Surgical treatment path planning method, device and medium for lesion complex form

Abstract

This invention provides a method for planning treatment pathways in energy-focused surgery for complex lesion morphologies, belonging to the field of medical technology. The method includes: acquiring geometric feature data of the complex lesion morphology; matching a predetermined path traversal function based on the geometric feature data, wherein the path traversal function covers all surgical operation points of the complex lesion morphology; obtaining treatment paths for the energy-focused surgical operation points based on a set speed or acceleration according to the path traversal function; and generating a path set based on the treatment paths to determine the treatment path. This invention also discloses a surgical treatment pathway planning device and corresponding electronic equipment for complex lesion morphologies.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a method, apparatus, and computer-readable storage medium for surgical treatment path planning of complex lesion morphologies. Background Technology

[0002] In the medical field, treatment pathway planning systems are a key technology that provides important support for precision medicine and minimizing the risks of treatment.

[0003] The development of treatment pathway planning in the medical field began with the need for more precise and personalized treatment methods. Advances in medical imaging technology and increased computing power have enabled more accurate identification and localization of lesion areas, providing the technological foundation for pathway planning. Based on this, pathway planning systems, through algorithmic optimization, ensure that therapeutic energy or surgical instruments are precisely delivered to the target area, maximizing the protection of normal tissue and improving treatment outcomes and patient safety.

[0004] Primarily used in neurosurgery, orthopedics, and other surgeries requiring extremely high precision, path planning systems help surgeons avoid critical structures and accurately reach the lesion site. Using computer-aided design (CAD) and computer-aided surgery (CAS) systems, real-time imaging is fused with pre-simulated paths to guide the surgical procedure. With technological advancements, energy therapy devices and robotic surgery are becoming increasingly diverse, and path planning systems are beginning to automatically plan treatment dosages and pathways, working in conjunction with robots to achieve even higher precision and efficiency in surgical treatments.

[0005] For energy therapy devices, the attenuation of energy varies as it passes through different tissues. Therefore, for robotic surgery involving energy therapy, in addition to planning the treatment area, the path planning of the robot carrying the energy emission device must also be taken into account to achieve more efficient and safer treatment results. Summary of the Invention

[0006] This invention provides a method, device, and computer-readable storage medium for surgical treatment path planning of complex lesion morphologies, providing path planning for energy-focused surgery, thereby enabling accurate and efficient surgical operations.

[0007] In a first aspect, a method for planning treatment paths in energy-focused surgery for complex lesion morphologies is provided, comprising: acquiring geometric feature data of the complex lesion morphology; matching a predetermined path traversal function based on the geometric feature data, wherein the path traversal function covers all surgical operation points of the complex lesion morphology; obtaining treatment paths for the energy-focused surgical operation points based on a set speed or acceleration according to the path traversal function; and generating a path set based on the treatment paths to determine the treatment path.

[0008] In some embodiments, the geometric feature data includes: line feature data, rectangle feature data, cuboid feature data, irregular shape feature data, and three-dimensional feature data.

[0009] In some embodiments, matching a predetermined path traversal function based on the geometric feature data includes: matching a continuous line traversal function for the straight line feature data; matching a continuous rectangle traversal function for the rectangle feature data; matching a cuboid traversal function for the cuboid feature data; matching an irregular shape traversal function or an irregular shape surface heat dissipation traversal function for the irregular shape feature data; and matching a solid of revolution traversal function for the three-dimensional feature data.

[0010] In some embodiments, the positioning module is further configured to record the already determined positioning of the robotic arm of the intelligent surgical robot as the initial value for the next movement.

[0011] In some embodiments, obtaining the treatment path of the energy-focusing surgical operation point according to the set speed or acceleration based on the path traversal function includes: when the path traversal function is a continuous straight-line traversal function, it includes: obtaining the two endpoints of the straight-line feature data segment and traversing the straight-line feature data back and forth; when the path traversal function is a continuous rectangular traversal function, it includes: obtaining the centroid, width, and height of the rectangular feature data, and traversing the rectangular feature data in a zigzag pattern according to the distance from the rectangular feature data to the centroid; when the path traversal function is a continuous cuboid traversal function, it includes: obtaining the centroid, width, and height of the rectangular feature data, and traversing the rectangular feature data in a zigzag pattern according to the distance from the rectangular feature data to the centroid; when the path traversal function is a continuous rectangular traversal function, it includes: obtaining the centroid, width, and height of the rectangular feature data, and traversing the rectangular feature data in a zigzag pattern according to the distance from the centroid of the rectangular feature data; when the path traversal function is a continuous cuboid traversal function, it includes: obtaining the centroid, width, and height of the rectangular feature data, and traversing the rectangular feature data in a zigzag pattern according to the set speed or acceleration. In the case of continuous traversal, the process includes: obtaining the coordinates of the first and second reference points along the length direction of the cuboid, the coordinates of the third and fourth reference points along the width direction, and the diameter and center coordinates of the treatment ball relative to the cuboid; traversing the first, second, third, and fourth reference points of the cuboid. In the case of irregular shape traversal, the process includes: dividing the image echo intensity of the shape to be traversed into continuous regions of similar intensity; and inputting the distance to the center of the treatment ball, the direction of travel, and the number of reciprocations based on tissue characteristics. After each region is set... The path traversal function is a serpentine traversal of the irregular shape. When the path traversal function is an irregular shape surface heat dissipation traversal function, it includes: obtaining the coordinates of the treatment area exceeding the heat threshold, and moving the treatment focus out of the treatment area at a predetermined heat dissipation rate; or, using a path heat dissipation planning algorithm to plan the treatment path; when the path traversal function is a rotational body traversal function, it includes: obtaining the three-dimensional shape of the lesion; if the three-dimensional shape of the lesion can be covered by a rotational body, then selecting a lesion cross-section based on the three-dimensional shape, making the cross-section the basic plane of rotation, and specifying the rotation axis position based on the basic plane of rotation. The rotating basic surface is subjected to tiling processing. The rotating basic surface is the pattern to be tiled. Regular hexagons are used as tiling patterns to tile it. The size of the regular hexagons comes from the predetermined focal area shape size guided by the image. The diameter of the largest inscribed circle inside the focal area shape is measured and reduced to 10% to 50%. The inscribed regular hexagon of this circle is used as the size of the regular hexagon. When tiling the rotating basic surface, the annealing algorithm is used to minimize the number of tiling patterns required. After tiling, the centroid position of each regular hexagon is determined, so that all tiling patterns rotate around the rotation axis to cover the three-dimensional shape of the lesion.

[0012] In some embodiments, the path heat dissipation planning algorithm includes the following steps: Introducing heat diffusion: in, Represents temperature. Represents the thermal diffusivity. Represents the temperature gradient. represents the Laplace operator, which describes the rate of heat diffusion, and t represents time; The treatment area is spatially meshed with a grid spacing equal to the diameter of a basic circle. The treatment area is then surrounded by a circle, which is then halved to generate the basic circle. Store the heat information for each grid and diffuse the heat to adjacent grids. Store the grid heat state information using triples. The thermal state of the region is estimated based on the thermal evaluation function. The temperature of each grid cell is checked at each time step. If the temperature exceeds a predetermined maximum threshold, the cost of path selection is increased to prevent paths from passing through this region. The thermal evaluation function is: f(n)=g(n)+Rem*Vs+λ×temperature(x,y) Where f(n) represents the heat assessment function, g(n) represents the cumulative cost from the starting point of the path to the current position, Rem represents the number of remaining uncounted grids, Vs represents the traversal speed, λ represents the temperature weighting coefficient, and temperature(x, y) is the temperature at the current position, where x and y represent the x and y coordinates of the current position.

[0013] In some embodiments, the method further includes the following steps: when the number of grids is greater than a predetermined threshold, traversal is performed using a fractal nesting method, including: after planning in a local area, planning is performed again as a whole to generate high λ solutions for large-area traversal and small-area 3*3 grids; when a fever treatment parameter with low heat generation is selected, the representative solution of λ value in the 3*3 grid is in the form of serpentine path traversal and straight path traversal, with traversal speed and heat dissipation speed alternating.

[0014] In some embodiments, the procedure further includes the step of further optimizing the treatment path according to the order of the abscissa or ordinate of the surgical operation points of the selected path from smallest to largest.

[0015] Secondly, a surgical treatment path planning device for complex lesion morphologies is provided, comprising: a data acquisition module for acquiring geometric feature data of the complex lesion morphology; a configuration module for matching a predetermined path traversal function based on the geometric feature data, wherein the path traversal function covers all surgical operation points of the complex lesion morphology; a path calculation module for obtaining the treatment path of the energy-focusing surgical operation point based on a set speed or acceleration according to the path traversal function; and a path determination module for generating a path set based on the treatment path and determining the treatment path.

[0016] Thirdly, the present invention provides an electronic device comprising: a processor; and a memory storing computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, the above-described surgical treatment path planning method for complex lesion morphology is implemented.

[0017] Fourthly, the present invention also provides a computer-readable storage medium storing program code, which can be called by a processor to execute the above-described surgical treatment path planning method for complex lesion morphology.

[0018] Compared with existing technologies, the present invention can achieve at least one of the following beneficial effects: providing path planning for energy-focused surgical treatment, thereby providing conditions for accurate and efficient surgical operation.

[0019] The summary section is provided to present the chosen concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify essential or necessary features of this disclosure, nor is it intended to limit the scope of this disclosure. Attached Figure Description

[0020] The above and other objects, features and advantages of this disclosure will become more apparent from the accompanying drawings, in which like reference numerals generally denote like parts.

[0021] Figure 1 A schematic diagram of a method for planning the treatment path of energy-focused surgery for complex lesion morphology provided in an embodiment of this application is shown; Figure 2A This illustration shows a schematic diagram of the rectangular feature data with the motion direction traversing from bottom to top in a zigzag pattern, provided in an embodiment of this application. Figure 2B This illustration shows a schematic diagram of rectangular feature data with a motion direction traversing from left to right in a zigzag pattern, provided in an embodiment of this application. Figure 2C A schematic diagram of multi-layer mesh traversal provided in an embodiment of this application is shown; Figure 2D This illustration shows a schematic diagram of traversal using the annealing algorithm provided in an embodiment of this application; Figure 2E A schematic diagram illustrating traversal using a rotating body is shown in an embodiment of this application; Figure 2F A schematic diagram of a regular hexagon and a semicircle provided in an embodiment of this application is shown; Figure 2G A schematic diagram of the rotating body provided in an embodiment of this application is shown; Figure 2HThis illustration shows a fractal diagram of the traversed region provided in an embodiment of this application; Figure 2I This paper illustrates a schematic diagram of a 3x3 grid traversal path provided in an embodiment of this application. Figure 2J This illustration shows another 3x3 grid traversal path provided in an embodiment of this application; Figure 3 This illustration shows a schematic diagram of an energy-focused surgical treatment path planning device for complex lesion morphology provided in an embodiment of this application. Detailed Implementation

[0022] Embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0023] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0024] This application provides a method for planning the treatment path in energy-focused surgery for complex lesion morphologies. Please refer to [link / reference]. Figure 1 This figure is a schematic diagram of the first embodiment of this application. The following is in conjunction with... Figure 1 The first embodiment of this application provides a detailed description of a method 100 for energy-focused surgical treatment path planning for complex lesion morphology.

[0025] This application provides a method for energy-focused surgical treatment path planning for complex lesion morphologies. The method may include the following steps: Step S102: Obtain data information, that is, obtain the geometric feature data of the complex morphology of the lesion; Step S104: Matching path traversal function, that is, matching a predetermined path traversal function according to the geometric feature data, wherein the path traversal function covers all surgical operation points of the lesion complex morphology. Step S106: Calculate the treatment path, that is, according to the path traversal function and the set speed or acceleration, obtain the treatment path of the energy focusing surgical operation point; Step S108: Determine the treatment path, that is, generate a path set based on the treatment path and determine the treatment path.

[0026] In some embodiments, the geometric feature data includes: line feature data, rectangle feature data, cuboid feature data, irregular shape feature data, and three-dimensional feature data.

[0027] In some embodiments, matching a predetermined path traversal function based on the geometric feature data includes: matching a continuous line traversal function for the straight line feature data; matching a continuous rectangle traversal function for the rectangle feature data; matching a cuboid traversal function for the cuboid feature data; matching an irregular shape traversal function or an irregular shape surface heat dissipation traversal function for the irregular shape feature data; and matching a solid of revolution traversal function for the three-dimensional feature data.

[0028] In some embodiments, the positioning module is further configured to record the already determined positioning of the robotic arm of the intelligent surgical robot as the initial value for the next movement.

[0029] In some embodiments, the treatment path of the energy-focused surgical operation point is obtained according to the path traversal function and a set speed or acceleration, including the following cases: When the path traversal function is a continuous straight-line traversal function, it includes: acquiring the two endpoints of the straight-line feature data segment, and traversing the straight-line feature data back and forth. For example, in energy focusing surgery, the focus can be moved to the two endpoints of the required traversed straight line based on image guidance. Each time the focus is moved to an endpoint, the user needs to click to upload coordinates. After the system confirms the line segment in space through the two endpoints, the user can input the velocity, acceleration, and number of repetitions. The system will then use the first uploaded coordinates as the starting point to traverse the line segment in space accordingly. When the path traversal function is a rotational traversal function, it includes: acquiring the three-dimensional shape of the lesion; if the three-dimensional shape of the lesion can be covered by a rotational body, then selecting the lesion cross-section based on the three-dimensional shape, making the cross-section the rotational basic plane, and specifying the rotation axis position based on the rotational basic plane; performing tiling processing on the rotational basic plane, and the rotational basic plane... This surface is the pattern to be tiled, and regular hexagons are used as the tiling pattern to tile it. The size of the regular hexagons comes from the predetermined focal area shape size guided by the image. The diameter of the largest inscribed circle inside the focal area shape is measured, and this diameter is reduced to 10% to 50%. The inscribed regular hexagon of this circle is used as the size of the regular hexagon. When tiling the rotating basic surface, the annealing algorithm is used to minimize the number of tiling patterns required. After tiling, the centroid position of each regular hexagon is determined, so that all tiling patterns rotate around the rotation axis to cover the three-dimensional shape of the lesion.

[0030] Some embodiments can also use the rotation traversal function. This function requires the user to define the basic plane and rotation axis of rotation according to the three-dimensional shape of the lesion. The user also needs to select the tiling pattern according to the shape of the focal energy region (cavitation bubble cluster) observed by the image guidance. This system provides rectangles and circles. The user can fill in the length and width of the tiling rectangle or the diameter of the circle after reducing the image size by 10% according to the image they see. The user draws the rotational planes and rotation axes by connecting points according to the shape of the lesion. This article will use a sphere (a special ellipsoid) as an example to explain the implementation method of this function: (a) Input the tessellation parameters, which in this example is the diameter of the circle, and the rotational planes to be traversed on the sphere, which in this example is the diameter of the semicircle; (b) The system generates a tessellated hexagonal region inscribed in the tessellated circle according to the diameter of the tessellated circle; (c) The system randomly places the rotational planes input by the user into the tessellated hexagonal region; (d) The simulated annealing algorithm is used to optimize the number of overlaps between the semicircle and the hexagon until the number is minimized; (e) When the system's computing power is limited and the mobility of the mobile platform is restricted, a special solution for the sphere is used to make the rotational planes more scalable. The center of the circle overlaps with the centroid of the regular hexagon, which, although sacrificing some efficiency, greatly simplifies the required hardware; (f) The user moves the focus to the center of the sphere to be traversed, enters the center coordinates (for other bodies of revolution, the user needs to enter two points to indicate the direction of the body of revolution and input a Z-axis coordinate to indicate the bottom of the body of revolution), enters the traversal speed, and the dwell time at the pivot point (the system will use a fast yielding speed when moving between non-traversal movements, such as when jumping between layers). The system will calculate the relative position between the focus points based on the center coordinates of the sphere and the relative coordinates of the regular hexagon on the basic surface of rotation, obtain the radius from the rotation axis, and rotate around the rotation axis from each coordinate. Taking a sphere as an example, the cross-section of the sphere is formed, such as... Figure 2E As shown. The system also provides a step-by-step therapy mode. In this mode, the path and path settings are the same as the continuous movement path, but the user needs to set the dwell time and step distance. In this mode, the system will stop and move along the path according to the set parameters, with a set dwell time for each step, and then move forward a distance before stopping again, until the path is completed.

[0031] For example, in order to place the fundamental plane of rotation within the inscribed regular hexagon so that the number of overlaps between the semicircles, which are the tessellation pattern, and the inscribed regular hexagon is minimized, the annealing algorithm can be used. The annealing algorithm is a global optimization method based on random perturbation and probability acceptance mechanism. Its idea comes from the solid annealing process: the system can accept a poor state at high temperature, thus escaping local minima; as the temperature decreases, the system gradually tends to stabilize and converges to a better solution. In this embodiment, the annealing algorithm can be used in the following way: (1) Generate a hexagonal tessellation region. According to the side length and honeycomb rules, generate a set of hexagonal center points within a specified range and construct each hexagonal polygon. (2) Define the target pattern. According to the radius and the current center position, construct a closed semicircular region. (3) Traverse all hexagons. Part of the program code is as follows: # Simulated Annealing Algorithm Implementation: Optimizing the position of the semicircle to minimize the area of ​​the overlapping hexagons import math # Simulated Annealing Algorithm: Finding the Optimal Semicircle Position def simulated_annealing(initial_temperature=100, cooling_rate=0.99, stop_temperature=0.01, max_iterations=1000): # Initial solution: Randomly generate a semicircle center position current_center = (random.uniform(-4, 4), random.uniform(-4, 4)) current_area, _ = calculate_area_overlap_half_circle_with_lower_threshold(current_center) # Current optimal solution best_center = current_center best_area = current_area temperature = initial_temperature iteration = 0 # Simulated Annealing Main Loop while temperature > stop_temperature and iteration < max_iterations: # Generate neighborhood solutions (with small-amplitude random perturbations) new_center = (current_center[0] + random.uniform(-0.5, 0.5), current_center[1] + random.uniform(-0.5, 0.5)) new_center = (max(-4, min(new_center[0], 4)), max(-4, min(new_center[1], 4))) # Ensure the center position is within a reasonable range # Calculate the overlapping area of ​​the new solution new_area, _ = calculate_area_overlap_half_circle_with_lower_threshold(new_center) # Calculate the energy difference (energy is the intersection area). delta_area = current_area - new_area # Acceptance Criterion: If the new solution is better, or if there is a certain probability that a worse solution will be accepted. if delta_area > 0 or random.random() < math.exp(delta_area / temperature): current_center = new_center current_area = new_area # Update the optimal solution if new_area < best_area: best_center = new_center best_area = new_area # Lower the temperature temperature *= cooling_rate iteration += 1 return best_center, best_area # Optimize the semicircle position using simulated annealing algorithm best_circle_center, best_area = simulated_annealing() # Calculate the overlapping hexagon at the optimal semi-circle center position overlap_area, best_selected_centers =calculate_area_overlap_half_circle_with_lower_threshold(best_circle_center) # Draw the optimized hexagonal mesh and the semicircle at the optimal semicircle center position. def plot_optimized_semi_circle_with_grid_simulated_annealing():""" Plot the hexagonal mesh optimized using simulated annealing and the semicircle at the optimal semicircle center position. """ fig, ax = plt.subplots(figsize=(8, 8)) hex_centers = hexagon_centers_corrected() # Draw a hexagonal grid for center in hex_centers: vertices = hexagon_vertices(center) hexagon = plt.Polygon(vertices, edgecolor='gray', facecolor='none')ax.add_patch(hexagon) # Draw the semicircle with the optimal semicircle center position semi_circle = patches.Wedge(best_circle_center, 2.5, 0, 180,edgecolor='green', facecolor='lightblue', lw=2) ax.add_patch(semi_circle) # Draw the selected hexagon for center in best_selected_centers: vertices = hexagon_vertices(center) hexagon = plt.Polygon(vertices, edgecolor='green', facecolor='none',linestyle='-', lw=2) ax.add_patch(hexagon) # Configure graphics display ax.set_aspect('equal', 'box') ax.set_xlim(-7, 7) ax.set_ylim(-7, 7) plt.grid(True) plt.show() # Draw the final result plot_optimized_semi_circle_with_grid_simulated_annealing() When the path traversal function is a continuous rectangle traversal function, it includes: obtaining the centroid, width, and height of the rectangle feature data; and traversing the rectangle feature data in a zigzag pattern based on the distance from the rectangle feature data to the centroid. For example, if the rectangle can only be traversed on the ultrasound observation surface, this function requires the user to move the focus to the centroid of the rectangle to be traversed according to the image guidance. The user needs to upload the centroid coordinates, input the width and height of the rectangle, set the speed and acceleration, input the diameter of the treatment ball based on the observed energy region (size of cavitation bubble cloud), input the treatment centroid distance based on tissue characteristics, and the number of reciprocations (from A to B counts as one, from A to B and back to A counts as two). The user also needs to select the movement direction from bottom to top or from left to right. After confirmation, the system will traverse the rectangle to be traversed on the observation surface in a zigzag pattern, traversing the path, such as... Figure 2A The direction of motion is shown as from bottom to top. Figure 2B The direction of movement is shown from left to right.

[0032] like Figure 2D As shown, the tessellation pattern is an inscribed regular hexagon. The fundamental plane of revolution is placed within the inscribed regular hexagon, minimizing the overlap between the semicircles of the tessellation pattern and the inscribed regular hexagon; or, the center of the fundamental circle of revolution overlaps with the centroid of the inscribed regular hexagon, such that the solid of revolution traverses the centroid of every inscribed regular hexagon, as shown. Figure 2EAs shown. In some embodiments, after the rotational basic faces are arranged, the geometric relationship between each regular hexagon and the semicircle is determined. A coordinate system is established with the center of the semicircle as the origin, and the centroids of the other regular hexagons will have coordinates, thus establishing their relative positions. After the relative positions are established, the coordinates of the semicircle's center are positioned at the target location, thus obtaining the coordinates of each point, as shown. Figure 2F As shown. A schematic diagram of the solid of revolution is shown below, illustrating its traversal of the centroid of each inscribed regular hexagon. Figure 2G As shown.

[0033] When the path traversal function is a cuboid continuous traversal function, it includes: obtaining the coordinates of the first and second reference points along the length direction of the cuboid, the coordinates of the third and fourth reference points along the width direction, and the diameter and center coordinates of the treatment ball relative to the cuboid; and traversing the first, second, third, and fourth reference points of the cuboid. For example: after moving to a specific location guided by the image for verification, the coordinates are manually revised. The coordinates of the two points along the width direction are given, and the revision method is the same. After completion, the body center coordinates are entered, the diameter of the treatment ball is entered, and the distance from the center of the treatment ball and the number of reciprocations are input according to the tissue characteristics. At this time, the system automatically calculates the height coordinates and automatically completes the slicing. The system will traverse each rectangular slice according to the rectangular traversal function.

[0034] When the path traversal function is an irregular shape traversal function, it includes: dividing the image echo intensity of the shape to be traversed into continuous regions with similar intensity, and inputting the distance to the center of the treatment ball, the direction of travel, and the number of reciprocations according to the tissue characteristics. After each region is set, the irregular shape is traversed in a serpentine manner.

[0035] When the path traversal function is an irregular graphic surface heat dissipation traversal function, it includes: obtaining the coordinate values ​​of the treatment area that exceeds the heat threshold, and moving the treatment focus out of the treatment area at a predetermined heat dissipation rate; or, planning the treatment path using a path heat dissipation planning algorithm.

[0036] In some embodiments, when a treatment area becomes overheated, the system will quickly move the focus to another treatment area at a heat dissipation rate Vk or stop energy emission, and plan the optimal treatment path based on a path heat dissipation planning algorithm, which includes the following steps: Introducing heat diffusion: in, Represents temperature. Represents the thermal diffusivity. Represents the temperature gradient. The Laplace operator represents the rate of heat diffusion, and t represents time. The path heat dissipation planning algorithm is used to determine the size of the observed energy region (cavitation bubble cloud) under high heat generation parameters, which can generally be regarded as a circle. The diameter of this circle is reduced by 50% as the basic circle for path planning. Taking a rectangle as an example, the user needs to set a traversal speed, and the system itself also has a preset heat dissipation speed, which is much faster than the traversal speed.

[0037] In some embodiments, the method further includes the following steps: when the number of grids exceeds a predetermined threshold, traversal is performed using a fractal nesting method, including: after planning a local region, it is planned again as a whole to generate high λ solutions for large-area traversal and small-area 3*3 grids; when a fever treatment parameter with low heat generation is selected, the representative solution of λ value in the 3*3 grid is a serpentine path traversal and a straight path traversal, with traversal speed and heat dissipation speed alternating. Specifically, some embodiments perform fractal traversal on the area to be traversed, and after planning a local small region, it is incorporated into a large region for planning, generating high λ solutions for large-area traversal and small-area 3*3 grids, where solid arrows represent slow traversal speeds and dashed arrows represent fast traversal speeds, such as... Figure 2H As shown. When selecting a treatment parameter with lower calorific value, λ can be taken as a lower value. Its representative solution in a 3*3 grid is in the form of serpentine path traversal and straight path traversal, with the traversal speed and heat dissipation speed alternating, such as... Figure 2I and Figure 2J As shown. In other words, the temperature of each grid cell is checked at each time step. If the temperature of a cell exceeds the maximum limit, it indicates that the area is overheated, and the sphere needs to wait or change its path. It then moves to another location at a heat dissipation rate Vk and restarts traversal at a traversal rate Vs. Figure 2H , 2IFigure 2J illustrates the process of fine-tuning the brute-force solution, calculating the possible times and selecting the shortest one. The diagram shows that the first cell is traversed using Vs. At this point, the first cell and its surrounding area may overheat. The device then switches to Vk and moves to the top of cell (0,3). Assuming a coordinate system with the bottom left as the origin, the device then traverses (0,3) and (0,2) again using Vs. Local overheating occurs again, so the device moves to the bottom of cell (3,0) using Vk, then switches back to Vs and traverses (3,0). Next, it switches back to Vk and moves to (3,3), then traverses (3,3) and (3,2) again using Vs. Finally, it moves to (2,0) and then traverses (2,0), (2,1), and (2,3) using Vs. This algorithm outputs this path. It can be understood that the device generates heat at Vs speed, requiring Vk to dissipate heat before continuing operation. This algorithm is an optimized solution that minimizes overheating. The treatment area is spatially meshed with a grid spacing equal to the diameter of a basic circle. The treatment area is then surrounded by a circle, which is then halved to generate the basic circle. Store the heat information for each grid and diffuse the heat to adjacent grids. Store the grid heat state information using triples. The thermal state of the region is estimated based on the thermal evaluation function. The temperature of each grid cell is checked at each time step. If the temperature exceeds a predetermined maximum threshold, the cost of path selection is increased to prevent paths from passing through this region. The thermal evaluation function is: f(n)=g(n)+Rem*Vs+λ×temperature(x,y) Where f(n) represents the heat assessment function, g(n) represents the cumulative cost from the starting point of the path to the current position, Rem represents the number of remaining uncounted grids, Vs represents the traversal speed, λ represents the temperature weighting coefficient, and temperature(x, y) is the temperature at the current position, where x and y represent the x and y coordinates of the current position.

[0038] The search difficulty of this algorithm increases with the number of grid cells. When the number of grid cells exceeds a certain limit, the algorithm fractals the region to be traversed, planning small local areas before incorporating them into a larger region for planning. Specifically, when multiple traversal surfaces exist, the algorithm simplifies these layers into a single grid, with each grid cell storing its heat information and traversal time. The traversal order of each layer is determined by the grid traversal order. Figure 2C As shown.

[0039] In some embodiments, the procedure further includes the step of further optimizing the treatment path according to the order of the abscissa or ordinate of the surgical operation points of the selected path from smallest to largest.

[0040] In some embodiments, the method further includes the step of: presupposing limiting conditions to exclude non-lesion organs along the treatment pathway.

[0041] like Figure 3 As shown, a surgical treatment path planning device 300 is used for complex lesion morphologies. Please refer to [the image / document / reference]. Figure 3 The surgical treatment path planning device 300 for complex lesion morphologies may include the following modules: a data acquisition module 302, a configuration module 304, a path calculation module 306, and a path determination module 308. Specifically, the data acquisition module 302 is used to acquire geometric feature data of the complex lesion morphology; the configuration module 304 is used to match a predetermined path traversal function based on the geometric feature data, wherein the path traversal function covers all surgical operation points of the complex lesion morphology; the path calculation module 306 is used to obtain the treatment path of the energy-focusing surgical operation point based on the path traversal function and a set speed or acceleration; and the path determination module 308 is used to generate a path set based on the treatment path and determine the treatment path.

[0042] An electronic device provided in this embodiment of the invention may include a processor and a memory. Optionally, the electronic device may further include a transceiver. The processor, memory, and transceiver may be connected via a communication bus. The memory stores computer-readable instructions, which, when executed by the processor, implement the steps of the surgical treatment path planning method for complex lesion morphologies described above.

[0043] In a specific implementation, as one example, the processor may include one or more CPUs.

[0044] In a specific implementation, as one example, the electronic device may also include multiple processors, each of which may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0045] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.

[0046] A transceiver is used to communicate with network devices or with terminal devices.

[0047] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0048] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the interface circuit of the electronic device. This embodiment of the invention does not specifically limit this.

[0049] It should be noted that the structure of the electronic device described above does not constitute a limitation on the electronic device. Actual electronic devices may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Furthermore, the technical effects of the electronic device can be referred to the technical effects of the above method embodiments, and will not be repeated here.

[0050] In an exemplary embodiment, the present invention also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the steps of the surgical treatment path planning method for complex lesion morphologies described above. For example, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0051] This invention also provides an electronic device, which includes: a processor; and a memory storing computer-readable instructions. When the computer-readable instructions are executed by the processor, the above-described surgical treatment path planning method for complex lesion morphologies is implemented.

[0052] This invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores program code, which can be called by a processor to execute the above-described surgical treatment path planning method for complex lesion morphology.

[0053] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0054] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0055] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers 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.

[0056] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0057] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0058] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0059] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for planning treatment pathways in energy-focused surgery for complex lesion morphologies, characterized in that, include: Obtain the geometric feature data of the complex morphology of the lesion; A predetermined path traversal function is matched based on the geometric feature data, wherein the path traversal function covers all surgical operation points of the lesion complex morphology; Based on the path traversal function and the set speed or acceleration, the treatment path of the energy focusing surgical operation point is obtained; A set of treatment paths is generated based on the treatment path, and the treatment path is determined.

2. The surgical treatment path planning method for complex lesion morphology according to claim 1, characterized in that, Geometric feature data includes: straight line feature data, rectangular feature data, cuboid feature data, irregular shape feature data, and three-dimensional feature data.

3. The surgical treatment path planning method for complex lesion morphology according to claim 2, characterized in that, The function of matching a predetermined path based on the geometric feature data includes: The function of matching the line feature data with a continuous line traversal is provided. The function is to match the rectangular feature data with a continuous rectangle traversal. The cuboid feature data is matched with a cuboid traversal function; The irregular graphic feature data is matched with an irregular graphic traversal function or an irregular graphic surface heat dissipation traversal function. The function of matching rotational bodies to the three-dimensional feature data is provided.

4. The surgical treatment path planning method for complex lesion morphology according to claim 3, characterized in that, Based on the path traversal function and the set speed or acceleration, the treatment path of the energy-focusing surgical operation point is obtained, including: When the path traversal function is a continuous straight line traversal function, it includes: obtaining the two endpoints of the straight line feature data segment and traversing the straight line feature data back and forth. When the path traversal function is a rectangular continuous traversal function, it includes: obtaining the centroid, width and height of the rectangular feature data, and traversing the rectangular feature data in a figure-eight pattern according to the distance from the rectangular feature data to the centroid; When the path traversal function is a cuboid continuous traversal function, it includes: obtaining the coordinates of the first and second reference points in the length direction of the cuboid, the coordinates of the third and fourth reference points in the width direction, and the coordinates of the diameter and center of the treatment ball relative to the cuboid, and traversing the first, second, third, and fourth reference points of the cuboid. When the path traversal function is an irregular shape traversal function, it includes: dividing the image echo intensity of the shape to be traversed into continuous regions with similar intensity, and inputting the distance to the center of the treatment ball, the direction of travel, and the number of reciprocations according to the tissue characteristics. After each region is set, the irregular shape is traversed in a serpentine manner. When the path traversal function is an irregular graphic surface heat dissipation traversal function, it includes: obtaining the coordinate values ​​of the treatment area that exceeds the heat threshold, and moving the treatment focus out of the treatment area at a predetermined heat dissipation rate; or, planning the treatment path using a path heat dissipation planning algorithm. When the path traversal function is a rotational traversal function, the method includes: obtaining the three-dimensional shape of the lesion; if the three-dimensional shape of the lesion can be covered by a rotational body, then selecting a lesion cross-section based on the three-dimensional shape, making the cross-section the rotational basic surface, and specifying the rotation axis position based on the rotational basic surface; performing tiling processing on the rotational basic surface, where the rotational basic surface is the shape to be tiled, and using regular hexagons as tiling shapes to tile it; the size of the regular hexagon comes from the predetermined focal area shape size guided by the image, measuring the diameter of the largest inscribed circle inside the focal area shape, reducing the diameter to 10% to 50%, and using the inscribed regular hexagon of that circle as the size of the regular hexagon; when tiling the rotational basic surface, using an annealing algorithm to minimize the required tiling shapes, and after tiling, determining the centroid position of each regular hexagon, so that all tiling shapes rotate around the rotation axis to cover the three-dimensional shape of the lesion.

5. The surgical treatment path planning method for complex lesion morphology according to claim 4, characterized in that, The path heat dissipation planning algorithm includes the following steps: Introducing heat diffusion: in, Represents temperature. Represents the thermal diffusivity. Represents the temperature gradient. represents the Laplace operator, which describes the rate of heat diffusion, and t represents time; The treatment area is spatially meshed with a grid spacing equal to the diameter of a basic circle. The treatment area is then surrounded by a circle, which is then halved to generate the basic circle. Store the heat information for each grid and diffuse the heat to adjacent grids. Store the grid heat state information using triples. The thermal state of the region is estimated based on the thermal evaluation function. The temperature of each grid cell is checked at each time step. If the temperature exceeds a predetermined maximum threshold, the cost of path selection is increased to prevent paths from passing through this region. The thermal evaluation function is: f(n)=g(n)+Rem*Vs+λ×temperature(x,y) Where f(n) represents the heat assessment function, g(n) represents the cumulative cost from the starting point of the path to the current position, Rem represents the number of remaining uncounted grids, Vs represents the traversal speed, λ represents the temperature weighting coefficient, and temperature(x, y) is the temperature at the current position, where x and y represent the x and y coordinates of the current position.

6. The surgical treatment path planning method for complex lesion morphology according to claim 1, characterized in that, It also includes the following steps: When the number of grid cells exceeds a predetermined threshold, a fractal nesting method is used for traversal, including: After planning in a local area, it is planned again as a whole to generate high λ solutions for large-area traversal and small-area 3*3 grids; When selecting a fever treatment parameter with low heat generation, the representative solution for λ value in a 3*3 grid is a serpentine path traversal and a straight path traversal, with the traversal speed and heat dissipation speed alternating.

7. The surgical treatment path planning method for complex lesion morphology according to any one of claims 1 to 6, characterized in that, It also includes the following steps: The treatment path is further optimized by ordering the horizontal or vertical coordinates of the surgical operation points along the selected path from smallest to largest.

8. A surgical treatment path planning device for complex lesion morphologies, characterized in that, include: The data acquisition module is used to acquire the geometric feature data of the complex morphology of the lesion; A configuration module is used to match a predetermined path traversal function based on the geometric feature data, wherein the path traversal function covers all surgical operation points of the lesion complex morphology; The path calculation module is used to obtain the treatment path of the energy focusing surgical operation point based on the path traversal function and the set speed or acceleration. The path determination module is used to generate a path set based on the treatment path and determine the treatment path.

9. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the surgical treatment path planning method for complex lesion morphology as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code, which can be called by a processor to execute the surgical treatment path planning method for complex lesion morphology as described in any one of claims 1 to 7.

Images