A method for optimizing parameters of high-voltage steep pulse ablation
Through deep learning and finite element simulation combined with genetic algorithm, the high-pressure steep pulse ablation parameters are optimized, which solves the problems of poor ablation effect and damage to healthy tissue caused by ablation parameter fixation in the existing technology, and achieves high accuracy and safety Personalized treatment plan.
Patent Information
- Application Number
- CN202411180695.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-27
AI Technical Summary
Existing high-pressure steep pulse ablation equipment lacks systematic methods to dynamically adjust ablation parameters according to specific lesion characteristics, resulting in poor ablation effect or damage to surrounding healthy tissues.
The characteristics of the lesion region are obtained through deep learning image processing, the finite element method simulates the ablation effect, and the optimization objective function is defined using genetic algorithm to optimize the high-pressure steep pulse ablation parameters to achieve personalized ablation parameter settings.
It improves the accuracy and effectiveness of high-pressure steep pulse ablation, significantly improves the treatment effect, reduces damage to surrounding tissues, improves the safety of treatment, and adapts to the needs of different lesion types and locations.
Smart Images

Figure CN118711757B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of high-voltage steep pulse ablation, and in particular to a method for optimizing high-voltage steep pulse ablation parameters. Background Art
[0002] High-voltage steep pulse ablation technology has significant advantages in treating various lesions (such as tumors). However, how to optimize the ablation parameters according to the type and location of the specific lesion remains a challenge.
[0003] Most current ablation devices use fixed parameters, which may lead to poor ablation effects or damage to surrounding healthy tissues. The existing technology lacks a systematic method to dynamically adjust ablation parameters according to specific lesion characteristics to achieve precise treatment. Summary of the invention
[0004] The purpose of the present invention is to provide a method for optimizing high-voltage steep pulse ablation parameters to achieve the best ablation effect and minimize damage to surrounding healthy tissues.
[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:
[0006] A method for optimizing high-voltage steep pulse ablation parameters, characterized by comprising the following steps:
[0007] S1) Input lesion area features
[0008] Obtain patient imaging data through CT or MRI equipment, use deep learning image processing algorithms to segment the images and mark the lesion areas, and calculate the area and shape characteristics of the lesion areas;
[0009] S2) Simulation of ablation effect
[0010] According to the physical properties of the lesion area, such as conductivity and dielectric constant, the finite element method was used to simulate the ablation area and energy distribution of high-voltage steep pulses under different parameter combinations, and the ablation effect under different parameter combinations was evaluated.
[0011] S3) Define the optimization objective function
[0012] The optimization objective function is defined to maximize the ablation efficiency of the lesion area and minimize the damage to healthy tissues. The objective function is: ,in, is the parameter combination vector, For ablation efficiency, is the penalty coefficient, for damage to healthy tissue;
[0013] S4) Optimization using genetic algorithms
[0014] First, several initial parameter combinations are generated as the initialization population, and then the optimization objective function in step S3) is used to calculate the fitness of each parameter combination. According to the fitness, excellent parameter combinations are selected for crossover and mutation to generate a new generation of parameter combinations; the fitness evaluation and selection process is repeated until the optimization objective function converges to the optimal value;
[0015] S5) Output the optimal parameter combination
[0016] Select the parameter combination with the highest fitness As the final optimal parameter combination, a detailed ablation plan is generated;
[0017] ,in, To optimize the objective function The parameter combination with the maximum value, For a given parameter combination The objective function below.
[0018] Further, in step S2), the electric field intensity distribution is ,in, is the electric field strength at a distance r from the ablation needle and a time t, is the pulse intensity, r is the distance from the ablation needle, is the attenuation coefficient; the energy distribution is ,in, is the energy distribution at a distance r from the ablation needle and a time t, is the electric field intensity pulse intensity at time t, is the integration variable.
[0019] Compared with the prior art, the present invention has the following advantages:
[0020] The present invention discloses a method for optimizing parameters of high-voltage steep pulse ablation, which realizes personalized ablation parameter setting; adopts a genetic algorithm to optimize parameters and establish an accurate ablation physical model, thereby improving the accuracy and effectiveness of high-voltage steep pulse ablation, significantly improving the treatment effect, while reducing damage to surrounding tissues and improving the safety of treatment; meets personalized treatment plans and adapts to the needs of different lesion types and locations. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION
[0022] The embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings.
[0023] A method for optimizing high-voltage steep pulse ablation parameters, such as Figure 1As shown, the following steps are included:
[0024] S1) Input lesion area features
[0025] Obtain the patient's imaging data through CT or MRI equipment, use deep learning image processing algorithms (such as U-Net model) to segment the image and mark the lesion area, and calculate the area and shape characteristics of the lesion area; the details are as follows:
[0026] S1-1) Image segmentation
[0027] ,in, is the label value of the pixel (x, y) in the image;
[0028] S1-2) Calculation of lesion area
[0029] , where A is the area of the lesion.
[0030] S2) Simulation of ablation effect
[0031] According to the physical properties of the lesion area, such as conductivity and dielectric constant, the finite element method (FEM) was used to simulate the ablation area and energy distribution of high-voltage steep pulses under different parameter combinations (pulse intensity, duration, frequency, etc.), and the ablation effect under different parameter combinations was evaluated;
[0032] S2-1) Electric field intensity distribution
[0033] ,in, is the electric field strength at a distance r from the ablation needle and a time t, is the pulse intensity, r is the distance from the ablation needle, is the attenuation coefficient;
[0034] S2-2) Energy distribution
[0035] ,in, is the energy distribution at a distance r from the ablation needle and a time t, is the electric field intensity pulse intensity at time t, is the integration variable
[0036] S3) Define the optimization objective function
[0037] The optimization objective function is defined to maximize the ablation efficiency of the lesion area and minimize the damage to healthy tissues. The objective function is: ,in, is the parameter combination vector, For ablation efficiency, is the penalty coefficient, Damage to healthy tissue.
[0038] S4) Optimization using genetic algorithms
[0039] First, generate several initial parameter combinations as the initialization population, then use the optimization objective function in step S3) to calculate the fitness of each parameter combination, select excellent parameter combinations according to the fitness for crossover and mutation, and generate a new generation of parameter combinations; repeat the fitness evaluation and selection process until the optimization objective function converges to the optimal value; the details are as follows:
[0040] S4-1) Initialize the population: generate several initial parameter combinations
[0041] ,in, is the initial population, is the population size, is the integral variable of the i-th parameter combination;
[0042] S4-2) Fitness evaluation: Calculate the fitness of each parameter combination based on the simulated ablation effect
[0043] ,in, is the fitness of the ith parameter combination, is the i-th parameter combination, which represents a specific parameter set in the population. These parameters are key variables that determine the ablation effect, such as pulse intensity, duration, and frequency. For a given parameter combination The optimization target value under is usually an evaluation function of the ablation effect, which takes into account the ablation efficiency and the damage to healthy tissues;
[0044] S4-3) Selection: Select parameter combinations with high fitness for reproduction
[0045] ,in, is the t+1 generation population, For selection operation;
[0046] S4-4) Crossover and mutation: generating new parameter combinations
[0047] ,in, For crossover operation, is a mutation operation;
[0048] S4-5) Loop processing: Repeat the fitness evaluation and selection process until convergence to the optimal parameter combination
[0049] .
[0050] S5) Output the optimal parameter combination
[0051] Select the parameter combination with the highest fitness As the final optimal parameter combination, a detailed ablation plan is generated, including parameters such as optimal pulse intensity, duration and frequency, as well as the corresponding ablation path and operation guidance:
[0052] ,in, To optimize the objective function The parameter combination with the maximum value, is the objective function for a given parameter combination p.
[0053] The above description is only a preferred embodiment of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and modifications without departing from the concept of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.
Claims
1. A method for optimizing high-voltage steep pulse ablation parameters, characterized in that: The steps include: S1) Input lesion area features Obtain patient imaging data through CT or MRI equipment, use deep learning image processing algorithms to segment the images and mark the lesion areas, and calculate the area and shape characteristics of the lesion areas; S2) Simulation of ablation effect According to the physical properties of the lesion area, such as conductivity and dielectric constant, the finite element method was used to simulate the ablation area and energy distribution of high-voltage steep pulses under different parameter combinations, and the ablation effect under different parameter combinations was evaluated. S3) Define the optimization objective function The optimization objective function is defined to maximize the ablation efficiency of the lesion area and minimize the damage to healthy tissues. The objective function is: ,in, is the parameter combination vector, For ablation efficiency, is the penalty coefficient, for damage to healthy tissue; S4) Optimization using genetic algorithms First, several initial parameter combinations are generated as the initialization population, and then the optimization objective function in step S3) is used to calculate the fitness of each parameter combination. According to the fitness, excellent parameter combinations are selected for crossover and mutation to generate a new generation of parameter combinations; the fitness evaluation and selection process is repeated until the optimization objective function converges to the optimal value; S5) Output the optimal parameter combination Select the parameter combination with the highest fitness As the final optimal parameter combination, a detailed ablation plan is generated; ,in, To optimize the objective function The parameter combination with the maximum value, For a given parameter combination The objective function below.
2. A method for optimizing high-voltage steep pulse ablation parameters according to claim 1, characterized in that: In step S2), the electric field intensity distribution is ,in, The distance from the ablation needle is , time is The electric field strength, is the pulse intensity, is the distance from the ablation needle, is the attenuation coefficient; the energy distribution is ,in, The distance from the ablation needle is , time is The energy distribution of For time The electric field strength pulse intensity at is the integration variable.
