A cutting path planning method and system for ultrasonic knife equipment

Abstract

The present invention discloses a cutting path planning method and system for an ultrasonic scalpel device, and relates to the field of medical technology. A cutting path planning system for an ultrasonic scalpel device includes: a cutting path planning module and a cutting path calibration module. The present invention performs image recognition by inputting a cutting image annotation model to obtain a cutting object feature map, and utilizes an improved spatial trajectory planning algorithm and image registration algorithm to efficiently predict and optimize the initial cutting path and ensure the accuracy of the cutting path; by registering the simulated cutting object image and analyzing it based on a cutting error judgment model, potential cutting errors can be identified before surgery, and the cutting path can be adjusted in advance, thereby reducing the impact of the error. The initial cutting path is updated using the error judgment result, effectively preventing path deviations caused by errors.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a cutting path planning method and system for ultrasonic scalpel equipment. Background Art

[0002] Currently, ultrasonic scalpel devices are mainly used for precise cutting and coagulation of soft tissues during surgical operations to reduce bleeding and thermal damage. The importance of ultrasonic scalpel device path planning lies in ensuring the accuracy, safety and efficiency of the operation. Accurate path planning can ensure that the ultrasonic scalpel cuts along the predetermined path, thereby reducing human errors and improving the accuracy of the operation. However, in actual operations, especially when long-term surgery or treatment is involved, the patient may experience uncontrollable displacement. This displacement may be caused by the patient's own physiological activities, such as breathing, heartbeat, changes in body position, muscle relaxation or tension, etc., which may cause the ultrasonic scalpel to deviate from the predetermined cutting path, which will seriously affect the accuracy of the predetermined path.

[0003] Therefore, it is necessary to design a cutting path planning method for ultrasonic scalpel equipment that takes into account the patient's displacement factor. This method simulates the possible displacement of the patient before the operation, predicts and adjusts the planned path, so that it can flexibly respond to the patient's displacement during the operation, ensure the accuracy of the auxiliary cutting path, and thus improve the overall effect of the operation. Summary of the Invention

[0004] The present invention aims to provide a cutting path planning method and system for an ultrasonic scalpel device, which can flexibly respond to patient displacement and ensure the accuracy of the auxiliary cutting path.

[0005] A cutting path planning method for an ultrasonic scalpel device comprises the following steps:

[0006] Acquire an image of the object to be cut; the image of the object to be cut includes a marker ball of the object to be cut; input the image of the object to be cut into the cutting image annotation model for image recognition to obtain a cutting object feature map P1; the cutting object feature map P1 is annotated with cutting feature points and marker ball feature points O1';

[0007] The cutting object feature map P1 is input into the cutting path planning model for calculation to obtain the initial cutting path; the cutting path planning model is established based on the improved spatial trajectory planning algorithm;

[0008] A cutting digital twin model is established based on the object to be cut; based on the cutting digital twin model, M-1 simulated cutting object images and corresponding simulated physiological parameters of the object to be cut are obtained; all simulated cutting object images are input into the cutting image annotation model for image recognition, and a cutting object feature map P is obtained. m and the marker ball feature point O m', m=2, ..., M; using the improved image registration algorithm to cut the object feature map P m and the cut object feature map P m-1 Perform image registration and obtain the image error judgment result T m ; The image error judgment result T m The corresponding simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result J m ; Based on the cutting error judgment result J m The initial cutting path is updated to obtain an updated cutting path; and auxiliary path planning is performed on the object to be cut based on the updated cutting path.

[0009] As a preferred technical solution of the present invention, the cut image annotation model includes an image preprocessing layer, an improved convolution layer, an improved attention feature mechanism layer and an improved residual convolution layer;

[0010] The image preprocessing layer is used to perform image preprocessing operations on the image of the object to be cut, so as to obtain a preprocessed image of the object to be cut;

[0011] The improved convolution layer is used to perform a convolution operation on the preprocessed image of the object to be cut to obtain a convolution feature map of the object to be cut;

[0012] In the improved convolution layer, the number of layers of the convolution feature map of the object to be cut is set to N, n=1, 2, ..., N;

[0013] Using formula R n =R n-1 + (a-1) * (l-1) to calculate the n-th layer receptive field R n , a is the size of the convolution kernel in the convolution feature map of the object to be cut in the nth layer, l is the expansion rate set in the convolution feature map of the object to be cut in the nth layer; all receptive fields R n Perform convolution calculation to obtain the convolution feature map of the object to be cut;

[0014] The improved attention feature mechanism layer is used to extract features from the convolution feature map of the object to be cut using the improved attention feature mechanism to obtain the initial feature map of the object to be cut;

[0015] In the improved attention feature mechanism layer, the output initial feature map of the object to be cut is set to include B layers, b=1, 2, ..., B;

[0016] Using the formula H=conv 1*1*1 (concat(V d，b *F b , V s，b *F b )+concat(Z d，b *Fb , Z s，b *F b ) + F b ) Calculate the convolution feature map of the object to be cut to obtain the feature map of the object to be cut;

[0017] Among them, V d，b Represents the channel attention vector of the initial feature map of the object to be cut in layer b, V d，b =Φ(conv 1*1*1 (conv 1*1*1 (Q(F b-1 ))));V s，b Represents the estimated value of the spatial attention vector of the initial feature map of the object to be cut in layer b, V s，b =Φ(conv 1*1*1 (conv 2*2*2 (conv 1*1*1 (F b-1 ))));Z d，b Represents the channel attention vector of the high-level feature channel after filtering the initial feature map of the object to be cut in layer b, Z d，b =Φ(conv 1*1*1 (conv 1*1*1 (Q(F b+1 ))));Z s，b Represents the attention mechanism vector contained in the feature space after segmentation of the initial feature map of the object to be cut in layer b, Z s，b =Φ(conv 1*1*1 (conv 2*2*2 (conv 1*1*1 (F b+1 ))));conv( ) represents the convolution operation, concat ( ) represents the feature channel fusion operation, F b represents the low-dimensional feature map of layer b, Q( ) represents the global average pooling operation; Φ( ) represents the sigmoid activation operation;

[0018] The improved residual convolution layer is used to further extract features from the initial feature map of the object to be cut, and obtain the feature map P1 of the cut object;

[0019] In the improved residual convolution layer, the formula P1=σ(W 1*1 (W 1*1 (K(U)))) performs fusion convolution on the initial feature map of the object to be cut to obtain the feature map of the cut object P1; where σ represents the activation function, K(U) represents the value of the average pooling of the initial feature map of the object to be cut, W represents the convolution kernel, and W1*1 Represents a 1*1 convolution operation, and U represents the initial feature map of the object to be cut.

[0020] As a preferred technical solution of the present invention, the cutting path planning model includes a feature point recognition layer and a path planning layer;

[0021] The feature point recognition layer is used to identify feature points based on the cutting object feature map P1 to obtain a cutting feature point set;

[0022] The path planning layer is used to perform path planning based on the cutting feature point set and the improved spatial trajectory planning algorithm to obtain the initial cutting path.

[0023] As a preferred technical solution of the present invention, the specific steps of performing path planning in the path planning layer include:

[0024] According to the cutting feature point set and the spatial trajectory planning algorithm, I groups of cutting path individuals Y to be optimized are randomly generated. i , i=1, 2, ..., I; I groups of cutting path individuals Y to be optimized i Combine and obtain the optimized cutting path iterative population; set the inertia weight X1, inertia weight X2 and the current iteration number g, g = 1, 2, ..., G, G is the maximum iteration number;

[0025] For the individual Y of the optimized cutting path in the iterative population of optimized cutting paths i Perform simulated ultrasonic knife path cutting calculation to obtain simulated cutting time , simulate cutting time The reciprocal of is the individual Y of the cutting path to be optimized i Fitness ;

[0026] When performing population iteration, use the formula:

[0027] and Calculate and obtain the inertia weight X1 and inertia weight X2. The inertia weight X1 represents the individual Y of the cutting path to be optimized in the iterative population of the optimized cutting path. i The weight of approaching the current individual extreme point, the inertia weight X2 represents the individual Y of the cutting path to be optimized in the iterative population of the optimized cutting path i The weight of approaching the global individual extreme point; where α is the preset calculation parameter, β is the standard deviation of the Gaussian distribution, g is the current number of iterations; e is a mathematical constant; according to the inertia weight X1 and the inertia weight X2, the crossover and mutation operations are performed on the optimized cutting path iterative population;

[0028] When the current iteration number g=G, the output fitness is the individual Y of the cutting path to be optimized corresponding to the maximum i, which is the optimal cutting path individual to be optimized; the path in the optimal cutting path individual to be optimized is used as the initial cutting path.

[0029] As a preferred technical solution of the present invention, the improved image registration algorithm is used to register the cutting object feature map P m and the cut object feature map P m-1 Perform image registration. The specific steps include:

[0030] Calculate the cutting object feature map P m and the cut object feature map P m-1 The similarity error of is obtained to obtain the overall similarity error of image registration;

[0031] Mark the ball feature point O m ' and mark ball feature point O m-1 'Construct three-dimensional coordinate calibration and obtain the three-dimensional calibration coordinate ZB (P m ') and three-dimensional calibration coordinates ZB (P m-1 ');

[0032] Calculate the three-dimensional calibration coordinates ZB (P m ') and three-dimensional calibration coordinates ZB (P m-1 '), and obtain the image registration reprojection error and image registration benchmark error;

[0033] The image registration reprojection error and the image registration benchmark error are subtracted from the overall similarity error of the image registration to obtain the image error judgment result T m .

[0034] As a preferred technical solution of the present invention, the cutting error judgment model includes a physiological parameter evaluation layer, an image error feature extraction layer and an error factor fusion layer;

[0035] The physiological parameter evaluation layer is used to extract the characteristics of the simulated physiological parameters of the object to be cut, and obtain the characteristics of the simulated physiological parameters of the object to be cut;

[0036] The image error feature extraction layer is used to judge the image error result T m Perform feature extraction to obtain the image error judgment result feature T m ';

[0037] The error factor fusion layer is used to simulate the physiological parameter characteristics of the object to be cut and the image error judgment result characteristics T m 'Carry out error factor fusion calculation to obtain cutting error judgment result J m .

[0038] A cutting path planning system for an ultrasonic scalpel device, comprising:

[0039] The cutting path planning module includes a planning preparation unit and a path planning unit; the planning preparation unit is used to obtain an image of the object to be cut; the image of the object to be cut includes a marker ball of the object to be cut; the image of the object to be cut is input into the cutting image annotation model for image recognition to obtain a cutting object feature map P1; the cutting object feature map P1 is annotated with cutting feature points and marker ball feature points O1'; the path planning unit is used to input the cutting object feature map P1 into the cutting path planning model for calculation to obtain an initial cutting path; the cutting path planning model is established based on the improved spatial trajectory planning algorithm;

[0040] The cutting path calibration module includes an error judgment unit and a path recalibration unit; the error judgment unit is used to establish a cutting digital twin model based on the object to be cut; based on the cutting digital twin model, M-1 simulated cutting object images and corresponding simulated physiological parameters of the object to be cut are obtained; all simulated cutting object images are input into the cutting image annotation model for image recognition, and the cutting object feature map P is obtained. m and the marker ball feature point O m ', m=2, ..., M; using the improved image registration algorithm to cut the object feature map P m and the cut object feature map P m-1 Perform image registration and obtain the image error judgment result T m ; The image error judgment result T m The corresponding simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result J m ; The path recalibration unit is used to judge the result based on the cutting error J m The initial cutting path is updated to obtain an updated cutting path; and auxiliary path planning is performed on the object to be cut based on the updated cutting path.

[0041] The present invention has the following advantages:

[0042] 1. The present invention uses a cutting image annotation model as input for image recognition to obtain a cutting object feature map. Using an improved spatial trajectory planning algorithm and image registration algorithm, the method can efficiently predict and optimize the initial cutting path, ensuring the accuracy of the cutting path. By registering simulated cutting object images and analyzing them based on a cutting error judgment model, potential cutting errors can be identified preoperatively, allowing adjustments to the cutting path in advance to reduce the impact of errors. The initial cutting path is updated using the error judgment results, effectively preventing path deviations caused by errors.

[0043] 2. The present invention ensures image quality through the image preprocessing layer, laying a good foundation for subsequent processing. The improved convolution layer enhances the model's ability to capture image features by dynamically calculating the receptive field; the improved attention feature mechanism layer strengthens the recognition of key features and improves the accuracy of feature extraction through the channel and spatial attention mechanism; the improved residual convolution layer further refines features and ensures high-quality output of feature maps; the training process of the entire cut image annotation model is continuously optimized until the preset annotation accuracy is achieved, ensuring the practicality and reliability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a structural diagram of a cutting path planning system for an ultrasonic scalpel device used in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0046] Example 1, a cutting path planning method for an ultrasonic scalpel device, comprising the following steps:

[0047] Acquire an image of the object to be cut; the image of the object to be cut includes a marker ball of the object to be cut; input the image of the object to be cut into the cutting image annotation model for image recognition to obtain a cutting object feature map P1; the cutting object feature map P1 is annotated with cutting feature points and marker ball feature points O1';

[0048] The object to be cut is the incision part of the patient who needs surgery. The marking ball of the object to be cut is a fixed ball used for position calibration during path planning, and is fixedly positioned in the same manner as the camera.

[0049] The cut image annotation model includes an image preprocessing layer, an improved convolution layer, an improved attention feature mechanism layer, and an improved residual convolution layer;

[0050] The image preprocessing layer is used to perform image preprocessing operations on the image of the object to be cut, so as to obtain a preprocessed image of the object to be cut;

[0051] The improved convolution layer is used to perform a convolution operation on the preprocessed image of the object to be cut to obtain a convolution feature map of the object to be cut;

[0052] In the improved convolution layer, the number of layers of the convolution feature map of the object to be cut is set to N, n=1, 2, ..., N;

[0053] Using formula R n =R n-1 + (a-1) * (l-1) to calculate the n-th layer receptive field Rn , a is the size of the convolution kernel in the convolution feature map of the object to be cut in the nth layer, l is the expansion rate set in the convolution feature map of the object to be cut in the nth layer; all receptive fields R n Perform convolution calculations to obtain the convolution feature map of the object to be cut; set the expansion rate to change according to actual needs, use a smaller expansion rate to extract local information in the image, and use a larger expansion rate to extract long-distance information in the overall image;

[0054] The improved attention feature mechanism layer is used to extract features from the convolution feature map of the object to be cut using the improved attention feature mechanism to obtain the initial feature map of the object to be cut;

[0055] In the improved attention feature mechanism layer, the output initial feature map of the object to be cut is set to include B layers, b=1, 2, ..., B;

[0056] Using the formula H=conv 1*1*1 (concat(V d，b *F b , V s，b *F b )+concat(Z d，b *F b , Z s，b *F b ) + F b ) Calculate the convolution feature map of the object to be cut to obtain the feature map of the object to be cut;

[0057] Among them, V d，b Represents the channel attention vector of the initial feature map of the object to be cut in layer b, V d，b =Φ(conv 1*1*1 (conv 1*1*1 (Q(F b-1 ))));V s，b Represents the estimated value of the spatial attention vector of the initial feature map of the object to be cut in layer b, V s，b =Φ(conv 1*1*1 (conv 2*2*2 (conv 1*1*1 (F b-1 ))));Z d，b Represents the channel attention vector of the high-level feature channel after filtering the initial feature map of the object to be cut in layer b, Z d，b =Φ(conv 1*1*1 (conv 1*1*1 (Q(F b+1 ))));Z s，b Represents the attention mechanism vector contained in the feature space after segmentation of the initial feature map of the object to be cut in layer b, Z s，b =Φ(conv1*1*1 (conv 2*2*2 (conv 1*1*1 (F b+1 ))));conv( ) represents the convolution operation, concat ( ) represents the feature channel fusion operation, F b represents the low-dimensional feature map of layer b, Q( ) represents the global average pooling operation; Φ( ) represents the sigmoid activation operation;

[0058] The improved residual convolution layer is used to further extract features from the initial feature map of the object to be cut, and obtain the feature map P1 of the cut object;

[0059] In the improved residual convolution layer, the formula P1=σ(W 1*1 (W 1*1 (K(U)))) performs fusion convolution on the initial feature map of the object to be cut to obtain the feature map of the cut object P1; where σ represents the activation function, K(U) represents the value of the average pooling of the initial feature map of the object to be cut, W represents the convolution kernel, and W 1*1 Represents a 1*1 convolution operation, and U represents the initial feature map of the object to be cut;

[0060] The cut image annotation model is trained using the cut image annotation training set. The specific steps are as follows: collecting a number of images with feature point annotations and original images, combining the images with feature point annotations and the original images to obtain the cut image annotation training set; using the cut image annotation training set to train the cut image annotation model to obtain an initial cut image annotation model; if the initial cut image annotation model meets the preset annotation accuracy, the initial cut image annotation model is used as the cut image annotation model; otherwise, the model training is continued using the cut image annotation training set; the preset annotation accuracy is set manually;

[0061] The improved convolutional layer improves image distortion during processing by adjusting the receptive field size based on the visual receptive field characteristics, thereby improving overall image quality. The original image passes through a multi-scale semantic feature focusing module, namely the improved convolutional layer, which can extract highly representative features. By implementing the dilated convolution operation, the model's receptive field is effectively expanded, enhancing its ability to capture image details and improving the efficiency and quality of feature extraction. The improved attention feature mechanism module further optimizes the feature selection and aggregation process, significantly improving segmentation accuracy. The model also finely filters and processes features through a combination of deconvolution and pooling layers, namely the improved residual convolution layer, ensuring that the final output image has excellent feature extraction effects.

[0062] The cutting object feature map P1 is input into the cutting path planning model for calculation to obtain the initial cutting path; the cutting path planning model is established based on the improved spatial trajectory planning algorithm;

[0063] The cutting path planning model includes a feature point recognition layer and a path planning layer;

[0064] The feature point recognition layer is used to identify feature points based on the cutting object feature map P1 to obtain a cutting feature point set;

[0065] The path planning layer is used to perform path planning based on the cutting feature point set and the improved spatial trajectory planning algorithm to obtain the initial cutting path;

[0066] The specific steps of path planning in the path planning layer include:

[0067] According to the cutting feature point set and the spatial trajectory planning algorithm, I groups of cutting path individuals Y to be optimized are randomly generated. i , i=1, 2, ..., I; I groups of cutting path individuals Y to be optimized i Combine and obtain the optimized cutting path iteration population; set the inertia weight X1, inertia weight X2 and the current iteration number g, g = 1, 2, ..., G, G is the maximum iteration number, and the maximum iteration number is set manually;

[0068] For the individual Y of the optimized cutting path in the iterative population of optimized cutting paths i Perform simulated ultrasonic knife path cutting calculation to obtain simulated cutting time , simulate cutting time The reciprocal of is the individual Y of the cutting path to be optimized i Fitness ;

[0069] When performing population iteration, use the formula:

[0070] and Calculate and obtain the inertia weight X1 and inertia weight X2. The inertia weight X1 represents the individual Y of the cutting path to be optimized in the iterative population of the optimized cutting path. i The weight of approaching the current individual extreme point, the inertia weight X2 represents the individual Y of the cutting path to be optimized in the iterative population of the optimized cutting path iThe weight of approaching the global individual extreme point; where α is the preset calculation parameter, β is the standard deviation of the Gaussian distribution, and g is the current number of iterations; e is a mathematical constant; crossover and mutation operations are performed on the optimized cutting path iterative population according to the inertia weight X1 and the inertia weight X2; the crossover operation is adjusted based on the inertia weight X2. When the value of the inertia weight X2 is high, it will lead to frequent crossover during global convergence to explore the global optimal solution; the compilation operation is adjusted based on the inertia weight X1. When the inertia weight X1 is large, the frequency of mutation is low, indicating that the individual is mainly approaching the current optimal path; when the inertia weight X1 is small, the frequency of mutation is high, increasing the breadth of exploration;

[0071] The inertia weight X1 is used to control the influence of the current optimal path, determining how the individual continues to explore based on the current solution to avoid over-reliance on historical solutions. The inertia weight X2 controls the degree of convergence of the individual to the global optimal solution, allowing individuals in the population to continuously adjust towards the global optimal solution to explore a wider area of ​​the solution space.

[0072] When the current iteration number g=G, the output fitness is the individual Y of the cutting path to be optimized corresponding to the maximum i , which is the optimal cutting path individual to be optimized; the path in the optimal cutting path individual to be optimized is used as the initial cutting path;

[0073] Through the feature point recognition layer, key feature points can be accurately extracted to provide reliable input data for path planning and improve the accuracy of path planning; using the improved spatial trajectory planning algorithm, combined with randomly generated path individuals and optimization iterative process, the optimal cutting path can be quickly found; by simulating ultrasonic knife path cutting calculation, the feasibility and efficiency of the path are ensured; combining feature points and spatial trajectory planning algorithms to generate paths, in line with the actual surgical needs of the object to be cut, while minimizing the wound surface and the shortest time, and simulating ultrasonic knife path cutting calculation to ensure the feasibility and efficiency of the path; dynamically adjusting the inertia weights X1 and X2 makes the path optimization process more flexible and efficient, and can balance local and global searches at different iterative stages; through multiple iterations and optimization, it is ensured that the final output path is the global optimal, which improves the accuracy and efficiency of cutting; through efficient path planning and optimization algorithms, high-quality cutting paths can be generated in a relatively short time, which is suitable for real-time application scenarios;

[0074] A cutting digital twin model is established based on the object to be cut; based on the cutting digital twin model, M-1 simulated cutting object images and corresponding simulated physiological parameters of the object to be cut are obtained; all simulated cutting object images are input into the cutting image annotation model for image recognition, and a cutting object feature map P is obtained. m and the marker ball feature point O m', m=2, ..., M; using the improved image registration algorithm to cut the object feature map P m and the cut object feature map P m-1 Perform image registration and obtain the image error judgment result T m ; The image error judgment result T m The corresponding simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result J m ; Based on the cutting error judgment result J m The initial cutting path is updated to obtain an updated cutting path; and auxiliary path planning is performed on the object to be cut based on the updated cutting path;

[0075] A digital twin model refers to a virtual model constructed through real-time mapping of data and physical objects for analysis and prediction in a virtual environment. The steps to establish a cutting digital twin model are as follows: First, it is necessary to obtain detailed information about the object to be cut through high-precision sensors and scanning equipment. This information includes parameters such as the object's geometry, position, density, and hardness. Based on the collected data, computer-aided design software or 3D modeling tools are used to construct a geometric model of the physical object. The patient's anatomical structure can be converted into a virtual three-dimensional model to ensure the accuracy of the model. Based on the geometric model, physical properties need to be added to each part, such as the elastic modulus, hardness, and density of the tissue. These properties usually come from medical image processing, physical simulation, and experimental data. The constraints that may be encountered during the cutting process are simulated to ensure that the digital twin model can not only reflect the morphology of the target object, but also the physical processes associated with the surgery.

[0076] The purpose of acquiring simulated cutting object images and corresponding physiological parameters is to predict and optimize the surgical process and simulate the displacement movements that may occur during the cutting process. Cutting algorithms are applied to the digital twin model, such as cutting simulation based on the finite element method or other physical simulation technologies to simulate cutting. This process requires simulating the interaction between the tool and the object, including mechanical behavior, thermal effects, etc. Whenever the simulated object is offset, the digital twin model updates and generates a new object image, namely the simulated cutting object image, which represents the simulated effect of the movement of the patient's cutting part during the cutting process.

[0077] The improved image registration algorithm is used to identify the feature map P of the cutting object. m and the cut object feature map P m-1 Perform image registration. The specific steps include:

[0078] Calculate the cutting object feature map P m and the cut object feature map P m-1 The similarity error of is obtained to obtain the overall similarity error of image registration;

[0079] Mark the ball feature point O m ' and mark ball feature point O m-1 'Construct three-dimensional coordinate calibration and obtain the three-dimensional calibration coordinate ZB (P m ') and three-dimensional calibration coordinates ZB (P m-1 ');

[0080] Calculate the three-dimensional calibration coordinates ZB (P m ') and three-dimensional calibration coordinates ZB (P m-1 '), and obtain the image registration reprojection error and image registration benchmark error;

[0081] The image registration reprojection error and the image registration benchmark error are subtracted from the overall similarity error of the image registration to obtain the image error judgment result T m ;

[0082] By calculating the overall similarity error of image registration, the degree of match between two images can be accurately assessed, ensuring high-precision registration. Using 3D coordinate calibration further improves the accuracy of registration, especially in complex scenes such as simulated cutting. By calculating the reprojection error and benchmark error, registration errors caused by factors such as noise and occlusion can be effectively reduced, improving the robustness of registration. By comprehensively considering the overall similarity error, reprojection error, and benchmark error, the accuracy of the registration results can be comprehensively assessed to ensure registration quality. Through efficient similarity calculation and error assessment methods, image registration can be completed in a relatively short time.

[0083] The cutting error judgment model includes a physiological parameter evaluation layer, an image error feature extraction layer, and an error factor fusion layer;

[0084] The physiological parameter evaluation layer is used to extract the characteristics of the simulated physiological parameters of the object to be cut, and obtain the characteristics of the simulated physiological parameters of the object to be cut;

[0085] The image error feature extraction layer is used to judge the image error result T m Perform feature extraction to obtain the image error judgment result feature T m ';

[0086] The error factor fusion layer is used to simulate the physiological parameter characteristics of the object to be cut and the image error judgment result characteristics T m 'Carry out error factor fusion calculation to obtain cutting error judgment result J m ;

[0087] The specific steps for training the error factor fusion layer in the cutting error judgment model include:

[0088] Collecting several groups of error factor fusion training samples; each group of error factor fusion training samples contains physiological parameter features, image error features and annotated fusion cutting error results; combining several groups of error factor fusion training samples to obtain an error factor fusion training set;

[0089] The error factor fusion training set is input into the cutting error judgment model to train the error factor fusion layer to obtain the initial error factor fusion layer; the initial error factor fusion layer is evaluated to obtain the initial error factor fusion layer model evaluation result; if the initial error factor fusion layer model evaluation result is passed, the initial error factor fusion layer is used as the error factor fusion layer in the cutting error judgment model; otherwise, the model training is continued using the error factor fusion training set;

[0090] Through the physiological parameter evaluation layer and the image error feature extraction layer, the key features that affect the cutting error can be comprehensively extracted, improving the accuracy of error evaluation. The combination of physiological parameter features and image error features enables the model to more accurately predict the cutting error. The model can adapt to different types of objects to be cut and different cutting environments and has strong adaptability. Through multi-step feature extraction and error evaluation, the final cutting error judgment result is ensured to be reliable, reducing the possibility of misjudgment and saving time for re-path planning.

[0091] If the cutting error judgment result J m If it does not meet the cutting path planning threshold, then according to all cutting object feature maps P m The initial cutting path is updated to obtain an updated cutting path; otherwise, the initial cutting path is maintained and used as the updated cutting path; the cutting path planning threshold is set manually;

[0092] Based on the cutting object feature map P m The new path planning is performed with the cutting path planning model to obtain M-1 process cutting paths; the M-1 process cutting paths and the initial cutting path are subjected to feature fusion in the form of weighted average to obtain an updated cutting path.

[0093] In this embodiment, for example, before an ultrasonic scalpel surgery for tumor resection, the above-mentioned ultrasonic scalpel device cutting path planning method is used to assist path planning; before the surgery, the patient's image of the object to be cut is first obtained through imaging examination, and the patient is scanned using CT / MRI or ultrasonic equipment to obtain a high-resolution image of the object to be cut (such as a tumor or other tissue area); the image of the object to be cut is input into the cutting image annotation model, and the feature points of the image are extracted through the improved image preprocessing layer, convolution layer, attention feature mechanism layer and residual convolution layer; this step will generate a cutting object feature map, and mark the cutting feature points and marker ball feature points; the cutting object feature map will be input into the cutting path planning model for path calculation; in this process, the improved spatial trajectory planning algorithm is used to generate the initial cutting path; based on the object to be cut, the initial cutting path is generated. Images and physiological parameters are combined to establish a cutting digital twin model, which can accurately reflect the geometric shape, physical characteristics and physiological state of the object to be cut; several simulated cutting object images are obtained in the cutting digital twin model, the displacement movement of the object to be cut during the cutting process is simulated, and the corresponding simulated physiological parameters are obtained; all simulated cutting object images are aligned using the improved image registration algorithm to obtain the image error judgment result. This step ensures that the path planning model can accurately reflect the changes in different cutting scenarios by calculating the image similarity error, reprojection error and reference error; the image error judgment result and the simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result; based on this result, the initial cutting path is updated to ensure that the path planning has high accuracy and stability.

[0094] Example 2, a cutting path planning system for ultrasonic knife equipment, see Figure 1 As shown, including:

[0095] The cutting path planning module includes a planning preparation unit and a path planning unit; the planning preparation unit is used to obtain an image of the object to be cut; the image of the object to be cut includes a marker ball of the object to be cut; the image of the object to be cut is input into the cutting image annotation model for image recognition to obtain a cutting object feature map P1; the cutting object feature map P1 is annotated with cutting feature points and marker ball feature points O1'; the path planning unit is used to input the cutting object feature map P1 into the cutting path planning model for calculation to obtain an initial cutting path; the cutting path planning model is established based on the improved spatial trajectory planning algorithm;

[0096] The cutting path calibration module includes an error judgment unit and a path recalibration unit; the error judgment unit is used to establish a cutting digital twin model based on the object to be cut; based on the cutting digital twin model, M-1 simulated cutting object images and corresponding simulated physiological parameters of the object to be cut are obtained; all simulated cutting object images are input into the cutting image annotation model for image recognition, and the cutting object feature map P is obtained. m and the marker ball feature point O m ', m=2, ..., M; using the improved image registration algorithm to cut the object feature map P m and the cut object feature map P m-1 Perform image registration and obtain the image error judgment result T m ; The image error judgment result T m The corresponding simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result J m ; The path recalibration unit is used to judge the result based on the cutting error J m The initial cutting path is updated to obtain an updated cutting path; and auxiliary path planning is performed on the object to be cut based on the updated cutting path.

[0097] It should be understood that those skilled in the art may make improvements or modifications based on the above description, and all such improvements and modifications shall fall within the scope of protection of the appended claims. Any portion of this specification not described in detail is prior art known to those skilled in the art.

Claims

1. A cutting path planning method for an ultrasonic scalpel device, characterized in that: The following steps are involved: Acquire an image of the object to be cut; the image of the object to be cut includes a marker ball of the object to be cut; input the image of the object to be cut into the cutting image annotation model for image recognition to obtain a cutting object feature map P1; the cutting object feature map P1 is annotated with cutting feature points and marker ball feature points O1'; Input the cutting object feature map P1 into the cutting path planning model for calculation to obtain the initial cutting path; The cutting path planning model is established based on the improved spatial trajectory planning algorithm; A cutting digital twin model is established based on the object to be cut; based on the cutting digital twin model, M-1 simulated cutting object images and corresponding simulated physiological parameters of the object to be cut are obtained; all simulated cutting object images are input into the cutting image annotation model for image recognition, and a cutting object feature map P is obtained. m and the marker ball feature point O m ', m = 2, ..., M; The improved image registration algorithm is used to identify the feature map P of the cutting object. m and the cut object feature map P m-1 Perform image registration and obtain the image error judgment result T m ; The image error judgment result T m The corresponding simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result J m ; Based on the cutting error judgment result J m The initial cutting path is updated to obtain an updated cutting path; Perform auxiliary path planning on the object to be cut based on the updated cutting path; The improved image registration algorithm is used to identify the feature map P of the cutting object. m and the cut object feature map P m-1 Perform image registration. The specific steps include: Calculate the cutting object feature map P m and the cut object feature map P m-1 The similarity error of is obtained to obtain the overall similarity error of image registration; Mark the ball feature point O m ' and mark ball feature point O m-1 'Construct three-dimensional coordinate calibration and obtain the three-dimensional calibration coordinate ZB (P m ') and three-dimensional calibration coordinates ZB (P m-1 '); Calculate the three-dimensional calibration coordinates ZB (P m ') and three-dimensional calibration coordinates ZB (P m-1 '), and obtain the image registration reprojection error and image registration benchmark error; The image registration reprojection error and the image registration benchmark error are subtracted from the overall similarity error of the image registration to obtain the image error judgment result T m ; The cutting error judgment model includes a physiological parameter evaluation layer, an image error feature extraction layer, and an error factor fusion layer; The physiological parameter evaluation layer is used to extract the characteristics of the simulated physiological parameters of the object to be cut, and obtain the characteristics of the simulated physiological parameters of the object to be cut; The image error feature extraction layer is used to judge the image error result T m Perform feature extraction to obtain the image error judgment result feature T m '; The error factor fusion layer is used to simulate the physiological parameter characteristics of the object to be cut and the image error judgment result characteristics T m 'Carry out error factor fusion calculation to obtain cutting error judgment result J m .

2. The cutting path planning method of an ultrasonic knife device according to claim 1, characterized in that: The cut image annotation model includes an image preprocessing layer, an improved convolution layer, an improved attention feature mechanism layer, and an improved residual convolution layer; The image preprocessing layer is used to perform image preprocessing operations on the image of the object to be cut, so as to obtain a preprocessed image of the object to be cut; The improved convolution layer is used to perform a convolution operation on the preprocessed image of the object to be cut to obtain a convolution feature map of the object to be cut; In the improved convolution layer, the number of layers of the convolution feature map of the object to be cut is set to N, n=1, 2, ..., N; Using formula R n =R n-1 + (a-1) * (l-1) to calculate the n-th layer receptive field R n , a is the size of the convolution kernel in the convolution feature map of the object to be cut in the nth layer, l is the expansion rate set in the convolution feature map of the object to be cut in the nth layer; all receptive fields R n Perform convolution calculation to obtain the convolution feature map of the object to be cut; The improved attention feature mechanism layer is used to extract features from the convolution feature map of the object to be cut using the improved attention feature mechanism to obtain the initial feature map of the object to be cut; In the improved attention feature mechanism layer, the output initial feature map of the object to be cut is set to include B layers, b=1, 2, ..., B; Using the formula H=conv 1*1*1 (concat(V d，b *F b , V s，b *F b )+concat(Z d，b *F b , Z s，b *F b ) + F b ) Calculate the convolution feature map of the object to be cut to obtain the feature map of the object to be cut; Among them, V d，b Represents the channel attention vector of the initial feature map of the object to be cut in layer b, V d，b =Φ(conv 1*1*1 (conv 1*1*1 (Q(F b-1 ))));V s，b Represents the estimated value of the spatial attention vector of the initial feature map of the object to be cut in layer b, V s，b =Φ(conv 1*1*1 (conv 2*2*2 (conv 1*1*1 (F b-1 ))));Z d，b Represents the channel attention vector of the high-level feature channel after filtering the initial feature map of the object to be cut in layer b, Z d，b =Φ(conv 1*1*1 (conv 1*1*1 (Q(F b+1 ))));Z s，b Represents the attention mechanism vector contained in the feature space after segmentation of the initial feature map of the object to be cut in layer b, Z s，b =Φ(conv 1*1*1 (conv 2*2*2 (conv 1*1*1 (F b+1 ))));conv( ) represents the convolution operation, concat ( ) represents the feature channel fusion operation, F b represents the low-dimensional feature map of layer b, Q( ) represents the global average pooling operation; Φ( ) represents the sigmoid activation operation; The improved residual convolution layer is used to further extract features from the initial feature map of the object to be cut, and obtain the feature map P1 of the cut object; In the improved residual convolution layer, the formula P1=σ(W 1*1 (W 1*1 (K(U)))) performs fusion convolution on the initial feature map of the object to be cut to obtain the feature map of the cut object P1; where σ represents the activation function, K(U) represents the value of the average pooling of the initial feature map of the object to be cut, W represents the convolution kernel, and W 1*1 Represents a 1*1 convolution operation, and U represents the initial feature map of the object to be cut.

3. The cutting path planning method of an ultrasonic scalpel device according to claim 2, characterized in that: The cutting path planning model includes a feature point recognition layer and a path planning layer; The feature point recognition layer is used to identify feature points based on the cutting object feature map P1 to obtain a cutting feature point set; The path planning layer is used to perform path planning based on the cutting feature point set and the improved spatial trajectory planning algorithm to obtain the initial cutting path.

4. The cutting path planning method of an ultrasonic scalpel device according to claim 3, characterized in that: The specific steps of path planning in the path planning layer include: According to the cutting feature point set and the spatial trajectory planning algorithm, I groups of cutting path individuals Y to be optimized are randomly generated. i , i=1, 2, ..., I; I groups of cutting path individuals Y to be optimized i Combine and obtain the optimized cutting path iterative population; set the inertia weight X1, inertia weight X2 and the current iteration number g, g = 1, 2, ..., G, G is the maximum iteration number; For the individual Y of the optimized cutting path in the iterative population of optimized cutting paths i Perform simulated ultrasonic knife path cutting calculation to obtain simulated cutting time , simulate cutting time The reciprocal of is the individual Y of the cutting path to be optimized i Fitness ; When performing population iteration, use the formula: and Calculate and obtain the inertia weight X1 and inertia weight X2. The inertia weight X1 represents the individual Y of the cutting path to be optimized in the iterative population of the optimized cutting path. i The weight of approaching the current individual extreme point, the inertia weight X2 represents the individual Y of the cutting path to be optimized in the iterative population of the optimized cutting path i The weight of approaching the global individual extreme point; where α is the preset calculation parameter, β is the standard deviation of the Gaussian distribution, g is the current number of iterations; e is a mathematical constant; according to the inertia weight X1 and the inertia weight X2, the crossover and mutation operations are performed on the optimized cutting path iterative population; When the current iteration number g=G, the output fitness is the individual Y of the cutting path to be optimized corresponding to the maximum i , which is the optimal cutting path individual to be optimized; the path in the optimal cutting path individual to be optimized is used as the initial cutting path.

5. A cutting path planning system for an ultrasonic scalpel device, characterized in that: The system applies a cutting path planning method for an ultrasonic scalpel device according to any one of claims 1 to 4, comprising: The cutting path planning module includes a planning preparation unit and a path planning unit; the planning preparation unit is used to obtain an image of the object to be cut; the image of the object to be cut includes a marker ball of the object to be cut; the image of the object to be cut is input into the cutting image annotation model for image recognition to obtain a cutting object feature map P1; the cutting object feature map P1 is annotated with cutting feature points and marker ball feature points O1'; the path planning unit is used to input the cutting object feature map P1 into the cutting path planning model for calculation to obtain an initial cutting path; the cutting path planning model is established based on the improved spatial trajectory planning algorithm; The cutting path calibration module includes an error judgment unit and a path recalibration unit; the error judgment unit is used to establish a cutting digital twin model based on the object to be cut; based on the cutting digital twin model, M-1 simulated cutting object images and corresponding simulated physiological parameters of the object to be cut are obtained; all simulated cutting object images are input into the cutting image annotation model for image recognition, and the cutting object feature map P is obtained. m and the marker ball feature point O m ', m=2, ..., M; using the improved image registration algorithm to cut the object feature map P m and the cut object feature map P m-1 Perform image registration and obtain the image error judgment result T m ; The image error judgment result T m The corresponding simulated physiological parameters of the object to be cut are input into the cutting error judgment model for calculation to obtain the cutting error judgment result J m ; The path recalibration unit is used to judge the result based on the cutting error J m The initial cutting path is updated to obtain an updated cutting path; and auxiliary path planning is performed on the object to be cut based on the updated cutting path.

Images