Ablation automated navigation method and system

Abstract

The application provides an ablation automatic navigation method and system, and relates to the technical field of computer-aided medicine, which comprises the following steps: setting ablation path hard constraint conditions and soft constraint conditions; initializing multiple preliminary ablation paths meeting the hard constraint conditions based on the hard constraint conditions; calculating risk indexes of the preliminary ablation paths based on the soft constraint conditions; sorting the preliminary ablation paths in order from low to high according to the risk indexes, and selecting the preliminary ablation paths at the front of the order as initial solutions of a penguin optimization algorithm; optimizing the ablation paths through the penguin optimization algorithm to determine multiple candidate ablation paths; sorting the candidate ablation paths in order from low to high according to fitness, and selecting the candidate ablation paths at the front of the order for organ damage assessment; determining an optimal ablation path from the candidate ablation paths according to the organ damage assessment result; and performing ablation navigation according to the needle insertion position, angle and depth determined by the optimal ablation path.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer-aided medical technology, in particular to an ablation automatic navigation method and system. BACKGROUND

[0002] Ablation automatic navigation improves the accuracy and safety of ablation therapy, reduces the risk of physician error, avoids damage to normal tissue, and improves treatment outcomes. It not only shortens the operation time and promotes the rapid recovery of patients, but also reduces the operating pressure of physicians and improves the efficiency of surgery through personalized treatment plans and decision support, which is an important technology for improving treatment quality and patient experience in modern medicine.

[0003] Current ablation navigation technology mainly relies on medical images to plan ablation paths. However, current ablation navigation technology has limited ablation path planning capabilities when faced with multiple tumors or tumors located deep or in complex locations, making it difficult to conduct comprehensive risk assessments of ablation paths and assess potential damage to surrounding tissues and organs, which may result in improper selection of puncture paths and cause irreversible damage or complications. SUMMARY

[0004] To solve the technical problem of current ablation navigation technology, which has limited ablation path planning capabilities when faced with multiple tumors or tumors located deep or in complex locations, making it difficult to conduct comprehensive risk assessments of ablation paths and assess potential damage to surrounding tissues and organs, which may result in improper selection of puncture paths and cause irreversible damage or complications, the present application provides an ablation automatic navigation method and system.

[0005] The technical solutions provided by the embodiments of the present application are as follows:

[0006] First aspect:

[0007] The ablation automatic navigation method provided by the embodiments of the present application comprises:

[0008] S1: setting ablation path hard constraint conditions and soft constraint conditions;

[0009] S2: initializing a plurality of preliminary ablation paths that satisfy the hard constraint conditions based on the hard constraint conditions;

[0010] S3: calculating the risk index of each preliminary ablation path based on the soft constraint conditions;

[0011] S4: sorting each preliminary ablation path in order of the risk index from low to high, and selecting the first predetermined number of preliminary ablation paths with the highest ranking as the initial solution of the sea gull optimization algorithm;

[0012] S5: Optimizing the ablation path using the Seagull optimization algorithm to determine multiple candidate ablation paths;

[0013] S6: sorting the candidate ablation paths in order of fitness from low to high, and selecting a second preset number of candidate ablation paths with the highest rankings for organ damage assessment;

[0014] S7: determining an optimal ablation path from the candidate ablation paths according to the organ damage assessment result;

[0015] S8: Perform ablation navigation according to the needle insertion position, angle, and depth determined by the optimal ablation path.

[0016] Second aspect:

[0017] An embodiment of the present invention provides an automated ablation navigation system, comprising:

[0018] processor;

[0019] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the automated ablation navigation method as described in the first aspect is implemented.

[0020] The third aspect:

[0021] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the automated ablation navigation method as described in the first aspect is implemented.

[0022] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0023] In an embodiment of the present invention, hard constraints, soft constraints, the Seagull optimization algorithm, and organ damage assessment are used to determine the optimal ablation path through multi-stage path optimization. This can cope with cases with multiple tumors or tumors with deep and complex locations. A comprehensive risk assessment of the ablation path is performed to assess the potential damage of the path to surrounding tissues and organs. This can ensure that the ultimately selected path not only has a lower risk index, but also avoids damage to normal organs to the greatest extent possible, thereby ensuring the safety and effectiveness of the ablation process and improving the accuracy of path selection and the efficiency of ablation navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0025] Figure 1 A flowchart of an ablation automatic navigation method provided by an embodiment of the present application is shown in FIG. 1.

[0026] Figure 2 A structural diagram of an ablation automatic navigation system provided by an embodiment of the present application is shown in FIG. 2. DETAILED DESCRIPTION

[0027] The technical solutions in the present application will be described below with reference to the drawings.

[0028] In the embodiments of the present application, the words such as “example”, “for example” are used to represent an example, illustration or description. Any embodiment or design scheme described as “example” in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. In fact, the word “example” is intended to present the concept in a specific way. In addition, in the embodiments of the present application, the meaning expressed by “and / or” can be both, or can be one of the two.

[0029] In the embodiments of the present application, “image” and “picture” can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. “Of”, “corresponding” and “corresponding” can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0030] In order to make the technical problems, technical solutions and advantages of the present application clearer, the following will be described in detail with reference to the drawings and specific embodiments.

[0031] Reference is made to the drawings attached Figure 1 in the description of the present application, a flowchart of an ablation automatic navigation method provided by an embodiment of the present application is shown in FIG. 1.

[0032] The present application provides an ablation automatic navigation method, which can be realized by an ablation automatic navigation device. The ablation automatic navigation device can be a terminal or a server. The processing flow of the ablation automatic navigation method can include the following steps:

[0033] S1: setting ablation path hard constraint conditions and soft constraint conditions.

[0034] The hard constraint condition refers to basic requirements that must be met in the ablation path planning, mainly including avoiding risk structures (such as important organs, blood vessels and the like), puncture depth, puncture angle and needle length and the like restrictions. These hard constraint conditions ensure the basic safety and feasibility of the ablation process, and are a prerequisite for path planning.

[0035] Optionally, the hard constraint condition specifically includes: avoiding obstacle constraint, puncture depth constraint, puncture angle constraint and needle length constraint.

[0036] The avoiding obstacle constraint: the ablation path must avoid risk structures.

[0037] The risk structure can be an important organ, a blood vessel and the like.

[0038] It should be noted that the avoiding obstacle constraint requires the ablation path to avoid all risk structures, thereby minimizing the damage to the surrounding healthy tissues and important organs during the ablation process, reducing the incidence of surgical complications and ensuring the safety of the ablation process. By avoiding collision between the puncture path and the risk structure, the risk of serious complications such as bleeding and infection can be reduced.

[0039] The puncture depth constraint: the puncture depth of the ablation path must be greater than a set depth threshold.

[0040] The depth threshold can be set by a person skilled in the art according to the actual situation, and the present application is not limited.

[0041] It should be noted that the puncture depth constraint ensures that the puncture depth of the ablation needle is greater than the set depth threshold, which can ensure that the ablation needle can reach the depth of the tumor and effectively perform treatment. If the depth is insufficient, the ablation needle may not be able to accurately reach the tumor, affecting the treatment effect. Setting an appropriate depth threshold helps to avoid excessive puncture or damage to the surface tissue, ensuring the effectiveness and safety of the ablation area.

[0042] The puncture angle constraint: the puncture angle at which the ablation path intersects the surface of the ablation organ must be greater than a set angle threshold.

[0043] The angle threshold can be set by a person skilled in the art according to the actual situation, and the present application is not limited.

[0044] It should be noted that the puncture angle constraint requires the puncture angle at which the ablation path intersects the surface of the ablation organ to be greater than the set angle threshold, which can ensure that the ablation needle enters the ablation organ at an appropriate angle when puncturing the ablation organ, thereby better avoiding blood vessels and other critical structures of the ablation organ, reducing the risk of bleeding and other complications. In addition, an appropriate angle helps to ensure accurate positioning of the ablation needle and improve the treatment effect.

[0045] Needle length constraint: the length of the ablation path is less than or equal to the maximum length of the needle.

[0046] It should be noted that the needle length constraint ensures that the length of the ablation path is less than or equal to the maximum length of the needle, ensuring the operability of the ablation path and avoiding the situation that the needle is not suitable for actual treatment due to the excessively long path. By limiting the path length, it can be ensured that the ablation needle can be smoothly inserted into the target position, avoiding the influence of the accuracy and safety of the treatment due to insufficient or excessive length.

[0047] Among them, the soft constraint condition is the optimization requirement for the ablation path planning, aiming to further improve the safety and efficiency of the path on the basis of meeting the hard constraint condition. The soft constraint includes requirements such as avoiding the path passing through the risk structure as much as possible, increasing the puncture angle, reducing the puncture depth, and reducing the number of CT layers passed through. These soft constraint conditions are not necessarily strictly met, but they can optimize path selection, reduce damage to normal tissues, and improve the overall effect of the ablation process and the recovery speed of the patient.

[0048] Optionally, the soft constraint condition specifically includes: a first soft constraint, a second soft constraint, a third soft constraint, and a fourth soft constraint.

[0049] The first soft constraint: the ablation path should be as far away from the risk structure as possible.

[0050] It should be noted that by avoiding the risk structure near the ablation organ to the maximum extent, the risk of damage to the surrounding normal tissues and organs by the puncture path can be effectively reduced. Reducing the contact with these important structures can significantly reduce the incidence of postoperative complications such as bleeding, infection, and organ function damage, thereby improving the safety of treatment.

[0051] The second soft constraint: the puncture angle of the ablation path intersecting the surface of the ablation organ should be as large as possible.

[0052] It should be noted that by selecting a larger puncture angle, the stability of the puncture can be ensured, and the ablation needle can be better avoided from the key structures such as blood vessels and bile ducts of the ablation organ, reducing the damage to these sensitive areas during the puncture process. A larger puncture angle can usually help ensure that the insertion path of the ablation needle is more perpendicular to the surface of the ablation organ, avoiding excessive puncture of the outer tissues of the ablation organ, thereby ensuring the accuracy and effectiveness of the treatment.

[0053] The third soft constraint: the depth of the ablation path should be as shallow as possible.

[0054] It should be noted that by selecting a shallower ablation path, the depth of penetration into the liver surface and other tissues can be reduced, thereby reducing the risk of damage to the liver surface and other adjacent organs during the procedure. A shallower path also helps to reduce the difficulty of operating the ablation needle, reducing trauma to the patient, while also reducing the incidence of postoperative complications such as bleeding and infection.

[0055] Fourth soft constraint: the CT layers crossed by the ablation path should be as few as possible.

[0056] It should be noted that by reducing the number of CT layers crossed, the exposure time of the patient to radiation during the procedure can be shortened, reducing the potential health risks associated with radiation. In addition, fewer CT layers mean that the path is planned more simply, reducing the complexity of the path and thus reducing the difficulty of the procedure, improving the efficiency and accuracy of the treatment.

[0057] S2: Based on the hard constraint conditions, initialize multiple preliminary ablation paths that satisfy the hard constraint conditions.

[0058] Specifically, path search algorithms such as A* algorithm, Dijkstra algorithm, etc. can be used to search for paths in the three-dimensional model to ensure that multiple preliminary ablation paths that satisfy the hard constraint conditions are found.

[0059] S3: Based on the soft constraint conditions, calculate the risk index of each preliminary ablation path.

[0060] In one possible implementation, S3 specifically includes sub-steps S301 to S303:

[0061] S301: Calculate the distance between each preliminary ablation path and the risk structure, the penetration angle, the penetration depth, and the number of CT layers crossed.

[0062] S302: Normalize the distance between each preliminary ablation path and the risk structure, the penetration angle, the penetration depth, and the number of CT layers crossed to determine the risk structure risk value, the penetration angle risk value, the penetration depth risk value, and the number of CT layers crossed risk value of the preliminary ablation path.

[0063] It should be noted that in path planning, each soft constraint condition usually has different dimensions and numerical ranges. For example, the distance of the path may be in centimeters, the angle may be in degrees, and the depth may be in milliseconds or centimeters. The differences between these values affect their comparison and integration in the calculation. Normalization can convert them to the same numerical range, so that they can be compared and integrated on the same basis.

[0064] Optionally, S302 specifically includes:

[0065] S3021: Normalize the distance between each preliminary ablation path and the risk structure to determine the risk structure risk value of the preliminary ablation path:

[0066]

[0067] wherein f di represents the risk structure risk value of the i-th preliminary ablation path, d i represents the distance between the i-th preliminary ablation path and the risk structure, d max represents the maximum distance between each preliminary ablation path and the risk structure, and d min represents the minimum distance between each preliminary ablation path and the risk structure.

[0068] S3022: Normalize the puncture angle of each preliminary ablation path to determine the puncture angle risk value of the preliminary ablation path:

[0069]

[0070] wherein f ai represents the puncture angle risk value of the i-th preliminary ablation path, a i represents the puncture angle of the i-th preliminary ablation path, d max represents the maximum puncture angle of each preliminary ablation path, and d min represents the maximum puncture angle of each preliminary ablation path.

[0071] S3023: Normalize the puncture depth of each preliminary ablation path to determine the puncture depth risk value of the preliminary ablation path:

[0072]

[0073] wherein f hi represents the puncture depth risk value of the i-th preliminary ablation path, h i represents the puncture depth of the i-th preliminary ablation path, h max represents the maximum puncture depth of each preliminary ablation path, and h min represents the maximum puncture depth of each preliminary ablation path.

[0074] S3024: Normalize the number of CT layers passed by each preliminary ablation path to determine the number of CT layers passed risk value of the preliminary ablation path:

[0075]

[0076] wherein f θi represents the number of CT layers passed risk value of the i-th preliminary ablation path, θ idenotes the number of CT layers passed through by the i-th preliminary ablation path, θ max denotes the maximum number of CT layers passed through in each preliminary ablation path, θ min denotes the minimum number of CT layers passed through in each preliminary ablation path.

[0077] S303: Calculate the risk index of the preliminary ablation path according to the risk structure risk value, the puncture angle risk value, the puncture depth risk value, and the risk value of the number of CT layers passed through.

[0078] Optionally, the calculation method of the risk index in S303 is specifically:

[0079] ρ i = μ d f di + μ a f ai + μ h f hi + μ θ f θi

[0080] Wherein, ρ i denotes the risk index of the i-th preliminary ablation path, μ d denotes the fusion coefficient of the risk structure term, μ a denotes the fusion coefficient of the puncture angle term, μ h denotes the fusion coefficient of the puncture depth term, and μ θ denotes the fusion coefficient of the number of CT layers passed through term.

[0081] Wherein, the person skilled in the art can set the size of the fusion coefficient μ d of the risk structure term, the fusion coefficient μ a of the puncture angle term, the fusion coefficient μ h of the puncture depth term, and the fusion coefficient μ θ of the number of CT layers passed through term according to the actual situation, and the present application is not limited.

[0082] In the present application, the calculation method of the risk index can comprehensively evaluate the safety of each preliminary ablation path by combining multiple soft constraint conditions. The risk value of each factor represents the performance of the path in a specific aspect, and the comprehensive calculation of these risk values helps to obtain a more comprehensive evaluation, ensuring that the path selection considers all key safety factors.

[0083] S4: Sort the preliminary ablation paths according to the risk index from low to high, and select the first preset number of preliminary ablation paths with high ranking as the initial solution of the sea gull optimization algorithm.

[0084] Optionally, the first preset number is specifically 10.

[0085] S5: optimizing the ablation path by the seagull optimization algorithm to determine a plurality of candidate ablation paths.

[0086] The seagull optimization algorithm is a natural heuristic algorithm simulating the foraging behavior of a seagull colony, which optimizes the solution process of a problem by simulating the cooperation and competition between seagulls in the process of finding food. In the algorithm, each seagull represents a potential solution, and the quality of the solution is updated through the following and attack behaviors between seagulls to find the optimal solution. The seagull optimization algorithm has global search capability and strong explorability, and can effectively solve complex optimization problems such as ablation path planning and machine learning parameter tuning. Its advantages are that it can find the global optimal or approximate optimal solution in the solution space, and has good convergence and robustness.

[0087] Optionally, the fitness function of the seagull optimization algorithm is specifically:

[0088] F(l)=λ d d l +λ a a l -λ h h l -λ h θ l

[0089] Wherein, F() represents the fitness function, l represents the ablation path, d l represents the distance between the ablation path l and the risk structure, λ d represents the weight coefficient of the risk structure term, a l represents the puncture angle of the ablation path l, λ a represents the weight coefficient of the puncture angle term, h l represents the puncture depth of the ablation path l, λ h represents the weight coefficient of the puncture depth term, θ l represents the number of CT layers passed by the ablation path l, λ θ represents the weight coefficient of the CT layer number term.

[0090] Wherein, the person skilled in the art can set the weight coefficient λ d of the risk structure term, the weight coefficient λ a of the puncture angle term, the weight coefficient λ h of the puncture depth term, and the weight coefficient λ θ of the CT layer number term according to the actual situation, which is not limited by the present application.

[0091] Specifically, the ablation path l can be represented in the form of coding to facilitate the search of the seagull optimization algorithm.

[0092] In the present application, by designing such fitness function, multiple factors of ablation path can be comprehensively considered to evaluate the safety and effectiveness of the path, and the optimization focus can be dynamically adjusted according to different clinical needs and treatment goals.

[0093] The present application introduces a brand-new seagull optimization algorithm, and the specific way of determining multiple candidate ablation paths by the seagull optimization algorithm is as follows:

[0094] The preliminary ablation paths are sorted in order of risk index from low to high, and the first preset number of preliminary ablation paths at the top of the sorting are selected as the initial solution of the seagull optimization algorithm, and the seagull individuals are initialized, each seagull individual represents a feasible model parameter set, and each seagull individual is composed of multiple dimension components, each component represents a model parameter.

[0095] In the global search stage, avoid collision and move towards the optimal individual:

[0096]

[0097] Wherein, represents the position of the i-th seagull individual after the global search stage at the t-th iteration, represents the position of the i-th seagull individual after the anti-collision processing at the t-th iteration, A represents the control factor, represents the position of the i-th seagull individual at the t-th iteration, represents the displacement of the i-th seagull individual moving towards the optimal individual at the t-th iteration, B represents the search balance factor, represents the position of the optimal individual at the t-th iteration.

[0098] In the present application, the anti-collision processing ensures that the individuals in the search process will not produce unreasonable paths or overlap, thereby avoiding unnecessary calculation and optimization deviation.

[0099] Further, by controlling the factor and the search balance factor, the algorithm can balance the relationship between exploration and utilization, so that the individuals can maintain a certain randomness in the search process and gradually converge to the optimal solution. This mechanism enhances the global search ability of the algorithm, avoids falling into local optimal solution, and improves the convergence speed and the accuracy of path optimization.

[0100]

[0101] Wherein, t represents the current iteration number, T represents the maximum iteration number, f c represents the linear descent frequency.

[0102] In the present application, the value of the control factor is gradually reduced with the increase of the iteration number, so that the search process has strong exploratory in the early stage and can widely search the solution space. In the later stage, the local search ability is enhanced and gradually concentrates in the vicinity of the optimal solution. This dynamic adjustment can avoid premature convergence in the early stage, ensure the diversity of the search, and accelerate the convergence in the later stage, improve the efficiency and stability of the algorithm.

[0103] B = 2A 2 r1

[0104] wherein r1 represents a random number between 0 and 1.

[0105] In the present application, the random number r1 makes the search step in each iteration have a certain uncertainty, thereby avoiding the algorithm falling into a local optimal solution. With the gradual reduction of the control factor, the search balance factor is adjusted, enhancing the flexibility of the search. In this way, the algorithm can explore more solution space in the early stage, and can more concentratedly converge to the optimal solution in the later stage, balancing the global search and local optimization ability, improving the efficiency and robustness of the algorithm.

[0106] In the local search stage, a random number r2 is generated, and according to the random number r2, the spiral search strategy and the surrounding strategy are selected in parallel to displace in a spiral motion:

[0107]

[0108] x = rsinη

[0109] x = rcosη

[0110] z = rη

[0111] r = ue ηv

[0112] wherein, represents the position of the i-th seagull individual after spiral motion in the t-th iteration, x represents the spiral flight coefficient in the x direction, y represents the spiral flight coefficient in the y direction, z represents the spiral flight coefficient in the z direction, r represents the spiral flight trajectory radius, η represents a random number between 0 and 2π, u and v represent spiral constants, and e represents a natural constant.

[0113] In the present application, the flexibility and diversity of the search can be increased by generating random numbers and selecting between the spiral search strategy and the surrounding strategy in parallel. The introduction of spiral movement helps the seagull individuals to expand and contract in the form of a spiral in the solution space, thereby avoiding falling into a local optimal solution. This strategy can perform detailed local search when approaching the optimal solution, while providing more exploration opportunities when far from the optimal solution, thereby balancing the needs of global search and local optimization. By introducing randomness and spiral paths, the algorithm can more effectively find the optimal solution in the solution space, improving the efficiency and accuracy of the optimization process.

[0114] Performing a mutation operation on each seagull individual:

[0115]

[0116] where V i t represents the position of the i-th seagull individual after mutation at the t-th iteration, P r represents a random individual, and γ represents an adaptive scaling factor.

[0117] In the present application, the mutation operation can introduce new solutions based on the current solution, making the search

[0118] more flexible, not only enhancing the exploration ability of the algorithm, but also improving the convergence speed, which helps to find better solutions.

[0119]

[0120] where γ max represents the maximum scaling factor, and γ min represents the minimum scaling factor, and sin represents the sine function.

[0121] In the present application, the dynamic adjustment approach can provide a larger mutation amplitude in the early stages of the search, thereby enhancing the global exploration ability and avoiding the algorithm falling into a local optimal solution. In the later stages of iteration, as the scaling factor gradually decreases, the algorithm gradually converges to the vicinity of the optimal solution, performing more detailed local search. This gradually decreasing mutation amplitude ensures a good balance between global search and local optimization, improving search efficiency and the quality of the final solution.

[0122] Determine whether the fitness value of the mutated position is greater than the fitness value of the position before mutation. If yes, replace the position before mutation with the mutated position. Otherwise, keep the position before mutation unchanged.

[0123] Update the fitness values of each seagull individual and the global optimal individual.

[0124] It is judged whether the current iteration number reaches the maximum iteration number. If yes, the model parameter set represented by the seagull individual with the highest fitness is output. Otherwise, the iteration is continued.

[0125] In the present application, the ablation path is optimized by the seagull optimization algorithm, which can effectively explore and optimize the path space and determine multiple candidate ablation paths.

[0126] S6: Sort the candidate ablation paths in order of fitness from low to high, and select the top second preset number of candidate ablation paths for organ damage assessment.

[0127] Optionally, the second preset number is specifically 5.

[0128] S7: Determine the optimal ablation path from the candidate ablation paths according to the organ damage assessment result.

[0129] In one possible implementation, S7 specifically includes sub-steps S701-S703:

[0130] S701: Functionally partition the ablation organ.

[0131] Specifically, the ablation organ can be functionally partitioned according to current academic research results. For example, for the liver, the current academic research can divide the liver into 8 functionally independent units, i.e., liver eight segments, to provide an anatomical basis for liver tumor surgery planning.

[0132] S702: Determine the number of functionally partitioned units that each candidate ablation path passes through, and perform organ damage assessment according to the number of functionally partitioned units passed through. The fewer the number of functionally partitioned units passed through, the smaller the organ damage, and the more the number of functionally partitioned units passed through, the greater the organ damage.

[0133] It should be noted that by functionally partitioning the ablation organ and assessing organ damage according to the number of functionally partitioned units passed through by each candidate ablation path, the ablation path can minimize the impact on the function of the liver and other organs. The fewer the number of functionally partitioned units passed through, the smaller the damage to normal tissues, thereby reducing the risk of postoperative complications and protecting more healthy liver function areas.

[0134] S703: Determine the candidate ablation path with the smallest number of functionally partitioned units passed through as the optimal ablation path.

[0135] In the present application, by selecting a path that passes through fewer functionally partitioned units as the optimal path, not only is the treatment effect optimized, but also the safety is improved, and the damage to important functional areas during ablation is reduced. Ultimately, it can ensure that the ablation treatment is more accurate, effective and safe, and improve the treatment effect and recovery speed of patients.

[0136] S8: ablation navigation is performed according to the needle insertion position, angle and depth determined according to the optimal ablation path.

[0137] In a possible implementation, S8 specifically includes:

[0138] S801: a plurality of markers are pasted on the surface of the patient's abdomen skin.

[0139] S802: based on the plurality of markers, a preliminary registration is performed between the three-dimensional model constructed based on the preoperative image and the patient point cloud:

[0140]

[0141] wherein L intra represents the coordinates of the markers in the patient intraoperative point cloud image, T initial represents an initial registration matrix, which is used for roughly aligning the three-dimensional model constructed based on the preoperative image and the patient point cloud, represents a marker transformation matrix, which is tracked in real time by an optical tracking system, represents an ultrasound calibration matrix, which represents the relationship between the ultrasound device coordinate system and the tracking coordinate system, L pre represents the coordinates of the markers in the preoperative image.

[0142] In the present application, the three-dimensional model constructed based on the preoperative image is docked with the patient point cloud, which can realize high-precision matching of the preoperative image and the actual intraoperative point cloud, thereby ensuring the accuracy of the ablation path, improving the controllability and safety of the treatment effect, and reducing the intraoperative error.

[0143] S803: based on the preliminary registration, an improved non-rigid ICP algorithm is used to perform forward point matching by minimizing the Euclidean distance:

[0144]

[0145] wherein, represents forward point matching, represents the i th data point in the deformed preoperative three-dimensional model, and argmin represents the variable value that minimizes the function value, represents the j th data point in the patient point cloud, P represents the patient point cloud, and || || 2 represents the two-norm calculation, N Q represents the total number of data points in the three-dimensional model constructed based on the preoperative image, N P represents the total number of data points in the patient point cloud.

[0146] It should be noted that by minimizing the Euclidean distance, each data point in the preoperative three-dimensional model is matched with the closest point in the patient point cloud, thereby ensuring the refinement of the preliminary registration. This method can minimize the error caused by patient position changes or anatomical deformation, ensuring that the preoperative model is highly consistent with the actual situation during surgery.

[0147] Backward point matching is performed by global search:

[0148]

[0149] wherein, represents the backward point matching.

[0150] It should be noted that through global search, the backward point matching can confirm whether the points in each patient point cloud have been matched with the points in the preoperative three-dimensional model, thereby further improving the accuracy of the matching. Backward matching ensures the correctness and consistency of registration, which helps to further refine the matching results and avoid false matching.

[0151] In the present application, by combining forward and backward point matching, the preoperative image and the actual intraoperative anatomy of the patient can be accurately aligned, the registration accuracy is improved, and a reliable basis is provided for accurate planning of the ablation path, thereby ensuring the safety and effectiveness of the treatment.

[0152] S804: Based on the forward point matching result and the backward point matching result, a registration cost function is set:

[0153]

[0154] wherein, J represents the registration cost function, Q' represents the data points in the deformed preoperative three-dimensional model, ω i represents the registration result parameter of the i th data point in the deformed preoperative three-dimensional model, ω i is 1 when the i th data point in the deformed preoperative three-dimensional model has a corresponding data point, otherwise 0, M i represents the affine transformation matrix for transforming the i th data point in the preoperative three-dimensional model, ω j represents the registration result parameter of the j th data point in the patient point cloud, ω j is 1 when the j th data point in the patient point cloud has a corresponding data point, otherwise 0, M j represents the affine transformation matrix for transforming the j th data point in the patient point cloud, and a represents the regularization coefficient.

[0155] In the present application, the registration quality between the preoperative model and the patient point cloud can be accurately evaluated through the registration cost function calculation based on forward point matching and backward point matching. The registration cost function combines the Euclidean distance between the matching points and the difference of the transformation matrix to optimize the alignment accuracy of the model.

[0156] Further, by introducing the registration result parameter, the effectiveness of the matching points is flexibly considered, avoiding the interference of the unmatched points on the registration result. At the same time, the regularization term makes the registration process smoother, reduces unnecessary deformation, and ensures more accurate and stable registration results, thereby improving the accuracy of ablation path planning and navigation and providing reliable guidance for surgery.

[0157] S805: Iterative optimization is performed to reduce the registration cost function, and the three-dimensional model constructed based on the preoperative image is accurately registered with the patient point cloud.

[0158] S806: The optimal ablation path is mapped into the patient point cloud.

[0159] S807: Ablation navigation is performed according to the needle insertion position, angle and depth determined after mapping.

[0160] In the present application, after accurate registration is achieved through iterative optimization, the optimal ablation path is mapped into the patient point cloud to provide accurate guidance for ablation navigation. Accurate path planning can be provided in real time during surgery to reduce errors and complications and ensure that the ablation needle accurately reaches the target area, thereby improving the safety and effectiveness of treatment.

[0161] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0162] In the embodiment of the present application, hard constraint conditions, soft constraint conditions, penguin optimization algorithm and organ damage evaluation are used to determine the optimal ablation path through multi-stage path optimization. It can deal with multiple tumors or cases with deep and complex tumor positions, conduct comprehensive risk assessment of the ablation path, assess the potential damage of the path to the surrounding tissues and organs, and enable the finally selected path to not only have a low risk index, but also avoid damage to normal organs to the greatest extent, ensuring the safety and effectiveness of the ablation process and improving the accuracy of path selection and ablation navigation efficiency.

[0163] Referring to the structure diagram of the ablation automatic navigation system 20 provided by the present application shown in the accompanying drawings of the specification, Figure 2 , a structure diagram of an ablation automatic navigation system provided by the present application is shown.

[0164] The present application also provides an ablation automatic navigation system 20 applied to the ablation automatic navigation method described above, comprising:

[0165] A processor 201.

[0166] The memory 202 stores computer readable instructions, and the computer readable instructions are executed by the processor 201 to implement the ablation automatic navigation method of the method embodiment.

[0167] The ablation automatic navigation system 20 provided by the present application can execute the ablation automatic navigation method and achieve the same or similar technical effects. To avoid repetition, the present application will not be described again.

[0168] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0169] In the embodiment of the present application, the hard constraint condition, the soft constraint condition, the seagull optimization algorithm and the organ damage evaluation are adopted to determine the optimal ablation path through multi-stage path optimization, which can cope with multiple tumors or cases with deep or complex tumor positions, comprehensively evaluate the risks of the ablation path, evaluate the potential damage of the path to the surrounding tissues and organs, and make the finally selected path not only have a low risk index, but also can maximize the avoidance of damage to normal organs, ensure the safety and effectiveness of the ablation process, and improve the accuracy of path selection and the efficiency of ablation navigation.

[0170] It should be understood that the processor in the embodiment of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0171] It should also be understood that the memory in the embodiments of the present application can be volatile or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. The volatile memory can be random access memory (RAM) used as external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0172] The above-described embodiments can be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0173] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0174] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0175] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0176] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0177] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0178] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0179] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0180] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0181] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0182] The embodiment of the present application provides a computer readable storage medium, which stores a computer program. The program is executed by a processor to realize the ablation automatic navigation method described in the method embodiment.

[0183] The computer readable storage medium provided by the present application can realize the steps and effects of the ablation automatic navigation method of the above-mentioned method embodiment. To avoid repetition, the present application will not be described again.

[0184] The technical solutions provided by the embodiment of the present application have at least the following beneficial effects:

[0185] In the embodiment of the present application, the hard constraint condition, the soft constraint condition, the seagull optimization algorithm and the organ damage evaluation are adopted. The optimal ablation path is determined through multi-stage path optimization. The method can cope with multiple tumors or cases with deep and complex tumor positions. The method can comprehensively evaluate the risk of the ablation path, evaluate the potential damage of the path to the surrounding tissues and organs, can make the finally selected path not only have a low risk index, but also can avoid damage to normal organs to the greatest extent, ensure the safety and effectiveness of the ablation process, and improve the accuracy of path selection and ablation navigation efficiency.

[0186] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0187] The following points need to be explained:

[0188] (1) The drawings of the embodiments of the present application only relate to the structures involved in the embodiments of the present application, and other structures can refer to the general design.

[0189] (2) For clarity, in the drawings used to describe the embodiments of the present application, the thickness of layers or regions are exaggerated or reduced, that is, the drawings are not drawn on scale. It will be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, it can be "directly" on or under the other element or an intervening element can also be present.

[0190] (3) The embodiments of the present application and the features in the embodiments can be combined with each other to obtain new embodiments, without conflict.

[0191] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An automated ablation navigation system, characterized in that: include: processor; A memory having computer-readable instructions stored therein, wherein when the computer-readable instructions are executed by the processor, the following automated ablation navigation method is implemented: S1: Set hard and soft constraints of the ablation path; S2: Based on the hard constraints, initializing multiple preliminary ablation paths that satisfy the hard constraints; S3: Calculating a risk index of each of the preliminary ablation paths based on the soft constraint conditions; S4: sorting the preliminary ablation paths in order from low to high according to the risk index, and selecting a first preset number of preliminary ablation paths with the highest ranking as initial solutions of the Seagull optimization algorithm; S5: Optimizing the ablation path using the Seagull optimization algorithm to determine multiple candidate ablation paths; S6: sorting the candidate ablation paths in order of fitness from low to high, and selecting a second preset number of candidate ablation paths with the highest rankings for organ damage assessment; S7: determining an optimal ablation path from the candidate ablation paths according to the organ damage assessment result; S8: performing ablation navigation according to the needle insertion position, angle, and depth determined by the optimal ablation path; The fitness function of the Seagull optimization algorithm is specifically: F(l)=λ d d l +λ a a l -l h h l -l h i l Among them, F() represents the fitness function, l represents the ablation path, d l represents the distance between the ablation path l and the risk structure, λ d Represents the weight coefficient of the risk structure item, a l represents the puncture angle of the ablation path l, λ a represents the weight coefficient of the puncture angle term, h l represents the puncture depth of the ablation path l, λ h represents the weight coefficient of the puncture depth term, θ l represents the number of CT layers that the ablation path l passes through, λ θ Represents the weight coefficient of the number of CT layers; Wherein, the S5 specifically includes: S501: sorting the preliminary ablation paths in descending order of risk index, selecting the first preset number of preliminary ablation paths with the highest order as the initial solutions of the seagull optimization algorithm, and initializing the seagull individuals. Each seagull individual represents a feasible model parameter set. Each seagull individual is composed of multiple dimensional components, each component representing a model parameter. S502: In the global search phase, avoid collisions and move towards the optimal individual: in, represents the position of the i-th seagull individual after the global search phase at the t-th iteration, represents the position of the i-th seagull after anti-collision processing at the t-th iteration, A represents the control factor, P i t represents the position of the i-th seagull individual at the t-th iteration, represents the displacement of the i-th seagull individual towards the optimal individual at the t-th iteration, B represents the search balance factor, represents the optimal individual position at the tth iteration; Among them, t represents the current number of iterations, T represents the maximum number of iterations, and f c Indicates linearly decreasing frequency; B=2A 2 r1 Among them, r1 represents a random number between 0 and 1; S503: In the local search phase, a random number r2 is generated. Based on the random number r2, a spiral search strategy and an encirclement strategy are selected in parallel, and displacement is performed in a spiral motion: x=rsinη x=rcosη z=rη r=ue ηv in, represents the position of the i-th seagull after spiral motion at the t-th iteration, x represents the spiral flight coefficient in the x-direction, y represents the spiral flight coefficient in the y-direction, z represents the spiral flight coefficient in the z-direction, r represents the radius of the spiral flight trajectory, η represents a random number between 0 and 2π, u and v represent spiral constants, and e represents a natural constant; S504: Perform mutation operations on each seagull individual: Among them, V i t represents the position of the ith seagull individual after mutation at the tth iteration, P r represents a random individual, γ represents an adaptive scaling factor; Among them, γ max represents the maximum scale factor, γ min represents the minimum scale factor, sin represents the sine function; S505: Determine whether the fitness value of the position after the mutation is greater than the fitness value of the position before the mutation; if so, replace the position before the mutation with the position after the mutation; otherwise, keep the position before the mutation unchanged; S506: Update the fitness value of each seagull individual and the global optimal individual; S507: Determine whether the current number of iterations has reached the maximum number of iterations; if so, output the model parameter set representing the seagull individual with the highest current fitness; otherwise, return to continue iteration; Wherein, the S8 specifically includes: S801: affix multiple markers to the patient's abdominal skin surface; S802: Preliminary registration of the 3D model constructed based on the preoperative image with the patient's point cloud based on multiple landmarks; S803: Based on the preliminary registration, an improved non-rigid ICP algorithm is used to perform forward point matching by minimizing the Euclidean distance; backward point matching is performed through global search; S804: Based on the forward point matching results and the backward point matching results, set the registration cost function: Where J represents the registration cost function, Q′ represents the data points in the deformed preoperative 3D model, and ω i Represents the registration result parameter of the i-th data point in the deformed preoperative 3D model. When the i-th data point in the deformed preoperative 3D model has a corresponding data point, ω i is 1, otherwise it is 0, M i represents the affine transformation matrix for transforming the i-th data point in the preoperative 3D model, ω j Represents the registration result parameter of the jth data point in the patient point cloud. When the jth data point in the patient point cloud has a corresponding data point, ω j is 1, otherwise it is 0, M j represents the affine transformation matrix for transforming the jth data point in the patient point cloud, and α represents the regularization coefficient; S805: performing iterative optimization with the goal of reducing the registration cost function, and accurately registering the three-dimensional model constructed based on the preoperative image with the patient point cloud; S806: Mapping the optimal ablation path to the patient point cloud; S807: Perform ablation navigation according to the needle insertion position, angle, and depth determined after mapping.

Images