A cutting system for medical films

Abstract

The present invention relates to the technical field of medical film cutting, and specifically discloses a cutting system for medical films. The cutting system includes a cutting device, a medical image contour recognition module, an adaptive blade pressure real-time regulation module, and a cutting path planning module. The cutting device uses a blade to cut the medical film, reducing layer separation and cutting damage. The medical image contour recognition module generates a cutting path by scanning the film contour and combining medical image data. The adaptive blade pressure real-time regulation module dynamically adjusts the blade pressure to reduce cutting damage. The cutting path planning module is used to optimize the movement path of the cutting tool on the material to minimize the processing time. The present invention uses automated operation to replace traditional manual cutting, shortens the processing time, and overall realizes intelligent cutting with high efficiency, high precision, and low damage.

Description

Technical Field

[0001] The present invention relates to the technical field of medical film cutting, and more specifically, the present invention relates to a cutting system for medical films. Background Art

[0002] Medical films play a crucial role in medical imaging and radiotherapy. Traditional medical film cutting mainly relies on manual operations, usually using scissors or manual paper cutters for cutting. This method has many limitations in terms of accuracy, efficiency, and consistency. To solve these problems, numerical control cutting technology has been introduced into the processing of medical films.

[0003] Existing published document 1 (Research and Application of Electric X-ray Film Slicer, 2007) proposes an electric slicer, which includes a chassis, a scale panel, a film pressing plate, a bow-shaped clamping plate, and a saw blade. The usage method of this slicer is as follows: Connect the power supply, turn on the motor switch to make the saw blade run; then adjust the sliding bow-shaped clamping plate to select the cutting size; then place the film flat with both hands on the workbench and push it forward along the inner edge of the clamping plate for cutting; finally, turn off the motor switch after cutting. However, this electric slicer has the problem of low processing efficiency. Existing published document 2 (Design and Implementation of a New Type of Historical Aerial Film Digitization Device Based on Industrial Cameras, 2021) proposes a high-precision professional aerial film digitization device. This device selects a PhaseOne iXM-RS150F camera, is equipped with a PhaseOne RS–110 lens, and calculates the optimal installation height of the camera according to the formula. The workbench surface includes a base, a reel and a rotating device, a film pressing mechanism, and a light homogenizing table. The base determines the photographing area, the reel manually winds the film, the film pressing device uses two transparent flat glasses, the light source uses a cold cathode fluorescent lamp, and the non-uniformity of the light intensity of the light homogenizing table is less than 15%. The device is temporarily manually wound, and manual participation is required in the film loading, transmission and other links. However, the automation degree of this device is not high, which increases the labor cost and the complexity of operation, and may also affect the digitization efficiency and quality due to human factors.

[0004] Therefore, there is an urgent need for a cutting system for medical films that can improve processing efficiency and achieve automation. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a cutting system for medical films, which cuts the medical film through a cutting device, combines image recognition with medical imaging data to generate a cutting path, and reduces cutting damage by adjusting the blade pressure in real time, optimizes the cutting path based on the simulated annealing algorithm, and improves the processing efficiency to solve the problems mentioned in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A cutting system for medical films, comprising a cutting device, a medical image contour recognition module, an adaptive blade pressure real-time regulation module, and a cutting path planning module; the medical image contour recognition module generates a cutting path by scanning the film contour; the adaptive blade pressure real-time regulation module dynamically adjusts the blade pressure; the cutting path planning module is used to optimize the movement path of the tool on the material to improve the processing efficiency; the specific steps for the cutting path planning module to optimize the cutting path of the tool are as follows:

[0008] Step Z1, assume there are mandatory cutting points to pass through, and the th cutting point has two-dimensional coordinates: , , is the abscissa of the cutting point, is the ordinate of the cutting point, is the set of cutting points, is the first cutting point, is the second cutting point, is the th cutting point, and the purpose is to find a path with the shortest length , is the current path;

[0009] Step Z2, define the path state based on the simulated annealing algorithm as the arrangement of cutting points: , and define the energy function , and the energy is the path length: ;

[0010] Step Z3, define the energy difference of path change: , is the newly generated solution by iteration. If , then the new path is better, and accept the new solution: ; if , then accept the inferior solution with a probability to avoid local optimality. Among them, is the current temperature, is the probability decay function, and the temperature gradually decreases after each iteration, controlling the search range to shrink. When any of the following conditions is met, terminate the iteration: 1. The temperature drops to the threshold, that is , is the preset minimum temperature; 2. The number of iterations reaches the upper limit, that is , is the preset maximum number of iterations.

[0011] As a further solution of the present invention, the simulated annealing algorithm controls the search process through temperature, and the initial temperature affects the search range of the algorithm: , where is the temperature coefficient, is the initial random path length, is the standard deviation of the initial path length. In order to ensure that the initial temperature is high enough so that the algorithm can fully search different solution spaces, the value of the initial temperature is .

[0012] As a further solution of the present invention, the temperature gradually decreases after each iteration to control the narrowing of the search range, and the attenuation method is logarithmic annealing: , where is the current iteration number, is the temperature for the next iteration of the simulated annealing algorithm, is the cooling rate coefficient of logarithmic annealing.

[0013] As a further solution of the present invention, the cutting device uses a blade to cut medical film to reduce layer separation and cutting damage, including the following specific contents: The cutting device includes a working area, a scanner, a touch screen LCD operation panel, a USB interface and a blade. The maximum cutting size of the working area is , the maximum scanning area is , and the minimum cuttable size is . The resolution of the scanner is 300 DPI. The touch screen LCD operation panel is used to adjust the cutting pattern and set cutting parameters. The USB interface supports importing and exporting cutting instructions, and users can upload patterns by connecting external devices through USB. The cutting device adopts a design with a replaceable blade to adapt to the cutting needs of different types of materials, and the blade adopts a knob-type adjustment design. The cutting device uses a sticky working pad to fix the material, and the function of the working pad is to ensure that the material does not move or warp during the cutting process, thereby ensuring the cutting accuracy. The adhesive layer of the working pad can effectively adsorb the material firmly to prevent deviation during the cutting process due to the feeding of the machine or the movement of the blade. The cutting device is equipped with two different types of blades, namely a standard blade and a deep cutting blade. The extended length of the standard blade is 1 mm, which is suitable for lightweight materials; the extended length of the deep cutting blade is 1.5 mm, which is suitable for thicker or harder materials.

[0014] As a further solution of the present invention, the medical image contour recognition module generates a cutting path by scanning the film contour and combining medical image data, including the following specific contents: The medical image contour recognition module includes an image acquisition unit, a light source system, an image processing unit, and a positioning control unit. The image acquisition unit is responsible for obtaining the image information of the film and uses a high-resolution camera. The light source system is used to provide uniform and stable illumination for the image acquisition unit.

[0015] The image processing unit processes and analyzes the acquired image, and extracts key information such as the edges and feature points of the film. The image processing unit preprocesses the acquired image, and the preprocessing includes grayscale conversion, noise reduction, and smoothing processing to improve the image quality and reduce the influence of noise on subsequent processing. Then, the image processing unit uses the Sobel operator edge detection algorithm to perform edge detection on the image and extract the edge information of the film. The Sobel operator realizes edge detection by calculating the gradient of pixel points in the image and highlighting the edge part. The Sobel operator identifies points with significant changes as feature points by analyzing the local structure of the image.

[0016] The positioning control unit receives the image feature points extracted by the image processing unit and calculates the translation and rotation parameters of the film relative to the coordinate system of the cutting device. The coordinates of the th point on the film in the image coordinate system are: , being the abscissa of this point in the image coordinate system, being the ordinate of this point in the image coordinate system, then the coordinates of this point in the coordinate system of the cutting device are: , and after expansion, we get: , and by calculation, we get: , where is the homogeneous transformation matrix, is the rotation matrix, is the translation vector, is the abscissa of this point in the coordinate system of the cutting device, is the ordinate of this point in the coordinate system of the cutting device, is the translation vector of the film in the x-axis direction, is the translation vector of the film in the y-axis direction, is the rotation angle.

[0017] Using the feature points extracted by the image processing unit, calculate , and . Select at least two matching points and , and calculate the rotation angle : The translation amount is solved by the following formula: , , where is the average value of all matching points in the x-axis coordinate system of the cutting device, is the average value of all matching points in the y-axis coordinate system of the cutting device, is the average value of all matching points on the x-axis in the image coordinate system, is the average value of all matching points on the y-axis in the image coordinate system.

[0018] As a further solution of the present invention, the adaptive blade pressure real-time regulation module dynamically adjusts the blade pressure to reduce cutting damage, including the following specific content: The adaptive blade pressure real-time regulation module includes a sensor unit and a numerical control system. The sensor unit monitors the parameters during the machining process in real time. The parameters include tool position, tool feed speed, tool cutting depth, and tool cutting force, and feeds the parameters back to the numerical control system. The numerical control system obtains the parameter information during the machining process in real time, so that the tool pressure can be dynamically adjusted according to the real-time error to ensure the stability and high precision of the machining. During the cutting process, the tool pressure is a comprehensive parameter, which is affected by factors such as tool position error, feed speed error, cutting depth error, and cutting force error. By establishing an adaptive error compensation tool pressure control model, the tool pressure can be dynamically adjusted with the change of the error. The specific steps are as follows:

[0019] Step S1, the position of the target tool is: , is the x-axis coordinate of the target tool, is the y-axis coordinate of the target tool, is the z-axis coordinate of the target tool; the position of the actual tool is: , is the x-axis coordinate of the actual tool, the y-axis coordinate of the actual tool, is the z-axis coordinate of the actual tool; the error calculation formula for the tool position is: , , , is the error of the tool position in the x-axis direction, is the error of the tool position in the y-axis direction, is the error of the tool position in the z-axis direction; the feed speed of the target tool is , the feed speed of the actual tool is , then the feed speed error of the tool is: ; the target cutting depth is , the actual cutting depth is , the cutting depth error is: ; the target cutting force is , the actual cutting force is , the cutting force error is: .

[0020] Step S2, establish an adaptive error compensation tool pressure control model, and the calculation formula is: , is the tool pressure at the current moment, is the tool pressure at the next moment. When the tool position deviation increases, that is, increases, the numerical control system increases the tool pressure; when the feed speed is lower than the target value, that is, , the numerical control system increases the tool pressure to increase the cutting speed. On the contrary, it reduces the tool pressure to prevent overload; when the cutting depth is insufficient, that is, , the numerical control system increases the tool pressure, and on the contrary, reduces the tool pressure to prevent tool damage; when the cutting force is insufficient, that is, , the numerical control system increases the tool pressure to improve the cutting efficiency, and on the contrary, reduces the tool pressure to reduce the tool load.

[0021] As a further solution of the present invention, the cutting path planning module is used to optimize the movement path of the tool on the material to minimize the processing time, including the following specific contents: During the numerical control cutting of medical films, optimizing the tool cutting path can not only improve the processing efficiency, but also reduce material waste and ensure the cutting quality.

[0022] The technical effects and advantages of a cutting system for medical films according to the present invention: By integrating a cutting device, a medical image contour recognition module, a dynamic pressure adjustment module, and a cutting path planning module, the present invention improves the cutting efficiency and automation level of medical films; the cutting system combines high-resolution image recognition with medical image data to generate a cutting path; the dynamic pressure adjustment module adjusts the blade pressure in real time to reduce cutting damage and adapt to different material thicknesses; the cutting path planning module significantly shortens the processing time and reduces material waste based on the path optimization of the simulated annealing algorithm. The present invention uses automated operation to replace traditional manual cutting, effectively reducing labor costs and human errors. At the same time, it supports multiple blade types and sticky fixing designs, enhancing the adaptability to different medical films. Overall, it realizes intelligent cutting with high efficiency, high precision, and low damage, and solves the problems of insufficient automation, low efficiency, and unstable quality in the prior art. Description of the Drawings

[0023] Figure 1Structural diagram of a cutting system for a medical film according to the present invention.

[0024] Figure 2 Structural diagram of an electric slicing machine in the prior art.

[0025] Figure 3 Optimization curve graph of the cutting path according to the present invention.

[0026] Figure 4 Temperature decay curve graph based on the simulated annealing algorithm according to the present invention. Detailed implementation manners

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] Embodiment 1

[0029] Refer to Figure 1 In the shown structural diagram, an embodiment of the present invention provides a cutting system for a medical film, including: a cutting device, a medical image contour recognition module, an adaptive blade pressure real-time regulation module, and a cutting path planning module. The cutting device uses a blade to cut the medical film to reduce layer separation and cutting damage. The medical image contour recognition module generates a cutting path by scanning the film contour and combining medical image data. The adaptive blade pressure real-time regulation module dynamically adjusts the blade pressure to reduce cutting damage. The cutting path planning module is used to optimize the movement path of the tool on the material to minimize the processing time.

[0030] In this embodiment, refer to Figure 2 the shown structural diagram, which is an electric slicing machine in the prior art. The slicing machine includes a chassis, a scale panel, a film pressing plate, a bow-shaped clamping plate, and a saw blade. The usage method of the slicing machine is as follows: Connect the power supply, turn on the motor switch to make the saw blade run; then adjust the sliding bow-shaped clamping plate to select the cutting size of the film; then place the film flat on the workbench with both hands and push it forward along the inner edge of the clamping plate for cutting; finally, turn off the motor switch after cutting is completed. However, this electric slicing machine has the problem of low processing efficiency.

[0031] Furthermore, the cutting device uses a blade to cut the medical film to reduce layer separation and cutting damage, including: The cutting device includes a working area, a scanner, a touch screen LCD operation panel, a USB interface, and a blade. The maximum cutting size of the working area is , the maximum scanning area is , the minimum cuttable size is The resolution of the scanner is 300 DPI. The touchscreen LCD operation panel is used to adjust the cutting pattern and set the cutting parameters. The USB interface supports the import and export of cutting instructions, and users can upload patterns by connecting external devices through USB. The cutting device adopts a design with replaceable blades to meet the cutting requirements of different types of materials. The blade adopts a knob-type adjustment design, and users can select the appropriate blade length according to the material thickness. The cutting device uses a sticky working pad to fix the material. The function of the working pad is to ensure that the material does not move or warp during the cutting process, thus ensuring the cutting accuracy. The adhesive layer of the working pad can effectively adsorb the material firmly and prevent deviation caused by the feeding of the machine or the movement of the blade during the cutting process. The cutting device is equipped with two different types of blades, namely standard blades and deep cutting blades. The extended length of the standard blade is 1 mm, which is suitable for lightweight materials; the extended length of the deep cutting blade is 1.5 mm, which is suitable for thicker or harder materials.

[0032] Further, the medical image contour recognition module generates a cutting path by scanning the film contour and combining medical image data, including: The medical image contour recognition module includes an image acquisition unit, a light source system, an image processing unit, and a positioning control unit. The image acquisition unit is responsible for obtaining the image information of the film and uses a high-resolution camera.

[0033] The light source system is used to provide uniform and stable illumination for the image acquisition unit to ensure the acquisition of high-quality images, thereby improving the accuracy and reliability of image processing.

[0034] The image processing unit processes and analyzes the acquired image, extracts key information such as the edges and feature points of the film. The image processing unit preprocesses the acquired image, and the preprocessing includes grayscale conversion, noise reduction, and smoothing processing to improve the image quality and reduce the influence of noise on subsequent processing. Then, the image processing unit uses the Sobel operator edge detection algorithm to perform edge detection on the image and extract the edge information of the film. The Sobel operator detects edges by calculating the gradients of pixel points in the image and highlighting the edge part, thereby realizing edge detection. The Sobel operator identifies points with significant changes as feature points by analyzing the local structure of the image.

[0035] The positioning control unit receives the image feature points extracted by the image processing unit and calculates the translation and rotation parameters of the film relative to the coordinate system of the cutting device. The th point on the film has coordinates in the image coordinate system as: , is the abscissa of this point in the image coordinate system, is the ordinate of this point in the image coordinate system, and the coordinates of this point in the cutting device coordinate system are: , after expansion, we get: , and by calculation, we get: , where is the homogeneous transformation matrix, is the rotation matrix, is the translation vector, is the abscissa of this point in the cutting device coordinate system, is the ordinate of this point in the cutting device coordinate system, is the translation vector of the film in the x-axis direction, is the translation vector of the film in the y-axis direction, is the rotation angle.

[0036] Using the feature points extracted by the image processing unit, calculate , and . Select at least two matching points and , and calculate the rotation angle through the following formula: . The translation amount is solved through the following formula: , , where is the average value of all matching points in the cutting device x-axis coordinate system, is the average value of all matching points in the cutting device y-axis coordinate system, is the average value of all matching points on the x-axis in the image coordinate system, is the average value of all matching points on the y-axis in the image coordinate system.

[0037] Furthermore, the adaptive blade pressure real-time regulation module dynamically adjusts the blade pressure to reduce cutting damage, including: The adaptive blade pressure real-time regulation module includes a sensor unit and a numerical control system. The sensor unit monitors the parameters during the machining process in real time. The parameters include tool position, tool feed speed, tool cutting depth, and tool cutting force, and feeds the parameters back to the numerical control system. The numerical control system obtains the parameter information during the machining process in real time, so that the tool pressure can be dynamically adjusted according to the real-time error to ensure the stability and high precision of the machining. During the cutting process, the tool pressure is a comprehensive parameter, which is affected by factors such as tool position error, feed speed error, cutting depth error, and cutting force error. By establishing an adaptive error compensation tool pressure control model, the tool pressure can be dynamically adjusted with the change of the error. The specific steps are as follows:

[0038] Step S1, the position of the target tool is: , is the x-axis coordinate of the target tool, is the y-axis coordinate of the target tool, is the z-axis coordinate of the target tool; The position of the actual tool is: , is the x-axis coordinate of the actual tool, the y-axis coordinate of the actual tool, is the z-axis coordinate of the actual tool; The error calculation formula for the tool position is: , , , is the error of the tool position in the x-axis direction, is the error of the tool position in the y-axis direction, is the error of the tool position in the z-axis direction; The feed rate of the target tool is , the feed rate of the actual tool is , then the feed rate error is: ; The target cutting depth is , the actual cutting depth is , the cutting depth error is: ; The target cutting force is , the actual cutting force is , the cutting force error is: .

[0039] Step S2, establish an adaptive error compensation tool pressure control model, and the calculation formula is: , is the current tool pressure at time, is the tool pressure at the next moment. When the tool position deviation increases, that is increases, the numerical control system increases the tool pressure; When the feed rate is lower than the target value, that is , the numerical control system increases the tool pressure to increase the cutting speed. On the contrary, it reduces the tool pressure to prevent overload; When the cutting depth is insufficient, that is , the numerical control system increases the tool pressure. On the contrary, it reduces the tool pressure to prevent tool damage; When the cutting force is insufficient, that is , the numerical control system increases the tool pressure to improve the cutting efficiency. On the contrary, it reduces the tool pressure to reduce the tool load.

[0040] Further, the cutting path planning module is used to optimize the movement path of the tool on the material to minimize the processing time, including: during the numerical control cutting of medical films, optimizing the cutting path of the tool can not only improve the processing efficiency, but also reduce material waste and ensure the cutting quality. Refer to Figure 3 the curve graph shown, and the specific steps for optimizing the cutting path of the tool are as follows:

[0041] Step Z1, during the cutting process, assuming there are mandatory cutting points to pass through, the th cutting point has two-dimensional coordinates: , , is the abscissa of the cutting point, is the ordinate of the cutting point, is the set of cutting points, is the first cutting point, is the second cutting point, is the th cutting point; the purpose is to find an optimal path, that is: make the tool start from the starting point, pass through all the cutting points and then return to the starting point, and the total length of the path is the shortest, where is the current path, expressed by the following objective function: .

[0042] Step Z2, define the path state based on the simulated annealing algorithm as the arrangement of cutting points: . Define the energy function , and the energy is the path length: , where the lower the energy, the more optimal the path. The simulated annealing algorithm controls the search process through temperature. The initial temperature affects the search range of the algorithm: , where is the temperature coefficient, is the initial random path length, is the standard deviation of the initial path length. To ensure that the initial temperature is high enough to enable the algorithm to fully search different solution spaces, the value of the initial temperature is .

[0043] Step Z3, in each iteration, the ways to generate a new solution include: 1. Random exchange method, exchange two points in the path; 2. Local inversion method, select a section of the path and invert it; 3. Insertion method, move a point to another position in the path. Define the energy difference of the path change: , if , if the new path is better, then unconditionally accept the new solution: ; if , then with probability accept the inferior solution to avoid local optimality, where is the current temperature, is the probability decay function. Refer to the curve graph shown in Figure 4 . The temperature gradually decreases after each iteration, controlling the search scope to narrow, and the decay method is logarithmic annealing: , where is the current iteration number, is the temperature for the next iteration of the simulated annealing algorithm, is the cooling rate coefficient of logarithmic annealing. Terminate the iteration when any of the following conditions is met: 1. The temperature drops to the threshold, i.e., , is the preset minimum temperature; 2. The iteration number reaches the upper limit, i.e., , is the preset maximum iteration number. The following table is the experimental data of the cutting path optimization algorithm:

[0044] Table 1 Experimental data of the cutting path optimization of medical film based on the simulated annealing algorithm

[0045]

[0046] During the experiment, the average length range of the initial random path is in [2450, 2600]. Using the initial temperature (T0 = 1500) and the low temperature decay rate (0.97), in experiment No. 11, the optimal path is 1739.6, with the best effect, shortening by 28.9% - 33.1% compared to the random path. The experimental results show that the annealing process avoids local optimal solutions and finally obtains a better path.

[0047] The present invention integrates a cutting device, a medical image contour recognition module, a dynamic pressure regulation module, and a cutting path planning module, improving the cutting efficiency and automation level of medical film; the cutting system combines high-resolution image recognition with medical image data to generate a cutting path; the dynamic pressure regulation module adjusts the blade pressure in real time, reducing cutting damage and adapting to different material thicknesses; the cutting path planning module significantly shortens the processing time and reduces material waste based on the path optimization of the simulated annealing algorithm. The present invention uses automated operation to replace traditional manual cutting, effectively reducing labor costs and human errors. At the same time, it supports multiple blade types and sticky fixing designs, enhancing the adaptability to different medical films, and overall achieving intelligent cutting with high efficiency, high precision, and low damage, solving the problems of insufficient automation, low efficiency, and unstable quality in the prior art.

[0048] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0049] Finally: The above description is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A medical film cutting system, characterized in that: It includes a cutting device, a medical image contour recognition module, an adaptive blade pressure real-time control module and a cutting path planning module; the medical image contour recognition module generates a cutting path by scanning the film contour; the adaptive blade pressure real-time control module dynamically adjusts the blade pressure; the cutting path planning module is used to optimize the movement path of the tool on the material to improve the processing efficiency; the specific steps of optimizing the tool cutting path by the cutting path planning module are as follows: Step Z1, assuming that The cutting point that must be passed, Cutting points With 2D coordinates: , , is the horizontal coordinate of the cutting point, is the ordinate of the cutting point, is the set of cutting points, is the first cutting point, is the second cutting point, For the The purpose is to find a path with the shortest length. , is the current path; Step Z2, define the path state based on the simulated annealing algorithm Arrangement of cutting points: , define the energy function , energy is the path length: ; Step Z3, define the energy difference of path change: , is the new solution generated by iteration, if , then the new path is better, accept the new solution: the probability is 1; if , then the probability is , accept inferior solutions to avoid local optimality, where is the current temperature, is the probability decay function, temperature After each iteration, the temperature gradually decreases, and the control search range is narrowed. When any of the following conditions is met, the iteration is terminated:

1. The temperature drops to the threshold, that is, , is the preset minimum temperature; 2. The number of iterations reaches the upper limit, that is , is the preset maximum number of iterations; The adaptive blade pressure real-time control module includes a sensor unit and a numerical control system; the sensor unit monitors the tool position, feed speed, cutting depth and cutting force in real time; the numerical control system dynamically adjusts the tool pressure based on the real-time error; the calculation formula for dynamically adjusting the tool pressure is: , For the current Tool pressure at all times; is the tool pressure at the next moment; is the error of the tool position in the x-axis direction, is the error of the tool position in the y-axis direction, is the error of the tool position in the z-axis direction; is the tool feed speed error, satisfying , is the feed rate of the target tool, is the actual tool feed speed; is the cutting depth error, satisfying , is the target cutting depth, is the actual cutting depth; is the cutting force error, satisfying , is the target cutting force, is the actual cutting force.

2. A medical film cutting system according to claim 1, characterized in that ,The simulated annealing algorithm controls the search process by temperature, the initial temperature Affects the algorithm's search scope: ,in, is the temperature coefficient, is the initial random path length, is the standard deviation of the initial path length. In order to ensure that the initial temperature is high enough so that the algorithm can fully search different solution spaces, the initial temperature The value of .

3. A medical film cutting system according to claim 1, characterized in that , the temperature It gradually decreases after each iteration, controlling the search range to shrink, and the decay method is logarithmic annealing: ,in, is the current iteration number, is the temperature of the next iteration of the simulated annealing algorithm, is the cooling rate coefficient of logarithmic annealing.

4. A medical film cutting system according to claim 1, characterized in that: The positioning control unit in the medical image contour recognition module receives the image feature points extracted by the image processing unit, calculates the translation and rotation parameters of the film relative to the coordinate system of the cutting device, and the first Points The coordinates in the image coordinate system are: , is the horizontal coordinate of the point in the image coordinate system, is the ordinate of the point in the image coordinate system, then the coordinate of the point in the cutting device coordinate system is: , after expansion: , calculated: ,in, is the homogeneous transformation matrix, is the rotation matrix, is the translation vector, is the horizontal coordinate of the point in the cutting device coordinate system, is the ordinate of the point in the cutting device coordinate system, is the translation vector of the film in the x-axis direction, is the translation vector of the film in the y-axis direction, is the rotation angle.

5. A medical film cutting system according to claim 4, characterized in that: Using the feature points extracted by the image processing unit, calculate , and , select at least two matching points and , the rotation angle is calculated by the following formula : , the translation amount is solved by the following formula: , ,in, is the average value of all matching points in the x-axis coordinate system of the cutting device, is the average value of all matching points in the y-axis coordinate system of the cutting device, is the average value of all matching points on the x-axis in the image coordinate system, It is the average value of all matching points on the y-axis in the image coordinate system.

6. A medical film cutting system according to claim 1, characterized in that: The cutting device includes a working area, a scanner, a touch screen LCD operation panel, a USB interface and a blade; the maximum cutting size of the working area is 29.8cm×29.8cm, the maximum scanning area is 30.5cm×30.5cm, and the minimum cuttable size is 5mm×5mm; the resolution of the scanner is 300DPI; the touch screen LCD operation panel is used to set cutting parameters; the USB interface supports importing and exporting cutting instructions; the blade includes a standard blade and a deep cutting blade, the extension length of the standard blade is 1mm, and the extension length of the deep cutting blade is 1.5mm.

7. A medical film cutting system according to claim 1, characterized in that: The medical image contour recognition module includes an image acquisition unit, a light source system, an image processing unit and a positioning control unit; the image acquisition unit uses a camera to obtain a film image; the light source system provides uniform and stable lighting; the image processing unit performs grayscale, noise reduction and smoothing on the acquired image, and uses the Sobel operator edge detection algorithm to extract the film edge and feature points; the positioning control unit calculates the coordinates of the film in the cutting device coordinate system through a homogeneous transformation matrix.

Images