Orthopedic prescription optimization method, system, device and storage medium based on genetic algorithm
By applying a genetic algorithm to optimize the adjustment sequence of the telescopic rods in the Taylor frame, the problems of reliance on experience and uncontrolled traction rate in existing technologies are solved, thereby improving the safety and comfort of the skeletal orthopedic process.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- WUHAN MAIHETONGLUO HEALTH TECH CO LTD
- Filing Date
- 2025-12-26
- Publication Date
- 2026-05-29
AI Technical Summary
The calculation methods for orthopedic prescriptions in the current technology rely on the doctor's experience and fail to accurately control the traction rate and bone segment movement trajectory, which may lead to collisions between bone segments and surrounding soft tissues, increasing the risk of secondary injury.
A genetic algorithm was used to optimize the adjustment sequence of the telescopic rods in the Taylor scaffold. By setting orthopedic feature points at the bone notch section and controlling the traction rate, the optimal adjustment sequence was generated to reduce collision between bone segments and soft tissues.
It effectively reduces the collision between bone segments and soft tissues during traction, improving the comfort and safety of the orthopedic procedure.
Smart Images
Figure CN122117308A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent diagnosis and treatment technology, specifically to a method, system, device, and storage medium for optimizing orthopedic prescriptions based on genetic algorithms. Background Technology
[0002] Using external fixators to gradually restore deformed areas to their normal physiological and anatomical structure through slow traction is a clinical orthopedic method. However, the key issue is how to adjust the external fixator, i.e., the formulation of the orthopedic prescription. Traditional orthopedic prescription formulation mainly uses linear calculation methods, which rely heavily on the clinician's experience. In clinical practice, it is difficult to achieve precise control of the traction rate during the adjustment of the Taylor frame, and different adjustment sequences of the telescopic rods will cause different movement trajectories of the moving bone segments. This unstable traction process may lead to unnecessary collisions between the moving bone segments and surrounding soft tissues, thereby increasing the risk of secondary injury to the patient.
[0003] Therefore, the problems and defects of the existing technology are as follows: the calculation method of the orthopedic prescription is highly dependent on the doctor's clinical experience and does not take into account the movement trajectory of the bone segment during the correction process, which may lead to collision between the bone segment and the surrounding soft tissue, thereby causing secondary damage and affecting the final orthopedic effect. Summary of the Invention
[0004] To address the problems existing in the prior art, this invention provides a method, system, device, and storage medium for optimizing deformity correction prescriptions based on genetic algorithms. By setting orthopedic feature points at the cross-sectional contour points of the bone defect to control the rate of traction correction, and by using a genetic algorithm to optimize the adjustment sequence of the telescopic rods in the Taylor frame, the length of the telescopic rods in the frame can be changed according to the optimized adjustment sequence, which can effectively reduce the patient's pain and improve the comfort during the orthopedic process.
[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.
[0006] According to a first aspect of this application, a method for optimizing orthodontic prescriptions based on genetic algorithms is provided, comprising: Establish a three-dimensional model of the patient's orthopedic skeleton; The initial and final poses of the mobile bone are obtained based on the three-dimensional model of the orthopedic skeleton. The expected orthopedic path is obtained based on the initial and final poses. Based on the expected orthopedic path, the daily pose parameters in the preset treatment cycle are generated. The osteotomy and Taylor brace were simulated on the three-dimensional model of the orthopedic skeleton. The cross-sectional contour points were used as orthopedic feature points. Based on the daily pose parameters in the preset treatment cycle, the daily orthopedic feature changes of each orthopedic feature point in the preset treatment cycle were obtained. Based on the daily changes in orthopedic features of each orthopedic feature point in the preset treatment cycle, a daily composite transformation matrix is generated, and the daily length of each telescopic rod in the Taylor stent is obtained based on the daily composite transformation matrix. Based on the daily length of each telescopic rod in the Taylor stent, a genetic algorithm is used to obtain the optimal daily adjustment order of each telescopic rod in the Taylor stent.
[0007] In some embodiments of this application, based on the foregoing scheme, the expected orthopedic path is a straight path, and the step of obtaining the expected orthopedic path based on the initial pose and the final pose, and generating daily pose parameters in a preset treatment cycle based on the expected orthopedic path, includes: Establish the functional relationship between daily pose parameters:
[0008]
[0009] in, , , The first Displacement along the coronal, sagittal, and horizontal planes; , , The first The angles of rotation around the coronal, sagittal, and horizontal planes are based on the initial and final poses. , and These represent the translations from the initial pose to the final pose in the coronal, sagittal, and horizontal planes, respectively. , and These represent the angles required to transform from the initial pose to the final pose in the coronal, sagittal, and horizontal planes, respectively. The adjustment increment is obtained based on the initial and final poses. The adjustment increment includes displacement increment and angle increment. The displacement increment and angle increment are evenly distributed to each day of the preset treatment cycle, and the pose parameters are constrained for each day. The calculation formula is as follows:
[0010] in, , , The first Displacement along the coronal, sagittal, and horizontal planes; , , The first The angles of rotation in the coronal, sagittal, and horizontal planes are based on the initial and final poses. This refers to the number of days of treatment.
[0011] In some embodiments of this application, based on the aforementioned scheme, the daily correction rate is obtained based on the daily changes in orthopedic features over two consecutive days, and the calculation formula is as follows:
[0012] in, For the first The daily displacement of the points showing changes in orthopedic features along the coronal plane. For the first The daily displacement of the points showing changes in orthopedic features along the coronal plane. For the first The daily changes in orthopedic features along the sagittal plane. For the first The daily changes in orthopedic features along the sagittal plane. For the first The daily displacement of the points showing changes in orthopedic features along the horizontal plane. For the first The daily displacement of the points of change in orthopedic features along the horizontal plane; If the daily correction rate is greater than the preset maximum traction rate, the preset treatment cycle is incremented, and the expected correction path is obtained again based on the initial and final poses. Based on the expected correction path, the daily pose parameters in the preset treatment cycle are generated, and based on the daily pose parameters in the preset treatment cycle, the daily correction feature change points of each correction feature point in the preset treatment cycle are obtained, until the daily correction rate is less than or equal to the preset maximum traction rate.
[0013] In some embodiments of this application, based on the aforementioned scheme, the composite transformation matrix of the daily moving bone segment relative to the reference bone segment is generated based on the daily changes in the orthopedic feature points corresponding to the preset treatment cycle. The calculation formula is as follows:
[0014] in, The coordinates of the orthopedic feature points, For the first The coordinates of the daily changes in orthopedic features in the reference bone segment coordinate system. This is the transformation matrix of the moving bone segment relative to the reference bone segment; The daily lengths of each telescopic strut in the Taylor scaffold are obtained based on the daily composite transformation matrix, including: The mapping relationship between the pose matrix and the composite transformation matrix of the moving ring relative to the reference ring is obtained by the following formula;
[0015] in, Let be the pose matrix of the reference ring relative to the reference bone segment. Let be the pose matrix of the moving ring relative to the moving bone segment. For the first The pose matrix of the moving ring relative to the reference ring; The pose matrix of the moving ring relative to the reference ring is used to perform inverse pose solving to obtain the daily length of each telescopic rod in the Taylor support.
[0016] In some embodiments of this application, based on the foregoing scheme, the step of using a genetic algorithm to obtain the optimal daily adjustment order of each telescopic rod in the Taylor stent based on the daily rod length of each telescopic rod in the Taylor stent includes: Using the daily adjustment sequence of each telescopic rod as a variable, the total deviation between the actual orthopedic path and the expected orthopedic path is established; The optimization objective is to minimize the total deviation. A genetic algorithm is then used to optimize the daily adjustment sequence of each telescopic rod to obtain the optimal daily adjustment sequence.
[0017] In some embodiments of this application, based on the aforementioned scheme, the step of establishing an optimization objective with the minimum total deviation and using a genetic algorithm to optimize the daily adjustment order of each telescopic rod to obtain the optimal daily adjustment order includes: An initial population is generated, wherein the initial population comprises several individuals, each corresponding to a daily adjustment order; The total deviation for each individual is obtained by: establishing the actual daily orthopedic path based on the daily adjustment sequence and daily length of each telescopic rod; generating several intermediate path points based on the actual daily orthopedic path; and using the sum of the vertical distances from the several intermediate path points to the expected orthopedic path as the total deviation. When the preset maximum number of iterations is reached, the iteration process terminates, and the daily adjustment order corresponding to the individual with the smallest total deviation is selected as the optimal daily adjustment order.
[0018] In some embodiments of this application, based on the aforementioned scheme, selection, crossover, and mutation operations are used to update the individuals in the initial population to obtain an updated population.
[0019] According to a second aspect of this application, a deformity correction prescription optimization system based on a genetic algorithm is provided, comprising: The model building module is used to create a three-dimensional model of the patient's orthopedic skeleton. The first acquisition module is used to acquire the initial and final poses of the moving bone based on the three-dimensional model of the orthopedic skeleton, acquire the expected orthopedic path based on the initial and final poses, and generate daily pose parameters in the preset treatment cycle based on the expected orthopedic path. The second acquisition module is used to simulate osteotomy and Taylor bracket installation on the three-dimensional model of the orthopedic skeleton, and to use the cross-sectional contour points as orthopedic feature points. Based on the daily pose parameters in the preset treatment cycle, the module acquires the daily orthopedic feature change points of each orthopedic feature point in the preset treatment cycle. The third acquisition module is used to generate a daily composite transformation matrix based on the daily changes in the orthopedic features of each orthopedic feature point in the preset treatment cycle, and to obtain the daily length of each telescopic rod in the Taylor stent based on the daily composite transformation matrix. The fourth acquisition module is used to obtain the optimal daily adjustment order of each telescopic rod in the Taylor support based on the daily rod length of each telescopic rod in the Taylor support using a genetic algorithm.
[0020] According to a third aspect of this application, a computer-readable storage medium is provided that stores a computer program thereon, the computer program including executable instructions that, when executed by a processor, implement the method described above.
[0021] According to a fourth aspect of this application, an electronic device is provided, comprising: One or more processors; A memory for storing executable instructions of the processor, which, when executed by the one or more processors, cause the one or more processors to implement the method described above.
[0022] The beneficial effects of this application are as follows: (1) The deformity correction prescription optimization method, system, device and storage medium based on genetic algorithm provided in this application controls the rate of traction correction by setting correction feature points at the bone section, thereby reducing unnecessary collisions between the moving bone segment and the surrounding soft tissue during the traction process.
[0023] (2) The deformity correction prescription optimization method, system, device and storage medium provided in this application use a genetic algorithm to optimize the adjustment order of the Taylor stent telescopic rod. Patients can effectively reduce pain and improve comfort during the correction process by changing the length of the stent telescopic rod according to the optimized adjustment order.
[0024] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit this application. Attached Figure Description
[0025] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and are intended to explain the invention, but do not constitute an undue limitation thereof. In the drawings: Figure 1This is a schematic diagram of a deformity correction prescription optimization method based on genetic algorithm according to the present invention; Figure 2 This is a flowchart of a deformity correction prescription optimization method based on genetic algorithm according to the present invention; Figure 3 This is a three-dimensional model of the foot and ankle in a specific embodiment of the present invention; Figure 4 This is a schematic diagram of the orthopedic feature points set in a specific embodiment of the present invention; Figure 5 This is a schematic diagram of the optimization target in a specific embodiment of the present invention. The optimization target is the total offset of the five intermediate waypoints to the preset path. Figure 6 This is a model diagram simulating the installation of the Taylor bracket before orthodontic treatment in a specific embodiment of the present invention, wherein the Taylor bracket is fixed at both ends of the osteotomy site; Figure 7 This is a model diagram simulating the installation of a Taylor brace after orthodontic treatment in a specific embodiment of the present invention; Figure 8 This is a comparison of the total offset of the moving bone segment pose point from the ideal path before and after the adjustment order of the telescopic rods in the prescription report is optimized using a genetic algorithm in a specific embodiment of the present invention, when all telescopic rods have been adjusted. Figure 9 In a specific embodiment of the present invention, the percentage reduction in the total daily offset of the moving bone segment pose point after all telescopic rods have been adjusted is calculated by using a genetic algorithm to optimize the adjustment order of the telescopic rods in the prescription report. Figure 10 This is a schematic diagram of a deformity correction prescription optimization system based on a genetic algorithm according to the present invention; Figure 11 This is a schematic diagram of an electronic device according to the present invention. Detailed Implementation
[0026] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0027] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.
[0028] According to the first aspect of this application, please refer to Figure 1 and Figure 2 As shown, this embodiment provides a method for optimizing orthodontic prescriptions based on genetic algorithms, including the following steps: Step S1: Create a three-dimensional model of the patient's orthopedic skeleton.
[0029] In some embodiments of this example, a high-precision 3D model is generated by 3D reconstruction of bone CT image data and imported into the 3D bone orthopedic system. In this example, the orthopedic bones are the ankle, femur, tibia, fibula, etc., and this example is not limited to these. In this example, the 3D model format can be a .stl format model, etc., and this example is not limited to these.
[0030] This facilitates simulation and optimization of the patient's orthopedic skeletal correction.
[0031] Step S2: Obtain the initial and final poses of the moving bone based on the three-dimensional model of the orthopedic skeleton, obtain the expected orthopedic path based on the initial and final poses, and generate daily pose parameters in the preset treatment cycle based on the expected orthopedic path.
[0032] In this embodiment, the initial pose of the movable bone is the initial pose of the movable bone at the start of the correction, and the final pose of the movable bone is the initial pose of the movable bone at the end of the correction.
[0033] In some embodiments of this example, the expected orthopedic path is a straight path, and planning the orthopedic path as a straight path makes the pose trajectory smoother.
[0034] In some embodiments of this example, obtaining the expected orthopedic path based on the initial and final poses, and generating daily pose parameters for a preset treatment cycle based on the expected orthopedic path, includes: Establish the functional relationship between daily pose parameters:
[0035]
[0036] in, , , The first Displacement along the coronal, sagittal, and horizontal planes; , , The first The angles of rotation around the coronal, sagittal, and horizontal planes are based on the initial and final poses. , and These represent the translations from the initial pose to the final pose in the coronal, sagittal, and horizontal planes, respectively. , and These represent the angles required to transform from the initial pose to the final pose in the coronal, sagittal, and horizontal planes, respectively. The adjustment increment is obtained based on the initial and final poses. The adjustment increment includes displacement increment and angle increment. The displacement increment and angle increment are evenly distributed to each day of the preset treatment cycle, and the pose parameters are constrained for each day. The calculation formula is as follows:
[0037] in, , , The first Displacement along the coronal, sagittal, and horizontal planes; , , The first The angles of rotation around the coronal, sagittal, and horizontal planes are based on the initial and final poses. This refers to the number of days of treatment.
[0038] Thus, given the initial and final poses of the moving bone, in order to plan the orthopedic path as a straight path, it is necessary to ensure that the pose parameters are evenly distributed on the planned orthopedic path each day, and to evenly distribute the displacement increment and angle increment to each day of the treatment cycle.
[0039] Step S3: Simulate osteotomy and Taylor bracket installation on the three-dimensional model of the orthopedic skeleton. Use the cross-sectional contour points as orthopedic feature points. Based on the daily pose parameters in the preset treatment cycle, obtain the daily orthopedic feature change points of each orthopedic feature point in the preset treatment cycle.
[0040] In some embodiments of this example, Taylor frames are installed at both ends of the osteotomy site. The Taylor frames include a static platform, a dynamic platform, and telescopic rods. The static platform is fixed to the reference bone segment as a fixed ring, and the dynamic platform is fixed to the moving bone segment as a movable ring for orthodontic treatment. The static platform and the dynamic platform are connected by several telescopic rods.
[0041] In some embodiments of this example, the daily correction rate is obtained based on the daily changes in orthopedic features over two consecutive days, and the calculation formula is as follows:
[0042] in, For the first The daily displacement of the points showing changes in orthopedic features along the coronal plane. For the first The daily displacement of the points showing changes in orthopedic features along the coronal plane. For the first The daily changes in orthopedic features along the sagittal plane. For the first The daily changes in orthopedic features along the sagittal plane. For the first The daily displacement of the points showing changes in orthopedic features along the horizontal plane. For the first The daily displacement of the points of change in orthopedic features along the horizontal plane.
[0043] Throughout the entire orthopedic treatment, the daily orthopedic rate must not exceed the set maximum traction rate, calculated using the following formula:
[0044] in, Indicates the maximum pulling rate. Represents the total number of orthopedic feature points, in the th... The corrective surgery was completed at the right time.
[0045] If the daily traction rate of each orthopedic feature point meets the above conditions, the entire orthopedic process is considered safe and reliable.
[0046] If the daily correction rate is greater than the preset maximum traction rate, the preset treatment cycle is incremented, and the expected correction path is obtained again based on the initial and final poses. Based on the expected correction path, the daily pose parameters in the preset treatment cycle are generated, and based on the daily pose parameters in the preset treatment cycle, the daily correction feature change points of each correction feature point in the preset treatment cycle are obtained, until the daily correction rate is less than or equal to the preset maximum traction rate. The path planning is completed and the preset treatment cycle is determined. Then, the daily length of each telescopic rod in the Taylor frame is calculated.
[0047] Specifically, assuming a preset treatment cycle of n=1, calculate the daily pose parameters of the corresponding points on the moving bone. And obtain the daily orthopedic feature points. Coordinates in the reference bone coordinate system The system checks whether the maximum traction rate constraint is met. If not, the preset treatment cycle n is incremented, and the daily pose parameters are recalculated for verification. If the constraint is met, the current n value is the final preset treatment cycle, and the above process is repeated until the maximum traction rate requirement is met.
[0048] In some embodiments of this example, in order to quantitatively evaluate the maximum traction rate of bone during orthopedic treatment, the contour points at the incision site are used as orthopedic feature points, and the coordinates of each orthopedic feature point are recorded. By recording each orthopedic feature point The daily orthopedic rate accurately reflects the daily traction volume. To ensure the safety of orthopedic treatment, each orthopedic feature point... The daily orthopedic rate should not exceed the maximum traction rate by 1 mm / day.
[0049] Step S4: Based on the daily changes in orthopedic features of each orthopedic feature point in the preset treatment cycle, generate a daily composite transformation matrix, and obtain the daily length of each telescopic rod in the Taylor stent based on the daily composite transformation matrix.
[0050] In some embodiments of this example, the calculation formula for generating a composite transformation matrix of the daily moving bone segment relative to the reference bone segment based on the daily changes in the orthopedic feature points corresponding to the preset treatment cycle is as follows:
[0051] in, The coordinates of the orthopedic feature points, For the first The coordinates of the daily changes in orthopedic features in the reference bone segment coordinate system. This is the transformation matrix of the moving bone segment relative to the reference bone segment.
[0052] The daily lengths of each telescopic strut in the Taylor scaffold are obtained based on the daily composite transformation matrix, including: The mapping relationship between the pose matrix and the composite transformation matrix of the moving ring relative to the reference ring is obtained by the following formula;
[0053] in, Let be the pose matrix of the reference ring relative to the reference bone segment. Let be the pose matrix of the moving ring relative to the moving bone segment. For the first The pose matrix of the moving ring relative to the reference ring; Inverse pose solving of the pose matrix of the moving ring relative to the reference ring yields the daily length of each telescopic rod in the Taylor frame, i.e., for the th... The pose inverse of the moving ring relative to the reference ring is used to obtain the pose of each telescopic rod in the Taylor support. The top pole is long.
[0054] Step S5: Based on the daily length of each telescopic rod in the Taylor stent, a genetic algorithm is used to obtain the optimal daily adjustment order of each telescopic rod in the Taylor stent.
[0055] In this embodiment, the Taylor frame exhibits nonlinear motion characteristics during the adjustment of the telescopic rod length. The actual orthopedic path of the moving bone segment will deviate from the expected orthopedic path. A genetic algorithm is used to optimize the adjustment sequence of the telescopic rod to avoid unnecessary damage to the surrounding soft tissues.
[0056] In some implementations of this embodiment, the following are also included: Using the daily adjustment sequence of each telescopic rod as a variable, the total deviation between the actual orthopedic path and the expected orthopedic path is established; The optimization objective is to minimize the total deviation. A genetic algorithm is then used to optimize the daily adjustment sequence of each telescopic rod to obtain the optimal daily adjustment sequence.
[0057] In some embodiments of this example, the step of establishing an optimization objective based on minimizing the total deviation and using a genetic algorithm to optimize the daily adjustment order of each telescopic rod to obtain the optimal daily adjustment order includes: An initial population is generated, wherein the initial population comprises several individuals, each corresponding to a daily adjustment order; The total deviation for each individual is obtained by: establishing the actual daily orthopedic path based on the daily adjustment sequence and daily length of each telescopic rod; generating several intermediate path points based on the actual daily orthopedic path; and using the sum of the vertical distances from the several intermediate path points to the expected orthopedic path as the total deviation. When the preset maximum number of iterations is reached, the iteration process terminates, and the daily adjustment order corresponding to the individual with the smallest total deviation is selected as the optimal daily adjustment order.
[0058] In some implementations of this embodiment, the following are also included: The individuals in the initial population are updated using selection, crossover, and mutation operations to obtain an updated population.
[0059] In one specific embodiment, the genetic algorithm parameter values are shown in Table 1. The specific steps for using the genetic algorithm to solve for the minimum total deviation are as follows: Table 1 Algorithm Parameter Table
[0060] In some embodiments of this example, the optimization objective is established with minimizing the total deviation, and a genetic algorithm is used to optimize the daily adjustment order of each telescopic rod to obtain the optimal daily adjustment order, including the following steps: Step S501: Individual Encoding. The objects of the genetic algorithm are individuals represented by symbol strings. In the process of solving for the minimum total offset, the variable is the daily adjustment order of the telescopic rods. Therefore, the daily adjustment order needs to be encoded into a specific symbol string format. An integer array containing several telescopic rod numbers represents a daily adjustment order, i.e., an individual, and each element in the array represents the order in which the telescopic rods are adjusted. In a specific embodiment, the Taylor frame has 6 telescopic rods, where {5, 2, 1, 4, 3, 6} represents the daily adjustment order of the telescopic rods as number 5, number 2, number 1, number 4, number 3, and number 6, respectively. Step S502: Generate an initial population. After encoding, an initial population is generated, and each individual in the population represents a daily adjustment order. The population size is set to 20, meaning the population consists of 20 individuals, each generated randomly. Step S503: Fitness calculation. In genetic algorithms, the quality of an individual is quantitatively evaluated using its fitness value. The fitness value directly determines the individual's probability of inheritance in the population. During the orthopedic procedure, the lengths of each telescopic rod need to be adjusted from... The state of the day is gradually adjusted according to the daily adjustment sequence encoded by the individual, up to the [number missing]. The target length for the day. After all six telescopic rods have been adjusted, the total offset is obtained. The total offset is the fitness value. The smaller the total offset, the closer the movement trajectory of the moving bone segment is to the planned path, and the better the individual's fitness. Step S504: Selection operation, selects high-quality individuals from the current population based on their fitness values. Common selection strategies include roulette wheel selection, tournament selection, sorting, and elite retention. This method uses roulette wheel selection. Step S505: Crossover operation. Each telescopic rod is adjusted only once, therefore the offspring sequence must be a valid permutation and cannot have duplicate telescopic rod numbers. A partial mapping crossover method is used: a segment of telescopic rod adjustment numbers is randomly selected from individual 1, and the unique telescopic rod adjustment numbers from individual 2 are concatenated to generate a new individual, ensuring that the generated offspring do not contain duplicate elements. Step S506: Crossover mutation operation, randomly select two positions of the bar regulation numbers in an individual and swap them, instead of directly changing the value of a certain site, to ensure the effectiveness of the bar regulation numbers in the individual's gene sequence; Step S507: Termination condition determination. The iteration process terminates when the genetic algorithm reaches the preset maximum number of iterations. After the genetic algorithm finishes running, the individual with the smallest total deviation is selected from the final population as the optimal solution output. The daily adjustment order of the telescopic rod corresponding to this individual is the optimal daily adjustment order.
[0061] In one specific embodiment, 3D reconstruction was performed on CT image data of a case of distal tibial anterior arch deformity. The reconstructed .stl format model was imported into a developed foot and ankle 3D orthopedic system. A supra-ankle wedge osteotomy was performed, simulating osteotomy and installing a Taylor brace for progressive traction correction. The CT images were reconstructed to obtain a foot and ankle model, which was stored in .stl format. This model was then imported into a preoperative intelligent planning system for foot and ankle 3D osteotomy orthopedic surgery. In this specific embodiment, as... Figure 3 As shown, the imported orthopedic skeletal 3D model is a foot and ankle 3D model. Figure 4 As shown, the contour points at the cut are used as orthopedic feature points, and the coordinates of each orthopedic feature point are recorded. The orthopedic feature points determined in this embodiment. For example... Figure 5 As shown, the Taylor frame exhibits non-linear motion characteristics during the adjustment of the telescopic rod lengths. The actual pose of the moving bone segment deviates from the expected path. The Taylor frame has six telescopic rods; adjusting five rods creates five intermediate path points. Only when all six rods are adjusted will the pose of the moving bone segment reach the expected orthopedic path. The five intermediate path points are... , , , and To indicate, For the first The distance from each intermediate path point to the expected path is used to optimize the total deviation of the objective. for sum. like Figure 6 As shown, Taylor frames are installed at both ends of the osteotomy site. The static platform acts as a fixation ring, fixed to the reference bone segment, while the movable platform acts as a moving ring, fixed to the moving bone segment for correction. The static and movable platforms are connected by six telescopic rods. Figure 7 As shown, after determining the corrective angle required to restore the foot and ankle deformity to a normal physiological state, the deformed area is gradually restored to its normal physiological and anatomical structure by using a Taylor brace for slow traction. Figure 8 and Figure 9 The figure shows a comparison of the total offset of the moving bone segment pose point from the ideal path before and after optimizing the adjustment order of the telescopic rods in the prescription report using a genetic algorithm, and the percentage reduction in the total offset of the moving bone segment pose point per day after all telescopic rods have been adjusted. Figure 8As can be seen from the data, the optimized offset in this specific embodiment is significantly reduced, all controlled within 1.5mm. Meanwhile, from... Figure 9 As can be seen from the table, the percentage reduction in the total daily displacement of the bone segment pose points corresponding to this specific embodiment ranges from 32.94% to 88.75%, with an average reduction rate of 64.24%. Through the progressive traction of the Taylor frame, the deformity is gradually corrected, and the relevant clinical parameters in this specific embodiment are eventually restored to the normal range, as shown in Table 2. The optimal daily adjustment sequence under the deformity state in the current embodiment is calculated and generated, and some of the daily adjustment sequences in the orthopedic scheme are shown in Table 3.
[0062] Table 2 Recovery status of relevant clinical parameters
[0063] Table 3. Daily adjustment sequence in the orthopedic plan
[0064] According to the second aspect of this application, such as Figure 10 As shown in the figure, this embodiment provides a deformity correction prescription optimization system based on genetic algorithm, including: The model building module is used to create a three-dimensional model of the patient's orthopedic skeleton. The first acquisition module is used to acquire the initial pose and final pose of the mobile bone based on the three-dimensional model of the orthopedic skeleton, acquire the expected orthopedic path based on the initial pose and final pose, and generate daily pose parameters in the preset treatment cycle based on the expected orthopedic path. The second acquisition module is used to simulate osteotomy and Taylor bracket installation on the three-dimensional model of the orthopedic skeleton, and to use the cross-sectional contour points as orthopedic feature points. Based on the daily pose parameters in the preset treatment cycle, the module acquires the daily orthopedic feature change points of each orthopedic feature point in the preset treatment cycle. The third acquisition module is used to generate a daily composite transformation matrix based on the daily changes in the orthopedic features of each orthopedic feature point in the preset treatment cycle, and to obtain the daily length of each telescopic rod in the Taylor stent based on the daily composite transformation matrix. The fourth acquisition module is used to obtain the optimal daily adjustment order of each telescopic rod in the Taylor support based on the daily rod length of each telescopic rod in the Taylor support using a genetic algorithm.
[0065] Specifically, this embodiment corresponds one-to-one with the above method embodiments. The functions of each module have been described in detail in the corresponding method embodiments, so they will not be repeated here.
[0066] According to a third aspect of this application, this embodiment provides a computer-readable storage medium having a computer program stored thereon, the computer program including executable instructions that, when executed by a processor, implement the method described above.
[0067] The present invention can implement all or part of the processes in the above methods, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0068] According to the fourth aspect of this application, such as Figure 11 As shown, an electronic device is provided, comprising: One or more processors; Memory is used to store executable instructions for the processor, which, when executed by one or more processors, cause one or more processors to implement the methods described above.
[0069] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and a bus connecting different system components (including memory and processor).
[0070] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of a computer system, connecting all parts of the computer system through various interfaces and lines.
[0071] Memory can be used to store computer programs and / or modules. The processor implements various functions of the computer system by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system and at least one application program required for a function (e.g., sound playback, image playback, etc.); the data storage area can store data created based on the use of the mobile phone (e.g., audio data, video data, etc.). Furthermore, memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMedia Cards (SMC), Secure Digital (SD) cards, Flash Cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.
[0072] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, servers, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and memory) containing computer-usable program code.
[0073] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), servers, and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.
[0074] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0075] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0076] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0077] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0078] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for optimizing orthodontic prescriptions based on genetic algorithms, characterized in that, include: Establish a three-dimensional model of the patient's orthopedic skeleton; The initial and final poses of the mobile bone are obtained based on the three-dimensional model of the orthopedic skeleton. The expected orthopedic path is obtained based on the initial and final poses. Based on the expected orthopedic path, the daily pose parameters in the preset treatment cycle are generated. The osteotomy and Taylor brace were simulated on the three-dimensional model of the orthopedic skeleton. The cross-sectional contour points were used as orthopedic feature points. Based on the daily pose parameters in the preset treatment cycle, the daily orthopedic feature changes of each orthopedic feature point in the preset treatment cycle were obtained. Based on the daily changes in orthopedic features of each orthopedic feature point in the preset treatment cycle, a daily composite transformation matrix is generated, and the daily length of each telescopic rod in the Taylor stent is obtained based on the daily composite transformation matrix. Based on the daily length of each telescopic rod in the Taylor stent, a genetic algorithm is used to obtain the optimal daily adjustment order of each telescopic rod in the Taylor stent.
2. The method according to claim 1, characterized in that, The expected orthopedic path is a straight path. The process of obtaining the expected orthopedic path based on the initial and final poses, and generating daily pose parameters for a preset treatment cycle based on the expected orthopedic path, includes: Establish the functional relationship between daily pose parameters: in, , , The first Displacement along the coronal, sagittal, and horizontal planes; , , The first The angles of rotation around the coronal, sagittal, and horizontal planes are based on the initial and final poses. , and These represent the translations from the initial pose to the final pose in the coronal, sagittal, and horizontal planes, respectively. , and These represent the angles required to transform from the initial pose to the final pose in the coronal, sagittal, and horizontal planes, respectively. The adjustment increment is obtained based on the initial and final poses. The adjustment increment includes displacement increment and angle increment. The displacement increment and angle increment are evenly distributed to each day of the preset treatment cycle, and the pose parameters are constrained for each day. The calculation formula is as follows: in, , , The first Displacement along the coronal, sagittal, and horizontal planes; , , The first The angles of rotation around the coronal, sagittal, and horizontal planes are based on the initial and final poses. This refers to the number of days of treatment.
3. The method according to claim 1, characterized in that: Based on the daily changes in orthopedic features over two consecutive days, the daily orthopedic rate is obtained, and the calculation formula is as follows: in, For the first The daily displacement of the points showing changes in orthopedic features along the coronal plane. For the first The daily displacement of the points showing changes in orthopedic features along the coronal plane. For the first The daily changes in orthopedic features along the sagittal plane. For the first The daily changes in orthopedic features along the sagittal plane. For the first The daily displacement of the points showing changes in orthopedic features along the horizontal plane. For the first The daily displacement of the points of change in orthopedic features along the horizontal plane; If the daily correction rate is greater than the preset maximum traction rate, the preset treatment cycle is incremented, and the expected correction path is obtained again based on the initial and final poses. Based on the expected correction path, the daily pose parameters in the preset treatment cycle are generated, and based on the daily pose parameters in the preset treatment cycle, the daily correction feature change points of each correction feature point in the preset treatment cycle are obtained, until the daily correction rate is less than or equal to the preset maximum traction rate.
4. The method according to claim 1, characterized in that: The composite transformation matrix of the daily moving bone segment relative to the reference bone segment is generated based on the daily changes in the orthopedic feature points corresponding to the preset treatment cycle. The calculation formula is as follows: in, The coordinates of the orthopedic feature points, For the first The coordinates of the daily changes in orthopedic features in the reference bone segment coordinate system. This is the transformation matrix of the moving bone segment relative to the reference bone segment; The daily lengths of each telescopic strut in the Taylor scaffold are obtained based on the daily composite transformation matrix, including: The mapping relationship between the pose matrix and the composite transformation matrix of the moving ring relative to the reference ring is obtained by the following formula; in, Let be the pose matrix of the reference ring relative to the reference bone segment. Let be the pose matrix of the moving ring relative to the moving bone segment. For the first The pose matrix of the moving ring relative to the reference ring; The pose matrix of the moving ring relative to the reference ring is used to perform inverse pose solving to obtain the daily length of each telescopic rod in the Taylor support.
5. The method according to claim 1, characterized in that, The optimal daily adjustment order of each telescopic rod in the Taylor stent, based on the daily rod length, is obtained using a genetic algorithm, including: Using the daily adjustment sequence of each telescopic rod as a variable, the total deviation between the actual orthopedic path and the expected orthopedic path is established; The optimization objective is established with the total deviation being minimized. A genetic algorithm is then used to optimize the daily adjustment sequence of each telescopic rod in the Taylor support, resulting in the optimal daily adjustment sequence.
6. The method according to claim 5, characterized in that, The optimization objective is to minimize the total deviation. A genetic algorithm is used to optimize the daily adjustment sequence of each telescopic rod to obtain the optimal daily adjustment sequence, including: An initial population is generated, wherein the initial population comprises several individuals, each corresponding to a daily adjustment order; The total deviation for each individual is obtained by: establishing the actual daily orthopedic path based on the daily adjustment sequence and daily length of each telescopic rod; generating several intermediate path points based on the actual daily orthopedic path; and using the sum of the vertical distances from the several intermediate path points to the expected orthopedic path as the total deviation. When the preset maximum number of iterations is reached, the iteration process terminates, and the daily adjustment order corresponding to the individual with the smallest total deviation is selected as the optimal daily adjustment order.
7. The method according to claim 1, characterized in that, Also includes: The individuals in the initial population are updated using selection, crossover, and mutation operations to obtain an updated population.
8. A deformity correction prescription optimization system based on genetic algorithm, characterized in that, include: The model building module is used to create a three-dimensional model of the patient's orthopedic skeleton. The first acquisition module is used to acquire the initial and final poses of the moving bone based on the three-dimensional model of the orthopedic skeleton, acquire the expected orthopedic path based on the initial and final poses, and generate daily pose parameters in the preset treatment cycle based on the expected orthopedic path. The second acquisition module is used to simulate osteotomy and Taylor bracket installation on the three-dimensional model of the orthopedic skeleton, and to use the cross-sectional contour points as orthopedic feature points. Based on the daily pose parameters in the preset treatment cycle, the module acquires the daily orthopedic feature change points of each orthopedic feature point in the preset treatment cycle. The third acquisition module is used to generate a daily composite transformation matrix based on the daily changes in the orthopedic features of each orthopedic feature point in the preset treatment cycle, and to obtain the daily length of each telescopic rod in the Taylor stent based on the daily composite transformation matrix. The fourth acquisition module is used to obtain the optimal daily adjustment order of each telescopic rod in the Taylor support based on the daily rod length of each telescopic rod in the Taylor support using a genetic algorithm.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program includes executable instructions that, when executed by a processor, implement the method of any one of claims 1-7.
10. An electronic device, characterized in that, include: One or more processors; A memory for storing executable instructions of the processor, which, when executed by the one or more processors, cause the one or more processors to perform the method according to any one of claims 1-7.