Ablation puncture surgery navigation system under AI visual guidance

Abstract

The invention belongs to the technical field of ablation puncture navigation, and particularly relates to an ablation puncture surgery navigation system under AI visual guidance. Through cooperative work of the phase monitoring module, the channel construction module, the needle moving control module, the displacement prediction module and the feedback control module, an intelligent surgical navigation system is constructed, breathing phase information and multi-modal medical image data of a patient can be obtained in real time, and therefore a safe and optimized needle moving path is accurately planned, and the operation accuracy is improved. Meanwhile, through real-time monitoring and quantitative evaluation of parameters such as tissue deformation and pressure distribution in the needle moving process, potential operation risks can be found and corrected in time, smooth operation is ensured, in addition, the system can dynamically adjust the needle moving path and the puncture angle according to the real-time breathing state of a patient, and the operation safety is improved. The accuracy and the safety of the operation are further improved, so that intelligent management and personalized treatment in the ablation puncture operation process are realized.

Description

Technical Field

[0001] This invention belongs to the field of ablation puncture navigation technology, specifically relating to an AI vision-guided ablation puncture surgical navigation system. Background Technology

[0002] With the continuous advancement of medical technology, ablation puncture surgery has been widely used in fields such as tumor treatment. However, traditional ablation puncture surgery has problems such as inaccurate positioning and complex operation, which poses a great challenge to doctors and patients. In order to improve the accuracy and safety of ablation puncture surgery, current research focuses on developing intelligent navigation systems to assist doctors in performing surgical operations, thereby improving the precision of needle insertion during ablation surgery and further reducing surgical risks.

[0003] While some medical image-based navigation systems have been developed to assist doctors in ablation and puncture procedures, most of these systems rely on static medical image data and do not fully consider the impact of physiological activities such as respiratory movements on the surgical procedure. Therefore, in practical applications, there are still certain positioning errors and operational risks, which may lead to poor surgical results or complications. Based on this, this solution proposes an AI vision-guided ablation and puncture surgical navigation system to address the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide an AI-guided visual navigation system for ablation and puncture surgery, which can dynamically optimize the needle path based on real-time respiratory movements and organ displacement, thereby improving the accuracy and safety of ablation and puncture surgery.

[0005] The specific technical solution adopted by this invention is as follows: An AI-guided vision-guided ablation puncture surgical navigation system includes: The multimodal image fusion module is used to acquire and fuse patients' multimodal medical image data in real time, including CT, MRI and ultrasound image data; The respiratory phase monitoring module is used to monitor the patient's respiratory phase information in real time and dynamically correct the position of the target area based on the respiratory phase information. The channel construction module is used to construct acupuncture channels from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data; The needle control module is used to send auxiliary commands to the operating terminal to adjust the feed speed of the ablation puncture needle; The displacement prediction module is used to determine the predicted displacement vector of the target area and to correct the needle insertion angle of the ablation puncture needle in advance based on the predicted displacement vector to compensate for the positional deviation caused by breathing. The feedback control module is used to collect the patient's tissue dynamics indicators in real time during the acupuncture process, and to evaluate the stability of the acupuncture channel based on the tissue dynamics indicators. When the confidence score of the acupuncture channel is lower than the preset threshold, the ablation needle is paused and an alarm signal is issued.

[0006] In a preferred embodiment, the multimodal image fusion module includes an image acquisition unit, a cross-modal registration unit, and a fusion unit; The image acquisition unit is used to acquire CT, MRI, and ultrasound image data of the area to be ablated; The cross-modal registration unit is used to perform non-rigid spatial transformations on CT, MRI, and ultrasound image data to generate image datasets with a unified coordinate system. The fusion unit is used to perform pixel-level fusion of image information from registered CT, MRI and ultrasound image data to form a three-dimensional fused image that includes information on blood vessels, nerves, bones and soft tissue structures around the puncture target.

[0007] In a preferred embodiment, the respiratory phase monitoring module includes a multi-source sensor array, a phase recognition unit, and a dynamic correction unit. The multi-source sensor array includes an inertial measurement unit attached to the patient's chest and abdomen, a distributed fiber optic strain sensor, and an infrared thermal imaging sensor. The inertial measurement unit is used to detect the three-dimensional acceleration and angular velocity information of the patient's chest and abdomen in real time. The distributed fiber optic strain sensor is used to detect the deformation information of the patient's chest and abdomen in real time. The infrared thermal imaging sensor is used to detect the temperature change information of the patient's chest and abdomen in real time. The phase recognition unit is used to identify the patient's respiratory cycle and respiratory phase information based on the three-dimensional acceleration, angular velocity, deformation, and temperature change information. The dynamic correction unit is used to determine the dynamic offset of the target area based on the identified respiratory phase information and to update the target point coordinates in the target area in real time according to a preset update cycle. Among them, respiratory phase information corresponds to multiple phase states, including inspiratory phase, expiratory phase and steady phase; During the inspiratory phase, the patient's thoracic cavity volume increases; during the expiratory phase, the patient's thoracic cavity volume decreases; and during the steady phase, the patient's respiratory state is relatively stable, and changes in the patient's thoracic cavity volume are ignored.

[0008] In a preferred embodiment, the channel construction module includes a channel planning unit and a channel optimization unit. The channel planning unit is used to initially plan a safe acupuncture path from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data. The safe acupuncture path can avoid blood vessels and nerves. The channel optimization unit is used to receive the phase state output by the phase monitoring module and dynamically adjust the radius of curvature of the safe acupuncture path according to the time ratio of the inspiratory phase and the expiratory phase to obtain an optimized acupuncture channel. During the inspiratory phase, the radius of curvature of the safe acupuncture path increases to accommodate the spatial changes caused by the increase in thoracic cavity volume; during the expiratory phase, the radius of curvature of the safe acupuncture path decreases to accommodate the spatial changes caused by the decrease in thoracic cavity volume.

[0009] In a preferred embodiment, after the optimized needle insertion channel is output, the optimized needle insertion channel is aligned layer by layer with the organ contour in the ultrasound image; Real-time monitoring and optimization of the expansion and contraction rates of the needle channel cross-sectional area; When the expansion rate or contraction rate exceeds the preset safety threshold but is below the safety upper limit, an alarm signal is issued and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation puncture needle. When the expansion rate or contraction rate exceeds the preset safety limit, a braking command is immediately sent to the operating end to stop the feeding of the ablation puncture needle; In addition, the pressure feedback parameters of the ablation needle body are monitored in real time, including axial pressure, radial shear force and torque value; When the pressure feedback parameter exceeds the preset pressure threshold but is lower than the pressure upper limit, an alarm signal is issued and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation puncture needle. When the pressure feedback parameter exceeds the pressure limit, a braking command is immediately sent to the operating end to stop the advance of the ablation puncture needle.

[0010] In a preferred embodiment, the needle control module includes a speed adjustment unit and an emergency braking unit. The speed adjustment unit is used to determine the adjustment speed of the ablation puncture needle according to the received deceleration command. The emergency braking unit is used to trigger an alarm signal after receiving a braking command and send it to the operating terminal simultaneously.

[0011] In a preferred embodiment, the needle control module further includes a needle deviation correction unit, which is used to monitor and optimize the gap distance between the inner wall of the needle channel and the outer wall of the ablation puncture needle in real time, and record it as the needle deviation amount. When the needle offset is less than the preset safe distance threshold, a correction command is sent to the operating terminal to correct the offset of the ablation puncture needle towards the central axis of the optimized needle channel, so as to correct the needle direction.

[0012] In a preferred embodiment, the displacement prediction module includes a prediction unit and a correction unit. The prediction unit is used to extract the target point coordinates in the target area in real time and construct a spatial displacement feature vector containing time series features. The displacement prediction model is trained using a pre-trained displacement prediction model to predict the target displacement vector during the required time period. The displacement prediction model is trained using respiratory motion and organ displacement mapping datasets collected before surgery. The correction unit is used to calculate the real-time needle angle compensation of the ablation puncture needle based on the predicted displacement vector and send it to the operating terminal to form a needle compensation command.

[0013] In a preferred embodiment, the feedback control module includes a tissue deformation monitoring unit and a confidence assessment unit. The tissue deformation monitoring unit is used to collect the local pressure distribution and three-dimensional deformation characteristics of the tissue around the puncture path, and to perform spatiotemporal registration of the local pressure distribution and three-dimensional deformation characteristics to form a tissue deformation map. The confidence assessment unit is used to quantitatively assess the degree and trend of deformation in the tissue deformation map and generate a deformation confidence score. When the deformation confidence score is lower than a preset reliability threshold, a pause command is sent to the operating terminal to pause the ablation puncture operation and replan the needle passage.

[0014] The present invention also provides an electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the AI ​​vision-guided ablation puncture surgical navigation system described above.

[0015] The technical effects achieved by this invention are as follows: This invention utilizes an AI-guided vision-guided ablation puncture surgical navigation system to achieve precise control and real-time monitoring of the ablation puncture procedure, significantly improving surgical safety and success rates. Specifically, through the collaborative work of a phase monitoring module, channel construction module, needle movement control module, displacement prediction module, and feedback control module, an intelligent surgical navigation system is constructed. This system can acquire the patient's respiratory phase information and multimodal medical imaging data in real time, thereby accurately planning a safe and optimized needle movement path. Simultaneously, by real-time monitoring and quantitative evaluation of parameters such as tissue deformation and pressure distribution during needle movement, potential surgical risks can be promptly identified and corrected, ensuring the smooth progress of the procedure. Furthermore, the system can dynamically adjust the needle movement path and puncture angle based on the patient's real-time respiratory status, further improving the accuracy and safety of the procedure. This achieves intelligent management and personalized treatment of the ablation puncture surgical process. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the system modules of the present invention; Figure 2 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0020] Please see Figure 1 As shown, this invention provides an AI-guided vision-guided ablation and puncture surgical navigation system, comprising: The multimodal image fusion module is used to acquire and fuse patients' multimodal medical image data in real time, including CT, MRI and ultrasound image data; When liver ablation is required, the multimodal image fusion module acquires and fuses multimodal medical imaging data from within the patient in real time, including CT, MRI, and ultrasound images. For example, CT images can provide detailed skeletal structures, MRI images can display soft tissue details, and ultrasound images can provide real-time dynamic information during the procedure. Specifically, the multimodal image fusion module includes an image acquisition unit, a cross-modal registration unit, and a fusion unit. The image acquisition unit acquires CT, MRI, and ultrasound images of the area to be ablated, and the cross-modal registration unit processes the CT, MRI, and ultrasound images... Non-rigid spatial transformations (such as affine transformations and B-spline transformations) are performed to achieve precise alignment between images of different modalities and generate an image dataset with a unified coordinate system. The fusion unit is used to perform pixel-level fusion of image information from registered CT, MRI and ultrasound image data, so that the patient's bone structure, soft tissue details and real-time ultrasound dynamic information can be observed in a unified view. Finally, a three-dimensional fused image containing information on blood vessels, nerves, bones and soft tissue structures around the puncture target is formed, so that doctors can more accurately identify the puncture path during preoperative planning and intraoperative navigation and avoid damage to important blood vessels and nerve structures. In addition, it includes custom view units with the following features: Image browsing: Use the slider, mouse wheel, or crosshair to browse images in the two-dimensional image window; Image scaling: In a 2D or 3D window, scale images or models using custom mouse controls. Model rotation: In the 3D window, rotate the model by combining custom buttons with mouse operation keys; Image movement: In a 2D or 3D window, drag and drop images or models using custom mouse controls; The functions of the aforementioned custom view unit can also include window width and level adjustment, window layout, screenshot, adding text, image measurement, etc. These are the existing conventional functions for image operations, and will not be listed one by one here. In specific use, you can define them according to the actual operation requirements.

[0021] The respiratory phase monitoring module is used to monitor the patient's respiratory phase information in real time and dynamically correct the position of the target area based on the respiratory phase information. During ablation puncture surgery in the liver region, the patient's respiratory movements significantly affect the position of the target area. To ensure the accuracy of the surgery, the respiratory phase monitoring module can monitor the patient's respiratory phase information in real time and dynamically correct the position of the target area based on the respiratory phase information. This reduces the target displacement error caused by respiratory movements and improves the accuracy and safety of the surgery. The respiratory phase monitoring module includes a multi-source sensor array, a phase recognition unit, and a dynamic correction unit. The multi-source sensor array includes an inertial measurement unit attached to the patient's chest and abdomen, a distributed fiber optic strain sensor, and an infrared thermal imaging sensor. The inertial measurement unit is used to detect the three-dimensional acceleration and angular velocity information of the patient's chest and abdomen in real time. The distributed fiber optic strain sensor is used to detect the deformation information of the patient's chest and abdomen in real time. The infrared thermal imaging sensor is used to detect the temperature change information of the patient's chest and abdomen in real time. The phase recognition unit is used to identify the patient's respiratory cycle and respiratory phase information based on the three-dimensional acceleration, angular velocity, deformation, and temperature change information. The dynamic correction unit is used to determine the dynamic offset of the target area based on the identified respiratory phase information and update the target coordinates in the target area in real time according to a preset update cycle. Among them, respiratory phase information corresponds to multiple phase states, including inspiratory phase, expiratory phase and steady phase; During the inspiratory phase, the patient's thoracic cavity volume increases; during the expiratory phase, the patient's thoracic cavity volume decreases; during the steady phase, the patient's respiratory state is relatively stable, and changes in the patient's thoracic cavity volume are ignored. Specifically, the multi-source sensor array is a component of the respiratory phase monitoring module, including an inertial measurement unit (IMU), a distributed fiber optic strain sensor (DFO), and an infrared thermal imaging sensor (IR). These sensors capture the patient's respiratory information from different angles and dimensions, ensuring the comprehensiveness and accuracy of the data. The IMU, attached to the patient's chest and abdomen, can detect the patient's three-dimensional acceleration and angular velocity information in real time, reflecting the motion trajectory and velocity changes of the chest and abdomen. For example, when the patient inhales, the acceleration and angular velocity of the chest and abdomen increase significantly, while the opposite occurs during exhalation. The IMU can accurately capture these specific changes, providing corresponding data support for subsequent phase identification. The distributed fiber optic strain sensor can monitor the deformation of the chest and abdomen in real time, for example, during the inspiratory phase. During inhalation, the skin and muscles of the chest and abdomen stretch and expand, while they contract during exhalation. The DFO sensor detects this deformation to provide information about respiratory movements. An infrared thermal imaging sensor is used to detect real-time temperature changes in the patient's chest and abdomen. Temperature changes are closely related to respiratory activity, especially during inhalation and exhalation, when the temperature of the chest and abdomen fluctuates. The infrared thermal imaging sensor can capture these temperature changes and combine them with data from other sensors to improve the accuracy of respiratory phase recognition. For example, the temperature of the chest and abdomen rises during inhalation and falls during exhalation; this temperature change can be used as a basis for identifying the respiratory phase. The phase recognition unit is responsible for identifying the patient's respiratory cycle and respiratory phase information based on data collected by the multi-source sensor array. Specifically, the phase recognition unit... By comprehensively analyzing information such as acceleration, angular velocity, deformation, and temperature changes, and employing machine learning algorithms such as support vector machines (SVM), random forests (RF), or deep learning models (such as convolutional neural networks CNN), the respiratory cycle and respiratory phase can be accurately identified. For example, the respiratory rate of a normal adult is about 12-20 breaths per minute. If a patient's respiratory rate is detected to be outside this range, it may indicate certain health problems, such as anxiety or respiratory diseases.

[0022] It should be clarified that respiratory phases refer to the different stages in the respiratory cycle, mainly including the inspiratory phase, expiratory phase, and steady phase; Inspiratory phase: The patient's thoracic cavity volume increases, the acceleration and angular velocity of the chest and abdomen increase, the deformation expands outward, and the temperature rises.

[0023] During the expiratory phase: the patient's thoracic cavity volume decreases, the acceleration and angular velocity of the chest and abdomen decrease, the deformation contracts inward, and the temperature drops.

[0024] Steady phase: The patient's respiratory state is relatively stable, and the changes in acceleration, angular velocity, deformation and temperature in the chest and abdomen are small and can be ignored; The dynamic correction unit, also a component of the respiratory phase monitoring module, is responsible for real-time correction of the dynamic offset of the target area based on the identified respiratory phase information. It also updates the target point coordinates in the target area in real-time according to a preset update cycle, thereby ensuring the accuracy of the target point position during surgery. Specifically, the dynamic correction unit receives respiratory phase information from the phase recognition unit and, combined with real-time data collected by the multi-source sensor array, calculates the dynamic offset of the target area caused by respiratory motion. The formula for calculating the dynamic offset is: ; In the formula, Indicates the maximum displacement amplitude. Indicates real-time respiratory rate. This indicates the phase angle offset. , and Indicates the weighting coefficient. This represents the real-time deformation of a distributed fiber optic strain sensor. This represents the temperature change gradient detected by the infrared thermal imaging sensor. This represents the three-dimensional acceleration modulus of the inertial measurement unit. Indicates the integral gain coefficient of angular velocity. This represents the magnitude of the angular velocity vector.

[0025] The channel construction module is used to construct acupuncture channels from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data; The channel construction module is responsible for constructing an acupuncture channel from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data. This process requires factors such as tissue density, blood vessel distribution, and nerve pathways. Based on these conditions, the module can automatically construct an acupuncture channel from the patient's body surface to the target area and display it intuitively on a 3D model. The channel construction module includes a channel planning unit and a channel optimization unit. The channel planning unit is used to initially plan a safe acupuncture path from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data. The safe acupuncture path can avoid blood vessels and nerves. The channel optimization unit is used to receive the phase state output by the phase monitoring module and dynamically adjust the radius of curvature of the safe acupuncture path according to the time ratio of the inspiratory and expiratory phases to obtain an optimized acupuncture channel. During the inspiratory phase, the radius of curvature of the safe acupuncture path increases to adapt to the spatial changes caused by the increase in thoracic cavity volume; during the expiratory phase, the radius of curvature of the safe acupuncture path decreases to adapt to the spatial changes caused by the decrease in thoracic cavity volume. Specifically, during the execution of the channel planning unit, the patient's anatomical characteristics, such as rib orientation, muscle distribution, and the precise location of the target area (such as a tumor), are comprehensively considered. Using multimodal medical imaging data, such as CT (computed tomography) and MRI (magnetic resonance imaging), high-resolution three-dimensional anatomical information can be obtained. Based on this information, the channel planning unit will initially design a safe acupuncture path that avoids key anatomical structures (such as major blood vessels and important nerves) while accurately reaching the target area. Subsequently, the channel optimization unit will intervene and adjust the initially planned acupuncture path accordingly based on the phase status output in real time by the respiratory phase monitoring module. During the inspiratory phase, due to the increased thoracic cavity volume, the channel optimization unit will increase the radius of curvature of the safe acupuncture path to ensure that the needle tip has sufficient space margin during penetration and avoids unnecessary contact with surrounding tissues. Conversely, during the expiratory phase, the thoracic cavity volume decreases and the target area is closer to the body surface, so the channel optimization unit will correspondingly reduce the radius of curvature to make the acupuncture path more direct and safe. The dynamic adjustment of the radius of curvature can be represented by the following piecewise function. ; In the formula, This indicates the radius of curvature of the needle channel, which is dynamically adjusted in real time. Represents the initial radius of curvature. This represents the baseline thoracic cavity volume during calm breathing. Indicates the getter phase expansion coefficient. This indicates the real-time change in thoracic cavity volume during the inspiratory phase. Indicates the expiratory phase compressibility factor. This indicates the amount of real-time acceleration decay during the expiratory phase.

[0026] In addition, after optimizing the needle insertion channel output, the optimized needle insertion channel is aligned layer by layer with the organ contour in the ultrasound image; Real-time monitoring and optimization of the expansion and contraction rates of the needle channel cross-sectional area; When the expansion rate or contraction rate exceeds the preset safety threshold but is below the safety upper limit, an alarm signal is issued and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation puncture needle. When the expansion rate or contraction rate exceeds the preset safety limit, a braking command is immediately sent to the operating end to stop the feeding of the ablation puncture needle; In addition, the pressure feedback parameters of the ablation needle body are monitored in real time, including axial pressure, radial shear force and torque value; When the pressure feedback parameter exceeds the preset pressure threshold but is lower than the pressure upper limit, an alarm signal is issued and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation puncture needle. When the pressure feedback parameter exceeds the pressure limit, a braking command is immediately sent to the operating end to stop the feeding of the ablation puncture needle; In this embodiment, after optimizing the needle insertion channel output, the optimized channel is registered with the patient's actual anatomical structure to ensure accurate reflection of the patient's true condition during needle insertion navigation. Specifically, the optimized channel is aligned with preoperative multimodal medical imaging data to eliminate errors caused by changes in patient position or respiratory movements. After registration, the expansion and contraction rates of the optimized needle insertion channel's cross-sectional area are collected. The expansion rate reflects the speed at which the channel expands due to changes in thoracic cavity volume during respiration, while the contraction rate reflects its contraction speed. By monitoring the expansion and contraction rates of the optimized needle insertion channel's cross-sectional area in real time, dynamic changes in the channel can be captured promptly. During needle insertion, if the expansion or contraction rate exceeds a preset safety threshold but has not yet reached the safety upper limit, an alarm signal is immediately issued to alert the operator, and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation needle, thereby avoiding potential errors caused by channel changes. Needle deviation detection: This deceleration operation is designed to give the operator sufficient reaction time to adjust the needle insertion strategy or take other necessary interventions. However, if the expansion or contraction rate continues to rise until it exceeds the preset safety limit, a braking command will be immediately sent to the operating device to forcibly stop the advance of the ablation needle. This reduces the risk of needle insertion caused by drastic changes in the channel and ensures patient safety. In addition, the pressure feedback parameters of the ablation needle body will be monitored in real time. The pressure feedback parameters include axial pressure, radial shear force, and torque value, which reflect the resistance encountered by the ablation needle during insertion, thus helping the operator to judge whether the insertion is going smoothly. When the pressure feedback parameters exceed the preset pressure threshold but have not yet reached the pressure limit, an alarm signal will be issued and a deceleration command will be sent to the operating device. If the pressure feedback parameters continue to rise until they exceed the pressure limit, a braking command will be immediately executed to stop the advance of the ablation needle to prevent needle insertion failure or patient injury due to excessive pressure.

[0027] The needle control module is used to send auxiliary commands to the operating terminal to adjust the feed speed of the ablation puncture needle; The needle movement control module receives needle movement commands to adaptively adjust the feed speed of the ablation puncture needle. The needle movement commands include acceleration commands, constant speed commands, deceleration commands, and braking commands, thereby ensuring that the needle tip can reach the target position smoothly and accurately. The needle movement control module includes a speed adjustment unit and an emergency braking unit. The speed adjustment unit is used to determine the adjustment speed of the ablation puncture needle according to the received deceleration command, so that it gradually slows down to a safer feed rate to avoid needle movement deviation or patient discomfort caused by excessive speed. The emergency braking unit is used to trigger an alarm signal after receiving a braking command and send it to the operating terminal simultaneously, thereby ensuring the safety of the patient can be effectively protected in emergency situations. In the above, when adjusting the feed speed of the ablation puncture needle, the deceleration command issued due to the changes in the expansion and contraction rates of the optimized needle channel cross-sectional area is determined by the formula... Determine the adjustment speed of the ablation needle in this formula. This indicates the real-time dynamic adjustment of the feed rate of the ablation needle. Indicates the reference feed rate. The dynamic attenuation coefficient represents the channel deformation rate. This represents the real-time expansion rate of the channel cross-sectional area. The safety threshold representing the expansion rate, This represents the real-time channel cross-sectional area shrinkage rate. The safety threshold representing the rate of contraction; For deceleration commands issued due to pressure feedback parameters exceeding the preset pressure threshold, the adjustment speed is determined using another formula, specifically: In the formula, This represents the dynamic attenuation coefficient of the mechanical feedback pressure. This represents the pressure feedback parameter.

[0028] In addition, the needle control module also includes a needle deviation correction unit, which is used to monitor and optimize the gap distance between the inner wall of the needle channel and the outer wall of the ablation puncture needle in real time, and record it as the needle deviation amount. When the needle offset is less than the preset safe distance threshold, a correction command is sent to the operating terminal to correct the offset of the ablation puncture needle towards the central axis of the optimized needle channel, so as to correct the needle direction. During the movement of the ablation needle, it may deviate to one side of the needle channel. If this deviation is not corrected in time, it may lead to inaccurate needle movement or damage to surrounding tissues. When the deviation exceeds the safe range, the needle correction unit immediately activates the correction mechanism. With the assistance of the correction mechanism, the operator can fine-tune the trajectory of the ablation needle to gradually bring it closer to the central axis of the optimized needle channel, thereby ensuring the accuracy of the needle direction. In this way, the ablation needle can reach the target position smoothly and accurately, further improving the safety and effectiveness of the surgery.

[0029] The displacement prediction module is used to determine the predicted displacement vector of the target area and to correct the needle insertion angle of the ablation puncture needle in advance based on the predicted displacement vector to compensate for the positional deviation caused by breathing. The displacement prediction module is used to predict the displacement changes of the target area during the operation and to correct the needle angle of the ablation puncture needle in advance based on the prediction results. Specifically, it calculates the displacement vector of the target area by combining the patient's respiratory phase information and real-time image data. By correcting the needle angle in advance, it can effectively compensate for the positional deviation caused by breathing and ensure that the needle tip is always on the correct path. The displacement prediction module includes a prediction unit and a correction unit. The prediction unit is used to extract the target point coordinates in the target area in real time and construct a spatial displacement feature vector containing time series features. The displacement prediction model is trained using a pre-trained displacement prediction model to predict the target displacement vector during the required time period. The displacement prediction model is trained using respiratory motion and organ displacement mapping datasets collected before surgery. The correction unit is used to calculate the real-time needle angle compensation of the ablation puncture needle based on the predicted displacement vector and send it to the operating terminal to form a needle compensation command.

[0030] Specifically, the displacement prediction module consists of a prediction unit and a correction unit. The prediction unit can extract the coordinate information of key target points in the target area in real time. The target point coordinate information is used to construct a spatial displacement feature vector. The spatial displacement feature vector not only contains the current position information of the target point, but also incorporates time series features to reflect the changing trend of the target point over time. Subsequently, the spatial displacement feature vector is input into a pre-trained displacement prediction model, which can predict the displacement vector of the target point within the required time period. The displacement prediction model is a convolutional neural network model based on deep learning algorithms. It is trained before the operation by collecting a large number of patients' respiratory motion and organ displacement mapping datasets, so as to accurately predict the displacement changes of the target area during the respiratory process. This is a common technique in the existing technology and will not be elaborated on here. The correction unit is responsible for calculating the real-time needle angle compensation of the ablation puncture needle based on the predicted displacement vector. In the formula, This indicates the amount of real-time needle angle compensation. Indicates the predicted displacement vector. This represents the unit vector indicating the current direction of travel. This vector is used to determine the amount of needle angle compensation that the ablation needle needs to be adjusted. This adjustment instruction is then sent to the operating terminal. After receiving the adjustment instruction, the operator will adjust the puncture angle of the ablation needle accordingly. This ensures that the ablation needle can always travel along the correct path during breathing and will not deviate from the target position due to displacement changes caused by breathing. This ensures that the ablation needle can accurately puncture the target area, improving the accuracy and success rate of the surgery.

[0031] The feedback control module is used to collect the patient's tissue dynamics indicators in real time during the acupuncture process, and to evaluate the stability of the acupuncture channel based on the tissue dynamics indicators. When the confidence score of the acupuncture channel is lower than the preset threshold, the ablation needle is paused and an alarm signal is issued. The feedback control module collects real-time tissue dynamics indicators during acupuncture, such as tissue pressure, temperature, and conductivity, to assess the stability of the acupuncture channel. When the confidence score of the acupuncture channel falls below a preset threshold, the ablation needle is automatically paused and an alarm signal is issued. This not only allows for the timely detection of potential risks but also provides doctors with important reference information. For example, when tissue abnormalities are detected, doctors can adjust the surgical plan based on the feedback information to avoid unnecessary complications. The feedback control module includes a tissue deformation monitoring unit and a confidence assessment unit. The tissue deformation monitoring unit collects the local pressure distribution and three-dimensional deformation characteristics of the tissue around the puncture path and performs spatiotemporal registration of the local pressure distribution and three-dimensional deformation characteristics to form a tissue deformation map. The confidence assessment unit then quantifies and assesses the degree and trend of deformation in the tissue deformation map to generate a deformation confidence score. In the formula, This represents the confidence score for deformation. and Indicates the weighting coefficient. Indicates the degree of real-time deformation. This indicates the preset safety threshold. Parameters representing deformation trend The trend sensitivity coefficient (used to control the rate of exponential decay) is used. When the deformation confidence score is lower than the preset reliability threshold, a pause command is sent to the operator to pause the ablation puncture operation and replan the needle channel.

[0032] Please see Figure 2 An electronic device, characterized in that: the electronic device comprises: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to execute the aforementioned AI vision-guided ablation puncture surgical navigation system.

[0033] The processor of the aforementioned electronic device can be a central processing unit (CPU), graphics processing unit (GPU), field-programmable gate array (FPGA), digital signal processor (DSP), application-specific integrated circuit (ASIC), or any other type of processor or processing circuit, or a combination of the above processors. The processor may include one or more processing cores, which may be general-purpose processor cores or application-specific processor cores. The memory may include volatile memory (such as random access memory (RAM)) and non-volatile memory (such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD)). The memory may store the operating system, computer programs, data, and other application programs. In addition, the electronic device may also include an arithmetic logic unit (ALU), input devices, and output devices. The ALU may be an arithmetic logic unit (ALU) for performing various arithmetic and logical operations. Input devices may include a keyboard, mouse, touch screen, etc., for receiving user input commands. Output devices may include a display, printer, etc., for displaying processing results to the user or printing relevant information.

[0034] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0035] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. An AI-guided vision-guided ablation and puncture surgical navigation system, characterized in that: include: The multimodal image fusion module is used to acquire and fuse patients' multimodal medical image data in real time, including CT, MRI and ultrasound image data; The respiratory phase monitoring module is used to monitor the patient's respiratory phase information in real time and dynamically correct the position of the target area based on the respiratory phase information. The channel construction module is used to construct acupuncture channels from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data; The needle control module is used to send auxiliary commands to the operating terminal to adjust the feed speed of the ablation puncture needle; The displacement prediction module is used to determine the predicted displacement vector of the target area and to correct the needle insertion angle of the ablation puncture needle in advance based on the predicted displacement vector to compensate for the positional deviation caused by breathing. The feedback control module is used to collect the patient's tissue dynamics indicators in real time during the acupuncture process, and to evaluate the stability of the acupuncture channel based on the tissue dynamics indicators. When the confidence score of the acupuncture channel is lower than the preset threshold, the ablation needle is paused and an alarm signal is issued.

2. The AI-guided ablation and puncture surgical navigation system according to claim 1, characterized in that: The multimodal image fusion module includes an image acquisition unit, a cross-modal registration unit, and a fusion unit; The image acquisition unit is used to acquire CT, MRI, and ultrasound image data of the area to be ablated; The cross-modal registration unit is used to perform non-rigid spatial transformations on CT, MRI, and ultrasound image data to generate image datasets with a unified coordinate system. The fusion unit is used to perform pixel-level fusion of image information from registered CT, MRI and ultrasound image data to form a three-dimensional fused image that includes information on blood vessels, nerves, bones and soft tissue structures around the puncture target.

3. The AI-guided ablation and puncture surgical navigation system according to claim 2, characterized in that: The respiratory phase monitoring module includes a multi-source sensor array, a phase recognition unit, and a dynamic correction unit. The multi-source sensor array includes an inertial measurement unit attached to the patient's chest and abdomen, a distributed fiber optic strain sensor, and an infrared thermal imaging sensor. The inertial measurement unit is used to detect the three-dimensional acceleration and angular velocity information of the patient's chest and abdomen in real time. The distributed fiber optic strain sensor is used to detect the deformation information of the patient's chest and abdomen in real time. The infrared thermal imaging sensor is used to detect the temperature change information of the patient's chest and abdomen in real time. The phase recognition unit is used to identify the patient's respiratory cycle and respiratory phase information based on the three-dimensional acceleration, angular velocity, deformation, and temperature change information. The dynamic correction unit is used to determine the dynamic offset of the target area based on the identified respiratory phase information and to update the target point coordinates in the target area in real time according to a preset update cycle. Among them, respiratory phase information corresponds to multiple phase states, including inspiratory phase, expiratory phase and steady phase; During the inspiratory phase, the patient's thoracic cavity volume increases; during the expiratory phase, the patient's thoracic cavity volume decreases; and during the steady phase, the patient's respiratory state is relatively stable, and changes in the patient's thoracic cavity volume are ignored.

4. The AI-guided ablation and puncture surgical navigation system according to claim 3, characterized in that: The channel construction module includes a channel planning unit and a channel optimization unit. The channel planning unit is used to initially plan a safe acupuncture path from the body surface to the target area based on real-time monitored respiratory phase information and multimodal medical imaging data. The safe acupuncture path can avoid blood vessels and nerves. The channel optimization unit is used to receive the phase state output by the phase monitoring module and dynamically adjust the radius of curvature of the safe acupuncture path according to the time ratio of the inspiratory phase and the expiratory phase to obtain an optimized acupuncture channel. During the inspiratory phase, the radius of curvature of the safe acupuncture path increases to accommodate the spatial changes caused by the increase in thoracic cavity volume; during the expiratory phase, the radius of curvature of the safe acupuncture path decreases to accommodate the spatial changes caused by the decrease in thoracic cavity volume.

5. The AI-guided ablation and puncture surgical navigation system according to claim 4, characterized in that: After the optimized needle insertion channel is output, the optimized needle insertion channel is aligned layer by layer with the organ contour in the ultrasound image; Real-time monitoring and optimization of the expansion and contraction rates of the needle channel cross-sectional area; When the expansion rate or contraction rate exceeds the preset safety threshold but is below the safety upper limit, an alarm signal is issued and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation puncture needle. When the expansion rate or contraction rate exceeds the preset safety limit, a braking command is immediately sent to the operating end to stop the feeding of the ablation puncture needle; In addition, the pressure feedback parameters of the ablation needle body are monitored in real time, including axial pressure, radial shear force and torque value; When the pressure feedback parameter exceeds the preset pressure threshold but is lower than the pressure upper limit, an alarm signal is issued and a deceleration command is sent to the operating terminal to reduce the feed speed of the ablation puncture needle. When the pressure feedback parameter exceeds the pressure limit, a braking command is immediately sent to the operating end to stop the advance of the ablation puncture needle.

6. The AI-guided ablation and puncture surgical navigation system according to claim 1, characterized in that: The needle control module includes a speed adjustment unit and an emergency braking unit. The speed adjustment unit is used to determine the adjustment speed of the ablation puncture needle according to the received deceleration command. The emergency braking unit is used to trigger an alarm signal after receiving a braking command and send it to the operating terminal simultaneously.

7. The AI-guided ablation and puncture surgical navigation system according to claim 1, characterized in that: The needle control module also includes a needle deviation correction unit, which is used to monitor and optimize the gap distance between the inner wall of the needle channel and the outer wall of the ablation puncture needle in real time, and record it as the needle deviation amount. When the needle offset is less than the preset safe distance threshold, a correction command is sent to the operating terminal to correct the offset of the ablation puncture needle towards the central axis of the optimized needle channel, so as to correct the needle direction.

8. The AI-guided ablation and puncture surgical navigation system according to claim 1, characterized in that: The displacement prediction module includes a prediction unit and a correction unit. The prediction unit is used to extract the target point coordinates in the target area in real time and construct a spatial displacement feature vector containing time series features. The displacement prediction model is trained using a pre-trained displacement prediction model to predict the target displacement vector during the required time period. The displacement prediction model is trained using respiratory motion and organ displacement mapping datasets collected before surgery. The correction unit is used to calculate the real-time needle angle compensation of the ablation puncture needle based on the predicted displacement vector and send it to the operating terminal to form a needle compensation command.

9. The AI-guided ablation and puncture surgical navigation system according to claim 1, characterized in that: The feedback control module includes a tissue deformation monitoring unit and a confidence assessment unit. The tissue deformation monitoring unit is used to collect the local pressure distribution and three-dimensional deformation characteristics of the tissue around the puncture path, and to perform spatiotemporal registration of the local pressure distribution and three-dimensional deformation characteristics to form a tissue deformation map. The confidence assessment unit is used to quantitatively assess the degree and trend of deformation in the tissue deformation map and generate a deformation confidence score. When the deformation confidence score is lower than a preset reliability threshold, a pause command is sent to the operating terminal to pause the ablation puncture operation and replan the needle channel.

10. An electronic device, characterized in that: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to execute the AI ​​vision-guided ablation puncture surgical navigation system as described in any one of claims 1 to 9.

Images