Intelligent puncture robot arm combined with microwave ablation instrument AI optimization intelligent diagnosis and treatment system and method

Abstract

The application discloses an AI optimization intelligent diagnosis and treatment system and method of a smart puncture mechanical arm combined with a microwave ablation instrument, relates to the AI treatment technical field, and combines organ activity data during extension and a puncture mechanical arm operation state to perform mechanical arm operation state deviation prediction, simulates three-dimensional space positions of a puncture path in a patient's body according to the operation track of the puncture mechanical arm and the external features of a puncture needle, analyzes the contact condition of the puncture path and organs, constructs a puncture path and organ contact condition risk degree evaluation model, obtains an evaluation result of the puncture path and organ contact condition risk degree, judges the safest path for microwave ablation in combination with the evaluation result of the puncture path and organ contact condition risk degree, the actual three-dimensional path is obtained through the mechanical arm operation deviation condition, and then the risk value is judged according to the contact condition with the organs, so that the best path is screened out, and the safety of treatment is improved.

Description

Technical Field

[0001] This invention relates to the field of AI treatment technology, and in particular to an AI-optimized intelligent diagnosis and treatment system and method combining an intelligent puncture robotic arm with a microwave ablation device. Background Technology

[0002] As a precise and minimally invasive treatment technology, the puncture robotic arm is now widely used in the treatment of various diseases. By integrating AI navigation, real-time image tracking and sub-millimeter precision control, the puncture robotic arm has achieved integrated minimally invasive treatment from biopsy sampling to tumor ablation.

[0003] Currently, the selection of puncture paths mostly involves obtaining the location of the lesion and surrounding anatomical structures through imaging, reconstructing a three-dimensional model of the patient, determining the spatial coordinates of the needle entry point, target point, and key anatomical structures of the initial puncture path, and planning a collision-free path in the three-dimensional model to avoid high-risk areas. Although this method is theoretically risk-free, in actual operation it can be affected by abnormal operation of the robotic arm and organ activity, which can reduce the safety of the puncture path and generate unforeseen risks.

[0004] To address the aforementioned issues, this invention provides an AI-optimized intelligent diagnosis and treatment system and method that combines an intelligent puncture robotic arm with a microwave ablation device. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an AI-optimized intelligent diagnosis and treatment system and method that combines an intelligent puncture robotic arm with a microwave ablation device. This invention obtains the actual three-dimensional path by analyzing the deviation of the robotic arm's operation, and then judges the risk value based on the contact with the organ, thereby selecting the optimal path and improving the safety of treatment.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The AI-optimized intelligent diagnosis and treatment method, which combines an intelligent puncture robotic arm with a microwave ablation device, includes the following specific steps:

[0008] S1. Real-time acquisition of the puncture robotic arm's operating data, combined with the puncture robotic arm's historical operating data and preset safe operating thresholds, to evaluate the puncture robotic arm's operating status.

[0009] S2. Real-time acquisition of organ activity data, combined with organ activity data during insertion and the operating status of the puncture robotic arm, to predict deviations of the robotic arm from its operating state.

[0010] S3. Based on the running trajectory of the puncture robotic arm and the external characteristics of the puncture needle, simulate the three-dimensional spatial position of the puncture path in the patient's body.

[0011] S4. Spatial matching of the simulated puncture path with the three-dimensional model of the organ, and analysis of the contact between the puncture path and the organ.

[0012] S5. Construct a risk assessment model for the contact between the puncture path and the organ. Input the contact between the puncture path and the organ, combine the risk level of the organ, and output the assessment result of the risk level of the contact between the puncture path and the organ.

[0013] S6. Determine the safest route based on the assessment results of the risk level of the puncture path and the contact with the organ.

[0014] Specifically, S1 includes the following steps:

[0015] The operation data of the puncture robotic arm is collected in real time, including the position coordinates, movement speed, acceleration, rotation angle and torque of the robotic arm;

[0016] Collect historical operating data and preset safe operating thresholds for the puncture robotic arm. The safe operating thresholds include the safe movement speed threshold, safe acceleration threshold, safe rotation angle threshold, and safe torque threshold of the robotic arm.

[0017] A unified timestamp is used to assess historical operational deviations based on historical operational data and to assess real-time operational compliance based on safe operational thresholds.

[0018] The operational status of the puncture robotic arm is assessed based on historical operational deviations and real-time operational compliance.

[0019] Specifically, S2 includes the following steps:

[0020] Real-time acquisition of organ activity data, including three-dimensional displacement vector, surface strain distribution, surface pressure distribution, respiratory amplitude, and respiratory rate;

[0021] Construct an organ displacement prediction model, input organ activity data, and output the predicted position of the organ at a set time point;

[0022] Construct a model to predict the deviation of the robotic arm from its operating state. Input the predicted location of the organ and the operating state of the puncture robotic arm, and output the deviation of the robotic arm from its operating state.

[0023] Specifically, S3 includes the following steps:

[0024] The set running path of the robotic arm is collected, and the actual running trajectory of the puncture robotic arm is obtained based on the set running path plus the deviation of the robotic arm from the running state.

[0025] Collect external characteristics of the puncture needle, including length, diameter, and curvature;

[0026] The puncture path is simulated in three-dimensional space within the patient's body based on the actual running trajectory of the puncture robotic arm and the external characteristics of the puncture needle.

[0027] Specifically, S4 includes the following steps:

[0028] Spatial matching is performed between the simulated puncture path and the three-dimensional model of the organ;

[0029] Based on spatial matching analysis, the contact between the puncture path and the organ is analyzed, and the contact includes the contact area and the contact depth.

[0030] Specifically, S5 includes the following steps:

[0031] Risk level of organ harvesting;

[0032] Construct a risk assessment model for the contact between the puncture path and the organ. Input the risk level of the organ and the contact between the puncture path and the organ, and output the assessment results of the risk level of the contact between the puncture path and the organ.

[0033] Specifically, S6 includes the following steps:

[0034] The assessment results of the risk level of each puncture path in contact with the organ are obtained, and the puncture path with the lowest risk level is set as the safest path.

[0035] The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm with a microwave ablation device is used to realize the AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm with a microwave ablation device. It includes: a robotic arm operation status assessment module, which is used to collect the operation data of the puncture robotic arm in real time, and to assess the operation status of the puncture robotic arm by combining the historical operation data of the puncture robotic arm and the preset safe operation threshold.

[0036] The deviation from the operating state prediction module is used to collect organ activity data in real time, and combine the organ activity data during the insertion process with the operating state of the puncture robotic arm to predict the deviation of the robotic arm from the operating state.

[0037] The three-dimensional position simulation module is used to simulate the three-dimensional spatial position of the puncture path in the patient's body based on the running trajectory of the puncture robotic arm and the external characteristics of the puncture needle.

[0038] The contact assessment module is used to spatially match the simulated puncture path with the three-dimensional model of the organ and analyze the contact between the puncture path and the organ.

[0039] The risk assessment module is used to construct a risk assessment model for the contact between the puncture path and the organ. It takes the contact between the puncture path and the organ as input, combines the risk level of the organ, and outputs the assessment result of the risk level of the contact between the puncture path and the organ.

[0040] The safe path determination module is used to determine the safest path for microwave ablation by combining the assessment results of the risk level of the puncture path and the contact with the organ.

[0041] An electronic device includes a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm and a microwave ablation device by calling the computer program stored in the memory.

[0042] A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the aforementioned AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm and a microwave ablation device.

[0043] The advantages of the technical solution provided by this invention are as follows: It collects real-time operational data of the puncture robotic arm, combines historical operational data with preset safe operating thresholds to assess the robotic arm's operational status, collects real-time organ activity data, and predicts deviations from the robotic arm's operational status based on organ activity data during insertion and the robotic arm's operational status. Based on the robotic arm's trajectory and the external characteristics of the puncture needle, it simulates the three-dimensional spatial position of the puncture path within the patient's body, spatially matches the simulated puncture path with the three-dimensional model of the organ, analyzes the contact between the puncture path and the organ, constructs a risk assessment model for the contact between the puncture path and the organ, inputs the contact between the puncture path and the organ, combines the organ's risk level, and outputs the assessment result of the risk level of the contact between the puncture path and the organ. Based on the assessment result, it determines the safest path for microwave ablation. This invention obtains the actual three-dimensional path through robotic arm deviation and then determines the risk value based on the contact with the organ, thereby selecting the optimal path for microwave ablation and improving treatment safety. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A schematic diagram of the AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm with a microwave ablation device provided by the present invention;

[0046] Figure 2A schematic diagram of the S1 process of the AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm and a microwave ablation device provided by the present invention.

[0047] Figure 3 A schematic diagram of the S2 process of the AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm and a microwave ablation device provided by the present invention.

[0048] Figure 4 A schematic diagram of the S3 process of the AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm and a microwave ablation device provided by the present invention.

[0049] Figure 5 This is a schematic diagram of the overall framework of the AI-optimized intelligent diagnosis and treatment system that combines an intelligent puncture robotic arm with a microwave ablation device, as provided by the present invention. Detailed Implementation

[0050] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0051] Please see Figure 1 The present invention provides an embodiment of an AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm with a microwave ablation device, which includes the following specific steps:

[0052] S1. Real-time acquisition of the puncture robotic arm's operating data, combined with the puncture robotic arm's historical operating data and preset safe operating thresholds, to evaluate the puncture robotic arm's operating status.

[0053] Please see Figure 2 In this embodiment, S1 includes the following specific steps:

[0054] Real-time acquisition of the puncture robotic arm's operational data, including the robotic arm's position coordinates, movement speed, acceleration, rotation angle, and torque;

[0055] In this embodiment, the data acquisition method for the puncture robotic arm can be as follows: The three-dimensional coordinates of the robotic arm's end effector are acquired in real time using a three-dimensional optical positioning system; a spatial mapping relationship between the robotic arm base and the medical image is established using a calibration plate for calibration; the motion speed and acceleration changes of each joint of the robotic arm are monitored in real time using an inertial measurement unit (IMU), and three-axis acceleration and angular velocity data are collected. Linear velocity is calculated using an integral algorithm, and the smoothness of the motion trajectory is processed by combining timestamp differential processing. The motion speed and acceleration reflect the motion characteristics of the robotic arm, which helps to analyze its motion stability and dynamic performance; high-precision rotary encoders are installed at the joints to monitor the pitch, yaw, and roll angles of each joint. The rotation angle data reflects the changes in the robotic arm's posture and the range of motion of the joints; dynamic torque sensors are integrated into the drive joints to collect the joint load torque in real time. The range needs to cover 120% of the maximum working torque of the robotic arm. The torque data reflects the force situation during the operation of the robotic arm and is an important indicator for evaluating the working status and safety of the robotic arm.

[0056] Collect historical operating data and preset safe operating thresholds for the puncture robotic arm. The safe operating thresholds include the safe movement speed threshold, safe acceleration threshold, safe rotation angle threshold, and safe torque threshold of the robotic arm.

[0057] A unified timestamp is used to assess historical operational deviations based on historical operational data and to assess real-time operational compliance based on safe operational thresholds.

[0058] In this embodiment, the historical operational deviation can be calculated using the following formula: ,in, To collect the value of the i-th type of operational data of the puncture robotic arm at time t in real time, Let be the value of the i-th type of historical operation data of the puncture robot at time t. The number of data types included in the puncture robot arm's operational data. The duration of data collection for the puncture robotic arm. Integral over time;

[0059] Real-time compliance can be calculated using the following formula: ,in, The safe operating threshold for the i-th type of operating data of the puncture robot arm;

[0060] The operational status of the puncture robotic arm is assessed based on historical operational deviations and real-time operational compliance.

[0061] In this embodiment, the operating status of the puncture robotic arm can be calculated using the following formula: ,in, Weighting for historical deviation. To enable real-time compliance weighting, .

[0062] S2. Real-time acquisition of organ activity data, combined with organ activity data during insertion and the operating status of the puncture robotic arm, to predict deviations of the robotic arm from its operating state.

[0063] Please see Figure 3 In this embodiment, S2 includes the following specific steps:

[0064] Real-time acquisition of organ activity data, including three-dimensional displacement vector, surface strain distribution, surface pressure distribution, respiratory amplitude, and respiratory rate;

[0065] In this embodiment, the three-dimensional displacement vector can be acquired through ultrasonic spot tracking to predict the movement trajectory of organs and avoid misalignment between the puncture needle and the target organ. The surface strain distribution can be acquired through ultrasonic elastography to detect changes in tissue stiffness and predict sudden changes in needle tip resistance. The surface pressure distribution can be acquired through an optical fiber sensor array to monitor the needle tip contact pressure in real time and avoid tissue damage. In specific cases, blood flow pulsation waveforms can also be acquired to predict periodic displacement caused by vascular pulsation. Temperature gradients can be acquired to identify inflammatory areas (prone to bleeding) and tumor cores (high resistance). Electromyographic signals can be acquired to predict sudden movements such as coughing and spasms.

[0066] Construct an organ displacement prediction model, input organ activity data, and output the predicted position of the organ at a set time point;

[0067] In this embodiment, the calculation formula for the organ displacement prediction model can be as follows: ,in, This represents the position of the organ at time t0 + Δt, where t0 is the current time and Δt is the predicted time point, a tiny time step typically used for real-time navigation or control. The initial position of an organ serves as a fundamental reference point for its movement. It can be understood as the organ's location in the absence of respiratory movements and external contact (such as surgical instrument pressure). This position is typically determined beforehand using imaging techniques (such as CT or MRI) at a specific respiratory phase (e.g., end-expiration). This is the respiratory motion component, used to simulate the periodic, reciprocating displacement of organs caused by a patient's spontaneous breathing. It causes the organ position to fluctuate sinusoidally over time, simulating the up-down, forward-backward, and left-right movements caused by respiration. To determine the respiratory amplitude, a Fast Fourier Transform (FFT) algorithm is used to analyze real-time organ displacement data acquired through electromagnetic tracking, ultrasound, or optical imaging. This algorithm identifies the displacement amplitude caused by respiratory motion, specifically the amplitude corresponding to the peak respiratory frequency in the frequency spectrum. This amplitude reflects the maximum displacement distance of the organ from its reference position caused by respiratory motion. The respiratory rate is obtained by real-time monitoring of the patient's respiratory signals through breathing belts, thoracic impedance, or image-based tracking algorithms. The phase offset, or the initial phase angle (in radians) of the sine function, represents the position of the respiratory motion in its cycle at the initial moment (e.g., at the midpoint of inspiration, the beginning of expiration, etc.). It is calibrated and determined based on the respiratory phase corresponding to the initial position (e.g., the end of expiration) and the real-time respiratory signal, which can ensure that the waveform of the sine function is synchronized with the actual respiratory motion.

[0068] Construct a model to predict the deviation of the robotic arm from its operating state. Input the predicted location of the organ and the operating state of the puncture robotic arm, and output the deviation of the robotic arm from its operating state.

[0069] In this embodiment, the calculation formula for the robotic arm deviation from the operating state prediction model can be as follows:

[0070] ,in, The influence coefficient of organ displacement on robotic arm offset can be obtained by: collecting the movement trajectory of the organ and the actual movement trajectory of the robotic arm end effector during historical surgeries, establishing a linear regression model for the two trajectories, calculating the organ movement trajectory through medical imaging, and obtaining the actual movement trajectory of the robotic arm end effector through the robotic arm's own encoder or optical tracking system. To simulate the non-periodic, directional deformation and displacement of organs caused by contact with the puncture robotic arm, this displacement is typically not a reciprocating motion, but rather a localized compression and overall displacement caused by instrument pressure. This refers to the maximum displacement distance of an organ under maximum contact pressure. For example, the maximum displacement distance of the liver is 2-5 mm, and the maximum displacement distance of the lung is 5-8 mm. This is a decay function, reflecting the relationship between contact pressure and the resulting displacement. The displacement increases with increasing pressure, but the rate of increase gradually slows down. Tissue stiffness coefficient reflects the ability of organ tissues to resist deformation. The larger the value, the greater the tissue stiffness, and the smaller the deformation displacement under the same contact pressure. For example, fat is soft and easily deformed, with a tissue stiffness coefficient of 0.2 / N, while tumors are hard and not easily deformed, with a tissue stiffness coefficient of 0.8 / N. Tissue stiffness coefficient can be obtained through in vitro experiments, finite element simulation, and other methods. The real-time contact pressure, i.e. the real-time contact pressure acting on the surface of the organ, is measured in real time by a pressure sensor (e.g., integrated into the tip of the surgical instrument). The organ's movement and the insertion of the puncture robotic arm interact with each other, causing the trajectory of the puncture robotic arm to deviate. This predictive model takes into account both the effects of physiological movement and external intervention, thus improving the accuracy of the prediction.

[0071] S3. Based on the running trajectory of the puncture robotic arm and the external characteristics of the puncture needle, simulate the three-dimensional spatial position of the puncture path in the patient's body.

[0072] Please see Figure 4 In this embodiment, S3 includes the following specific steps:

[0073] The set running path of the robotic arm is collected, and the actual running trajectory of the puncture robotic arm is obtained based on the set running path plus the deviation of the robotic arm from the running state.

[0074] In this embodiment, the method for obtaining the running path is set as follows: determine the state space (joint angles, end effector position / attitude) and operation space (joint space and Cartesian space) of the robotic arm, establish the mapping relationship between joint variables and end effector pose through kinematic model, generate a theoretical trajectory point sequence, use RRT (Fast Random Tree) algorithm to generate a collision-free path in operation space, expand the search tree through iterative sampling, connect the starting point and the target point, and smooth the generated path.

[0075] Collect external characteristics of the puncture needle, including length, diameter, and curvature;

[0076] In this embodiment, the actual length of the puncture needle is obtained by a laser rangefinder, the needle diameter is measured by an optical scanner, and the bending angle of the needle tip relative to the needle shank is measured by a structured light scanner. For non-linear needles, a geometric parameterized model (such as a Bézier curve) is established to describe its spatial shape. The collected feature data is synchronized with the position of the end effector of the robotic arm in time to ensure the spatiotemporal consistency of the subsequent path simulation.

[0077] The puncture path is simulated in three-dimensional space within the patient's body based on the actual running trajectory of the puncture robotic arm and the external characteristics of the puncture needle.

[0078] In this embodiment, based on the patient's preoperative CT / MRI images, a three-dimensional model of the target organ and blood vessels is reconstructed. A registration algorithm aligns the robotic arm coordinate system with the medical image coordinate system, establishing a spatial mapping relationship. The length, diameter, and curvature parameters of the puncture needle are converted into a three-dimensional geometric model. The needle body is represented by a cylinder, and the curvature parameter is converted into the radius of curvature. A Bézier curve is used to simulate the needle tip's bending trajectory. The curved segment is then joined with the cylinder to form a complete needle geometric entity. Using the robotic arm's end-effector trajectory as a reference, a safe path is generated based on the needle's features. The robotic arm's end-effector trajectory is coupled with the needle's curvature. If the needle's curvature is θ, then... The offset of the needle tip trajectory end can be obtained by multiplying the needle length by the tangent of the curvature. The end pose is corrected by a homogeneous transformation matrix to obtain the three-dimensional coordinate sequence of the needle tip in the patient's body. The blood vessel and organ model is decomposed into axial bounding boxes, and the overlapping area between the needle trajectory and the bounding box is checked. If there is an overlap, path replanning is triggered. Combined with the RRT algorithm (fast random tree) for dynamic obstacle avoidance, the needle geometric model is superimposed on the three-dimensional medical image, and the needle tip movement trajectory is dynamically rendered. The real-time positions of the needle entry point (puncture site), target point (lesion center), and needle tip are output. This three-dimensional space acquisition provides quantifiable path optimization basis for surgery by outputting the coordinates of key nodes.

[0079] S4. Spatial matching of the simulated puncture path with the three-dimensional model of the organ, and analysis of the contact between the puncture path and the organ.

[0080] In this embodiment, S4 includes the following specific steps:

[0081] Spatial matching is performed between the simulated puncture path and the three-dimensional model of the organ;

[0082] Spatial matching analysis is used to determine the contact between the puncture path and the organ, including the contact area and contact depth.

[0083] In this embodiment, the triangular mesh data of the three-dimensional model of the organ is acquired, and the coordinates of the simulated puncture path are obtained, ensuring that the puncture path and the three-dimensional model of the organ are in the same three-dimensional coordinate system. The puncture path is considered as a ray, with its direction from the starting point coordinate Z1 to the ending point coordinate Z2. Using the ray-triangular mesh intersection algorithm, all triangular meshes of the organ model are traversed. For each triangular mesh (defined by three vertices V0, V1, V2), it is calculated whether the ray intersects with it. If they intersect, the intersection point coordinates J1 and the parameter j along the ray are returned. The coordinates J1 of all intersection points with the model surface and their corresponding j values ​​are recorded. All the obtained intersection points are then analyzed according to their parameter j. The values ​​are sorted from smallest to largest. The point where the puncture path enters the organ model is usually the first intersection point, i.e., the smallest j value. The point where the puncture path leaves the organ model is usually the last intersection point, i.e., the largest j value. For concave organs or complex paths (e.g., passing through holes, multiple entries and exits), the number of intersection points will be even, and they need to be processed in pairs (e.g., the first and second intersection points are the first internal segment, the third and fourth intersection points are the second internal segment, and so on). The line segment between each pair of valid entry points Jin and exit points Jout is the part of the puncture path located inside the organ. If it is a single penetration (two intersection points), the contact depth is obtained by the Euclidean length of the entry point Jin and the exit point Jout, and the contact area is obtained by multiplying the contact depth by the circumference of the puncture needle. If it is a multiple penetration (multiple pairs of intersection points), the total contact depth is obtained by the sum of the lengths of all internal line segments, and the total contact area is obtained by the sum of the contact areas of all internal line segments.

[0084] S5. Construct a risk assessment model for the contact between the puncture path and the organ. Input the contact between the puncture path and the organ, combine the risk level of the organ, and output the assessment result of the risk level of the contact between the puncture path and the organ.

[0085] In this embodiment, S5 includes the following specific steps:

[0086] Risk level of organ harvesting;

[0087] In this embodiment, the risk level is divided into four levels, from low to high. The first level is adipose tissue and muscle, where the risk of bleeding is low, and the corresponding risk level value is set to 1. The second level is liver parenchyma, spleen, and renal cortex, where the risk of bleeding is moderate, and the corresponding risk level value is set to 1.2. The third level is blood vessels, pancreatic duct, and bile duct, where the risk of bleeding is high and repair is difficult, and the corresponding risk level value is set to 1.4. The fourth level is the heart, brainstem, and aorta and pulmonary artery, where the risk is the highest and irreversible damage is likely to occur, and the corresponding risk level value is set to 1.6.

[0088] Construct a risk assessment model for the contact between the puncture path and the organ. Input the risk level of the organ and the contact between the puncture path and the organ, and output the assessment results of the risk level of the contact between the puncture path and the organ.

[0089] In this embodiment, the calculation formula for the risk assessment model of the contact between the puncture path and the organ can be as follows: ,in, The risk level value corresponding to the risk level of the organ. For contact depth, For organ thickness, For contact area, The surface area of ​​the organ. The contact depth affects the weight. The contact area affects the weight. This assessment model simultaneously evaluates large-area contact (e.g., organ surface friction) and localized deep invasion (e.g., needle tip puncture of blood vessels), covering different injury mechanisms. It achieves spatial heterogeneity assessment based on organ zonal risk and provides early warning of potential contact risks.

[0090] In this embodiment, the weights and thresholds are obtained as follows: Historical surgical puncture robotic arm operation data and organ activity data are collected to determine the contact between the puncture path and organs during surgery. Based on historical surgical results, the risk level of the actual puncture path contact with organs is analyzed. The surgical robotic arm operation data and organ activity data are imported into the assessment results of the risk level of the puncture path contact with organs obtained in each step of this embodiment. The risk level of the actual puncture path contact with organs and the assessment results of the risk level of the puncture path contact with organs obtained in this embodiment are then imported into MATLAB fitting software for fitting to obtain the weights and thresholds of the group with the highest accuracy.

[0091] S6. Determine the safest route based on the assessment results of the risk level of the puncture path and the contact with the organ.

[0092] In this embodiment, S6 includes the following specific steps:

[0093] The assessment results of the risk level of each puncture path in contact with the organ are obtained, and the puncture path with the lowest risk level is set as the safest path.

[0094] Please see Figure 5The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm with a microwave ablation device is based on the aforementioned AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm with a microwave ablation device. It includes: a robotic arm operation status assessment module, which is used to collect the operation data of the puncture robotic arm in real time, and to assess the operation status of the puncture robotic arm by combining the historical operation data of the puncture robotic arm with the preset safe operation threshold.

[0095] The deviation from the operating state prediction module is used to collect organ activity data in real time, and combine the organ activity data during the insertion process with the operating state of the puncture robotic arm to predict the deviation of the robotic arm from the operating state.

[0096] The three-dimensional position simulation module is used to simulate the three-dimensional spatial position of the puncture path in the patient's body based on the running trajectory of the puncture robotic arm and the external characteristics of the puncture needle.

[0097] The contact assessment module is used to spatially match the simulated puncture path with the three-dimensional model of the organ and analyze the contact between the puncture path and the organ.

[0098] The risk assessment module is used to construct a risk assessment model for the contact between the puncture path and the organ. It takes the contact between the puncture path and the organ as input, combines the risk level of the organ, and outputs the assessment result of the risk level of the contact between the puncture path and the organ.

[0099] The safe path determination module is used to determine the safest path for microwave ablation by combining the assessment results of the risk level of the puncture path and the contact with the organ.

[0100] This embodiment provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned AI-optimized intelligent diagnosis and treatment method of intelligent puncture robotic arm combined with microwave ablation device by calling the computer program stored in the memory.

[0101] The electronic device can vary considerably depending on its configuration and performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program. This computer program is loaded and executed by the processor to implement the AI-optimized intelligent diagnosis and treatment method of the intelligent puncture robotic arm combined with a microwave ablation device provided in the above-described embodiment. The electronic device may also include other components for realizing its functions. For example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Details will not be elaborated upon in this embodiment.

[0102] This embodiment proposes a computer-readable storage medium storing instructions that, when a computer program is run on a computer device, cause the computer device to execute the aforementioned AI-optimized intelligent diagnosis and treatment method combining an intelligent puncture robotic arm and a microwave ablation device.

[0103] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0104] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0105] It should be understood that determining B based on A does not mean determining B solely based on A; it also means determining B based on A and / or other information.

[0106] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, they generate in whole or in part the flow or function according to the embodiments of the present invention. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0107] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this invention.

[0108] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0109] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only one, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0111] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0112] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example, and the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0113] The preferred embodiments of the present invention disclosed above are only for the purpose of illustrating the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm with a microwave ablation device, characterized in that: include: The robotic arm operation status assessment module is used to collect the operation data of the puncture robotic arm in real time, and to assess the operation status of the puncture robotic arm by combining the historical operation data of the puncture robotic arm and the preset safe operation threshold. The deviation from the operating state prediction module is used to collect organ activity data in real time, and combine the organ activity data during the insertion process with the operating state of the puncture robotic arm to predict the deviation of the robotic arm from the operating state. The three-dimensional position simulation module is used to simulate the three-dimensional spatial position of the puncture path in the patient's body based on the running trajectory of the puncture robotic arm and the external characteristics of the puncture needle. The contact assessment module is used to spatially match the simulated puncture path with the three-dimensional model of the organ and analyze the contact between the puncture path and the organ. The risk assessment module is used to construct a risk assessment model for the contact between the puncture path and the organ. It takes the contact between the puncture path and the organ as input, combines the risk level of the organ, and outputs the assessment result of the risk level of the contact between the puncture path and the organ. The safe path determination module is used to determine the safest path for microwave ablation by combining the assessment results of the risk level of the puncture path and the contact with the organ.

2. The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm and a microwave ablation device according to claim 1, characterized in that, The real-time acquisition of the puncture robotic arm's operational data, combined with the robotic arm's historical operational data and preset safe operating thresholds, to evaluate the robotic arm's operational status includes the following specific steps: The operation data of the puncture robotic arm is collected in real time, including the position coordinates, movement speed, acceleration, rotation angle and torque of the robotic arm; Collect historical operating data and preset safe operating thresholds for the puncture robotic arm. The safe operating thresholds include the safe movement speed threshold, safe acceleration threshold, safe rotation angle threshold, and safe torque threshold of the robotic arm. Historical operational deviations are assessed based on historical operational data, and real-time operational compliance is assessed based on safe operational thresholds. The operational status of the puncture robotic arm is assessed based on historical operational deviations and real-time operational compliance.

3. The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm and a microwave ablation device according to claim 2, characterized in that, The real-time acquisition of organ activity data, combined with organ activity data during insertion and the operating status of the puncture robotic arm, to predict deviations from the operating state of the robotic arm includes the following specific steps: Real-time acquisition of organ activity data, including three-dimensional displacement vector, surface strain distribution, surface pressure distribution, respiratory amplitude, and respiratory rate; Construct an organ displacement prediction model, input organ activity data, and output the predicted position of the organ at a set time point; Construct a model to predict the deviation of the robotic arm from its operating state. Input the predicted location of the organ and the operating state of the puncture robotic arm, and output the deviation of the robotic arm from its operating state.

4. The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm and a microwave ablation device according to claim 3, characterized in that, The process of simulating the three-dimensional spatial position of the puncture path within the patient's body based on the trajectory of the puncture robotic arm and the external characteristics of the puncture needle includes the following specific steps: The set running path of the robotic arm is collected, and the actual running trajectory of the puncture robotic arm is obtained based on the set running path plus the deviation of the robotic arm from the running state. Collect external characteristics of the puncture needle, including length, diameter, and curvature; The puncture path is simulated in three-dimensional space within the patient's body based on the actual running trajectory of the puncture robotic arm and the external characteristics of the puncture needle.

5. The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm and a microwave ablation device according to claim 4, characterized in that, The process of spatially matching the simulated puncture path with the three-dimensional model of the organ and analyzing the contact between the puncture path and the organ includes the following specific steps: Spatial matching is performed between the simulated puncture path and the three-dimensional model of the organ; Based on spatial matching analysis, the contact between the puncture path and the organ is analyzed, and the contact includes the contact area and the contact depth.

6. The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm and a microwave ablation device according to claim 5, characterized in that, The construction of the risk assessment model for the contact between the puncture path and the organ involves inputting the contact situation between the puncture path and the organ, combining it with the risk level of the organ, and outputting the assessment result of the risk level of the contact between the puncture path and the organ. The specific steps are as follows: Risk level of organ harvesting; Construct a risk assessment model for the contact between the puncture path and the organ. Input the risk level of the organ and the contact between the puncture path and the organ, and output the assessment results of the risk level of the contact between the puncture path and the organ.

7. The AI-optimized intelligent diagnosis and treatment system combining an intelligent puncture robotic arm and a microwave ablation device according to claim 6, characterized in that, The process of determining the safest route for microwave ablation, based on an assessment of the risk level between the puncture path and the organ contact situation, includes the following specific steps: The assessment results of the risk level of each puncture path in contact with the organ are obtained, and the puncture path with the lowest risk level is set as the safest path.

Images