo-convex depth h: The depth / height of the concave or convex area.

[0116] Principal curvature calculation (based on the implicit surface φ(x)):

[0117]

[0118] Among them, is the surface normal vector.

[0119] Pit depth:

[0120] In the formula: Gradient matrix of the normal vector, Ω anchor : Point set of the anchoring area.

[0121] Step 42a: Calculate the shape structure of the anchoring section of the embolization coil that matches its shape characteristics according to the shape characteristics of the target anchoring area.

[0122] The calculation process includes:

[0123] Anchor hook opening angle θ (matching curvature):

[0124]

[0125] In the formula, r: Anchor hook opening radius, which needs to satisfy κ max : The maximum principal curvature of the anchoring area.

[0126] Barb length l spike (matching concavo-convex depth):

[0127] l spike = α·h

[0128] where α is the safety factor to ensure that the barb depth exceeds the uneven height, and h is the uneven height of the anchoring area.

[0129] Number of anchor hooks (matching area size):

[0130]

[0131] where : the axial spacing of the anchor hooks (usually taken as 2 - 3 mm), : the total length of the anchoring area.

[0132] Step 43a, perform simulation calculations using the obtained shape structure of the embolization coil anchoring section;

[0133] Step 44a, when the anchoring force provided by the embolization coil anchoring section reaches the set threshold, output the shape structure of the embolization coil anchoring section.

[0134] Among them, the shape structure of the embolization coil anchoring section is the length shape feature of the embolization coil anchoring section.

[0135] The calculation process of the parameters of the embolization coil filling section includes:

[0136] Step 41b, calculate the length of the embolization coil filling section according to the shape characteristics of the filling area;

[0137] Step 42b, evaluate the rupture risk and filling deficiency risk, and adjust the length of the embolization coil filling section according to the evaluation results until there is no rupture risk and filling deficiency risk for the length of the embolization coil filling section.

[0138] Steps 41b to 42b include:

[0139] Calculate the wall stress of the hemangioma through finite element analysis and define the risk value where σ critical is the critical rupture stress of the wall, and σ max is the maximum principal stress of the wall.

[0140] Risk correction factor: Define α(R) as a non - linear function to ensure a significant reduction in the filling amount at high risk:

[0141] α(R)= α0·(1 + tanh(β R ))

[0142] where α0 is the basic correction factor (such as 0.2), and β is the risk sensitivity factor (such as 2.0).

[0143] Safety filling length calculation model:

[0144]

[0145] Constraints: (Minimum filling length, e.g., )

[0146] Where: d: Coil wire diameter, η: Filling efficiency (0.2 - 0.5, related to winding density), L min : Conservative threshold to prevent insufficient filling, L coil : Filling length.

[0147] During use, the anchoring section of the embolization coil first extends from the catheter into the target anchoring area (the anchoring section needs to be fabricated according to the calculated parameters). After the anchoring section reaches the predetermined position, under the action of body temperature, the shape of the anchoring section made of shape memory alloy restores to the designed shape, forms an anchor after fitting with the target anchoring area, and then the remaining filling section is filled into the interior of the hemangioma by basket winding or other filling methods to achieve the effect of filling the hemangioma and inducing thrombosis.

[0148] A computer device, comprising: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the above method by executing the computer instructions.

[0149] A computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the above method.

[0150] The present invention utilizes the analysis of the morphology of the hemangioma. After identifying the target anchoring area therein, the parameters of the anchoring section of the embolization coil are obtained according to the shape characteristics of the target anchoring area, so that the parameters of the anchoring section match the shape characteristics of the target anchoring area, which can provide better anchoring force and avoid the risk of the embolization coil falling off. At the same time, because it matches the shape characteristics of the target anchoring area, it can also prevent mechanical force from damaging the inner wall of the hemangioma during the anchoring process. Meanwhile, the embolization coil is an integral whole composed of an anchoring section and a filling section. Only one embolization coil is needed to complete the filling during the filling process, avoiding the problem in the prior art that multiple spring coils need to be reciprocally pushed, resulting in an increase in the operation time and difficulty. Moreover, the length of the integral embolization coil matches the volume of the hemangioma, and no breaking operation is required, which not only reduces the operation difficulty but also has no cross-section, avoiding additional harm to the patient.

[0151] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of the present disclosure. The appended method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy recited.

[0152] In the foregoing detailed description, various features are combined in a single embodiment to simplify the present disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are expressly recited in each claim. Rather, as reflected in the appended claims, the invention lies in less than all of the features of a single disclosed embodiment. Thus, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0153] Those skilled in the art should also understand that the various illustrative logical blocks, modules, circuits, and algorithmic steps described in connection with the embodiments herein can be implemented as electronic hardware, computer software, or combinations thereof. To clearly illustrate the interchangeability of hardware and software, the various illustrative components, blocks, modules, circuits, and steps have been generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in a variety of ways for each particular application, but such implementation decisions should not be interpreted as departing from the scope of the present disclosure.

[0154] The steps of a method or algorithm described in connection with the embodiments herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination thereof. The software module can be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. Of course, the storage medium can also be integral to the processor. The processor and the storage medium can be located in an ASIC. The ASIC can be located in a user terminal. Of course, the processor and the storage medium can also exist as discrete components in a user terminal.

[0155] For software implementation, the techniques described in this application can be implemented by modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is communicatively coupled to the processor via various means, which are well known in the art.

[0156] The above description includes examples of one or more embodiments. Of course, it is not possible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but those of ordinary skill in the art should recognize that the various embodiments can be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. In addition, with respect to the term "comprising" as used in the specification or claims, the way this term is encompassed is similar to the term "including" as interpreted when "including" is used as a transitional word in a claim. In addition, any use of the term "or" in the specification or claims of a patent is to mean "non-exclusive or".

Claims

1. A method for controlling the parameters of a cardiovascular hemangioma embolization coil, characterized in that Comprising: Obtain multi-modal image data of a hemangioma, and construct a three-dimensional model of the hemangioma based on the multi-modal image data; Use the three-dimensional model of the hemangioma to identify the target anchoring area of the embolization spring; Use the above recognition result to divide the inner cavity of the three-dimensional model of the hemangioma into a target anchoring area and a filling area; Calculate the parameters of the embolization coil according to the shape characteristics of the target anchoring area and the filling area respectively.

2. The method according to claim 1, wherein The multi-modal image data includes CT, MRI, and DSA image data, and the resolution of the obtained image data is consistent.

3. The method according to claim 2, characterized in that The process of constructing the three-dimensional model of the hemangioma includes: Preprocess the obtained multi-modal image data; Align the image data of different modalities to the same spatial coordinate system for multi-modal image registration; Use a deep learning model to segment the hemangioma area; Generate a three-dimensional model of the hemangioma.

4. The method according to claim 1, characterized in that The parameters of the embolization coil include the parameters of the anchoring section and the parameters of the filling section.

5. The method according to claim 4, wherein The process of identifying the target anchoring area includes the following steps: Extract geometric features from the inner cavity model of the hemangioma to identify at least one anchoring area; When the number of anchoring areas is greater than one, score the anchoring areas; Output the marked high-score anchoring area as the target anchoring area; When the number of anchoring areas is one, output it as the target anchoring area.

6. The method according to claim 5, wherein The calculation process of the parameters of the anchoring section of the embolization coil includes: Identify the shape characteristics of the target anchoring area; Calculate the shape structure of the anchoring section of the embolization coil adapted to its shape characteristics according to the shape characteristics of the target anchoring area; Perform simulation calculations using the obtained shape structure of the anchoring section of the embolization coil; When the anchoring force provided by the anchoring section of the embolization coil reaches the set threshold, output the shape structure of the anchoring section of the embolization coil.

7. The method according to claim 6, characterized in that, The shape structure of the anchoring section of the embolization coil is the length shape characteristic of the anchoring section of the embolization coil.

8. The method according to claim 4, wherein The calculation process of the parameters of the filling section of the embolization coil includes: Calculate the length of the filling section of the embolization coil according to the shape characteristics of the filling area; Evaluate the rupture risk and the risk of insufficient filling, and adjust the length of the filling section of the embolization coil according to the evaluation result until there is no rupture risk and no risk of insufficient filling in the filling section of the embolization coil.

9. A computer device, characterized in that, Comprising: A memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 8.

Images