Planning method, device and equipment for treating brain glioma through multi-fiber laser ablation

Abstract

The invention relates to a planning method, device and equipment for treating brain glioma through multi-fiber laser ablation. The method comprises the following steps: according to pre-acquired image information of a target patient and a segmentation result of a tumor region, sequentially performing segmentation sampling processing on the image information to obtain a candidate optical fiber path set; screening the candidate optical fiber path set according to an optical fiber planning objective function and an optical fiber planning constraint condition to obtain an intermediate optical fiber path set, and determining the number of optical fibers required by tumor ablation according to the intermediate optical fiber path set; determining a target optical fiber path set from the intermediate optical fiber path set according to the number of optical fibers required by tumor ablation and a predetermined path evaluation score; the target optical fiber path set at least comprises position information corresponding to each target optical fiber path. The method can improve the tumor ablation rate and reduce the use of optical fibers.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a planning method, device and equipment for multi-fiber laser ablation treatment of brain gliomas. Background Art

[0002] Malignant gliomas are among the most common central nervous system tumors. High-grade gliomas are difficult to treat, have a poor prognosis, and pose a serious threat to human health. Currently, surgical resection is the preferred treatment. However, some patients are not suitable for craniotomy due to factors such as tumor recurrence or deep brain location.

[0003] In this context, magnetic resonance imaging-guided laser interstitial thermal therapy (LITT) is gaining attention as a safe and effective alternative treatment. During LITT, doctors use a stereotactic surgical platform to insert an optical fiber into the designated treatment area within the brain, ablating the tumor tissue through laser heating.

[0004] However, currently LITT mostly relies on doctors to manually determine the position of the optical fiber based on the three-dimensional visualization image of the tumor, and perform ablation based on the manually determined position. The ablation range may not be able to completely cover the tumor, thereby affecting the full ablation of the tumor and limiting the treatment effect. Summary of the Invention

[0005] Based on this, it is necessary to provide a planning method, device and equipment for multi-fiber laser ablation treatment of brain gliomas that can improve tumor ablation coverage in response to the above technical problems.

[0006] In a first aspect, the present application provides a planning method for multi-fiber laser ablation treatment of brain gliomas, the method comprising:

[0007] Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information is segmented and sampled in sequence to obtain a set of candidate optical fiber paths;

[0008] Based on the fiber planning objective function and fiber planning constraints, the candidate fiber path set is screened to obtain an intermediate fiber path set, and the number of fibers required for tumor ablation is preliminarily determined based on the intermediate fiber path set.

[0009] A target fiber path set is determined from the intermediate fiber path set according to the number of optical fibers required for tumor ablation and a predetermined path evaluation score; the target fiber path set at least includes position information corresponding to each target fiber path.

[0010] In a second aspect, the present application also provides a planning device for multi-fiber laser ablation treatment of brain gliomas, the device comprising:

[0011] A segmentation module is used to perform segmentation and sampling processing on the image information in sequence based on the pre-acquired image information of the target patient and the segmentation result of the tumor area to obtain a set of candidate optical fiber paths;

[0012] A screening module is used to screen the candidate fiber path set according to the fiber planning objective function and fiber planning constraints to obtain an intermediate fiber path set, and determine the number of optical fibers required for tumor ablation based on the intermediate fiber path set;

[0013] The determination module is used to determine a target fiber path set from the intermediate fiber path set based on the number of optical fibers required for tumor ablation and a predetermined path evaluation score; the target fiber path set at least includes position information corresponding to each target fiber path.

[0014] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0015] Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information of the optical fiber path set is segmented and sampled in sequence to obtain a candidate optical fiber path set;

[0016] According to the fiber planning objective function and the fiber planning constraints, the candidate fiber path sets are screened to obtain the intermediate fiber path sets, and the number of optical fibers required for tumor ablation is preliminarily determined based on the intermediate fiber path sets.

[0017] The target fiber path set is determined from the intermediate fiber path set in the fiber path set according to the number of optical fibers required for tumor ablation in the fiber path set and a predetermined path evaluation score; the target fiber path set in the fiber path set includes at least the position information corresponding to each target fiber path in the fiber path set.

[0018] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0019] Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information of the optical fiber path set is segmented and sampled in sequence to obtain a candidate optical fiber path set;

[0020] According to the fiber planning objective function and the fiber planning constraints, the candidate fiber path sets are screened to obtain the intermediate fiber path sets, and the number of optical fibers required for tumor ablation is preliminarily determined based on the intermediate fiber path sets.

[0021] The target fiber path set is determined from the intermediate fiber path set in the fiber path set according to the number of optical fibers required for tumor ablation in the fiber path set and a predetermined path evaluation score; the target fiber path set in the fiber path set includes at least the position information corresponding to each target fiber path in the fiber path set.

[0022] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the following steps:

[0023] Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information of the optical fiber path set is segmented and sampled in sequence to obtain a candidate optical fiber path set;

[0024] According to the fiber planning objective function and the fiber planning constraints, the candidate fiber path sets are screened to obtain the intermediate fiber path sets, and the number of optical fibers required for tumor ablation is preliminarily determined based on the intermediate fiber path sets.

[0025] The target fiber path set is determined from the intermediate fiber path set in the fiber path set according to the number of optical fibers required for tumor ablation in the fiber path set and a predetermined path evaluation score; the target fiber path set in the fiber path set includes at least the position information corresponding to each target fiber path in the fiber path set.

[0026] The above-mentioned planning method, device and equipment for multi-fiber laser ablation treatment of brain gliomas generate a set of candidate fiber paths based on the target patient's imaging information and the tumor area segmentation results, and screen them in combination with the fiber planning objective function and constraints. Finally, the target fiber path set is determined based on the path evaluation score, which effectively improves the scientific nature and quantitative optimality of the fiber layout. Compared with the traditional method of relying on doctors to manually plan fiber paths in three-dimensional visualization images, this method can identify potential feasible paths and select better fiber solutions by combining quantitative evaluation methods, avoiding the problem of poor planning results due to insufficient manual experience or visual judgment errors. Furthermore, it helps to achieve sufficient and uniform coverage of the tumor area and significantly improve the integrity and treatment effect of tumor ablation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a diagram of the internal structure of a computer device in one embodiment;

[0028] Figure 2 1 is a flow chart of a method for planning multi-fiber laser ablation treatment of brain gliomas in one embodiment;

[0029] Figure 3 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0030] Figure 4 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0031] Figure 5 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0032] Figure 6 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0033] Figure 7 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0034] Figure 8 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0035] Figure 9 A schematic diagram of an optical fiber path solution algorithm and evaluation in one embodiment;

[0036] Figure 10 FIG1 is a flow chart of a planning method for multi-fiber laser ablation treatment of brain glioma in another embodiment;

[0037] Figure 11 Schematic diagram of a process of resampling to generate function f(k) in one embodiment;

[0038] Figure 12 A schematic diagram of a laser interstitial thermal therapy planning system in one embodiment;

[0039] Figure 13 1 is a structural block diagram of a planning device for multi-fiber laser ablation treatment of brain gliomas in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0041] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 1 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data in the planning process of multi-fiber laser ablation treatment of brain gliomas. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a planning method for multi-fiber laser ablation treatment of brain gliomas is implemented.

[0042] It will be understood by those skilled in the art that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0043] In one embodiment, Figure 2 As shown in the figure, a planning method for multi-fiber laser ablation treatment of brain glioma is provided. Figure 1 The computer device in the example is used to illustrate the process, including the following steps:

[0044] Step 201 : Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information is segmented and sampled in sequence to obtain a set of candidate optical fiber paths.

[0045] The target patient's imaging information refers to image data obtained through medical imaging equipment such as CT and MRI that reflects the target patient's internal tissue structure. This imaging information is used to locate the spatial distribution of the tumor area and surrounding tissues.

[0046] The segmentation result of the tumor area refers to the result of identifying and extracting the tumor area from the entire medical image through an image segmentation algorithm (such as an artificial intelligence model or image processing technology), which is used for subsequent path planning and fiber optic layout.

[0047] Segmentation sampling processing refers to discretizing the three-dimensional image information along a specific direction (such as multiple angles, multiple sections), and sampling to obtain a series of spatial points or path segments that can be used as candidates for optical fiber path insertion.

[0048] The candidate fiber path set refers to a set of all spatial paths generated by sampling in the image data that may serve as fiber insertion paths.

[0049] In the embodiments of the present application, medical imaging information of the target patient is first obtained and processed to obtain a segmentation result of the tumor region. The imaging information can be CT images, MRI images, or other three-dimensional medical imaging data. Segmentation techniques based on deep learning, image processing, or manual annotation are used to extract the spatial location and shape of the tumor, providing basic data for subsequent fiber path planning.

[0050] After obtaining the image information and tumor region segmentation results, the image information is segmented and sampled. Specifically, the tumor region and surrounding tissue are sampled along different directions in three-dimensional space to generate multiple candidate insertion paths that cover the tumor. These paths constitute a set of candidate fiber paths. Each fiber path in the set has clear starting and ending points, insertion direction, and tissue traversal information, indicating potential insertion feasibility.

[0051] Step 202 : Screen the candidate fiber path set according to the fiber planning objective function and fiber planning constraints to obtain an intermediate fiber path set, and determine the number of fibers required for tumor ablation based on the intermediate fiber path set.

[0052] Among them, the fiber planning objective function refers to a mathematical function used to evaluate the pros and cons of the fiber insertion plan, which usually considers multiple factors, such as: whether the fiber insertion angle is reasonable; whether the fiber path length is the shortest; whether it is far away from critical structures (such as blood vessels and nerves); and whether the ablation area coverage is sufficient.

[0053] Fiber planning constraints refer to the safety and clinical constraints that need to be met during the planning process, such as: a minimum safe distance must be maintained between the fiber and critical tissue; the fiber insertion angle must not exceed the angle allowed by human tissue; the fiber length must not exceed the maximum length of the device, etc.

[0054] The intermediate fiber path set refers to the set of fiber paths with high feasibility that remain after objective function evaluation and constraint screening in the candidate fiber path set. It is used for subsequent target set screening.

[0055] The number of optical fibers required for tumor ablation is the minimum or optimized number of optical fibers required to ensure the therapeutic effect, calculated based on the size, shape, and distribution of the tumor.

[0056] In this embodiment, a set of candidate fiber paths is screened based on a fiber path planning objective function and pre-set constraints. The fiber planning objective function can include multiple criteria, such as minimizing path length, ensuring the appropriateness of the puncture angle, and minimizing the physiological risk of tissue penetration. Constraints can include avoiding critical structures such as blood vessels and nerves, and limiting the insertion angle and depth range. This screening process eliminates paths that do not meet safety and effectiveness requirements, resulting in a set of intermediate fiber paths.

[0057] Next, the number of optical fibers required for tumor ablation is determined based on the relationship between the intermediate fiber pathways and the tumor area. This process can be estimated based on the tumor volume, the target ablation coverage, and the effective ablation range of a single optical fiber, ensuring that the treatment goal of complete tumor coverage is achieved with the minimum number of optical fibers used.

[0058] In a specific embodiment, when determining the number of optical fibers required for tumor ablation, the following method can be used: the laser interstitial thermal therapy (LITT) multi-fiber ablation problem is modeled in the form of combinatorial optimization, with the planning objective determined as the minimum number of optical fibers, and the constraints including coverage constraints and safety constraints. The coverage constraint is that the combination of ablation ranges can cover the tumor area, and the safety constraint is that the paths cannot damage critical tissues, there is no conflict between paths, and there is no risk of path placement. The final planning problem can be expressed as shown in formula (1).

[0059]

[0060] In the last line of formula (1), the set P is all possible single ablation operations, where I, J are the candidate point sets of the fiber entry point and the target point. The domain of the plan is the possible combinations of ablation operations, that is, all subsets of P, The first line of formula (1) represents the planning goal, which is to complete the surgical goal with fewer ablation operations, that is, to minimize the number of elements in the candidate subset min|X|. The second to fourth lines are the planning constraints, which mainly consider the requirements of tumor coverage and safety. The three-dimensional tumor range is reasonably discretized into a number of coverage target points s. The coverage of the tumor is equivalent to the combination of a single ablation that can cover all target points, that is, ∑ ( i,j,k )∈X C ijks ≥1, The safety requirements of the operation are that the insertion path should avoid causing damage to important anatomical structures of the brain, and the closest distance between the path and key tissues should be d. ij Greater than the safety threshold; there is no conflict between paths, and the distance between paths Greater than the safety threshold; in order to prevent slippage during insertion, the angle θ between the path and the normal of the skull surface ij Less than the safety threshold.

[0061] In order to facilitate further evaluation, the planning problem can be mathematically transformed. First, according to the second and third constraints in problem (1), the paths in set P that do not meet the constraints are deleted. Then the candidate paths in set P are encoded 1-n and vector x∈R n Indicates the selection of these paths. The kth component of x is 1, indicating that the kth path in the set P is selected, and -1 indicates that the path is not selected. diag(xx T )=e to ensure that the vector x meets the above value requirements. At this time, the constraint of covering the tumor is equivalent to C m (x+e)≥2e, matrix C m is a coverage matrix, where the i-th column represents the coverage of the target point by the i-th path. The constraint to avoid collision between paths can be written as (x+e) T P(x+e)=0, matrix C m is the collision matrix, where P ij =1 means there is a collision between path i and path j, and P ij = 0 means there is no conflict between the two. When c is a vector of all 1s, the optimization target min(c T x+c T e) / 2 is the number of minimized paths. Finally, the transformed formula is shown in formula (2).

[0062]

[0063] For each target patient, the parameters in planning problem (1) need to be calculated, and planning problem (2) is obtained according to the above deformation process. The key structures are segmented and sampled according to the preoperative imaging information to obtain the path entry point set I and the end point set J, thereby obtaining all possible fiber paths. The insertion angle θ of all fiber paths is further calculated. ij , distance from the anatomical structure d ij and coverage of tumor target points c ijs Then traverse the possible two fiber combinations, calculate whether there is a conflict between the fibers, and get the parameters

[0064] Step 203 : determining a target fiber path set from the intermediate fiber path set based on the number of optical fibers required for tumor ablation and a predetermined path evaluation score; the target fiber path set at least includes position information corresponding to each target fiber path.

[0065] Among them, the path evaluation score refers to an evaluation indicator that quantitatively scores each intermediate optical fiber path. It is usually a comprehensive score that reflects the comprehensive performance of the path in terms of puncture angle, path length, safety and treatment effectiveness.

[0066] The target fiber optic path set is the set of fiber optic paths ultimately selected for insertion into the tumor area for thermal ablation. This set should meet all planning objectives and clinical requirements and have specific three-dimensional position information (starting point, end point, angle, etc.).

[0067] In this embodiment, the target fiber path set for implementation is selected from the intermediate fiber path set based on the path evaluation score. This path evaluation score is a comprehensive assessment that combines factors such as path safety, path length, puncture angle, and tissue traversal complexity, prioritizing paths with higher scores. Based on the required number of optical fibers, several optimal paths are selected to form the final target fiber path set.

[0068] Finally, the detailed information of the target fiber path set is output, including the spatial position information of each fiber, such as the three-dimensional coordinate starting and ending points, insertion direction, path length, etc.

[0069] In the above-mentioned planning method for multi-fiber laser ablation treatment of brain gliomas, a set of candidate fiber paths is generated based on the target patient's imaging information and the tumor area segmentation results, and is screened in combination with the fiber planning objective function and constraints. Finally, the target fiber path set is determined based on the path evaluation score, which effectively improves the scientific nature and quantitative optimality of the fiber layout. Compared with the traditional method of relying on doctors to manually plan fiber paths in three-dimensional visualization images, this method can identify potential feasible paths and select better fiber solutions by combining quantitative evaluation methods, avoiding the problem of poor planning results due to insufficient manual experience or visual judgment errors. Furthermore, it helps to achieve sufficient and uniform coverage of the tumor area, significantly improving the integrity and treatment effect of tumor ablation.

[0070] In one embodiment, Figure 3 As shown, the above-mentioned “determining a target optical fiber path set from an intermediate optical fiber path set according to the number of optical fibers required for tumor ablation and a predetermined path evaluation score” includes:

[0071] Step 301: For each intermediate fiber path in the intermediate fiber path set, the path information corresponding to the intermediate fiber path is substituted into a pre-constructed path evaluation relationship to determine the path evaluation score of the intermediate fiber path; the path evaluation relationship is used to characterize the correspondence between the path evaluation score and the path information; the path information includes at least the fiber insertion angle, the distance between the fiber and the key tissue in the brain, the distance variance of the fiber coverage of the tumor target point, the fiber coverage rate of the tumor, and the fiber length.

[0072] Path information refers to a set of characteristic parameters used to describe the insertion of an intermediate optical fiber path in space, and is used to evaluate the feasibility and quality of the path. It specifically includes the following elements:

[0073] (1) Fiber insertion angle: refers to the angle between the fiber insertion path and the skin surface or standard direction (such as vertical direction), which affects the difficulty and safety of the operation.

[0074] (2) Distance between the optical fiber and key brain tissues: This refers to the minimum safe distance between the optical fiber path and key brain structures (such as blood vessels, nerve bundles, functional areas, etc.) in three-dimensional space. The larger the distance, the higher the path safety.

[0075] (3) Distance variance of the optical fiber coverage of the tumor target point: refers to the variance of the distance distribution between the optical fiber path and multiple target points in the tumor area, reflecting the uniformity of the path's coverage of the tumor area. The smaller the variance, the more concentrated the coverage and the more uniform the ablation effect.

[0076] (4) Fiber coverage of tumor: refers to the ratio of the tumor volume that can be covered by the fiber within its effective ablation range to the total tumor volume. It is an important indicator reflecting the completeness of treatment.

[0077] (5) Fiber length: refers to the length of the path from the insertion starting point to the end point. It is usually required to be moderate. Too long may cause puncture risk, and too short may not be able to penetrate the target area.

[0078] The path evaluation equation is a mathematical function that quantifies the mapping between path information and path evaluation scores. It can take the form of a weighted linear function, a neural network model, or a logistic regression function. The path information of each intermediate fiber path is used as input, and the equation is substituted into the output to produce the corresponding path evaluation score.

[0079] The pathway assessment score is a numerical indicator used to assess the quality of a fiber optic pathway, typically a normalized score. This score comprehensively considers safety, therapeutic efficacy, and operability, and is used to compare and rank all intermediate fiber optic pathways.

[0080] In this embodiment of the present application, after the intermediate fiber path set is screened, each intermediate fiber path in the set is further evaluated to determine the final target fiber path set. Specifically, for each intermediate fiber path in the fiber path set, the corresponding path information is extracted and substituted into a pre-established path evaluation equation to calculate the path evaluation score for the intermediate fiber path.

[0081] Path information is used to characterize the spatial characteristics and ablation potential of each intermediate optical fiber path, and includes at least the following parameters: the optical fiber insertion angle, that is, the angle between the optical fiber insertion path and the standard reference plane, which is used to reflect the operational feasibility of the insertion and the direction of tissue penetration; the distance between the optical fiber and key tissues in the brain, which is used to measure the safety of the path in avoiding key tissues (such as blood vessels, functional areas, etc.); the distance variance of the optical fiber coverage of the tumor target point, which reflects the uniformity of the optical fiber path's coverage distribution of various targets in the tumor; the optical fiber coverage rate of the tumor, that is, the ratio of the effective range of the optical fiber to the total tumor volume, which is used to reflect the completeness of the treatment; and the optical fiber length, which is used to limit the actual feasibility of the path and the adaptability of the device.

[0082] Based on the above path information, it is substituted into the path evaluation equation for scoring. This equation is used to establish a mapping relationship between the path evaluation score and the path information. It can be constructed through expert experience modeling, linear weighted formulas, machine learning models, etc. to quantify the quality of each path and output the path evaluation score as a unified evaluation standard. In a specific embodiment, the path evaluation equation can be expressed as Equation (3).

[0083] score ij =w1g θ (θ ij )+w2f d (d ij )+w3g var (var ij )+w4f c (c ij )+w5g I (l ij )

[0084]

[0085] Among them, θ ij is the fiber insertion angle, d ij is the distance between the optical fiber and the key tissue in the brain, var ij is the distance variance of the fiber covering the tumor target point, l ij is the coverage of the fiber to the tumor and the fiber length. Weights w1 to w5 are the weight coefficients of each clinical indicator, g and f are functional relationships, and x is the function variable, for example, θ ij d ij var ij and l ij .

[0086] Step 302 : sorting each intermediate optical fiber path in the set of intermediate optical fiber paths according to the path evaluation score to obtain a sorting result.

[0087] The ranking result is the result of arranging all intermediate optical fiber paths in descending order (or from best to worst) according to their path evaluation scores. This result is used to determine which paths are selected as the final implementation optical fibers.

[0088] In this embodiment of the present application, after obtaining the path evaluation scores of all intermediate fiber paths, all paths in the set of intermediate fiber paths are sorted according to the evaluation scores to generate a sorting result. The sorting can be performed from high to low scores, so that fiber paths with higher scores and better overall performance are arranged first, facilitating subsequent priority selection.

[0089] Step 303 : Determine a target optical fiber path set from the intermediate optical fiber path set based on the number of optical fibers required for tumor ablation and the ranking result.

[0090] In this embodiment, based on the determined number of optical fibers required for tumor ablation and the ranking results, a corresponding number of optical fiber paths are sequentially selected from the top-ranked intermediate optical fiber paths to determine the target optical fiber path set. The final selected target optical fiber path set is the path set to be used in the actual ablation operation, which has high ablation coverage, safety, and feasibility.

[0091] In one embodiment, Figure 4 As shown, the above-mentioned “determining a target optical fiber path set from an intermediate optical fiber path set based on the number of optical fibers required for tumor ablation and the ranking result” includes:

[0092] Step 401 : When the number of optical fibers required for tumor ablation is not greater than a preset value, all feasible intermediate optical fiber path combinations are screened from the intermediate optical fiber path set according to a predetermined coverage matrix.

[0093] The coverage matrix is ​​used to describe the coverage relationship between each optical fiber in the intermediate optical fiber path set and each target point in the tumor area. It is usually a two-dimensional matrix with the following structure:

[0094] Rows: represent different intermediate fiber paths;

[0095] Column: represents multiple target points (or voxels) divided in the tumor area;

[0096] Element value: Indicates whether a fiber can cover the corresponding target point, for example: 1 for coverage; 0 for non-coverage; or a floating-point number representing coverage strength / probability. This coverage matrix serves as the basic data structure for path combination screening, used to determine whether a particular intermediate fiber path combination can cover the entire tumor area or a preset proportion.

[0097] Intermediate fiber path combinations refer to multiple fiber path subsets formed from the intermediate fiber path set according to specific rules. The number of fibers in each subset is less than or equal to a preset value, and they jointly cover the tumor area spatially. These combinations must meet the coverage completeness requirements defined by the coverage matrix. That is, all fiber paths in the combination must jointly cover all key target points in the tumor area or the coverage rate must reach a preset threshold (such as 90%). All "feasible combinations" are generated based on these conditions.

[0098] Screening for intermediate fiber pathways with the required number of fibers for tumor ablation involves further selecting fiber pathways with the same number of fibers required for tumor ablation based on the pathway evaluation ranking results from all intermediate fiber pathway combinations that meet the coverage requirements. Prioritizing the top-ranked fibers during screening ensures optimal pathway quality and surgical outcomes while ensuring coverage.

[0099] In an embodiment of the present application, when the number of optical fibers required for tumor ablation is not greater than a preset value, all feasible path combinations are screened from the intermediate optical fiber path set based on a pre-constructed coverage matrix as candidate optical fiber combinations.

[0100] The preset value for the fiber path set is the maximum number of fibers that can be inserted, typically determined based on clinical operational limits, patient tolerance, or navigation system channel limitations. For example, in some application scenarios, a maximum of four or six fibers can be inserted simultaneously, so the preset value is 4 or 6. If the currently calculated number of fibers required for tumor ablation does not exceed this value, the combination optimization phase begins.

[0101] The coverage matrix is ​​a two-dimensional structure matrix whose rows represent each fiber in the set of intermediate fiber paths and whose columns represent each target point (or voxel unit) divided in the tumor area. The matrix elements are used to indicate whether a specific fiber can effectively cover a target point, for example, using the Boolean value "1" to indicate coverage and "0" to indicate non-coverage, or using real values ​​to express the degree of coverage. This coverage matrix is ​​constructed based on the three-dimensional spatial mapping of fiber paths and tumor areas, and can quantify the spatial coverage relationship under multiple path combinations.

[0102] Based on the coverage matrix, all intermediate fiber path combinations that do not exceed a preset limit are traversed, and feasible fiber combinations that can jointly cover all or a preset proportion of target points are selected. For example, if a coverage rate of 95% is required, only combinations whose combined coverage of target points meets this threshold are selected. This results in a set of all feasible fiber combinations that meet the requirement for complete tumor coverage.

[0103] Step 402 : Filter out intermediate optical fiber paths with the number of optical fibers required for tumor ablation from the intermediate optical fiber path combination according to the sorting result, and determine the filtered intermediate optical fiber paths as the target optical fiber path set.

[0104] In an embodiment of the present application, after obtaining the above-mentioned feasible combinations, these combinations are further screened in combination with the calculated path evaluation scores and the ranking results. The intermediate fiber paths with the same number of optical fibers as those required for tumor ablation are preferentially selected from the top-ranked fiber paths to form the final target fiber path set. This set not only meets the spatial coverage requirements of the tumor area, but also has advantages in multiple dimensions such as insertion angle, path length, and safety, and is suitable for subsequent surgical operations or navigation guidance. The final target fiber path set will contain the spatial position information and ablation parameters of each optical fiber.

[0105] In a specific embodiment, the preset value may be 2. In this case, when the number of required optical fibers is less than or equal to 2, all feasible pathway combinations are first screened based on the coverage matrix. The pathway combination that best meets clinical preferences is then selected based on the pathway evaluation score. This search, which comprehensively considers factors such as damage to normal tissue, insertion angle, and distance to critical tissue, facilitates obtaining pathway results that meet clinical constraints.

[0106] In one embodiment, Figure 5 As shown, the above-mentioned “determining a target optical fiber path set from an intermediate optical fiber path set based on the number of optical fibers required for tumor ablation and the ranking result” includes:

[0107] Step 501 : When the number of optical fibers required for tumor ablation is greater than a preset value, an initial path having the number of optical fibers required for tumor ablation is selected from a set of intermediate optical fiber paths according to a sorting result.

[0108] In the embodiments of this application, if the tumor area is large or the lesion distribution is complex, the number of optical fibers required for tumor ablation may exceed the preset value. To solve the path optimization problem under such high-dimensional combinations, this embodiment further introduces an iterative optimization algorithm to obtain a fiber layout solution that strikes a balance between accuracy and efficiency.

[0109] Specifically, if the number of fibers required for tumor ablation in a fiber path set exceeds a preset value, the initial path set is selected based on the generated intermediate fiber path sets and their corresponding path evaluation and sorting results. This initial path set provides a foundational solution for the subsequent optimization algorithm, accelerating convergence.

[0110] Step 502: for each initial path, iteratively optimize the initial path using a simulated annealing algorithm to obtain an intermediate path.

[0111] In the present embodiment, multiple rounds of iterative optimization were performed using a simulated annealing algorithm for each of the initial paths. This algorithm is a heuristic optimization algorithm with global search capabilities. By simulating the gradual temperature reduction and stabilization during the physical annealing process, it locally perturbs the path and accepts some non-optimal solutions, thereby avoiding falling into local optima.

[0112] In each iteration, a new intermediate path is generated through random substitution, adjusting the insertion angle, or fine-tuning the pathpoint set. Its path evaluation score is then calculated. A probabilistic acceptance strategy is used to decide whether to accept the new path based on the difference between the current temperature and the path score. As the number of iterations increases, the temperature gradually decreases, and the algorithm stabilizes.

[0113] Step 503 : When a preset number of iterations is met, an optimal path is selected from the initial path and multiple intermediate paths, and the optimal path is determined as a target optical fiber path set.

[0114] In this embodiment, after reaching a preset number of iterations, a set of paths with the highest overall scores is selected from the initial path and multiple generated intermediate paths based on the path evaluation scores as the final target fiber path set. This target fiber path set not only ensures tumor coverage integrity and quantity requirements, but also takes into account path safety, operability, and device compatibility.

[0115] In a specific embodiment, when more than two optical fibers are required for coverage, a greedy strategy is first used to select an initial solution based on the path evaluation score to meet a certain ablation rate requirement. Subsequently, iterative optimization is performed based on this initial solution to reduce the number of paths and further improve the ablation rate of the surgical plan.

[0116] Through the above method, in scenarios with a large number of optical fibers and complex combination space, efficient and reliable path optimization and target path output can still be achieved, effectively improving the scientific nature and individualization of the ablation plan.

[0117] In one embodiment, Figure 6 As shown, the above-mentioned "using the simulated annealing algorithm to iteratively optimize the initial path to obtain the intermediate path" includes:

[0118] Step 601: Construct a neighborhood path set of the initial path based on the initial path; the neighborhood path set is composed of paths distributed around the initial path in three-dimensional space; the neighborhood path set satisfies the path conditions that the Euclidean distance between the starting point of all neighborhood paths and the starting point of the initial path is less than a first distance threshold, and the Euclidean distance between the end point of the neighborhood path and the end point of the initial path is less than a second distance threshold.

[0119] In an embodiment of the present application, in the process of iteratively optimizing the initial path using the simulated annealing algorithm to obtain the intermediate path, first, based on the current initial path, a neighborhood path set with a close spatial distribution in three-dimensional space is constructed. The neighborhood path set of the optical fiber path set refers to a group of paths that meet the following spatial constraints: the Euclidean distance between the starting point of each path and the starting point of the initial path is less than a first distance threshold, and the Euclidean distance between the end point and the end point of the initial path is less than a second distance threshold. This neighborhood path construction strategy ensures that the generated path is close to the original path in spatial layout, so that it has similar puncture direction and surgical accessibility, which is conducive to improving diversity while maintaining the rationality of local search.

[0120] Step 602 : Based on an equal probability selection strategy, a path that covers the largest number of target treatment areas or a path with the smallest path coverage variance is selected from the neighborhood path set to obtain a candidate path.

[0121] In the embodiment of the present application, after constructing a set of neighborhood paths, an equal probability selection strategy is used to select candidate paths from them. Specifically, among the paths that meet the spatial constraints, the path with the largest number of coverage in the target treatment area or the smallest variance in the path coverage distance is preferentially selected as the candidate path to balance coverage and uniformity. The number of path coverage is used to measure the absolute coverage ability of the path to the tumor target point, while the path coverage variance reflects whether the spatial distribution between the target points is balanced, which helps to improve the uniformity of heat distribution and the comprehensiveness of the treatment effect.

[0122] Step 603: When the coverage of the tumor by the candidate path is less than a preset coverage threshold, the candidate path is deleted, and the deleted candidate path is evaluated according to a pre-constructed energy function to obtain an intermediate path; wherein the energy function includes a path quantity term, a coverage variance-related term, and an overall ablation rate penalty term. The energy function is used to evaluate the degree of optimization of the candidate path. The optimization goal of the energy function is to minimize the required number of paths and achieve a balanced distribution of the coverage area in space while meeting the clinically required ablation rate.

[0123] In this embodiment of the present application, if the coverage of a candidate path for the tumor is less than a preset coverage threshold, the candidate path is deleted. A pre-built energy function is introduced to optimize and evaluate the deleted candidate path to obtain the intermediate path corresponding to the current iteration. This energy function comprehensively considers factors such as the number of paths, coverage balance, and overall ablation rate, and specifically includes the following three contents:

[0124] (1) Path number item: used to measure the total number of fiber paths in the current scheme, with the goal of reducing the number of interventional paths, thereby reducing surgical trauma and operation complexity;

[0125] (2) Coverage variance related terms: used to quantify the spatial distribution uniformity of the covered target area. The smaller the variance, the more balanced the coverage area, which improves the consistency of the ablation effect.

[0126] (3) Overall ablation rate penalty: When a path combination fails to achieve the preset tumor area coverage (such as 90% or 95%), a penalty is introduced to reduce the energy function score of the path combination, encouraging the algorithm to converge toward a higher coverage.

[0127] The global optimization goal of this energy function is to minimize the number of required pathways while satisfying the clinically required minimum ablation rate constraint and achieving a balanced spatial distribution of coverage areas. By evaluating the energy function value of candidate pathways in each round of simulated annealing, and combining it with an annealing probability strategy to decide whether to accept the candidate pathway, the optimized intermediate pathway is ultimately obtained after multiple rounds of iterations, which is then used to further construct the target fiber pathway set.

[0128] In a specific embodiment, the iterative optimization is designed using a simulated annealing optimization method. In order to solve the LITT planning problem, a neighborhood construction, a new path construction, and a calculation strategy for the energy function are specially designed. The neighborhood set of path k is defined as all paths whose endpoints are less than a certain distance from the endpoint of path k. The neighborhood of each path is updated after each iteration. For the new path construction, in the neighborhood set N, the path with the largest number of covered target points or the smallest variance is selected with equal probability, representing the optimization trend of the iterative process towards optimal coverage and optimal coverage efficiency, respectively. The energy function f consists of three parts: the number of paths, the second term related to efficiency (g in the score), and the second term related to efficiency. var (var ij )) and the overall ablation rate, where the first item, the number of pathways, ensures that the iteration results in the minimum number of optical fibers, and the second and third items ensure compliance with clinical constraints.

[0129] In one embodiment, Figure 7 As shown, the above-mentioned “determining the number of optical fibers required for tumor ablation based on the set of intermediate optical fiber paths” includes:

[0130] Step 701 : Based on the path information corresponding to the intermediate optical fiber paths, the paths in the intermediate optical fiber path set are combined to obtain a plurality of path combinations.

[0131] In this embodiment, based on the path information corresponding to each fiber in the intermediate fiber path set, the paths in the set are first combined to construct multiple possible fiber path combination schemes. The path combination construction process considers the spatial relationship between the paths and the coverage effect, aiming to explore the adaptability and effectiveness of different path configurations for tumor ablation coverage.

[0132] Step 702 : For each path combination, if there is no spatial conflict between any two optical fiber paths in the path combination and the preset tumor area ablation coverage requirement is met, the number of optical fibers in the path combination is determined as the number of optical fibers required for tumor ablation.

[0133] In the present embodiment, for each path combination, a determination is made as to whether any two fiber paths in the combination experience spatial conflict. Spatial conflict refers to overlapping or close proximity of the paths of two fiber paths in three-dimensional space, potentially leading to physical interference or safety risks during surgical procedures. If no such conflict exists in the path combination, the combination is deemed spatially feasible.

[0134] Furthermore, it is necessary to confirm that the combined fiber path sets meet the pre-defined tumor region ablation coverage requirements. Specifically, the target tumor region covered by the combined paths must meet or exceed the clinically defined coverage threshold to ensure therapeutic efficacy. Coverage requirements include coverage rate and coverage uniformity metrics to ensure the integrity and balance of the ablation region.

[0135] When the path combination meets the above-mentioned spatial non-conflict and ablation coverage requirements, the computer device uses the number of optical fibers in the path combination as the basis for determining the number of optical fibers required for the current tumor ablation.

[0136] The above embodiment realizes the reasonable screening of the optical fiber path configuration, ensuring that the number of selected optical fibers not only meets the safety of the operation but also achieves the ideal treatment coverage effect.

[0137] In one embodiment, Figure 8 As shown, the above method also includes:

[0138] Step 801 : Based on a pre-built Lagrangian relaxation optimization model, the minimum number of optical fiber paths under the condition of complete tumor coverage is determined.

[0139] In this embodiment, a pre-built Lagrangian relaxation optimization model is used to determine the minimum number of fiber paths required for complete tumor coverage. By relaxing the constraints, this model transforms the original complex path optimization problem into a solvable mathematical optimization problem, aiming to find the minimum number of fiber paths required to achieve complete tumor coverage. This theoretical lower bound reflects the minimum number of paths required to achieve complete tumor coverage under ideal conditions, providing a reference benchmark for fiber planning.

[0140] Step 802 : If the number of optical fibers required for tumor ablation is consistent with the minimum number of optical fiber paths and the target optical fiber path set can achieve complete coverage of the tumor area, the target optical fiber path set is determined to be a valid optical fiber path set.

[0141] In this embodiment of the present application, when the number of optical fibers required for tumor ablation is consistent with the minimum number of optical fiber paths described above, a further determination is made as to whether the selected target optical fiber path set can achieve complete coverage of the tumor area. Complete coverage means that the tumor target points covered by the target optical fiber path set meet the clinically defined coverage threshold, ensuring the adequacy and safety of the treatment.

[0142] If the two aforementioned conditions are met—that is, the number of optical fibers required for tumor ablation equals the theoretical minimum number of pathways and the target pathway set achieves complete coverage—the target pathway set is considered a valid pathway set. A valid pathway set represents the optimal pathway planning solution in terms of both pathway number and coverage, demonstrating high clinical application value and feasibility.

[0143] In a specific embodiment, after iterating to obtain the path, Lagrangian relaxation is used to quickly calculate the fiber lower bound and evaluate the mathematical optimality of the result. Existing technical solutions have not yet used this method to verify the optimality of the solution. The iterative process is shown in formula (4).

[0144]

[0145] When c=e, the optimal solution corresponds to the minimum number of paths. The optimal solution of the original problem is denoted as Z p0 , the optimal solution of the relaxed problem is denoted as Z p1 Taking λ = 0, the problem can be simplified to a standard set covering problem, and its optimal solution is denoted as Z p2 If the number of paths obtained by the iterative algorithm is Z h , and the tumor is completely ablated, then the following inequality holds: Z h ≥Z p0 ≥Z p1 ≥Z p2 When the upper bound Z of the problem h and the lower bound Z p2When they are equal, the mathematical optimality of the method can be verified, and the location of the optimal fiber path can be output eventually.

[0146] In a specific embodiment, Figure 9 As shown, Figure 9 It is used to accurately generate safe, efficient and disease-adapted optical fiber pathways for optical fiber ablation treatment of tumors such as gliomas, achieving a deep integration of clinical needs and technical feasibility.

[0147] The process primarily determines whether more than two optical fibers are needed for tumor ablation. Branching strategies are then implemented based on clinical characteristics such as tumor size and morphological complexity.

[0148] When the number of optical fibers required for tumor ablation is ≤ 2 (suitable for scenarios with small tumors and simple path constraints), all feasible path combinations of 1-2 optical fibers are first traversed based on medical images such as T1ce enhanced MRI and safety constraints such as avoiding critical brain structures. Then, a weighted score is calculated based on evaluation parameters such as insertion angle compliance, tumor coverage completeness, and safety distance to select the path that best meets clinical needs and output it directly.

[0149] If the number of optical fibers required for tumor ablation is greater than 2 (suitable for scenarios with large tumors and irregular shapes), the initial path is heuristically constructed using a greedy rule (such as prioritizing coverage of the tumor center), and then a loop optimization of "neighborhood update - new path construction - iterative termination judgment" is entered:

[0150] The paths with endpoint distances <5 mm are dynamically defined as neighborhoods to narrow the search space. Within the neighborhood, the paths with the largest coverage of the unablated area and the smallest path variance are replaced with equal probability as the dual objectives. The results are then output after multiple iterations without any optimization of the path parameters.

[0151] Regardless of the strategy, the theoretical lower bound of the number of optical fibers is calculated using Lagrangian relaxation, set cover problem modeling, and branch-and-bound methods to verify whether the path is mathematically optimal (i.e., the actual number of optical fibers used is consistent with the theoretical minimum). Ultimately, the three-dimensional coordinates of the fiber entry point and target are output for surgical navigation, achieving a technical closed loop of "clinical needs guide path planning, mathematical verification ensures optimality, and iterative optimization adapts to complex conditions." This addresses the lack of adaptability of a single strategy, balances treatment safety and efficiency, and provides core technical support for fiber-optic ablation surgery. The number of optical fibers is the number required for tumor ablation.

[0152] In one embodiment, Figure 10 As shown, the above method also includes:

[0153] Step 901 : for each target optical fiber path, based on the spatial direction of the target optical fiber path, the ablation range corresponding to the target optical fiber path is modeled as a rotating ellipsoid with the target optical fiber path as the axis of symmetry.

[0154] Among them, the spatial direction of the target optical fiber path refers to the specific position and direction of the target optical fiber path in three-dimensional space, including the path trajectory of the optical fiber from entering the human body to the termination position, which is used to determine the spatial distribution of the ablation effect.

[0155] A rotating ellipsoid is a three-dimensional ellipsoidal shape formed by rotating around the target fiber path as its axis of symmetry. This model is used to approximate the diffusion range of ablation energy around the fiber and reflect the spatial coverage area of ​​ablation therapy.

[0156] In the embodiments of the present application, for each target fiber path in a fiber path set, the ablation range corresponding to the fiber is modeled as a rotating ellipsoid with the target fiber path as the axis of symmetry based on its spatial orientation in three-dimensional space, that is, the specific path and direction of the target fiber path from entry into the human body to its termination position. The fiber path set rotating ellipsoid refers to a three-dimensional ellipsoid generated by rotating about the axis of the fiber path, which is used to approximately describe the spatial distribution range of the ablation energy around the fiber, thereby reflecting the fiber's coverage of the tumor during actual treatment.

[0157] Step 902: Obtain the spatial intersection of the target optical fiber path and the tumor area as the corresponding target treatment area.

[0158] Among them, the target treatment area refers to the spatial intersection of the rotating ellipsoid and the tumor area, that is, the tumor volume area that the optical fiber can actually affect and treat, and is the effective range of optical fiber ablation.

[0159] In an embodiment of the present application, the spatial intersection of the rotating ellipsoid and the tumor area is obtained as the target treatment area of ​​the target optical fiber path. This area represents the subset of the tumor volume where the optical fiber can effectively act and achieve ablation.

[0160] Step 903 : Perform equidistant sampling along the path direction of the target optical fiber path to obtain multiple candidate ablation points, and construct a two-dimensional cross section perpendicular to the target optical fiber path at each candidate ablation point.

[0161] Equidistant sampling involves selecting a number of points at regular intervals along the fiber path as candidate ablation points. These points represent potential ablation locations, facilitating step-by-step control of the ablation process and enabling precise tumor treatment.

[0162] The two-dimensional cross section is a plane cut perpendicular to the direction of the optical fiber path at each candidate ablation point. It is used to analyze the coverage of the tumor area near the point and facilitate the calculation and evaluation of the local ablation effect.

[0163] In this embodiment of the present application, equidistant sampling is performed along the target fiber path. This means that multiple candidate ablation points are selected sequentially at fixed spatial intervals. These points represent potential ablation locations, facilitating precise point-by-point treatment of tumors. At each candidate ablation point, a two-dimensional cross-section perpendicular to the fiber path is constructed. The two-dimensional cross-section of the fiber path is a plane passing through the candidate point and perpendicular to the fiber direction, facilitating analysis of the spatial coverage of tumors near that location.

[0164] Step 904 : For each candidate ablation point, a maximum distance function from the candidate ablation point to the target treatment area within the cross section is calculated. The maximum distance function is used to represent the maximum treatment requirement of the candidate ablation point in the local area.

[0165] Among them, the farthest distance function is a function value that measures the maximum distance from the candidate ablation point to the boundary of the target treatment area, reflecting the maximum treatment demand of the ablation point in the local cross section and assisting in determining the ablation energy coverage range.

[0166] In an embodiment of the present application, for each candidate ablation point, a maximum distance function from the point to the target treatment area in the corresponding two-dimensional cross-section is calculated. This function quantifies the maximum treatment demand of the candidate ablation point in the local area, that is, the maximum distance from the candidate point to the tumor boundary, reflecting the coverage range that the ablation energy needs to achieve in this plane.

[0167] In step 905, based on the farthest distance function, a target ablation point and a short axis radius corresponding to the target ablation point are iteratively selected from multiple candidate ablation points to form a rotating ellipsoid, so that the target treatment area is completely covered in the cross-sectional direction and the number of optical fibers required is minimized while ensuring coverage integrity.

[0168] The minor axis radius is half the length of the minor axis of the ellipsoid in a cross section perpendicular to the fiber path. This parameter is used to adjust the lateral coverage of the ellipsoid to meet the coverage requirements of tumor treatment.

[0169] In this embodiment, based on the aforementioned maximum distance function, an iterative approach is employed to select target ablation points and their corresponding minor axis radius from multiple candidate ablation points to form a rotating ellipsoid. The minor axis radius is defined as half the length of the minor axis of the ellipsoid, measured in a cross section perpendicular to the fiber path. This iterative selection process aims to ensure complete coverage of the target treatment area along the cross-sectional direction, while optimizing the number of optical fibers required while ensuring complete coverage, leading to the optimal design of the ablation path.

[0170] In a specific embodiment, based on the optimal path, the ablation area is planned to evaluate the path.

[0171] Considering that the ablation range of a single time is an axisymmetric ellipsoid, the ablation zone planning is to place multiple ellipsoid centers on the axis of symmetry to achieve complete coverage of the ablation area. Therefore, the preoperative segmentation results can be resampled to simplify the planning problem from a three-dimensional space to a two-dimensional coverage problem. The resampling process is shown in the figure below. First, the intersection T of the single path ablation range and the tumor segmentation area is selected as the treatment area, as shown in Figure 11 As shown in Figure 1, the intersection of the ablation range of a single path and the tumor range is T. Subsequently, equidistant sampling is performed along the path to obtain a candidate ablation point k, and a plane P perpendicular to the path (i, j) is constructed at the candidate ablation point k. k ,like Figure 11 As shown. If P k The intersection area with T is recorded as A k , then the function is as shown in formula (5).

[0172]

[0173] f(k) represents the candidate ablation point k to region A k The maximum distance to any point in Figure 11 As shown in Figure 2. After obtaining the function f(k), ablation zone planning is equivalent to placing the centers of several symmetrical ellipses along the x-axis path (i, j) to ensure that the function f(x) is completely covered. The center position and minor axis radius of the ellipse correspond to the ablation point and ablation radius in LITT, respectively.

[0174] According to Step 1-Step 4, the greedy rule is used to solve the ablation point {o} and the ablation radius {b} to facilitate the evaluation of the planning results.

[0175] Step 1, set F = U{f(k)};

[0176] Step 2, take b = min (max (F) + 1, r thre ),o=argmax(F);

[0177] Step 3. Draw an ellipse T with o as the center and b as the short semi-circumference, and calculate F. t =∪ k∈T {f(k)};

[0178] Step 4. F=F\F t ,if Repeat Step 2-Step 4, otherwise, end.

[0179] Among them, Step 1: Construct the distance requirement set to be covered

[0180] First, execute Step 1 and aggregate the maximum coverage distance functions f(k) corresponding to all candidate ablation points k into a set F using F = U{f(k)}. f(k) describes the maximum distance of the tumor area that needs to be covered when ablation is performed centered on candidate point k. After aggregation, F represents all required distances within the tumor that need to be covered by ablation. This effectively consolidates scattered ablation requirements into a single set, facilitating subsequent planning.

[0181] Step 2: Determine the core parameters of the first ablation point

[0182] Enter Step 2, calculate b = min (max (F) + 1, r thre ), o = argmax(F). Where max(F) is the most difficult distance to cover in the set (the point in the tumor area that requires the largest ablation range), b takes max(F) + 1 (theoretical coverage radius) and the clinical safety threshold r thre The smaller value ensures that the ablation covers the required area without damaging normal tissue. o is the candidate point corresponding to the maximum value of F. It is selected as the center of the first ablation point to prioritize the most critical coverage requirement.

[0183] Step 3: Cover the area with an ellipse and mark the covered requirements

[0184] In Step 3, draw an axisymmetric ellipse T along the fiber path with o as the center and b as the minor semi-axis. This ellipse is the range that the current ablation point can cover. Then find all f(k) contained in the ellipse T and merge them into F t , meaning that the tumor areas corresponding to these f(k) points have already been covered by the current ablation point, and subsequent replanning is unnecessary. This step transforms the abstract distance requirement into the physical area that can be covered by the actual ablation, clarifying the requirements that have been addressed.

[0185] Step 4: Update the set to be covered, loop or end

[0186] Finally, in Step 4, F=F\F t The requirements F in F that are covered by ellipse T t Eliminate , and the remaining F is the tumor area that still needs to be covered by ablation. This means there are still uncovered areas. Return to Step 2 and repeat selecting new ablation points, calculating the radius, and drawing an ellipse. If The ablation requirements of all tumor areas are covered, and planning is complete. This iterative cycle allows the entire tumor to be covered with the minimum number of ablation point combinations, balancing treatment efficacy and safety costs.

[0187] In one embodiment, the method further includes:

[0188] Step 1: Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information is segmented and sampled in sequence to obtain a set of candidate optical fiber paths.

[0189] Step 2: According to the fiber planning objective function and the fiber planning constraints, the candidate fiber path set is screened to obtain the intermediate fiber path set.

[0190] Step 3: Based on the path information corresponding to the intermediate optical fiber paths, the paths in the intermediate optical fiber path set are combined to obtain multiple path combinations.

[0191] Step 4: For each path combination, if there is no spatial conflict between any two optical fiber paths in the path combination and the preset tumor area ablation coverage requirements are met, the number of optical fibers in the path combination is determined as the number of optical fibers required for tumor ablation.

[0192] Step 5: For each intermediate fiber path in the intermediate fiber path set, the path information corresponding to the intermediate fiber path is substituted into a pre-constructed path evaluation relationship to determine the path evaluation score of the intermediate fiber path; the path evaluation relationship is used to characterize the correspondence between the path evaluation score and the path information; the path information includes at least the fiber insertion angle, the distance between the fiber and the key tissue in the brain, the distance variance of the fiber coverage of the tumor target point, the fiber coverage rate of the tumor, and the fiber length.

[0193] Step 6: sort each intermediate optical fiber path in the intermediate optical fiber path set according to the path evaluation score to obtain a sorting result.

[0194] Step 7: When the number of optical fibers required for tumor ablation is not greater than a preset value, all feasible intermediate optical fiber path combinations are screened from the intermediate optical fiber path set according to a predetermined coverage matrix.

[0195] Step 8: Screen out intermediate optical fiber paths with the required number of optical fibers for tumor ablation from the intermediate optical fiber path combination according to the sorting result, and determine the screened intermediate optical fiber paths as the target optical fiber path set.

[0196] Step 9: When the number of optical fibers required for tumor ablation is greater than a preset value, an initial path with the number of optical fibers required for tumor ablation is selected from the set of intermediate optical fiber paths according to the sorting result.

[0197] Step 10: For each initial path, a neighborhood path set of the initial path is constructed based on the initial path; the neighborhood path set is composed of paths distributed around the initial path in three-dimensional space; the neighborhood path set satisfies the path conditions that the Euclidean distance between the starting point of all neighborhood paths and the starting point of the initial path is less than a first distance threshold, and the Euclidean distance between the end point of the neighborhood path and the end point of the initial path is less than a second distance threshold.

[0198] Step 11: Based on the equal probability selection strategy, the path covering the largest number of target treatment areas or the path with the smallest path coverage variance is selected from the neighborhood path set to obtain a candidate path.

[0199] Step 12: When the coverage of the tumor by the candidate path is less than the preset coverage threshold, the candidate path is deleted, and the deleted candidate path is evaluated according to the pre-constructed energy function to obtain the intermediate path; wherein the energy function includes the path number term, the coverage variance related term and the overall ablation rate penalty term. The energy function is used to evaluate the degree of optimization of the candidate path. The optimization goal of the energy function is to minimize the required number of paths and achieve a balanced distribution of the coverage area in space while meeting the clinically required ablation rate.

[0200] Step 13: When a preset number of iterations is met, an optimal path is selected from the initial path and multiple intermediate paths, and the optimal path is determined as a target optical fiber path set.

[0201] Step 14: Based on the pre-built Lagrangian relaxation optimization model, the minimum number of optical fiber paths under the condition of complete tumor coverage is determined.

[0202] Step 15: If the number of optical fibers required for tumor ablation is consistent with the minimum number of optical fiber paths and the target optical fiber path set can achieve complete coverage of the tumor area, the target optical fiber path set is determined to be a valid optical fiber path set.

[0203] Step 16: For each target optical fiber path, based on the spatial direction of the target optical fiber path, the ablation range corresponding to the target optical fiber path is modeled as a rotating ellipsoid with the target optical fiber path as the symmetry axis.

[0204] Step 17: Obtain the spatial intersection of the target optical fiber path and the tumor area as the corresponding target treatment area.

[0205] Step 18: Perform equidistant sampling along the path direction of the target optical fiber path to obtain multiple candidate ablation points, and construct a two-dimensional cross section perpendicular to the target optical fiber path at each candidate ablation point.

[0206] Step 19: For each candidate ablation point, a maximum distance function from the candidate ablation point to the target treatment area within the cross section is calculated. The maximum distance function is used to represent the maximum treatment requirement of the candidate ablation point in the local area.

[0207] In step 20, based on the farthest distance function, the target ablation point and the short axis radius corresponding to the target ablation point are iteratively selected from multiple candidate ablation points to form a rotating ellipsoid, so that the target treatment area is completely covered in the cross-sectional direction, and the number of optical fibers required is minimized while ensuring coverage integrity.

[0208] It should be noted that the execution order of steps 7 to 8 and steps 9 to 13 is not limited. In actual execution, steps 7 to 8 or steps 9 to 13 can be executed according to the number of optical fibers required for tumor ablation.

[0209] In one embodiment, Figure 12 As shown, the method further includes:

[0210] The first is the information input stage, which uses the patient's preoperative T1-weighted enhanced magnetic resonance imaging (T1ce image) and tumor area segmentation results as basic data.

[0211] Next, we enter the planning model establishment stage. First, we confirm the planning constraints based on clinical safety requirements (such as avoiding key structures such as the brainstem and large blood vessels), and then use the imaging data to calculate planning parameters such as path angle and safety distance, and finally construct the fiber optic planning model.

[0212] This is followed by the path solving and evaluation stage, where the "fiber path search and optimization" algorithm is used to find possible fiber paths under model constraints; then mathematical methods such as "Lagrangian relaxation" are used to verify the optimality of the path (ensuring that the tumor is covered with the least fiber and the safest path), and finally the precise fiber position is determined.

[0213] The last stage is the ablation plan evaluation. First, the ablation area is planned based on the optical fiber position (simulating the ablation range to see whether the tumor is completely covered). Then, "planning visualization" (such as 3D model display) is used to allow the doctor to make an intuitive judgment. Finally, a "clinical evaluation" is performed based on clinical experience to confirm whether the plan is safe and effective.

[0214] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0215] Based on the same inventive concept, the embodiments of the present application also provide a multi-fiber laser ablation treatment device for glioma planning, which is used to implement the aforementioned multi-fiber laser ablation treatment method for glioma planning. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the multi-fiber laser ablation treatment device for glioma planning provided below can be found in the limitations of the multi-fiber laser ablation treatment method for glioma planning described above, and will not be repeated here.

[0216] In one embodiment, Figure 13 As shown, a planning device for multi-fiber laser ablation treatment of brain glioma is provided, comprising: a segmentation module 1001, a screening module 1002 and a determination module 1003, wherein:

[0217] The segmentation module 1001 is used to perform segmentation and sampling processing on the image information in sequence based on the pre-acquired image information of the target patient and the segmentation result of the tumor area to obtain a set of candidate optical fiber paths;

[0218] A screening module 1002 is configured to screen a set of candidate fiber paths based on a fiber planning objective function and fiber planning constraints to obtain a set of intermediate fiber paths, and determine the number of optical fibers required for tumor ablation based on the set of intermediate fiber paths;

[0219] The determination module 1003 is configured to determine a target fiber path set from the intermediate fiber path set based on the number of optical fibers required for tumor ablation and a predetermined path evaluation score; the target fiber path set includes at least position information corresponding to each target fiber path.

[0220] In one embodiment, the above-mentioned determination module 1003 is specifically used to substitute the path information corresponding to each intermediate optical fiber path in the intermediate optical fiber path set into a pre-constructed path evaluation relationship to determine the path evaluation score of the intermediate optical fiber path; the path evaluation relationship is used to characterize the correspondence between the path evaluation score and the path information; the path information at least includes the optical fiber insertion angle, the distance between the optical fiber and the key tissue in the brain, the distance variance of the optical fiber covering the tumor target point, the coverage rate of the optical fiber on the tumor and the optical fiber length; according to the path evaluation score, each intermediate optical fiber path in the intermediate optical fiber path set is sorted to obtain a sorting result; according to the number of optical fibers required for tumor ablation and the sorting result, the target optical fiber path set is determined from the intermediate optical fiber path set.

[0221] In one embodiment, the above-mentioned determination module 1003 is specifically used to screen out intermediate fiber path combinations of all feasible paths from the intermediate fiber path set according to a predetermined coverage matrix when the number of optical fibers required for tumor ablation is not greater than a preset value; screen out intermediate fiber paths with the number of optical fibers required for tumor ablation from the intermediate fiber path combination according to the sorting result, and determine the screened intermediate fiber paths as the target fiber path set.

[0222] In one embodiment, the determination module 1003 is specifically configured to, when the number of optical fibers required for tumor ablation is greater than a preset value, select an initial path with the required number of optical fibers for tumor ablation from the set of intermediate optical fiber paths based on the sorting result; for each initial path, iteratively optimize the initial path using a simulated annealing algorithm to obtain an intermediate path; and when a preset number of iterations is met, select an optimal path from the initial path and multiple intermediate paths, and determine the optimal path as the target optical fiber path set.

[0223] In one embodiment, the above-mentioned determination module 1003 is specifically used to construct a neighborhood path set of the initial path based on the initial path; the neighborhood path set of the optical fiber path set is composed of paths distributed around the initial path of the optical fiber path set in three-dimensional space; the neighborhood path set satisfies the conditions that the Euclidean distance between the starting point of all neighborhood paths and the starting point of the initial path is less than a first distance threshold, and the Euclidean distance between the end point of the neighborhood path and the end point of the initial path is less than a second distance threshold; in the neighborhood path set, based on an equal probability selection strategy, the path covering the largest number of target treatment areas or the path with the smallest path coverage variance is selected from the neighborhood path set to obtain a candidate path; when the coverage rate of the tumor by the candidate path of the optical fiber path set is less than a preset coverage rate threshold, the candidate path of the optical fiber path set is deleted, and the deleted candidate path is evaluated and processed according to a pre-constructed energy function to obtain an intermediate path; wherein the energy function includes a path number term, a coverage variance related term, and an overall ablation rate penalty term, and the energy function is used to evaluate the degree of optimization of the candidate path. The optimization goal of the energy function is to minimize the required number of paths and achieve a balanced distribution of coverage areas in space while meeting the clinically required ablation rate.

[0224] In one embodiment, the above-mentioned screening module 1002 is specifically used to combine the paths in the intermediate optical fiber path set based on the path information corresponding to the intermediate optical fiber path to obtain multiple path combinations; for each path combination, if there is no spatial conflict between any two optical fiber paths in the path combination and the preset tumor area ablation coverage requirements are met, the number of optical fibers in the path combination is determined as the number of optical fibers required for tumor ablation.

[0225] In one embodiment, the above-mentioned planning device for multi-fiber laser ablation treatment of brain glioma is also used to determine the minimum number of fiber paths under the condition of complete tumor coverage based on a pre-built Lagrangian relaxation optimization model; when the number of optical fibers required for tumor ablation of the fiber path set is consistent with the minimum number of fiber paths in the fiber path set and the target fiber path set of the fiber path set can achieve complete coverage of the tumor area, the target fiber path set of the fiber path set is determined to be a valid fiber path set.

[0226] In one embodiment, the above-mentioned planning device for multi-fiber laser ablation treatment of brain glioma is further used to model, for each target optical fiber path, the ablation range corresponding to the target optical fiber path as a rotating ellipsoid with the target optical fiber path as the axis of symmetry based on the spatial direction of the target optical fiber path; obtain the spatial intersection of the target optical fiber path and the tumor area as the corresponding target treatment area; perform equidistant sampling along the path direction of the target optical fiber path to obtain multiple candidate ablation points, and construct a two-dimensional cross-section perpendicular to the target optical fiber path at each candidate ablation point; for each candidate ablation point, calculate the maximum distance function from the candidate ablation point to the target treatment area within the cross-section, and the maximum distance function is used to characterize the maximum treatment demand of the candidate ablation point in the local area;

[0227] Based on the maximum distance function, the target ablation point used to form the rotating ellipsoid and the short axis radius corresponding to the target ablation point are iteratively selected from multiple candidate ablation points, so that the target treatment area is completely covered in the cross-sectional direction, and the number of optical fibers required is minimized while ensuring coverage integrity.

[0228] Each module in the aforementioned multi-fiber laser ablation treatment planning device for gliomas can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or can be stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0229] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0230] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0231] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0232] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0233] Those skilled in the art can understand the path to implement all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0234] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0235] The above-described embodiments merely represent several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present application. It should be noted that a person skilled in the art may make several modifications and improvements without departing from the concept of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be based on the appended claims.

Claims

1. A planning method for multi-fiber laser ablation treatment of brain glioma, characterized in that: The method comprises: Based on the pre-acquired image information of the target patient and the segmentation result of the tumor area, the image information is sequentially segmented and sampled to obtain a set of candidate optical fiber paths; screening the candidate fiber path set according to the fiber planning objective function and the fiber planning constraints to obtain an intermediate fiber path set, and preliminarily determining the number of optical fibers required for tumor ablation based on the intermediate fiber path set; A target fiber path set is determined from the intermediate fiber path set according to the number of optical fibers required for tumor ablation and a predetermined path evaluation score; the target fiber path set includes at least position information corresponding to each target fiber path.

2. The method according to claim 1, characterized in that Determining a target optical fiber path set from the intermediate optical fiber path set according to the number of optical fibers required for tumor ablation and a predetermined path evaluation score includes: For each intermediate optical fiber path in the set of intermediate optical fiber paths, substituting the path information corresponding to the intermediate optical fiber path into a pre-constructed path evaluation relationship to determine a path evaluation score for the intermediate optical fiber path; the path evaluation relationship is used to characterize the correspondence between the path evaluation score and the path information; the path information at least includes the optical fiber insertion angle, the distance between the optical fiber and the key tissue in the brain, the distance variance of the optical fiber coverage of the tumor target point, the coverage rate of the optical fiber on the tumor, and the optical fiber length; sorting each of the intermediate optical fiber paths in the set of intermediate optical fiber paths according to the path evaluation score to obtain a sorting result; A target optical fiber path set is determined from the intermediate optical fiber path sets according to the number of optical fibers required for tumor ablation and the ranking result.

3. The method according to claim 2, characterized in that Determining a target optical fiber path set from the intermediate optical fiber path set according to the number of optical fibers required for tumor ablation and the ranking result includes: When the number of optical fibers required for tumor ablation is not greater than a preset value, screening out intermediate optical fiber path combinations of all feasible paths from the intermediate optical fiber path set according to a predetermined coverage matrix; According to the ranking result, intermediate optical fiber paths having the required number of optical fibers for tumor ablation are screened out from the intermediate optical fiber path combination, and the screened intermediate optical fiber paths are determined as the target optical fiber path set.

4. The method according to claim 2, characterized in that Determining a target optical fiber path set from the intermediate optical fiber path set according to the number of optical fibers required for tumor ablation and the ranking result includes: When the number of optical fibers required for tumor ablation is greater than a preset value, selecting an initial path with the number of optical fibers required for tumor ablation from the set of intermediate optical fiber paths according to the sorting result; For each initial path, the simulated annealing algorithm is used to iteratively optimize the initial path to obtain an intermediate path; When a preset number of iterations is met, an optimal path is selected from the initial path and the plurality of intermediate paths, and the optimal path is determined as the target optical fiber path set.

5. The method according to claim 4, characterized in that The iterative optimization of the initial path using a simulated annealing algorithm to obtain an intermediate path includes: A neighborhood path set of the initial path is constructed based on the initial path; the neighborhood path set is composed of paths distributed around the initial path in three-dimensional space; the neighborhood path set satisfies the conditions that the Euclidean distance between the starting point of each neighborhood path and the starting point of the initial path is less than a first distance threshold, and the Euclidean distance between the end point of each neighborhood path and the end point of the initial path is less than a second distance threshold; In the neighborhood path set, based on an equal probability selection strategy, a path that covers the largest number of target treatment areas or a path with the smallest path coverage variance is selected from the neighborhood path set to obtain a candidate path; When the coverage of the tumor by the candidate path is less than a preset coverage threshold, the candidate path is deleted, and the deleted candidate path is evaluated according to a pre-constructed energy function to obtain the intermediate path; wherein, the energy function includes a path quantity term, a coverage variance related term and an overall ablation rate penalty term, and the energy function is used to evaluate the degree of optimization of the candidate path. The optimization goal of the energy function is to minimize the required number of paths and achieve a balanced distribution of coverage areas in space while meeting the clinically required ablation rate.

6. The method according to claim 2, characterized in that Determining the number of optical fibers required for tumor ablation based on the intermediate optical fiber path set includes: Based on the path information corresponding to the intermediate optical fiber path, combining the paths in the intermediate optical fiber path set to obtain a plurality of path combinations; For each path combination, if there is no spatial conflict between any two optical fiber paths in the path combination and the preset tumor area ablation coverage requirements are met, the number of optical fibers in the path combination is determined as the number of optical fibers required for tumor ablation.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Based on a pre-built Lagrangian relaxation optimization model, the minimum number of fiber paths for complete tumor coverage is determined. When the number of optical fibers required for tumor ablation is consistent with the minimum number of optical fiber paths and the target optical fiber path set can achieve complete coverage of the tumor area, the target optical fiber path set is determined to be a valid optical fiber path set.

8. The method according to any one of claims 1 to 6, characterized in that The method further comprises: For each target optical fiber path, based on the spatial direction of the target optical fiber path, the ablation range corresponding to the target optical fiber path is modeled as a rotating ellipsoid with the target optical fiber path as the axis of symmetry; Obtaining a spatial intersection of the target optical fiber path and the tumor area as the corresponding target treatment area; Performing equidistant sampling along the path direction of the target optical fiber path to obtain multiple candidate ablation points, and constructing a two-dimensional cross section perpendicular to the target optical fiber path at each candidate ablation point; For each candidate ablation point, calculating a maximum distance function from the candidate ablation point to the target treatment area within the cross section, wherein the maximum distance function is used to represent the maximum treatment requirement of the candidate ablation point within the local area; Based on the farthest distance function, the target ablation point used to form a rotating ellipsoid and the short axis radius corresponding to the target ablation point are iteratively selected from the multiple candidate ablation points, so that the target treatment area is completely covered in the cross-sectional direction, and the number of optical fibers required is minimized while ensuring coverage integrity.

9. A planning device for multi-fiber laser ablation treatment of brain glioma, characterized in that: The device comprises: A segmentation module is used to perform segmentation and sampling processing on the image information of the target patient and the segmentation result of the tumor area acquired in advance to obtain a set of candidate optical fiber paths; a screening module, configured to screen the candidate fiber path set according to the fiber planning objective function and the fiber planning constraints to obtain an intermediate fiber path set, and preliminarily determine the number of optical fibers required for tumor ablation based on the intermediate fiber path set; A determination module is configured to determine a target fiber path set from the intermediate fiber path set based on the number of optical fibers required for tumor ablation and a predetermined path evaluation score; the target fiber path set includes at least position information corresponding to each target fiber path.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images