An interventional ultrasound method and system for minimally invasive surgery

Abstract

The application relates to the technical field of medical devices, and discloses an interventional ultrasound method and system for minimally invasive surgery, which comprises the following steps: acquiring ultrasound image data and operation state parameters; constructing a three-dimensional ultrasound image model through multi-layer scanning, analyzing and generating an initial tissue characteristic evaluation model; loading dynamic blood vessel data and operation constraint conditions, generating a comprehensive evaluation model, and performing dynamic simulation of a puncture point; constructing a dynamic blood vessel prediction model to train a puncture point adjustment model, and generating initial adjustment parameters; obtaining dynamic adjustment simulation information based on the parameters and the model; constructing a multi-path optimization model to iteratively optimize to obtain optimal path planning parameters; combining real-time image reasoning safety puncture probability to adjust real-time puncture strategy to realize dynamic matching. The system comprises data acquisition, image modeling and analysis and other modules. The application improves the safety and precision of minimally invasive surgery puncture, and is suitable for minimally invasive surgery scenes guided by interventional ultrasound.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to an interventional ultrasound method and system for minimally invasive surgery. Background Technology

[0002] In the field of modern medicine, minimally invasive surgery is widely used due to its advantages such as less trauma and faster recovery. Interventional ultrasound, as one of the key technologies in minimally invasive surgery, plays an important role in guiding surgical instruments for precise puncture and avoiding vascular damage. However, traditional interventional ultrasound technology faces many challenges in practical applications and is difficult to meet the precision requirements of complex surgical scenarios.

[0003] From the perspective of image modeling and analysis, traditional methods typically construct two-dimensional or simple three-dimensional models based on a single-level ultrasound scan, failing to comprehensively capture the dynamic tissue characteristics of the surgical site. For example, human tissues possess complex spatial structures and physiological characteristics; the density, vascular distribution, and other features of different tissues may dynamically change during surgery due to physiological activities such as respiration and heartbeat. Traditional modeling methods, lacking multi-level and multi-angle ultrasound imaging data, struggle to accurately classify tissue safety levels, leading to inaccurate safety assessments of puncture paths and increasing surgical risks.

[0004] In terms of puncture path planning, existing technologies often fail to fully integrate dynamic vascular distribution data with surgical constraints. Blood vessels, as structures that need to be carefully avoided during surgery, may change their location and morphology in real time due to hemodynamic variations. Traditional methods, which mostly use static vascular models for path planning, cannot adapt to these dynamic changes. Furthermore, surgical instruments have operational constraints such as maximum puncture angle limitations and minimum turning radii. Traditional path planning does not comprehensively consider these factors, easily leading to planned puncture paths that are difficult to implement in actual operation, or increasing surgical time and patient discomfort due to excessive operational difficulty.

[0005] Regarding puncture point adjustment and dynamic simulation, traditional systems lack effective dynamic prediction models and real-time adjustment mechanisms. When unexpected situations such as tissue displacement or changes in blood vessel morphology occur during surgery, traditional methods struggle to quickly generate accurate puncture point adjustment parameters, failing to achieve real-time dynamic optimization of the puncture strategy. Furthermore, in multi-path optimization, traditional algorithms often employ a single optimization strategy, failing to achieve an effective balance between multiple objectives such as path length, adjustment response speed, and operational safety, resulting in poor overall performance of the puncture path.

[0006] With the continuous development of medical imaging technology and artificial intelligence algorithms, the key to overcoming the bottlenecks of traditional technologies lies in introducing advanced 3D reconstruction technology, dynamic modeling methods, and intelligent optimization algorithms into the field of interventional ultrasound to construct a system capable of real-time dynamic assessment of tissue characteristics, precise planning of puncture paths, and adaptive adjustment of puncture strategies. Against this technological backdrop, this invention addresses the shortcomings of existing interventional ultrasound methods in terms of the comprehensiveness of image modeling, the dynamism of path planning, and the real-time nature of puncture adjustments. It proposes an interventional ultrasound method and system based on multi-layer ultrasound scanning, dynamic tissue feature analysis, and intelligent optimization algorithms to improve the safety and precision of minimally invasive surgery. Summary of the Invention

[0007] The purpose of this invention is to provide an interventional ultrasound method and system for minimally invasive surgery to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an interventional ultrasound method for minimally invasive surgery, the method comprising:

[0009] Acquire ultrasound imaging data of the patient's surgical site and operational status parameters of surgical instruments;

[0010] Multi-layer ultrasound scanning of the surgical site was performed and a three-dimensional ultrasound image model was constructed. The three-dimensional ultrasound image model was then dynamically analyzed for tissue characteristics based on the ultrasound image data to generate an initial tissue characteristic evaluation model.

[0011] Dynamic vascular distribution data and surgical operation constraints are loaded onto the initial tissue feature assessment model to generate a comprehensive tissue feature assessment model. Combined with operation state parameters, dynamic simulation of the puncture point is performed to obtain puncture point control simulation data.

[0012] A dynamic vascular prediction model is constructed and trained using simulation data of puncture point regulation to obtain a puncture point adjustment model, and then initial adjustment parameters are generated. The initial adjustment parameters include at least the initial puncture point position, the initial obstacle avoidance path, and the initial adjustment response parameters.

[0013] Based on the initial adjustment parameters, the comprehensive organizational characteristic evaluation model, and the operational state parameters, dynamic adjustment simulation information is obtained;

[0014] By combining dynamically adjusted simulation information with surgical plan design parameters, a multi-path optimization model is constructed and the design parameters are iteratively optimized to obtain the optimal path planning parameters;

[0015] Based on the real-time ultrasound imaging model, the path planning parameters for the current time period are inferred to generate the safe puncture probability for the current time period. By combining the optimal path planning parameters for the current time period with the actual path parameters, the real-time puncture strategy of the surgical instruments is adjusted to achieve the goal of dynamic puncture point matching.

[0016] Preferably, the puncture point control simulation data includes at least tissue density distribution, blood vessel density distribution, safe puncture area set, and dynamic adjustment priority sequence;

[0017] The dynamically adjusted simulation information includes at least the puncture point offset, path obstacle avoidance success rate, and stability evaluation indicators.

[0018] Preferably, the step of performing multi-layer ultrasound scanning of the surgical site and constructing a three-dimensional ultrasound image model, and then performing dynamic tissue feature analysis on the three-dimensional ultrasound image model based on the ultrasound image data to generate an initial tissue feature evaluation model, includes the following steps:

[0019] The surgical site is scanned from multiple angles with an ultrasound probe to obtain ultrasound image sequences of tissue morphology and blood vessel distribution;

[0020] The ultrasound image sequence is preprocessed to obtain standardized ultrasound image data, wherein the preprocessing includes one or more of the following: image denoising, coordinate registration, feature extraction, grid subdivision, and data alignment.

[0021] Based on standardized ultrasound imaging data, combined with 3D reconstruction technology, a 3D ultrasound imaging model is generated.

[0022] Dynamic tissue feature analysis is performed on a three-dimensional ultrasound image model to generate an initial tissue feature evaluation model. The dynamic tissue feature analysis includes at least grid weight allocation and feature parameter mapping. The tissue safety level is divided by grid weight allocation, and corresponding ultrasound image data is assigned to each level region.

[0023] Preferably, the step of loading dynamic vascular distribution data and surgical operation constraints onto the initial tissue feature evaluation model to generate a comprehensive tissue feature evaluation model, and combining this with operational state parameters to perform dynamic simulation of the puncture point, thereby obtaining puncture point control simulation data, includes the following steps:

[0024] Dynamic vascular distribution data is loaded onto the initial tissue feature assessment model to simulate real-time vascular changes, generating the first tissue feature assessment model.

[0025] Surgical operation constraints are applied to the first tissue feature evaluation model to generate a comprehensive tissue feature evaluation model. The surgical operation constraints include the maximum puncture angle limit, the minimum turning radius, and instrument operation redundancy parameters.

[0026] Based on a comprehensive tissue characteristic assessment model and operational state parameters, dynamic simulation of the puncture point is performed. The specific process includes:

[0027] A multi-constraint path planning equation is constructed, which includes at least an obstacle avoidance distance equation, a trajectory smoothness equation, and an operation difficulty equation. Combined with a comprehensive tissue feature evaluation model, the multi-constraint path planning equation is numerically solved by a piecewise linearization method to obtain tissue density distribution, blood vessel density distribution, safe puncture area set, and dynamic adjustment priority sequence.

[0028] Obtaining a set of safe puncture areas involves the following steps:

[0029] Based on the blood vessel density distribution, the blood vessel coverage index of each grid cell is calculated;

[0030] The system identifies regions in the comprehensive tissue feature assessment model where the vascular coverage index is no greater than a preset threshold, and generates a set of safe puncture regions, as shown below:

[0031] The set of safe puncture areas is the spatial distribution mapping result of the blood vessel coverage index and the preset threshold.

[0032] Preferably, the construction of the dynamic vascular prediction model and training it with puncture point adjustment simulation data to obtain the puncture point adjustment model, and then generating initial adjustment parameters, includes the following steps:

[0033] A dynamic blood vessel prediction model was constructed based on the features of three-dimensional ultrasound images.

[0034] The dynamic vascular prediction model was trained and validated using simulation data of puncture point adjustment to obtain the puncture point adjustment model.

[0035] Input the real-time operation status parameters into the puncture point adjustment model to predict the set of safe puncture areas;

[0036] Based on the predicted set of safe puncture areas, initial adjustment parameters are generated, wherein the initial adjustment parameters include at least the initial puncture point location, the initial obstacle avoidance path, and the initial adjustment response parameters.

[0037] Preferably, it also includes data reconstruction of the simulation data for puncture point control, specifically:

[0038] Based on the tissue density distribution, blood vessel density distribution, and safe puncture area set, an initial multi-dimensional path input tensor is constructed.

[0039] The initial multi-dimensional path input tensor is standardized and its features are hierarchically processed to generate the final multi-dimensional path input tensor.

[0040] Based on a dynamically adjusted priority sequence, a puncture point adjustment label tensor is constructed.

[0041] The training sample set is formed by combining the final multi-dimensional path input tensor with the puncture point adjusted label tensor.

[0042] Preferably, the generation of initial adjustment parameters based on the predicted set of safe puncture areas includes the following steps:

[0043] Extract the grid cell with the lowest blood vessel density from the predicted set of safe puncture areas to generate the initial puncture point location;

[0044] Based on the spatial connectivity of the predicted set of safe puncture zones, a feasible topology for the initial obstacle avoidance path is fitted to generate initial adjustment response parameters.

[0045] The tissue density gradient direction of the predicted set of safe puncture areas is calculated and normalized to a path reference vector, which is the initial obstacle avoidance path direction.

[0046] Preferably, obtaining dynamic adjustment simulation information based on initial adjustment parameters, a comprehensive organizational feature evaluation model, and operational state parameters includes the following steps:

[0047] The initial puncture point location is mapped to the comprehensive organizational feature evaluation model, the initial obstacle avoidance path and the initial adjustment response parameters are matched, the path nodes in the adjustment area are densified, the comprehensive organizational feature evaluation model is updated, the dynamic adjustment triggering conditions, path update rules and response parameter increments are defined, and a dynamic adjustment simulation model is generated.

[0048] Based on the dynamically adjusted simulation model, the multi-constraint path planning equations are iteratively solved using a piecewise linearization method to obtain dynamically adjusted simulation information, specifically including:

[0049] When the dynamic adjustment triggering conditions are met, update the puncture point offset, path obstacle avoidance success rate and stability evaluation index, and resolve the multi-constraint path planning equation until the simulation termination condition is reached.

[0050] The dynamic adjustment triggering condition includes triggering response parameter updates when the current path obstacle avoidance success rate is not greater than a preset success rate threshold; the path update rule includes adjusting the initial obstacle avoidance path based on the tissue density gradient direction; the response parameter increment has a piecewise linear relationship with the current stability evaluation index.

[0051] Preferably, the step of constructing a multi-path optimization model and iteratively optimizing the design parameters to obtain the optimal path planning parameters includes the following steps:

[0052] A multi-path optimization model is constructed, in which the optimization variables include path node density, turning angle threshold and operation force distribution ratio, the optimization objectives include minimizing path length and maximizing adjustment response speed, and the constraints include the upper limit of surgical instrument operation and the ultrasound imaging accuracy threshold.

[0053] The multi-path optimization model is initially solved using the A* algorithm to generate an initial population of optimized paths.

[0054] Based on the initial optimized path population, Dijkstra's algorithm is used for global optimization to generate optimal path planning parameters.

[0055] Preferably, the present invention further includes an interventional ultrasound system for minimally invasive surgery, the system comprising:

[0056] The data acquisition module is used to acquire ultrasound image data of the patient's surgical site and the operating status parameters of the surgical instruments;

[0057] The image modeling and analysis module is used to perform multi-layer ultrasound scanning of the surgical site and construct a three-dimensional ultrasound image model. It combines ultrasound image data to perform dynamic tissue feature analysis on the three-dimensional ultrasound image model and generate an initial tissue feature evaluation model.

[0058] The comprehensive evaluation and simulation module is used to load dynamic blood vessel distribution data and surgical operation constraints onto the initial tissue feature evaluation model, generate a comprehensive tissue feature evaluation model, and perform dynamic simulation of the puncture point by combining operation state parameters to obtain puncture point control simulation data.

[0059] The parameter generation module is used to construct a dynamic blood vessel prediction model and train it using simulation data of puncture point adjustment to obtain a puncture point adjustment model, and then generate initial adjustment parameters. The initial adjustment parameters include at least the initial puncture point position, the initial obstacle avoidance path, and the initial adjustment response parameters.

[0060] The dynamic adjustment simulation module is used to obtain dynamic adjustment simulation information based on initial adjustment parameters, comprehensive organizational feature evaluation model, and operational state parameters;

[0061] The path optimization module is used to combine dynamically adjusted simulation information with surgical plan design parameters to construct a multi-path optimization model and iteratively optimize the design parameters to obtain the optimal path planning parameters.

[0062] The strategy adjustment module is used to reason about the path planning parameters for the current time period based on the real-time ultrasound image model, generate the safe puncture probability for the current time period, and adjust the real-time puncture strategy of the surgical instruments by combining the optimal path planning parameters for the current time period with the actual path parameters to achieve the goal of dynamic puncture point matching.

[0063] Compared with the prior art, the beneficial effects of the present invention are:

[0064] In terms of image modeling and analysis, ultrasound images of the surgical site are obtained by scanning the surgical site from multiple angles using an ultrasound probe. These images are then preprocessed, including image denoising and coordinate registration, and combined with 3D reconstruction technology to generate a 3D ultrasound image model. Based on this, dynamic tissue feature analysis is performed through mesh weight allocation and feature parameter mapping. This allows for comprehensive and accurate classification of tissue safety levels, providing more realistic and detailed tissue feature information for subsequent puncture path planning. This effectively overcomes the limitations of traditional single-layer scanning modeling and improves the accuracy of understanding the anatomical structure of the surgical site.

[0065] In the comprehensive evaluation and dynamic simulation of the puncture point, dynamic vascular distribution data is loaded onto the initial tissue feature evaluation model to simulate real-time vascular changes. Surgical operation constraints, such as the maximum puncture angle limit, are then added to generate a comprehensive tissue feature evaluation model. A multi-constraint path planning equation is constructed by combining operational state parameters and numerically solved using a piecewise linearization method. This approach simultaneously considers multiple factors such as vascular distribution, tissue density, and instrument operation constraints, accurately calculating simulation data for puncture point control, including tissue density distribution, vascular density distribution, and the set of safe puncture areas. This process achieves dynamic simulation of the puncture path and accurate evaluation under multiple constraints, effectively avoiding the problem that traditional static models cannot adapt to dynamic changes in blood vessels and instrument operation limitations, significantly improving the safety and feasibility of the puncture path.

[0066] In terms of parameter generation and dynamic adjustment simulation, a dynamic vascular prediction model was constructed based on 3D ultrasound image features. This model was trained and validated using puncture point adjustment simulation data to obtain a puncture point adjustment model. This model can predict the set of safe puncture areas based on real-time operational state parameters, and then generate initial adjustment parameters including the initial puncture point position and initial obstacle avoidance path. Simultaneously, by constructing a dynamic adjustment simulation model, dynamic adjustment simulation information such as puncture point offset is updated in real time when dynamic adjustment trigger conditions are met, achieving dynamic optimization of the puncture path. This mechanism based on dynamic prediction and real-time adjustment enables the system to quickly respond to changes in tissues and blood vessels during surgery, significantly improving the adaptability and accuracy of puncture operations.

[0067] In terms of multi-path optimization and strategy adjustment, a multi-path optimization model was constructed, using path node density and other parameters as optimization variables, with the objectives of minimizing path length and maximizing adjustment response speed. Iterative optimization using the A* and Dijkstra algorithms yielded the optimal path planning parameters. This optimization process achieved a balance among multiple objectives, ensuring optimal overall performance of the puncture path. Furthermore, based on a real-time ultrasound imaging model, the safe puncture probability for the current time period was generated. By combining the optimal path planning parameters with the actual path parameters to adjust the real-time puncture strategy, the puncture point matching target could be dynamically achieved, further improving the safety and efficiency of the surgical procedure and reducing surgical time and patient trauma. Attached Figure Description

[0068] Figure 1 This is a schematic diagram illustrating the working principle of the interventional ultrasound method and system for minimally invasive surgery described in this invention.

[0069] Figure 2 Design drawings generated from simulation data for puncture point control;

[0070] Figure 3 Design drawings generated for initial parameter adjustments;

[0071] Figure 4 To dynamically adjust the design drawings generated from simulation information;

[0072] Figure 5 Design diagram for constructing a multi-path optimization model. Detailed Implementation

[0073] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0074] Please see Figures 1-5 The present invention relates to an interventional ultrasound method and system for minimally invasive surgery, the specific implementation steps of which are as follows:

[0075] Data acquisition steps: Ultrasound image data of the patient's surgical site is acquired through ultrasound imaging equipment, and at the same time, operation status parameters are collected in real time through sensors mounted on the surgical instruments. The operation status parameters include at least the instrument position, movement speed and puncture angle.

[0076] 3D modeling and initial assessment steps: Perform multi-layer ultrasound scanning on the surgical site, and construct a 3D ultrasound image model using 3D reconstruction technology; Combine ultrasound image data, divide tissue safety levels by grid weight allocation, and assign corresponding ultrasound image data to each level area to complete dynamic tissue feature analysis and generate an initial tissue feature assessment model.

[0077] Comprehensive evaluation and dynamic simulation steps: Load dynamic vascular distribution data into the initial tissue feature evaluation model to simulate real-time vascular changes and generate the first tissue feature evaluation model; further load surgical operation constraints (including maximum puncture angle limit, minimum turning radius and instrument operation redundancy parameters) to generate a comprehensive tissue feature evaluation model; based on this model and operation state parameters, construct a multi-constraint path planning equation including obstacle avoidance distance equation, trajectory smoothness equation and operation difficulty equation, and solve it numerically through piecewise linearization method to obtain puncture point control simulation data.

[0078] Parameter generation steps: A dynamic vascular prediction model is constructed based on the features of three-dimensional ultrasound images. The model is trained and verified using simulation data of puncture point adjustment to obtain the puncture point adjustment model. Real-time operation state parameters are input into the model to predict the set of safe puncture areas and generate initial adjustment parameters including the initial puncture point position, initial obstacle avoidance path and initial adjustment response parameters.

[0079] Dynamic adjustment simulation steps: Map the initial adjustment parameters to the comprehensive organizational feature evaluation model, update the model by encrypting the path nodes, define the dynamic adjustment trigger conditions, path update rules and response parameter increments, and construct a dynamic adjustment simulation model; based on this model, iteratively solve the multi-constraint path planning equations to obtain dynamic adjustment simulation information including puncture point offset, path obstacle avoidance success rate and stability evaluation indicators.

[0080] Path optimization steps: Construct a multi-path optimization model with path node density, turning angle threshold, and operation force distribution ratio as optimization variables, and minimizing path length and maximizing adjustment response speed as optimization objectives. Combine the surgical plan design parameters, generate an initial optimized path population using the A* algorithm, and then use Dijkstra's algorithm for global optimization to obtain the optimal path planning parameters.

[0081] Strategy adjustment steps: Based on the real-time ultrasound image model, infer the path planning parameters for the current time period to generate the safe puncture probability; combine the optimal path planning parameters with the actual path parameters to dynamically adjust the surgical instrument puncture strategy to achieve the puncture point matching target.

[0082] The present invention will be further described below with reference to Examples 1 to 5:

[0083] Example 1:

[0084] The specific implementation method in the 3D modeling and initial evaluation steps is as follows: First, the surgical site is scanned from multiple angles using an ultrasound probe, covering an angle range of 0° to 180°, with adjacent scanning angles not exceeding 15° to ensure complete acquisition of tissue morphology and vascular distribution information. The ultrasound probe can be a convex array probe or a linear array probe, with the appropriate type selected based on the depth and extent of the surgical site. For example, a convex array probe is used for abdominal surgery, while a linear array probe is used for superficial tissue surgery. During the scanning process, the probe remains in contact with the skin surface, and its movement is controlled manually or by a robotic arm to acquire a continuous sequence of ultrasound images. This sequence contains multiple frames of two-dimensional ultrasound images, each with a resolution of at least 512×512 pixels and a frame rate of at least 30 frames per second.

[0085] After acquiring the ultrasound image sequence, it needs to be preprocessed to obtain standardized ultrasound image data. The preprocessing process includes image denoising, coordinate registration, feature extraction, grid subdivision, and data alignment. Image denoising uses a nonlocal mean filtering algorithm, which calculates the similarity between image patches and performs a weighted average to effectively suppress speckle noise while preserving edge details. Coordinate registration unifies ultrasound images acquired from different angles into the same coordinate system. A feature point matching-based registration method is used, first extracting feature points from each frame using the Scale Invariant Feature Transform (SIFT) algorithm, then using the Random Sample Consensus (RANSAC) algorithm to remove mismatched points, and finally achieving coordinate transformation through an affine transformation matrix. In the feature extraction stage, a Gaussian pyramid combined with the Laplacian operator is used to extract edge, texture, and corner features from the image to generate feature images. Grid subdivision divides the ultrasound image into regular grid cells. The grid size is determined according to the ultrasound imaging resolution. For example, when the resolution is 0.5 mm, the grid side length is set to 1 mm to ensure that each grid cell contains sufficient tissue feature information. Data alignment involves spatially mapping the feature-extracted image to grid cells, so that each grid cell corresponds to a specific region in the image.

[0086] Based on standardized ultrasound image data, a three-dimensional ultrasound image model is generated using three-dimensional reconstruction technology. The three-dimensional reconstruction employs volume rendering technology, with the following steps: First, the standardized two-dimensional ultrasound image sequence is interpolated to fill the gaps between adjacent slices. Cubic spline interpolation is used to improve the smoothness of the reconstructed model. Then, the interpolated image sequence is converted into volume data, where the grayscale value of each voxel corresponds to the echo intensity of the ultrasound image. Finally, the volume data is rendered using a raycasting algorithm to generate a realistic three-dimensional ultrasound image model that can intuitively display the tissue layers and blood vessel distribution at the surgical site.

[0087] Dynamic tissue feature analysis is performed on a 3D ultrasound image model to generate an initial tissue feature assessment model. Dynamic tissue feature analysis includes at least grid weight allocation and feature parameter mapping. During grid weight allocation, a safety level weight is assigned to each grid cell based on the physiological characteristics of the tissue and the degree of surgical risk. First, the vascular density parameter within the grid cell is calculated. Vascular density is determined by the proportion of vascular pixels in the grid cell, calculated using the formula: Vascular density = Number of vascular pixels / Total number of pixels in the grid cell. Then, based on vascular density, the grid cells are divided into three safety levels: high, medium, and low. For example, a vascular density greater than 0.4 is classified as high risk, between 0.2 and 0.4 as medium risk, and less than 0.2 as low risk. Different weight coefficients are assigned to grid cells of different safety levels: 1.5 for high risk, 1.0 for medium risk, and 0.5 for low risk.

[0088] Feature parameter mapping associates feature parameters in ultrasound image data with grid cells. Feature parameters include grayscale values, texture features (such as entropy, energy, and correlation), vessel diameter, and blood flow velocity. Grayscale values ​​directly reflect the echo characteristics of tissues; high-echoic areas correspond to calcification or bone tissue, while low-echoic areas correspond to fluid or cystic tissue. Texture features are calculated using the Gray-Level Co-occurrence Matrix (GLCM). Entropy reflects the complexity of the image texture, energy reflects the uniformity of the texture, and correlation reflects the correlation between texture elements. Vessel diameter is calculated after extracting vessel boundaries using edge detection algorithms (such as the Canny operator), and blood flow velocity is obtained from color Doppler ultrasound data. After normalizing these feature parameters to the [0,1] interval, they are mapped to the corresponding grid cells, forming the feature vector for each grid cell.

[0089] An initial tissue feature assessment model is generated through grid weight allocation and feature parameter mapping. Based on a three-dimensional grid structure, each grid cell contains safety level weights and feature vector information, comprehensively reflecting the tissue characteristics and risk distribution of the surgical site. In subsequent puncture point planning and path optimization, the initial tissue feature assessment model provides fundamental data support for comprehensive evaluation and dynamic simulation, enabling the puncture strategy to be dynamically adjusted according to tissue characteristics, thereby improving the safety and accuracy of the surgery.

[0090] Throughout the entire 3D modeling and initial assessment process, each step is closely integrated, and the data processing workflow exhibits strict logic and standardization. Multi-angle scanning of ultrasound images ensures data integrity, preprocessing steps improve data quality and consistency, 3D reconstruction technology enables the conversion from 2D images to 3D models, and dynamic tissue feature analysis endows the model with the assessment functions required for clinical application. Parameter settings and algorithm selection at each stage are based on ultrasound imaging principles and clinical practice needs, ensuring that the generated initial tissue feature assessment model accurately reflects the actual situation at the surgical site, providing a reliable basis for subsequent interventional ultrasound surgery.

[0091] Example 2:

[0092] The specific implementation method in the comprehensive evaluation and dynamic simulation steps is as follows: First, dynamic vascular distribution data is loaded onto the initial tissue feature evaluation model to simulate real-time vascular changes, generating the first tissue feature evaluation model. The dynamic vascular distribution data comes from the vascular dynamic sequence obtained preoperatively via four-dimensional ultrasound. This sequence contains information on the position, diameter, and blood flow velocity changes of blood vessels during the cardiac cycle, with a sampling frequency of no less than 50Hz and a temporal resolution at the millisecond level. During the loading process, a temporal interpolation algorithm is used to perform spatiotemporal matching between the dynamic vascular distribution data and the three-dimensional mesh of the initial tissue feature evaluation model. Specifically, using the vascular mesh cells in the initial model as a reference, the spatial displacement vector of the vascular mesh cell at each time point is calculated based on the changes in vascular position in the time series. Cubic spline interpolation is used to smooth the displacement vector to ensure the continuity of vascular dynamic changes. At the same time, the attribute parameters of the vascular mesh cells are adjusted according to the blood flow velocity data. For example, a higher energy loss coefficient is set for areas with high blood flow velocity for resistance calculation in subsequent path planning.

[0093] Subsequently, surgical operation constraints are applied to the first tissue feature assessment model to generate a comprehensive tissue feature assessment model. These constraints include a maximum puncture angle limit, a minimum turning radius, and instrument operation redundancy parameters. The maximum puncture angle limit is determined based on the mechanical properties of the surgical instrument; for example, the maximum puncture angle for a flexible puncture needle is set to 60°, and for a rigid puncture needle, it is set to 45°. This angle is the angle between the needle axis and the normal to the tissue surface. The minimum turning radius is based on the instrument's bending performance parameters. For surgical instruments with active bending capabilities, the minimum turning radius is set to twice the instrument diameter; for passively bending instruments, it is set to three times. The instrument operation redundancy parameter is defined as the ratio of the maximum output power of the instrument's power system to the actual power used, typically set to 1.2-1.5 to ensure sufficient power reserve when the instrument encounters resistance. When applying the constraints, each parameter is embedded into the grid cell attributes of the comprehensive tissue feature assessment model through a constraint matrix. Each grid cell corresponds to a set of constraint vectors, including the allowed maximum puncture angle, the minimum turning radius threshold, and the power redundancy coefficient.

[0094] Based on a comprehensive tissue feature assessment model and operational state parameters, dynamic simulation of the puncture point is performed. First, a multi-constraint path planning equation is constructed, which includes at least an obstacle avoidance distance equation, a trajectory smoothness equation, and an operational difficulty equation. The obstacle avoidance distance equation ensures a safe distance between the puncture path and dangerous structures such as blood vessels; its expression is: d obstacle ≥d safe , where d obstacle d represents the distance between the puncture path and the hazardous structure. safe A preset safety distance is used (typically 2-5 mm, adjusted according to the organization's risk level). The trajectory smoothness equation is measured by the integral of the path curvature, and its expression is: Where κ(s) is the curvature of the path at position s, C smooth The smoothness threshold ranges from 0.5 to 1.0 rad / mm. The operational difficulty equation comprehensively considers factors such as puncture force and angle change rate, and its expression is: F force ≤F max and Where F force For puncture force, F max This is the maximum permissible force of the instrument (usually 5-10N). The rate of change of the puncture angle. This is the maximum permissible rate of angle change (taken as 10° / s).

[0095] A piecewise linearization method is used to numerically solve the multi-constraint path programming equation. First, the puncture path is discretized into N nodes, with the node spacing determined based on the ultrasound imaging resolution, typically 1-3 mm. Path segments between adjacent nodes are considered straight lines, and the node positions are adjusted to satisfy various constraints. For each node, parameters such as blood vessel density and tissue stiffness of its corresponding grid cell are calculated and substituted into the multi-constraint path programming equation for solution. During the solution process, obstacle avoidance distance constraints are first addressed to ensure that the distance between the node position and the hazardous structure is greater than a safe distance; then, trajectory smoothness is optimized by minimizing the path curvature integral by adjusting the node coordinates; finally, the operational difficulty constraint is verified. If the puncture force or angle change rate exceeds a threshold, the node position is adjusted and the calculation is repeated.

[0096] During the solution process, the tissue density distribution, blood vessel density distribution, safe puncture region set, and dynamically adjusted priority sequence are obtained. The steps for generating the safe puncture region set are as follows: Based on the blood vessel density distribution, the blood vessel coverage index of each grid cell is calculated. The blood vessel coverage index is defined as the ratio of the area of ​​blood vessel pixels within a grid cell to the total area of ​​the grid cells. The calculation formula is: Where A v A is the area of ​​the blood vessel pixel. g This represents the total area of ​​the grid cells. A threshold segmentation algorithm is used to identify areas in the comprehensive tissue feature assessment model where the vascular coverage index is no greater than a preset threshold. The preset threshold is determined based on the surgical risk level: 0.3 for low-risk surgeries, 0.2 for medium-risk surgeries, and 0.1 for high-risk surgeries. Qualifying grid cells constitute a set of safe puncture areas. This set is a spatial distribution mapping between the vascular coverage index and the preset threshold, stored as a three-dimensional grid index. Each safe grid cell records its coordinates, vascular coverage index, and tissue density parameters.

[0097] The generation of dynamically adjusted priority sequences is based on a comprehensive assessment of tissue density and vascular density. First, the risk index for each grid cell is calculated using the formula: R = w1·D t +w2·D v D t For tissue density, D v Here, w1 and w2 represent blood vessel density, and w1 and w2 are weighting coefficients (typically w1 = 0.6 and w2 = 0.4). Areas with higher risk indices have higher dynamic adjustment priorities. All grid cells are sorted from highest to lowest risk index to generate a dynamic adjustment priority sequence. This sequence guides the order of puncture path adjustments, ensuring that path planning for high-risk areas is addressed first.

[0098] Throughout the comprehensive evaluation and dynamic simulation process, data interaction and algorithm execution maintained strict temporal order. Loading dynamic vascular distribution data ensured the model could reflect vascular movement in real time; embedding surgical operation constraints ensured simulation results conformed to the physical characteristics of the instruments; and the construction of multi-constraint path planning equations comprehensively considered safety, smoothness, and operational feasibility. The piecewise linearization solution method transformed the complex continuous optimization problem into a computable numerical problem through discretization; and the generation of a safe puncture region set and a dynamically adjusted priority sequence provided crucial data support for subsequent puncture point adjustments and path optimization. Parameter settings and algorithm selection at each stage were based on clinical surgical needs and instrument performance parameters, ensuring that simulation results could be directly applied to the formulation of puncture strategies in actual surgery, providing reliable technical support for the precise implementation of minimally invasive surgery.

[0099] Example 3:

[0100] In the parameter generation step, the construction and training process of the dynamic vascular prediction model is as follows: First, a dynamic vascular prediction model is constructed based on the features of three-dimensional ultrasound images. The features of three-dimensional ultrasound images encompass the spatial geometric and dynamic features of blood vessels. Spatial geometric features include parameters such as vessel diameter, branch angle, and curvature, which are calculated after extracting the vessel boundaries using edge detection algorithms. For example, the Canny operator is used to detect the vessel cross-section in the three-dimensional ultrasound image, and an ellipse is fitted to obtain the vessel diameter parameter. Dynamic features include blood flow velocity and vessel wall motion amplitude, which are calculated using color Doppler ultrasound data and optical flow algorithms. The optical flow algorithm can track the displacement of vessel wall pixels in consecutive frames to obtain the motion velocity. The dynamic vascular prediction model adopts a convolutional neural network (CNN) architecture, including an input layer, convolutional layers, pooling layers, fully connected layers, and an output layer. The input layer receives volume data from the three-dimensional ultrasound image. The convolutional layers extract multi-scale vascular features through convolutional kernels of different scales. The pooling layers reduce the feature dimensionality and improve translation invariance. The fully connected layers integrate global features. The output layer predicts the position, morphology, and blood flow parameters of blood vessels in future time periods.

[0101] Next, the dynamic vascular prediction model will be trained and validated using simulation data of puncture point control. Before training, the simulation data of puncture point control needs to be reconstructed. The specific steps are as follows: First, based on the tissue density distribution, vascular density distribution, and safe puncture area set, an initial multi-dimensional path input tensor is constructed. The tissue density distribution is obtained through statistical analysis of the grayscale values ​​of ultrasound images. The grayscale value is positively correlated with the tissue density, and the calculation formula is: ρ t = k·mean(G)+b, where ρ tFor tissue density, G is the grayscale matrix within a grid cell, and k and b are calibration coefficients (determined through measurements of ex vivo tissue samples); the vascular density distribution is the percentage of vascular pixels within a grid cell; the set of safe puncture regions is represented by a three-dimensional binary mask, where 1 represents a safe region and 0 represents a dangerous region. These three types of data are concatenated along the channel dimension to form the initial multi-dimensional path input tensor. Where H, W, and D represent the height, width, and depth of the 3D mesh, respectively.

[0102] The initial multi-dimensional path input tensor is standardized and its features are layered to generate the final multi-dimensional path input tensor. The standardization process uses the Z-score standardization method, calculating the mean μ and standard deviation σ for each channel's data, and then applying the formula... Normalization is performed to ensure that the data in each channel follows a standard normal distribution. Feature hierarchical processing maps tissue density, blood vessel density, and safe regions to different feature levels. For example, tissue density is divided into low, medium, and high levels (corresponding to normalized value ranges of [-1, -0.3], [-0.3, 0.3], and (0.3, 1]), and blood vessel density is divided into sparse, medium, and dense levels. The safe region retains its binary attribute. This hierarchical mapping enhances the semantic discriminative power of the features, ultimately generating a tensor.

[0103] A puncture point adjustment label tensor is constructed based on a dynamically adjusted priority sequence. The dynamic adjustment priority sequence is an index list sorted according to the risk index of the grid cells (obtained by a weighted sum of tissue density and vessel density; a higher risk index corresponds to a higher adjustment priority). Puncture point adjustment label tensor Constructed as follows: For each grid cell, if its index in the dynamically adjusted priority sequence is i, then the label value is... (N is the total number of grid cells), so that the label values ​​are distributed in the interval [0,1], with larger values ​​indicating higher adjustment priority. This label tensor is used to supervise the model to learn the priority mapping relationship of puncture point adjustment.

[0104] The final multi-dimensional path input tensor and the puncture point adjustment label tensor are combined according to the sample dimensions to form a training sample set. Where M is the total number of samples. A supervised learning method is used to train the dynamic blood vessel prediction model, with the loss function being the mean squared error (MSE). The Adam optimizer is selected, and the initial learning rate is set to 10. -4 To prevent overfitting during training, an early stopping method was employed; training was stopped when the validation set loss did not decrease for five consecutive epochs. After training, the model was validated using test samples containing different tissue types and blood vessel distributions to ensure that the model could accurately predict the set of safe puncture areas.

[0105] Real-time operational status parameters are input into the puncture point adjustment model to predict a set of safe puncture areas. These parameters include the current position coordinates (x, y, z) of the surgical instrument, puncture speed v, and puncture angle θ, and are acquired in real-time via a six-dimensional force sensor and inertial measurement unit (IMU) at the instrument's end effector, with a sampling frequency of 100Hz. Based on a dynamic vascular prediction model and incorporating these real-time operational parameters, the puncture point adjustment model calculates and outputs a probability distribution of the safe puncture area set through forward propagation. Grid cells with a probability value greater than a preset threshold (e.g., 0.5) are considered safe areas.

[0106] Based on the predicted set of safe puncture areas, initial adjustment parameters are generated. First, the grid cell with the lowest blood vessel density in the predicted set of safe puncture areas is extracted. The blood vessel density is determined by the second channel value (normalized blood vessel density parameter) of this grid cell in the input tensor. The smaller the value, the lower the blood vessel density. The center coordinates of the grid cell with the smallest value are selected as the initial puncture point position (x0, y0, z0).

[0107] Based on the spatial connectivity of the predicted safe puncture zone set, a feasible topology for the initial obstacle avoidance path is fitted. Spatial connectivity analysis is performed using a three-dimensional connected domain detection algorithm, which divides adjacent safe grid cells (six-neighbor connected) into the same connected domain, calculates the volume and centroid position of each connected domain, and selects the connected domain with the largest volume as the main path channel. The feasible topology for the initial obstacle avoidance path is based on the centroid connection line of the connected domains, and a smooth path is formed by fitting a Bézier curve. The control points of the curve are determined by the coordinates of the boundary grid cells of the connected domains, ensuring that the path is completely within the safe puncture zone.

[0108] The tissue density gradient direction of the predicted set of safe puncture regions is calculated and normalized to a path reference vector. The tissue density gradient is calculated by numerically differentiating the three-dimensional tissue density field, resulting in the gradient vector at each grid cell. The solution is approximated using the central difference method. The average gradient direction is obtained by averaging the gradient vectors of all grid cells within the safe puncture zone set. After normalization, the path reference vector is obtained. This vector is the initial obstacle avoidance path direction, used to guide the puncture path along the direction of the gentlest tissue density change, in order to reduce puncture resistance.

[0109] The initial adjustment response parameters include the path adjustment step size and angle increment, which are determined based on the spatial dimensions of the safe puncture area and the precision of instrument operation. For example, when the average width of the safe area is 5 mm, the path adjustment step size is set to 1 mm and the angle increment is set to 5°, ensuring that each adjustment effectively avoids dangerous structures without causing excessive path twisting.

[0110] Throughout the parameter generation process, from data reconstruction to model training and parameter generation, each step strictly adheres to the fundamental principles of signal processing and machine learning. Multi-dimensional extraction of 3D ultrasound image features ensures the richness of the model input; standardization and feature hierarchical processing during data reconstruction enhance the data's learnability; and dynamically adjusting priority labels provides the model with clear supervisory signals. Based on real-time operational parameter prediction of the safe zone and the generation of initial parameters from geometric features, the system can dynamically generate adaptive puncture adjustment strategies according to the surgical progress, achieving intelligent and precise puncture point planning in interventional ultrasound surgery. The algorithm selection and parameter settings for each step are based on actual clinical needs and instrument performance parameters, ensuring that the generated initial adjustment parameters have practical guiding significance and can be directly applied to the motion control of surgical instruments.

[0111] Example 4:

[0112] The specific implementation method in the dynamic adjustment simulation step is as follows: First, the initial puncture point location is mapped to a comprehensive tissue feature evaluation model, which includes information such as tissue density, vascular distribution, and surgical operation constraints at the surgical site. For example, assuming the initial puncture point location corresponds to a grid cell with coordinates (x0, y0, z0) in the model, this cell is evaluated as a low-risk area with a vascular coverage index of 0.1 and a medium-level tissue density parameter. Next, the initial obstacle avoidance path and initial adjustment response parameters are matched. The initial obstacle avoidance path is generated based on the spatial connectivity of the set of safe puncture areas. For example, starting from the initial puncture point, it extends along the direction with the lowest vascular density, passing through multiple consecutive low-risk grid cells to form a preliminarily planned straight-line path. The initial adjustment response parameters are set according to the instrument operation accuracy, such as a path adjustment step size of 1.5 mm and an angle increment of 8°.

[0113] Subsequently, the path nodes in the adjustment area were densified to improve simulation accuracy. During the densification process, new nodes were inserted into the initial path at fixed intervals (e.g., 0.8 mm), tripling the total number of nodes to capture more detailed changes in tissue characteristics along the path. For example, if the initial path contained 10 nodes, it was expanded to 30 nodes after densification. Each node corresponds to a mesh cell in the model, recording parameters such as blood vessel density, tissue stiffness, and operational constraints at that location. After node densification was completed, the comprehensive tissue feature evaluation model was updated, incorporating the attribute parameters of the new nodes into the model calculation to ensure that the model could reflect more refined path details.

[0114] Define dynamic adjustment trigger conditions, path update rules, and response parameter increments to generate a dynamic adjustment simulation model. The dynamic adjustment trigger condition is set so that the current obstacle avoidance success rate is no greater than a preset success rate threshold, for example, 85%. When the obstacle avoidance success rate calculated during simulation is lower than this threshold, the path adjustment mechanism is triggered. The path update rule adjusts the initial obstacle avoidance path based on the tissue density gradient direction. For example, if a large tissue density gradient is detected in a region ahead of the path (indicating the presence of hard tissue or potential obstacles), the path is adjusted in the opposite direction of the gradient to avoid high-resistance areas. The response parameter increment has a piecewise linear relationship with the current stability assessment index, which is calculated comprehensively using parameters such as path curvature and puncture force fluctuation amplitude. For example, when the stability assessment index is greater than 0.6 (indicating poor path stability), the response parameter increment is set to a larger value (e.g., a step size increment of 0.5 mm); when the index is less than or equal to 0.6, the increment is set to a smaller value (e.g., a step size increment of 0.2 mm) to balance the adjustment magnitude and path smoothness.

[0115] Based on a dynamically adjusted simulation model, the multi-constraint path planning equations are iteratively solved using a piecewise linearization method to obtain dynamically adjusted simulation information. The piecewise linearization method divides the entire puncture path into multiple segments, each corresponding to a linear optimization problem. By solving and connecting these segments, the optimal path is approximated. During the iterative solution process, the parameters of the initial path are first calculated, such as obstacle avoidance distance, trajectory smoothness, and operational difficulty. For example, if the initial path has an obstacle avoidance distance of 3.2 mm (meeting the preset safety distance requirement of 2 mm), a trajectory curvature integral value of 0.8 rad / mm (within the smoothness threshold range of 0.5-1.0 rad / mm), and a puncture force of 4.5 N (lower than the instrument's maximum permissible force of 5 N), the obstacle avoidance success rate is calculated to be 90%, which is higher than the preset threshold, and the path does not require adjustment.

[0116] When a certain iteration step in the simulation detects dynamic displacement of blood vessels leading to an increase in the local vascular coverage index, the obstacle avoidance distance of the original path shortens to 1.8 mm (below the safe distance), and the obstacle avoidance success rate drops to 80%, triggering the dynamic adjustment condition. At this point, according to the path update rule, the path direction is adjusted along the tissue density gradient direction (assuming the gradient direction points to the right), increasing the puncture angle of the current node by 5°. Simultaneously, based on the stability evaluation index (calculated at 0.7, indicating high fluctuation), the response parameter increment is set to 0.5 mm, meaning the path adjustment step size increases from 1.5 mm to 2.0 mm. The adjusted path parameters are recalculated, the obstacle avoidance distance recovers to 2.5 mm, the obstacle avoidance success rate increases to 88%, and the stability evaluation index drops to 0.55, meeting the conditions for continuing the simulation.

[0117] Repeat the above iterative process until the simulation termination condition is met. The simulation termination condition can be set to the number of iterations reaching a preset value (e.g., 50 times) or the obstacle avoidance success rate stabilizing above 95%. In each iteration, the puncture point offset, path obstacle avoidance success rate, and stability evaluation index are updated in real time. For example, after 10 iterations, the cumulative puncture point offset reaches 4.8mm, the path obstacle avoidance success rate stabilizes at 92%, and the fluctuation range of the stability evaluation index shrinks to 0.4-0.6, indicating that the path adjustment tends to stabilize.

[0118] During dynamic simulation adjustments, it is necessary to continuously correlate the comprehensive tissue feature assessment model with operational status parameters. For example, when the actual puncture speed of the surgical instrument changes (e.g., from the preset 2 mm / s to 1.5 mm / s), the speed value in the operational status parameters is updated in the model, causing a corresponding change in the calculated puncture force, which in turn affects the solution to the operational difficulty equation and may trigger new path adjustments. Furthermore, the model must also consider tissue displacement caused by physiological factors such as patient respiratory movements. Through real-time loading of dynamic vascular distribution data, the model continuously updates vascular positions and risk areas to ensure that the simulation process is synchronized with the actual surgical environment.

[0119] The entire dynamic adjustment simulation process achieves dynamic optimization of the puncture path through refined node encryption, clear triggering conditions, and adjustment rules. Its core lies in transforming complex tissue features and instrument operation constraints into calculable simulation parameters, iteratively solving to gradually approximate a safe and feasible puncture path. This process considers not only static tissue anatomy but also dynamic factors such as vascular movement and instrument operation status, ensuring that the generated dynamic adjustment simulation information accurately reflects the actual surgical situation and provides a reliable basis for subsequent path optimization and puncture strategy adjustments. In clinical applications, such as liver tumor puncture surgery, this simulation process can help doctors predict path risks in advance, dynamically avoid intrahepatic blood vessels, improve puncture accuracy, and reduce the probability of surgical complications.

[0120] Example 5:

[0121] The specific implementation method for constructing a multi-path optimization model and iteratively optimizing the design parameters to obtain the optimal path planning parameters in the path optimization step is as follows:

[0122] Taking liver tumor biopsy as an example, assuming the three-dimensional ultrasound imaging model of the surgical site shows that the tumor is located in the right lobe of the liver, surrounded by the right hepatic vein and its branches, and there are regional differences in tissue density (higher density in the tumor area and lower density in the tissue surrounding the blood vessels). The surgical instrument is a puncture needle with active bending function, a maximum puncture force of 8N, a minimum turning radius of 2mm, and an ultrasound imaging accuracy of 0.3mm.

[0123] First, a multi-path optimization model is constructed. Optimization variables include path node density, turning angle threshold, and operational force distribution ratio. Path node density represents the number of nodes per unit length of path, with a value range of 5-20 nodes / mm. This controls the fineness of the path; for example, a node density of 10 nodes / mm means that each millimeter of path contains 10 planned nodes, capturing more subtle tissue feature changes. The turning angle threshold is defined as the maximum angle between two adjacent segments in the puncture path, with a value range of 30°-80°. A larger threshold allows for sharper turns in the path, suitable for avoiding densely packed blood vessels, while a smaller threshold tends to generate a smoother path. The operational force distribution ratio refers to the proportion of power output from the puncture needle in the X, Y, and Z coordinate axes. For example, a distribution ratio of 4:3:3 means that 40% of the power is distributed in the X-axis direction, and 30% each in the Y and Z axes, to accommodate differences in puncture resistance in different directions.

[0124] The optimization objectives include minimizing path length and maximizing adjustment response speed. Minimizing path length aims to reduce puncture time and tissue damage, such as selecting the shortest feasible path from the skin surface to the tumor center while safely avoiding blood vessels. Maximizing adjustment response speed requires the path planning to quickly adapt to intraoperative tissue displacement or instrument manipulation deviations; for example, the path should be replanned in a short time when a change in blood vessel position is detected. Constraints include upper limits on surgical instrument operation (maximum puncture force 8N, minimum turning radius 2mm) and ultrasound imaging accuracy thresholds (path node spacing not exceeding 0.3mm to ensure that each node position can be clearly imaged by ultrasound).

[0125] The A* algorithm is used to initially solve the multi-path optimization model, generating an initial population of optimized paths. The A* algorithm, combined with a heuristic search function, searches for feasible paths within the safe puncture area assessed by the comprehensive tissue feature evaluation model. Starting from the tumor center and the skin puncture site, the algorithm expands the node with the lowest cost each time until the target point is reached. During the search, constraints are verified in real time; for example, if the turning angle of a path segment is calculated to be 90° (exceeding the maximum allowable threshold of 80°), that path segment is discarded. After calculation by the A* algorithm, a population of 20 initial optimized paths is generated. Each path meets the safe puncture requirements; for example, path 1 has a length of 45mm, a node density of 12 / mm, and a turning angle threshold of 50°; path 2 has a length of 48mm, a node density of 8 / mm, and a turning angle threshold of 65°. The paths differ in parameters such as path length and node density, forming diverse initial solutions.

[0126] Based on the initial optimized path population, Dijkstra's algorithm is used for global optimization to generate optimal path planning parameters. Dijkstra's algorithm constructs a path graph model based on the initial path population, where each node represents an initial path, and the edge weights represent the differences between paths (such as path length difference, node density difference, etc.). The algorithm gradually updates the globally optimal solution of the paths through relaxation operations. For example, comparing the adjustment response speed of path 1 and path 2, it is found that path 1 has a higher node density and can respond to tissue displacement more quickly, thus giving it a higher priority in global optimization. Simultaneously, the algorithm verifies whether the operational force distribution ratio of each path meets the requirements of the instrument's power system. For example, if the X-axis force ratio of a certain path reaches 60%, resulting in insufficient power on the Y and Z axes and failing to meet the minimum turning radius constraint, this path is excluded.

[0127] During global optimization, the interactions between various optimization variables must be comprehensively considered. For example, increasing the path node density can improve the path's adaptability to tissue characteristics, but it will lead to increased computation and a decrease in adjustment response speed; decreasing the turning angle threshold can improve path smoothness, but may force the path to take a longer detour. Through repeated iterative adjustments, the optimal path planning parameters are finally generated. For example, the optimal path has a node density of 15 nodes / mm, a turning angle threshold of 55°, an operational force distribution ratio of 5:3:2 (X:Y:Z), and a path length of 42mm. This path satisfies the shortest path requirement, has a relatively fast adjustment response speed, and all operational parameters are within the instrument constraints.

[0128] Once the optimal path planning parameters are generated, they can directly drive the surgical instruments to perform the puncture operation. During the puncture, ultrasound imaging data is monitored in real time. If a deviation is found between the actual tissue characteristics and the model prediction (such as the tumor position shifting due to respiratory movements), the online update mechanism of the path optimization model is triggered. Based on the latest ultrasound imaging data, the optimal path parameters are regenerated to ensure that the puncture path always adapts to changes during the operation.

[0129] The entire path optimization process is closely integrated with clinical needs, achieving a balance between safety, accuracy, and operational feasibility through multivariate optimization and global search algorithms. Taking liver puncture as an example, this method effectively avoids intrahepatic blood vessels, selects the shortest and smoothest puncture path, and dynamically adjusts power distribution based on instrument performance to reduce puncture resistance and the risk of tissue damage. From the generation of the initial path population to the search for the global optimal solution, each step is based on actual surgical parameters and tissue characteristic data, ensuring the clinical operability of the optimization results and providing crucial technical support for the precise implementation of minimally invasive surgery.

[0130] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0131] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An interventional ultrasound system for use in minimally invasive surgery, characterized by, The system comprises: a data acquisition module for acquiring ultrasonic image data of a patient's surgical site and operation state parameters of a surgical instrument; an image modeling and analysis module for performing multi-layer ultrasonic scanning on the surgical site and constructing a three-dimensional ultrasonic image model, dynamically analyzing the three-dimensional ultrasonic image model in combination with the ultrasonic image data to generate an initial tissue feature evaluation model; a comprehensive evaluation and simulation module for loading dynamic blood vessel distribution data and surgical operation constraints on the initial tissue feature evaluation model to generate a comprehensive tissue feature evaluation model, and performing dynamic simulation of a puncture point in combination with the operation state parameters to obtain puncture point regulation simulation data; a parameter generation module for constructing a dynamic blood vessel prediction model and training the same through the puncture point regulation simulation data to obtain a puncture point adjustment model, and further generating initial adjustment parameters, wherein the initial adjustment parameters at least include an initial puncture point position, an initial obstacle avoidance path, and initial adjustment response parameters; a dynamic adjustment simulation module for obtaining dynamic adjustment simulation information based on the initial adjustment parameters, the comprehensive tissue feature evaluation model, and the operation state parameters; a path optimization module for constructing a multi-path optimization model and iteratively optimizing design parameters in combination with the dynamic adjustment simulation information and surgical scheme design parameters to obtain optimal path planning parameters; a strategy adjustment module for reasoning the path planning parameters of a current period based on a real-time ultrasonic image model to generate a current period safety puncture probability, adjusting a real-time puncture strategy of the surgical instrument in combination with the current period optimal path planning parameters and actual path parameters to achieve a dynamic puncture point matching target.

2. An interventional ultrasound system for use in minimally invasive surgery, characterized by, The system corresponds to an execution method comprising the following steps: acquiring ultrasonic image data of a patient's surgical site and operation state parameters of a surgical instrument; performing multi-layer ultrasonic scanning on the surgical site and constructing a three-dimensional ultrasonic image model, dynamically analyzing the three-dimensional ultrasonic image model in combination with the ultrasonic image data to generate an initial tissue feature evaluation model; loading dynamic blood vessel distribution data and surgical operation constraints on the initial tissue feature evaluation model to generate a comprehensive tissue feature evaluation model, and performing dynamic simulation of a puncture point in combination with the operation state parameters to obtain puncture point regulation simulation data; constructing a dynamic blood vessel prediction model and training the same through the puncture point regulation simulation data to obtain a puncture point adjustment model, and further generating initial adjustment parameters, wherein the initial adjustment parameters at least include an initial puncture point position, an initial obstacle avoidance path, and initial adjustment response parameters; obtaining dynamic adjustment simulation information based on the initial adjustment parameters, the comprehensive tissue feature evaluation model, and the operation state parameters; constructing a multi-path optimization model and iteratively optimizing design parameters in combination with the dynamic adjustment simulation information and surgical scheme design parameters to obtain optimal path planning parameters; reasoning the path planning parameters of a current period based on a real-time ultrasonic image model to generate a current period safety puncture probability, adjusting a real-time puncture strategy of the surgical instrument in combination with the current period optimal path planning parameters and actual path parameters to achieve a dynamic puncture point matching target.

3. An interventional ultrasound system for use in minimally invasive surgery according to claim 2, characterized in that, The puncture point regulation simulation data at least includes tissue density distribution, blood vessel density distribution, safe puncture region set and dynamic adjustment priority sequence; The dynamic adjustment simulation information at least includes puncture point offset, path obstacle avoidance success rate and stability evaluation index.

4. An interventional ultrasound system for use in minimally invasive surgery according to claim 2, characterized in that, The method comprises the following steps: The surgical site is scanned by an ultrasound probe at multiple angles to obtain an ultrasound image sequence of tissue morphology and blood vessel distribution; The ultrasound image sequence is preprocessed to obtain standardized ultrasound image data, wherein the preprocessing includes one or more of image denoising, coordinate registration, feature extraction, mesh subdivision and data alignment; A three-dimensional ultrasound image model is generated based on the standardized ultrasound image data and combined with three-dimensional reconstruction technology; The three-dimensional ultrasound image model is analyzed for dynamic tissue characteristics to generate an initial tissue characteristic evaluation model, wherein the dynamic tissue characteristic analysis at least includes mesh weight distribution and feature parameter mapping, and the tissue safety level is divided by mesh weight distribution, and the corresponding ultrasound image data is assigned to each level region.

5. An interventional ultrasound system for use in minimally invasive surgery according to claim 2, characterized in that, The initial tissue characteristic evaluation model is loaded with dynamic blood vessel distribution data and surgical operation constraints to generate a comprehensive tissue characteristic evaluation model, and the operation state parameters are combined to perform dynamic simulation of the puncture point to obtain puncture point regulation simulation data, including the following steps: The initial tissue characteristic evaluation model is loaded with dynamic blood vessel distribution data to simulate real-time blood vessel changes to generate a first tissue characteristic evaluation model; The first tissue characteristic evaluation model is loaded with surgical operation constraints to generate a comprehensive tissue characteristic evaluation model, wherein the surgical operation constraints include maximum puncture angle limit, minimum turning radius and instrument operation redundancy parameters; Based on the comprehensive tissue characteristic evaluation model and the operation state parameters, the puncture point dynamic simulation is performed, and the specific process includes: A multi-constraint path planning equation is constructed, which at least includes an obstacle avoidance distance equation, a trajectory smoothness equation and an operation difficulty equation, and the multi-constraint path planning equation is numerically solved by piecewise linearization method based on the comprehensive tissue characteristic evaluation model to obtain tissue density distribution, blood vessel density distribution, safe puncture region set and dynamic adjustment priority sequence; The safe puncture region set includes the following steps: Based on the blood vessel density distribution, the blood vessel coverage index of each grid cell is calculated; Regions in the comprehensive tissue characteristic evaluation model with a blood vessel coverage index not greater than a preset threshold are identified to generate a safe puncture region set, represented as follows: The safe puncture region set is a spatial distribution mapping result of the blood vessel coverage index and the preset threshold.

6. An interventional ultrasound system for use in minimally invasive surgery according to claim 2, characterized in that, The dynamic blood vessel prediction model is constructed and trained by the puncture point regulation simulation data to obtain a puncture point adjustment model, and then initial adjustment parameters are generated, including the following steps: A dynamic blood vessel prediction model is constructed based on three-dimensional ultrasound image features; The dynamic blood vessel prediction model is trained and verified by the puncture point regulation simulation data to obtain a puncture point adjustment model; Input the real-time operation state parameters into the puncture point adjustment model to predict a safe puncture region set; Generate initial adjustment parameters based on the predicted safe puncture region set, wherein the initial adjustment parameters at least include an initial puncture point position, an initial obstacle avoidance path and an initial adjustment response parameter.

7. An interventional ultrasound system for use in minimally invasive surgery according to claim 6, characterized in that, It also includes data reconstruction of the puncture point regulation simulation data, specifically: Based on the tissue density distribution, the blood vessel density distribution and the safe puncture region set, an initial multi-dimensional path input tensor is constructed; The initial multi-dimensional path input tensor is standardized and feature-layered to generate a final multi-dimensional path input tensor; Based on the dynamic adjustment priority sequence, a puncture point adjustment label tensor is constructed; Combined with the final multi-dimensional path input tensor and the puncture point adjustment label tensor, a training sample set is formed.

8. An interventional ultrasound system for use in minimally invasive surgery according to claim 7, characterized in that, The initial adjustment parameters generated based on the predicted safe puncture region set include the following steps: Extract the grid cell with the lowest blood vessel density in the predicted safe puncture region set to generate the initial puncture point position; According to the spatial connectivity of the predicted safe puncture region set, the feasible topological structure of the initial obstacle avoidance path is fitted to generate the initial adjustment response parameter; The tissue density gradient direction of the predicted safe puncture region set is normalized to a path reference vector, which is the direction of the initial obstacle avoidance path.

9. The interventional ultrasound system for use in minimally invasive surgery of claim 2, wherein, The dynamic adjustment simulation information is obtained based on the initial adjustment parameters, the comprehensive tissue feature evaluation model and the operation state parameters, including the following steps: Map the initial puncture point position to the comprehensive tissue feature evaluation model, match the initial obstacle avoidance path with the initial adjustment response parameter, encrypt the path nodes in the adjustment region, update the comprehensive tissue feature evaluation model, define the dynamic adjustment trigger condition, the path update rule and the response parameter increment, and generate the dynamic adjustment simulation model; Based on the dynamic adjustment simulation model, the multi-constraint path planning equation is iteratively solved by the piecewise linearization method to obtain the dynamic adjustment simulation information, specifically including: When the dynamic adjustment trigger condition is met, update the puncture point offset, the path obstacle avoidance success rate and the stability evaluation index, and re-solve the multi-constraint path planning equation until the simulation termination condition is reached; The dynamic adjustment trigger condition includes triggering the response parameter update when the current path obstacle avoidance success rate is not greater than the preset success rate threshold; the path update rule includes adjusting the initial obstacle avoidance path based on the tissue density gradient direction; the response parameter increment has a piecewise linear relationship with the current stability evaluation index.

10. The interventional ultrasound system for use in minimally invasive surgery of claim 2, wherein, The multi-path optimization model is constructed and the design parameters are iteratively optimized to obtain the optimal path planning parameters, including the following steps: Construct a multi-path optimization model, wherein the optimization variables include path node density, turning angle threshold and operation intensity distribution ratio, the optimization objectives include minimizing path length and maximizing adjustment response speed, and the constraint conditions include upper limit of surgical instrument operation and ultrasound imaging accuracy threshold; By The algorithm preliminarily solves the multi-path optimization model to generate an initial optimization path population; Based on the initial optimization path population, the Dijkstra algorithm is used for global optimization to generate the optimal path planning parameters.

Images