A surgical early warning method, system, medium and product based on region identification

Abstract

A surgical early warning method, system, medium and product based on region identification, relate to the field of medical technology, the method comprises: acquiring anatomical region image data; input the anatomical region image data to the preset anatomical positioning model, and identify the surgical target region and the safety buffer region; receive surgical instrument position data; calculate the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region; in the case where the shortest distance is less than the preset first length and greater than the preset second length, a first warning signal is issued; in the case where the shortest distance is less than the preset second length, a second warning signal is issued. By implementing the method, the surgical precision and safety can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical treatment, and in particular to a surgical early warning method and system based on region identification, a medium and a product. BACKGROUND

[0002] In the process of medical surgery, accurate surgical operation is crucial for patient safety and surgical success. Errors in surgery, especially deviations when cutting key anatomical structures, can lead to serious complications, even fatal results. Therefore, developing high-precision surgical assistance technology to ensure the accurate positioning and safe control of surgical instruments during operation is an important task in the medical field.

[0003] Currently, most surgical assistance systems rely on high-quality images and the experience of doctors, that is, in the process of surgery, the surgical assistance system tracks the position of the surgical instrument through medical imaging devices (such as MRI or CT scans), and the doctor needs to continuously monitor the imaging screen and judge the position of the surgical instrument relative to the surgical target area according to visual information to avoid injuring non-target tissues.

[0004] Although the surgical assistance systems in the related art provide a certain degree of protection for surgical safety, they still have some limitations in actual operation. Since the doctor needs to rely on personal experience to interpret images in real time, this dependence may lead to misjudgment due to doctor fatigue or distraction, thereby affecting the accuracy and safety of surgery. SUMMARY

[0005] The present application provides a surgical early warning method and system based on region identification, a medium and a product for improving surgical accuracy and safety.

[0006] In a first aspect, the present application provides a surgical early warning method based on region identification, applied to a surgical assistance system, the method comprising: acquiring anatomical region image data; inputting the anatomical region image data into a preset anatomical positioning model to identify a surgical target region and a safety buffer region, the surgical target region representing a region that needs to be cut, and the safety buffer region representing a region that limits the contact of a surgical instrument, the safety buffer region surrounding the surgical target region, and the distance difference between the outer boundary of the safety buffer region and the outer boundary of the surgical target region being a preset length; receiving surgical instrument position data; calculating the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region; in the case that the shortest distance is less than a preset first length and greater than a preset second length, issuing a first warning signal; in the case that the shortest distance is less than the preset second length, issuing a second warning signal, the intensity of the second warning signal being higher than that of the first warning signal.

[0007] By adopting the technical scheme, the surgical auxiliary system identifies the surgical target region and automatically generates the safety buffer region, and then monitors the shortest distance between the surgical instrument and the safety buffer region in real time. When the shortest distance is less than the preset first length and greater than the preset second length, a first early warning signal is sent, and when the shortest distance is less than the preset second length, a second early warning signal stronger than the first early warning signal is sent. By establishing a double-layer early warning mechanism, a hierarchical early warning signal is sent in time when the surgical instrument approaches the safety buffer region, thereby effectively reducing the risk of surgery. This progressive early warning mechanism avoids the subjectivity of the traditional method which completely relies on the experience of the doctor, and can help the doctor adjust the operation in time through early warning signals of different intensities, thereby significantly improving the accuracy and safety of the surgery.

[0008] In some embodiments of the first aspect, the inputting of the anatomical region image data into the preset anatomical positioning model to identify the surgical target region and the safety buffer region specifically comprises: pre-processing the anatomical region image data to obtain a standardized anatomical region image matrix; determining surgical feature information in the standardized anatomical region image matrix based on a feature extraction network in the anatomical positioning model, the anatomical positioning model comprising the feature extraction network and a region segmentation network; inputting the surgical feature information into the region segmentation network to obtain the surgical target region; and generating the safety buffer region based on the preset length on the periphery of the surgical target region, the inner boundary of the safety buffer region coinciding with the outer boundary of the surgical target region.

[0009] By adopting the technical scheme, first, the surgical auxiliary system pre-processes the anatomical region image data to obtain a standardized anatomical region image matrix, so as to reduce data difference interference. Second, the surgical auxiliary system cooperates the feature extraction network and the region segmentation network in the anatomical positioning model to effectively extract surgical feature information and accurately divide the surgical target region, thereby improving the accuracy and reliability of region identification. Third, the surgical auxiliary system generates the safety buffer region based on the preset length on the periphery of the surgical target region, thereby clearly defining the safety operation boundary, effectively preventing the surgical instrument from exceeding the range and causing damage to the surrounding tissue during surgery, and ensuring the safety of the surgery. At the same time, the automatic identification and region generation process significantly improves the efficiency of surgical planning compared with the traditional manual method, which helps the doctor to more efficiently formulate the surgical strategy, and improves the quality and safety of the surgery as a whole.

[0010] In some embodiments in combination with the first aspect, in some embodiments, the calculating the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region specifically comprises: extracting first point cloud data of the surgical instrument from the surgical instrument position data; determining second point cloud data of the outer boundary of the safety buffer region; calculating the Euclidean distance from each point in the first point cloud data to the nearest point in the second point cloud data; and taking the minimum Euclidean distance as the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region.

[0011] By adopting the above technical solution, the surgical assistance system converts the surgical instrument and the outer boundary of the safety buffer region into point cloud data respectively, and then calculates the minimum Euclidean distance between the two sets of point cloud data. This not only takes into account the overall shape and pose of the surgical instrument, but also significantly improves the accuracy and real-time performance of distance calculation. This point cloud-based distance calculation method is more accurate and comprehensive than traditional distance calculation methods, providing a reliable data foundation for the triggering of the warning mechanism and further improving the safety of surgery.

[0012] In some embodiments in combination with the first aspect, in some embodiments, after the step of issuing the second warning signal, the method further comprises: predicting the movement trend of the surgical instrument according to the change trend of the shortest distance within a preset time length; pausing the running state of the surgical instrument in the case that the movement trend is towards the safety buffer region and the shortest distance is less than the preset second length; and issuing a third warning signal in the case that the movement trend is away from the safety buffer region and the shortest distance is less than the preset second length, the intensity of the third warning signal being lower than that of the second warning signal.

[0013] By adopting the above technical solution, the surgical assistance system analyzes the change trend of the shortest distance within a preset time length to predict the movement trend of the surgical instrument in advance, and takes appropriate safety measures according to the movement trend. That is, when it is found that the surgical instrument has a trend of continuing to approach the safety buffer region and the shortest distance is less than the preset second length, the surgical assistance system will immediately pause the running state of the surgical instrument, effectively preventing accidental injury. When the surgical instrument shows a trend of moving away from the safety buffer region and the shortest distance is less than the preset second length, the surgical assistance system reduces the intensity of the warning signal to avoid interfering with normal surgical operations. This trend prediction-based proactive protection mechanism not only provides a more advanced safety guarantee than simple distance warning, but also ensures the continuity and smoothness of surgical operations, greatly improving the safety of surgery.

[0014] In some embodiments in combination with the first aspect, after the step of issuing the first warning signal when the shortest distance is less than the preset first length and greater than the preset second length or issuing the second warning signal when the shortest distance is less than the preset second length, the method further comprises: recording the triggering time, duration and triggering cause of the first warning signal or / and the second warning signal; and generating a safety warning log based on the triggering time, the duration and the triggering cause.

[0015] By adopting the above technical solution, the surgical assistance system establishes complete warning records, achieving full traceability of surgical safety management. The generated safety warning log can not only be used for postoperative analysis and summary to help the medical team optimize surgical strategies, but also serve as an important basis for surgical quality assessment and medical responsibility definition. In addition, by analyzing the rules and characteristics in the safety warning log, the parameter settings of the warning mechanism can be continuously improved, making the surgical assistance system better adapt to different types of surgical needs, thereby establishing a continuously self-improving surgical safety guarantee system.

[0016] In some embodiments in combination with the first aspect, after the step of inputting the anatomical region image data into a preset anatomical positioning model to identify the surgical target region and the safety buffer region, the method further comprises: determining an anatomical structure three-dimensional mapping model based on the surgical target region and the safety buffer region; and sending the anatomical structure three-dimensional mapping model to a projection device to project the anatomical structure three-dimensional mapping model onto a display screen by the projection device.

[0017] By adopting the above technical solution, the surgical target region and the safety buffer region are visualized through real-time projection display of the anatomical structure three-dimensional mapping model, greatly improving the intuitiveness of the surgery and the accuracy of the operation, enabling the doctor to clearly see the three-dimensional structure and safety boundary of the anatomical region, greatly reducing the difficulty of interpreting two-dimensional images and reducing the cognitive burden of surgical operation.

[0018] In some embodiments in combination with the first aspect, the method further comprises: determining position information and attitude information of the surgical instrument according to the surgical instrument position data; determining dynamic trajectory data of the surgical instrument based on the position information and the attitude information; and performing spatial registration of the dynamic trajectory data and the anatomical structure three-dimensional mapping model to obtain spatial relationship data between the surgical instrument and the anatomical region.

[0019] By adopting the technical solution, the surgical auxiliary system can not only acquire the position information and attitude information of the surgical instrument in real time, but also calculate dynamic trajectory data of the surgical instrument according to the position information and the attitude information, and perform real-time spatial registration with the anatomical structure three-dimensional mapping model. This dynamic spatial relationship display enables the doctor to accurately grasp the spatial relationship of the surgical instrument relative to the anatomical region, greatly improving the accuracy of the surgical operation.

[0020] In a second aspect, an embodiment of the present application provides a surgical auxiliary system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors invoke the computer instructions to enable the surgical auxiliary system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a surgical auxiliary system, enable the surgical auxiliary system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a surgical auxiliary system, enable the surgical auxiliary system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the surgical auxiliary system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method, which will not be described here.

[0024] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. Due to the adoption of the automatic recognition based on the anatomical positioning model and the multi-level early warning mechanism, the establishment of the accurate division system of the surgical target region and the safe buffer region, and the real-time distance monitoring system based on the point cloud data, intelligent monitoring and hierarchical early warning of the position of the surgical instrument can be realized during the surgery. This effectively solves the problems in the related art that the region judgment is completely dependent on the experience of the doctor, lacks objective early warning standards, and is easy to cause misjudgment due to human factors, thereby realizing the intelligentization and standardization of the surgical safety control, significantly improving the accuracy and safety of the surgery, greatly reducing the risk of the surgery, and providing reliable technical support and safety guarantee for the doctor.

[0026] 2. Due to the adoption of motion trend prediction and active protection technology, combined with surgical instrument trajectory analysis and intelligent control method, a complete early warning record is established, so that it can actively prevent and take corresponding safety measures before danger occurs. This effectively solves the problem that the related technology can only be passive response, lacks foresight protection, and cannot trace and analyze surgical safety events, thereby realizing the whole process controllable and traceable of surgical safety management, and significantly improving the safety and reliability of surgery.

[0027] 3. Due to the adoption of three-dimensional visualization display technology and spatial registration system, combined with real-time dynamic tracking and stereoscopic projection technology, an accurate three-dimensional mapping model of the anatomical region is constructed, so that it can provide intuitive and clear surgical navigation information for doctors. This effectively solves the problem that the anatomical region display is not intuitive and the spatial relationship is difficult to grasp in the related technology, thereby realizing the accurate guidance of surgical operation, and significantly improving the efficiency and quality of surgery. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 is a schematic diagram of an entity device structure of a surgical instrument in an embodiment of the present application;

[0029] Figure 2 is another schematic diagram of an entity device structure of a surgical instrument in an embodiment of the present application;

[0030] Figure 3 is a flowchart of a surgical early warning method based on region identification in an embodiment of the present application;

[0031] Figure 4 is another flowchart of a surgical early warning method based on region identification in an embodiment of the present application;

[0032] Figure 5 is a schematic diagram of an entity device structure of a surgical auxiliary system in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be limiting to the present application. As used in the specification of the present application, the singular expression "one", "a", "the", "said" and "this" are intended to include the plural expression, unless there is clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application means any or all possible combinations of one or more listed items.

[0034] The terms "first", "second", "third", etc. are used only for descriptive purposes and do not connote or imply relative importance or a specific number of features so indicated. Thus, a feature defined with "first", "second", etc. can include one or more of that feature, and the description of the embodiments of the present application, unless otherwise stated, "a plurality" means two or more.

[0035] For the convenience of understanding, the anatomical region, the surgical target region and the safety buffer region in the embodiments of the present application are introduced as follows.

[0036] The anatomical region refers to the entire anatomical structure range related to the surgery, including the surgical target region and all related tissue structures around it. For example, if a liver tumor resection surgery is to be performed, the anatomical region includes the entire liver and the important blood vessels, bile ducts and other anatomical structures around it.

[0037] The surgical target region is a specific region in the anatomical region that needs to be operated on, i.e. the direct action site of the surgery. In the surgical target region, the surgical instrument needs to be directly contacted and operated. For example, in a liver tumor resection surgery, the surgical target region is the scope of the tumor itself and the tissue around the tumor that needs to be resected.

[0038] The safety buffer region is a transition region generated automatically outside the surgical target region, which provides a warning before the surgical instrument approaches important tissue structures. The distance from the outer boundary of the safety buffer region to the outer boundary of the surgical target region is a carefully designed safety distance (preset length), and the range of the safety buffer region is dynamically adjusted according to the different surgical target regions, usually preset with different safety buffer region widths according to different surgical types and positions.

[0039] The relationship between the anatomical region, the surgical target region and the safety buffer region is that the anatomical region contains the surgical target region and the safety buffer region, and the surgical target region is surrounded by the safety buffer region, forming a three-layer structure from inside to outside.

[0040] Please refer to Figure 1 for a schematic diagram of an entity device structure of the surgical instrument in the embodiments of the present application.

[0041] Please refer to Figure 2Fig. 2 is a schematic diagram of another embodiment of the surgical instrument in the present application, wherein the surgical instrument is an electric bone drill 1, and the electric bone drill 1 comprises a housing 6, a battery box 12, a navigation tracking device 3, and a power assembly. The battery box 12 is detachably mounted on the lower part of the housing 6. In this embodiment, the battery box 12 is mounted on the lower part of the housing 6 in the form of a sliding groove and is detachable by a button 11. In this embodiment, the battery box 12 has a wireless communication function to realize wireless communication. The navigation tracking device 3 is fixedly mounted on the tail of the electric bone drill 1. The navigation tracking device 3 further comprises a signal receiver 5. The signal receiver 5 is mounted in the housing 6 and is sealed by a rear cover 4. Four tracking reflective balls 2 are arranged on the front part of the navigation tracking device 3, and four tracking reflective balls 2 are also arranged on the rear part of the navigation tracking device 3, which are used to receive the position data of the surgical instrument. The power assembly comprises a motor 15, a bearing 7, an output shaft 8, a loose sleeve 9, and a joint shaft 10. Different functional drill bits are replaceably mounted on the joint shaft 10. A trigger 14 and a safety button 13 are arranged on the hand-held part of the housing 6. The motor 15 is a step motor or a servo motor, which is not limited herein.

[0042] The method provided in the present application is described in the following flow. Figure 3 Fig. 3 is a flowchart of the surgical pre-warning method based on region recognition in the embodiment of the present application.

[0043] S301, acquiring anatomical region image data;

[0044] The anatomical region image data refers to the digital image information obtained by medical imaging scanning of the anatomical region, which usually includes CT, MRI, ultrasound, and other multi-modal medical image data. Medical imaging scanning refers to the process of checking the internal structure of the human body by using medical imaging equipment, which can obtain two-dimensional or three-dimensional images of the internal organs and tissues of the human body.

[0045] Specifically, the surgical auxiliary system receives and stores the DICOM format image data collected by CT, MRI, and other devices through the data interface with the medical imaging equipment; or the surgical auxiliary system retrieves the historical image data of the patient from the picture archiving and communication system (PACS) of the hospital; the surgical auxiliary system can also receive the dynamic image data stream generated by the real-time imaging equipment such as intraoperative ultrasound and X-ray in real time.

[0046] S302, inputting the anatomical region image data into a preset anatomical positioning model to identify a surgical target region and a safety buffer region, the surgical target region being used to represent the region that needs to be cut, the safety buffer region being used to represent the region that limits the contact of the surgical instrument, the safety buffer region surrounding the surgical target region, and the distance difference between the outer boundary of the safety buffer region and the outer boundary of the surgical target region being a preset length;

[0047] wherein the anatomical positioning model refers to a trained deep learning model used to automatically identify and locate anatomical structures in medical images; the outer boundary refers to the outermost contour line of the region; and the preset length refers to a width of a safety buffer region pre-set according to different types of surgery and positions.

[0048] Specifically, first, the surgical assistance system pre-processes the input anatomical region image data, including image enhancement, denoising, standardization and the like; then, the surgical assistance system inputs the pre-processed anatomical region image data into a pre-trained anatomical positioning model, which extracts key anatomical features in the anatomical region image data using a feature extraction network, and accurately identifies the location and boundary of the surgical target region through a region segmentation network; thereafter, the surgical assistance system automatically generates a safety buffer region around the surgical target region according to the preset length, the inner boundary of the safety buffer region seamlessly connects with the outer boundary of the surgical target region, forming a double-layer protection mechanism; finally, the surgical assistance system visualizes the identification results to clearly display the boundaries and spatial relationships of the regions.

[0049] Optionally, generally, inputting the anatomical region image data into the preset anatomical positioning model to identify the surgical target region and the safety buffer region can be achieved by the following way: pre-processing the anatomical region image data to obtain a standardized anatomical region image matrix; determining surgical feature information in the standardized anatomical region image matrix based on a feature extraction network in the anatomical positioning model, the anatomical positioning model including the feature extraction network and the region segmentation network; inputting the surgical feature information into the region segmentation network to obtain the surgical target region; and generating the safety buffer region around the surgical target region based on the preset length, the inner boundary of the safety buffer region coinciding with the outer boundary of the surgical target region.

[0050] S303, receiving surgical instrument position data;

[0051] wherein the surgical instrument refers to a medical instrument device used in the surgical process, such as a surgical knife, surgical forceps, surgical robot, etc.; and the surgical instrument position data refers to coordinate information of the surgical instrument in three-dimensional space, including spatial position and attitude angle.

[0052] Specifically, the surgical assistance system supports multiple communication modes to receive surgical instrument position data:

[0053] (1) wired communication mode:

[0054] RS485 communication: differential signal transmission, strong anti-interference ability, transmission distance up to 1200 meters;

[0055] CAN bus communication: high reliability and real-time, support for multiple devices parallel communication;

[0056] Ethernet communication: transmission rate up to 1000Mbps, support TCP / IP protocol family;

[0057] (2) Wireless communication mode:

[0058] WiFi communication: support IEEE 802.11 a / b / g / n protocol, transmission rate up to 300Mbps;

[0059] Bluetooth communication: using Bluetooth 5.0 technology, transmission distance up to 100 meters;

[0060] ZigBee communication: with low power, self-organizing network characteristics, suitable for medical Internet of Things applications;

[0061] 4G / 5G communication: support remote data transmission, wide coverage.

[0062] The surgical auxiliary system collects the surgical instrument position data in real time through the optical marker points or electromagnetic sensors installed on the surgical instruments. Among them, the surgical instrument position data includes the three-dimensional coordinates (X, Y, Z) of the end of the surgical instrument in the surgical space and the attitude information such as the pitch angle, yaw angle and roll angle of the surgical instrument. The surgical auxiliary system usually adopts high-frequency sampling mode (for example, ≥60Hz) to ensure the real-time of the surgical instrument position data, and filters the original surgical instrument position data to eliminate noise interference.

[0063] S304, calculate the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer area;

[0064] Among them, the shortest distance refers to the minimum Euclidean distance from any part of the surgical instrument to the outer boundary of the safety buffer area; the Euclidean distance refers to the straight line distance between two points in three-dimensional space.

[0065] Specifically, first, the surgical auxiliary system converts the surgical instrument position data into dense surgical instrument point cloud, and the sampling point number is usually 1000-5000 to ensure the accuracy; at the same time, the surgical auxiliary system also converts the outer boundary of the safety buffer area into safety buffer area outer boundary point cloud. Then, the surgical auxiliary system calculates the Euclidean distance from each point in the surgical instrument point cloud to all points in the safety buffer area outer boundary point cloud. Next, the surgical auxiliary system selects the minimum Euclidean distance as the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer area at the current time by comparing the values of all calculated Euclidean distances. The surgical auxiliary system continuously updates the calculation process at a frequency not less than 30Hz to ensure the real-time of the shortest distance monitoring.

[0066] Optionally, generally, the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region can be calculated by: extracting first point cloud data of the surgical instrument from the surgical instrument position data; determining second point cloud data of the outer boundary of the safety buffer region; calculating the Euclidean distance from each point in the first point cloud data to the nearest point in the second point cloud data; and taking the minimum Euclidean distance as the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region.

[0067] S305, in the case where the shortest distance is less than a preset first length and greater than a preset second length, a first warning signal is issued;

[0068] The preset first length represents a distance threshold for triggering the first warning signal, and is generally set according to different surgical types. The preset second length represents a distance threshold for triggering the second warning signal, and has a value less than the preset first length. The first warning signal refers to a low-level warning prompt issued by the surgical assistance system, which can include various forms such as visual, auditory, or tactile.

[0069] Specifically, the surgical assistance system continuously compares the calculated shortest distance with the preset first length (generally 10-15 mm) and the preset second length (generally between 5-8 mm). When the shortest distance falls between the preset first length and the preset second length, the surgical assistance system automatically triggers a low-level warning mechanism (i.e., issues the first warning signal), which includes highlighting in yellow on the display interface, issuing a low-frequency warning sound (e.g., 1 time per second, 60 decibels), and generating slight vibration feedback on the surgical instrument operation interface.

[0070] S306, in the case where the shortest distance is less than the preset second length, a second warning signal is issued, which has a higher intensity than the first warning signal.

[0071] The second warning signal refers to a high-level warning prompt issued by the surgical assistance system, which can include various forms such as visual, auditory, or tactile. The intensity of the warning signal refers to the degree of perception of the warning signal, such as sound volume, flashing frequency, etc.

[0072] Specifically, when the calculated shortest distance is less than the preset second length, the surgical assistance system immediately starts a high-level warning mechanism (i.e., issues the second warning signal), which includes flashing red display on the display interface, issuing a high-frequency alarm sound (e.g., 2 times per second, 80 decibels), and generating strong vibration feedback on the surgical instrument operation interface.

[0073] By adopting the technical scheme, the surgical auxiliary system identifies the surgical target region and automatically generates the safety buffer region, and then monitors the shortest distance between the surgical instrument and the safety buffer region in real time. When the shortest distance is less than the preset first length and greater than the preset second length, a first early warning signal is sent, and when the shortest distance is less than the preset second length, a second early warning signal of a stronger intensity is sent. By establishing a double-layer early warning mechanism, a hierarchical early warning signal is sent in time when the surgical instrument approaches the safety buffer region, and the surgical risk is effectively reduced. This progressive early warning mechanism not only avoids the subjectivity of completely relying on the experience of doctors in the traditional method, but also helps doctors to adjust the surgical operation in time through early warning signals of different intensities, thereby significantly improving the accuracy and safety of the surgery.

[0074] The method provided by the embodiment will be further described in a more specific flow. Figure 4 , another flowchart of the surgical early warning method based on region identification in the embodiment of the present application.

[0075] S401, acquire anatomical region image data;

[0076] Specifically, please refer to step S301, which will not be repeated here.

[0077] S402, input the anatomical region image data into a preset anatomical positioning model to identify a surgical target region and a safety buffer region, the surgical target region being used to represent a region that needs to be cut, the safety buffer region being used to represent a region that limits contact of a surgical instrument, the safety buffer region surrounding the surgical target region, and a distance difference between an outer boundary of the safety buffer region and an outer boundary of the surgical target region being a preset length;

[0078] Specifically, please refer to step S302, which will not be repeated here.

[0079] S403, determine an anatomical structure three-dimensional mapping model based on the surgical target region and the safety buffer region;

[0080] The anatomical structure three-dimensional mapping model refers to a digital three-dimensional model constructed according to the surgical target region and the safety buffer region, and is used to represent the spatial structure and positional relationship of the anatomical region.

[0081] Specifically, first, the surgical auxiliary system acquires boundary data of the identified surgical target region and safety buffer region, then the surgical auxiliary system constructs a three-dimensional grid model based on the boundary data, and adds spatial information such as depth and volume to generate a complete anatomical structure three-dimensional mapping model. The anatomical structure three-dimensional mapping model not only contains the geometric shapes of the surgical target region and the safety buffer region, but also contains the positional relationship, depth information and other three-dimensional features of the surgical target region and the safety buffer region.

[0082] S404, send the anatomical structure three-dimensional mapping model to the projection device, so that the projection device projects the anatomical structure three-dimensional mapping model onto the display screen;

[0083] Wherein, the projection device refers to a hardware device capable of converting the anatomical structure three-dimensional mapping model into a visual image, for realizing the stereoscopic display of the anatomical structure three-dimensional mapping model; the display screen refers to a display terminal device for displaying the anatomical structure three-dimensional mapping model, for presenting intuitive surgical visual information to the doctor.

[0084] Specifically, the surgical auxiliary system transmits the constructed anatomical structure three-dimensional mapping model to the projection device. After receiving the anatomical structure three-dimensional mapping model, the projection device performs image processing and rendering calculation, and converts the anatomical structure three-dimensional mapping model into a two-dimensional anatomical structure projection image. Then, the projection device projects the two-dimensional anatomical structure projection image onto the display screen for real-time display, so that the doctor can intuitively observe the spatial distribution of the surgical target region and the safety buffer region, and provide visual guidance for surgical operation.

[0085] S405, receive surgical instrument position data;

[0086] Specifically, please refer to step S303, which will not be repeated here.

[0087] S406, determine the position information and attitude information of the surgical instrument according to the surgical instrument position data;

[0088] Wherein, the surgical instrument position data is used to represent the real-time positioning information of the surgical instrument in three-dimensional space; the position information refers to the specific coordinate value of the surgical instrument in the standard three-dimensional coordinate system, such as (x, y, z) coordinate point; the attitude information refers to the spatial orientation and inclination angle of the surgical instrument, including pitch angle, yaw angle and roll angle, etc. Parameters are used to describe the spatial direction characteristics of the surgical instrument.

[0089] Specifically, first, the surgical auxiliary system pre-processes the received surgical instrument position data, including denoising and smoothing. Then, the surgical auxiliary system converts the pre-processed surgical instrument position data into position coordinate values in the standard three-dimensional coordinate system through coordinate transformation algorithm. Next, the surgical auxiliary system calculates the three rotation angles of the surgical instrument based on the relative relationship of multiple position coordinate points through geometric calculation method, and finally obtains the complete position information and attitude information of the surgical instrument.

[0090] S407, determine the dynamic trajectory data of the surgical instrument based on the position information and the attitude information;

[0091] The dynamic trajectory data refers to time series data describing a movement path of the surgical instrument, and is used to represent continuous movement characteristics of the surgical instrument in a three-dimensional space, including a position change curve and an attitude change curve.

[0092] Specifically, first, the surgical assistance system establishes a time series database, and stores the continuously collected position information and attitude information according to timestamps. Then, the surgical assistance system smoothes the discrete position points and attitude angles by an interpolation algorithm to form a continuous movement trajectory curve. Finally, the surgical assistance system extracts features from the movement trajectory curve, calculates kinematic parameters such as velocity and acceleration, and generates complete dynamic trajectory data.

[0093] S408, spatially registering the dynamic trajectory data and the anatomical structure three-dimensional mapping model to obtain spatial relationship data of the surgical instrument and the anatomical region;

[0094] The spatial registration refers to a process of aligning the dynamic trajectory data and the anatomical structure three-dimensional mapping model in the same coordinate system; and the spatial relationship data represents spatial attribute information such as a relative position, a distance, and a direction of the surgical instrument relative to the anatomical region.

[0095] Specifically, first, the surgical assistance system establishes a unified reference coordinate system, and converts the dynamic trajectory data and the anatomical structure three-dimensional mapping model to the same coordinate system through rigid body transformation. Then, the surgical assistance system calculates a transformation matrix between the dynamic trajectory data and the anatomical structure three-dimensional mapping model through a registration algorithm to realize accurate alignment. Finally, the surgical assistance system calculates spatial relationship parameters such as distances and included angles between the surgical instrument and each part of the anatomical region based on the aligned data, and updates these spatial relationship parameters in real time to form complete spatial relationship data.

[0096] S409, calculating a shortest distance between the surgical instrument position data and an outer boundary of the safety buffer region;

[0097] Specifically, refer to step S304, which will not be repeated here.

[0098] S410, in a case where the shortest distance is less than a preset first length and greater than a preset second length, issuing a first warning signal;

[0099] Specifically, refer to step S305, which will not be repeated here.

[0100] S411, in a case where the shortest distance is less than the preset second length, issuing a second warning signal, the intensity of the second warning signal being higher than that of the first warning signal;

[0101] Specifically, refer to step S306, which will not be repeated here.

[0102] S412, predict the movement trend of the surgical instrument according to the change trend of the shortest distance within the preset time length;

[0103] The preset time length refers to a time window preset for analyzing the change of the shortest distance, for determining the time range of the analysis data; the change trend refers to the change law of the shortest distance with time, for indicating the direction and rate of the maximum distance increase or decrease; and the movement trend indicates the possible movement direction and speed characteristics of the surgical instrument in the future.

[0104] Specifically, first, the surgical assistance system collects a plurality of shortest distance samples within a preset time length (such as 1 second) to form time series data. Then, the surgical assistance system analyzes the change law of the shortest distance by a curve fitting algorithm, and calculates the direction and rate of the change of the shortest distance. Finally, the surgical assistance system uses a prediction algorithm to calculate the possible movement direction and speed of the surgical instrument at the next moment based on the change law of the current shortest distance, thereby obtaining the prediction result of the movement trend.

[0105] S413, in the case that the movement trend deviates from the safety buffer area and the shortest distance is less than the preset second length, suspending the running state of the surgical instrument;

[0106] Specifically, first, the surgical assistance system determines whether the movement trend is directed to the safety buffer area, and simultaneously checks whether the shortest distance is less than the preset second length. In the case that the above two conditions are met simultaneously, the surgical assistance system cuts off the power output to control the surgical instrument to suspend the running state, so as to make the surgical instrument stop urgently and keep the current position, wherein the running state refers to the current working state of the surgical instrument, including movement or stop.

[0107] S414, in the case that the movement trend deviates from the safety buffer area and the shortest distance is less than the preset second length, issuing a third warning signal, the strength of the third warning signal being lower than that of the second warning signal;

[0108] The third warning signal refers to the warning prompt issued by the surgical assistance system, for reminding the doctor to pay attention but not to stop operating immediately; and the strength of the third warning signal is between the strength of the second warning signal and the strength of the first warning signal.

[0109] Specifically, when the surgical assistance system determines that the shortest distance is less than the preset second length, but the movement trend indicates that the surgical instrument is moving away from the safety buffer area, a third warning signal with lower strength is issued. The third warning signal can include a lower volume of beeping sound, a slower flashing indicator light, or a smaller font size of text prompt, etc., for reminding the doctor to be cautious in the current operation.

[0110] S415, record the trigger time, duration and trigger cause of the first warning signal or / and the second early warning signal;

[0111] The trigger time refers to the specific time when the first warning signal or / and the second early warning signal starts to be emitted; the duration represents the time period during which the first warning signal or / and the second early warning signal is continuously emitted; and the trigger cause refers to the specific conditions and scene description that cause the first warning signal or / and the second early warning signal to be emitted.

[0112] Specifically, the surgical assistance system immediately records the current system time as the trigger time each time a warning signal is emitted, and records the key parameters such as the shortest distance and motion trend at the time of triggering as the trigger cause. The surgical assistance system continuously monitors the state of the warning signal until the warning signal ends, and calculates and records the duration of the entire process.

[0113] S416, generate a safety warning log based on the trigger time, the duration and the trigger cause.

[0114] The safety warning log refers to the warning event record document generated by the surgical assistance system, which is used to record and track the safety warning situation in the surgical process.

[0115] Specifically, the surgical assistance system organizes the previously recorded trigger time, duration and trigger cause and other information according to a predetermined format to generate a structured log entry. The surgical assistance system simultaneously adds relevant information such as the operation number and operation type as a log index, and stores the complete log entry into the safety warning log for subsequent query and analysis.

[0116] Due to the adoption of automatic recognition based on the anatomical positioning model and the multi-level early warning mechanism, the establishment of an accurate division system of the surgical target area and the safety buffer area, and the real-time distance monitoring system based on point cloud data, intelligent monitoring and hierarchical early warning of the position of the surgical instrument during the surgical process can be achieved. This effectively solves the problems in the related art of completely relying on the experience of doctors for area judgment, lacking objective warning standards, and being prone to misjudgment due to human factors, and further realizes the intelligentization and standardization of surgical safety control, significantly improves the accuracy and safety of the surgery, and greatly reduces the risk of surgery, providing reliable technical support and safety protection for doctors.

[0117] Due to the adoption of motion trend prediction and active protection technology, combined with surgical instrument trajectory analysis and intelligent control methods, a complete early warning record is established, so that active prevention and corresponding safety measures can be taken before danger occurs. This effectively solves the problems in the related art of only being able to respond passively, lacking predictive protection, and being unable to trace and analyze surgical safety events, and further realizes the whole-process controllability and traceability of surgical safety management, significantly improving the safety and reliability of the surgery.

[0118] Due to the adoption of the three-dimensional visual display technology and the space registration system, combined with the real-time dynamic tracking and the stereoscopic projection technology, the accurate three-dimensional mapping model of the anatomical region is constructed, so that the intuitive and clear surgical navigation information can be provided for the doctors.

[0119] The surgical auxiliary system in the embodiment of the present application is described from the perspective of hardware processing below, please refer to Figure 5 , which is a schematic diagram of an entity device structure of the surgical auxiliary system in the embodiment of the present application.

[0120] It should be noted that, Figure 5 The structure of the surgical auxiliary system shown is only an example, and should not bring any limitation to the function and use range of the embodiment of the present application.

[0121] As Figure 5 shown, the surgical auxiliary system includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in a read-only memory (ROM) 502 or the program loaded from a storage portion 508 to a random access memory (RAM) 503, such as performing the method described in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0122] The following components are connected to the I / O interface 505: an input portion 506 including an audio input device, a button switch, and the like; an output portion 507 including a liquid crystal display (LCD) and an audio output device, an indicator, and the like; a storage portion 508 including a hard disk and the like; and a communication portion 509 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 510 as needed, so that a computer program read therefrom is installed in the storage portion 508 as needed.

[0123] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising computer programs for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, various functions defined in the present application are executed.

[0124] Note that specific examples of the computer readable storage medium can include one or more of the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, the computer readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0125] The flowcharts and block diagrams in the attached drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved.

[0126] In particular, the surgical assistance system of the present embodiment includes a processor and a memory, and the memory stores a computer program which, when executed by the processor, implements the region recognition-based surgical warning method provided by the above-described embodiments.

[0127] As another aspect, the present application also provides a computer readable storage medium, which can be included in the surgical assistance system described in the above embodiments, or can exist independently without being assembled into the surgical assistance system. The storage medium carries one or more computer programs, which, when executed by a processor of the surgical assistance system, cause the surgical assistance system to implement the surgical warning method based on region recognition provided in the above embodiments.

[0128] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; even though the present application has been described in detail with reference to the foregoing embodiments, those ordinarily skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0129] In the above embodiments, according to the context, the term "when" can be interpreted as meaning "if" or "after" or "in response to determining" or "in response to detecting". Similarly, according to the context, the phrase "upon determining" or "if detecting (the stated condition or event)" can be interpreted as meaning "if determining" or "in response to determining" or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)".

[0130] Those ordinarily skilled in the art can understand that all or part of the processes in the above method embodiments can be instructed by a computer program to relevant hardware, and the program can be stored in a computer readable storage medium, and when executed, can include the processes of the above method embodiments. The foregoing storage medium includes ROM or random storage memory RAM, magnetic disc or optical disc, and various program code storage media.

Claims

1. A surgical early warning method based on region recognition, characterized in that, The method is applied to a surgical auxiliary system, and the method comprises: acquiring anatomical region image data; inputting the anatomical region image data into a preset anatomical positioning model to identify a surgical target region and a safety buffer region, the surgical target region is used to represent a region that needs to be cut, the safety buffer region is used to represent a region that limits contact of a surgical instrument, the safety buffer region surrounds the surgical target region, and a distance difference between an outer boundary of the safety buffer region and an outer boundary of the surgical target region is a preset length; receiving surgical instrument position data; calculating a shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region; in a case where the shortest distance is less than a preset first length and greater than a preset second length, issuing a first early warning signal; and in a case where the shortest distance is less than the preset second length, issuing a second early warning signal, the second early warning signal has a higher intensity than the first early warning signal. The calculating of the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region specifically comprises: extracting first point cloud data of the surgical instrument from the surgical instrument position data; determining second point cloud data of the outer boundary of the safety buffer region; calculating a Euclidean distance from each point in the first point cloud data to a nearest point in the second point cloud data; and taking a minimum Euclidean distance as the shortest distance between the surgical instrument position data and the outer boundary of the safety buffer region. After the step of issuing the second early warning signal in the case where the shortest distance is less than the preset second length, the method further comprises: predicting a movement trend of the surgical instrument according to a change trend of the shortest distance within a preset time length; in a case where the movement trend deviates towards the safety buffer region and the shortest distance is less than the preset second length, pausing a running state of the surgical instrument; and in a case where the movement trend deviates away from the safety buffer region and the shortest distance is less than the preset second length, issuing a third early warning signal, the third early warning signal has a lower intensity than the second early warning signal.

2. The method of claim 1, wherein, The inputting of the anatomical region image data into the preset anatomical positioning model to identify the surgical target region and the safety buffer region specifically comprises: pre-processing the anatomical region image data to obtain a standardized anatomical region image matrix; determining surgical feature information in the standardized anatomical region image matrix based on a feature extraction network in the anatomical positioning model, the anatomical positioning model comprising the feature extraction network and a region segmentation network; inputting the surgical feature information into the region segmentation network to obtain the surgical target region; and based on the preset length, generating the safety buffer region at a periphery of the surgical target region, an inner boundary of the safety buffer region coincides with an outer boundary of the surgical target region.

3. The method of claim 1, wherein, The method further comprises: recording a triggering time, a duration and a triggering cause of the first warning signal or / and the second warning signal; and generating a safety warning log based on the triggering time, the duration and the triggering cause.

4. The method of claim 1, wherein, The method further comprises: determining position information and attitude information of the surgical instrument according to the surgical instrument position data; determining dynamic trajectory data of the surgical instrument based on the position information and the attitude information; and performing spatial registration of the dynamic trajectory data and the anatomical structure three-dimensional mapping model to obtain spatial relationship data of the surgical instrument and the anatomical region.

5. The method of claim 4, wherein, The surgical assistance system comprises one or more processors and a memory; the memory is coupled to the one or more processors; the memory is configured to store computer program codes, the computer program codes comprising computer instructions; and the one or more processors are configured to invoke the computer instructions to cause the surgical assistance system to perform the method according to any one of claims 1 to 5.

6. A surgical auxiliary system, characterized by, The instructions, when executed on the surgical assistance system, cause the surgical assistance system to perform the method according to any one of claims 1 to 5.

7. A computer-readable storage medium comprising instructions, wherein, The computer program product, when executed on the surgical assistance system, causes the surgical assistance system to perform the method according to any one of claims 1 to 5.

8. A computer program product, characterised in that, ​

Images