Gynecological and obstetrical operation intelligent monitoring system based on sensor

Abstract

The invention relates to the technical field of medical monitoring and assistance, in particular to a sensor-based intelligent monitoring system for obstetrical and gynecological operations, which comprises a multi-source sensing module, a feature fusion module, a mode recognition module, a collaborative early warning module and a decision output module, wherein the multi-source sensing module is used for outputting an instrument movement track, a uterine cavity pressure waveform, a fetal electrocardiosignal and a surgical field video stream; the feature fusion module is used for generating a multi-dimensional feature matrix; the mode recognition module is used for outputting an instrument risk label and a fetus risk level; the collaborative early warning module is used for generating a multi-level early warning instruction containing the coordinates of the risk part; and the decision output module is used for forming a dynamically updated safe operation boundary diagram and displaying the safe operation boundary diagram on the surgical field video stream in an overlapping manner. According to the invention, through a multi-source sensing and collaborative early warning mechanism, synchronous monitoring and dynamic risk prompting of operation behaviors and physiological states in the obstetrics and gynecology surgery are realized, and the safety management and control capability in the surgery is improved.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring and auxiliary technology, and in particular to a sensor-based intelligent monitoring system for obstetric and gynecological surgeries. Background Technology

[0002] During obstetric and gynecological surgeries, doctors need to pay attention to both the operation of surgical instruments and the physiological response of the patient (including the fetus). Any operational errors or physiological abnormalities that are not detected in time may lead to intraoperative risks.

[0003] Currently, most surgeries rely on doctors' experience for real-time judgment, lacking systematic, data-driven risk monitoring methods. Furthermore, existing equipment often only collects single types of sensor data, failing to achieve collaborative perception and dynamic early warning of multi-source information, and is insufficient to meet the actual needs of intraoperative safety intervention in complex scenarios. Therefore, there is an urgent need for a sensor-based intelligent monitoring system for obstetric and gynecological surgeries to provide real-time perception and intervention prompts for the surgical status. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a sensor-based intelligent monitoring system for obstetric and gynecological surgeries.

[0005] A sensor-based intelligent monitoring system for obstetric and gynecological surgeries includes a multi-source sensing module, a feature fusion module, a pattern recognition module, a collaborative early warning module, and a decision output module; wherein: Multi-source sensing module: includes sensor arrays configured on surgical instruments and the patient's body surface, which respectively output instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream; Feature fusion module: used to receive instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream, and synchronously map various types of information to a unified spatiotemporal coordinate system through spatiotemporal stamp alignment to generate a multi-dimensional feature matrix; Pattern recognition module: used to receive a multi-dimensional feature matrix, identify abnormal movement patterns of the device and fetal distress characteristics based on a preset threshold, and output device risk labels and fetal risk levels; Collaborative early warning module: Receives device risk labels and fetal risk levels, and generates multi-level early warning instructions containing the coordinates of risk sites based on a pre-loaded operation-physiology association rule base; Decision output module: It is used to receive multi-level early warning instructions, combine the current surgical stage information to generate a dynamically updated safety operation boundary map, overlay it on the surgical field video stream and output it to the display terminal.

[0006] Optionally, the multi-source sensing module includes a transmission state sensing unit, a uterine pressure detection unit, a fetal electrocardiogram monitoring unit, and a surgical field video acquisition unit: wherein: Transmission state sensing unit: It is configured at each motion node of the surgical instrument and collects the acceleration, angular velocity and attitude angle change data of the instrument through an integrated inertial measurement unit, and outputs the instrument motion trajectory after coordinate fusion calculation; Intrauterine pressure detection unit: It is attached to the patient's intrauterine catheter interface and collects changes in intrauterine pressure in real time through an embedded micro-pressure sensor, and outputs a standardized intrauterine pressure waveform sequence; Fetal ECG monitoring unit: It is used to adhere to the surface of the pregnant woman's abdomen and collect fetal ECG signals through a multi-lead electrode array; Surgical field video acquisition unit: It is fixedly installed near the surgical lighting device, and uses a high-definition wide-angle camera to acquire surgical field images in real time and output a time-synchronized surgical field video stream.

[0007] Optionally, the feature fusion module includes a data preprocessing unit, a spatiotemporal alignment unit, and a feature matrix generation unit; wherein: Data preprocessing unit: used to receive instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream respectively, and perform noise reduction, completion and time series standardization processing on different types of data; Spatiotemporal alignment unit: used to introduce timestamps and spatial markers in a unified format into the preprocessed data, realize the temporal alignment of multimodal data through interpolation and synchronous resampling, and map all data to a unified spatiotemporal coordinate system based on the spatial coordinate reference of the surgical field video stream; Feature matrix generation unit: It receives aligned data, encodes it into multi-dimensional feature vectors according to a preset format, and combines them in chronological order to generate a multi-dimensional feature matrix with a unified structure.

[0008] Optionally, the spatiotemporal alignment unit includes: The time interpolation and completion subunit is used to perform linear interpolation on data segments with missing timestamps or inconsistent sampling in the received instrument motion trajectory, intrauterine pressure waveform, and fetal electrocardiogram signal to construct a complete time series. Synchronous resampling subunit: Used to uniformly sample multi-source data after interpolation according to a set sampling period. Perform synchronous resampling to generate timestamp-aligned data sequences, ensuring that all data types have synchronous observations at each time point; Spatial mapping subunit: Used to map three-dimensional spatial points in the instrument motion trajectory to image plane coordinates using the image coordinates in the surgical field video stream as a reference and through a coordinate transformation function.

[0009] Optionally, the pattern recognition module includes a device motion analysis unit, a fetal physiological state assessment unit, and a risk labeling output unit; wherein: Instrument motion analysis unit: used to receive feature sub-vectors of instrument motion trajectory from multi-dimensional feature matrix, extract continuous change values ​​of velocity, acceleration and angular velocity, and compare them with corresponding safety thresholds to determine whether there is violent operation, abnormal shaking or angular deviation. Fetal physiological state assessment unit: used to extract fetal electrocardiogram signal features from a multidimensional feature matrix, including heart rate variability. Late deceleration characteristics The fetal distress is determined to exist if it is compared with the preset normal reference range and deceleration threshold; if any of the following conditions are met. Condition 1, ; Condition 2, ;in, Indicates current heart rate variability; Indicates the total deceleration rate during the evening period per unit time; These represent the upper and lower limits of the normal variation range; The threshold for determining deceleration; Risk Labeling Output Unit: Used to map the identification results of the device motion analysis unit and the fetal physiological status assessment unit into device risk labels, respectively. and fetal risk level .

[0010] Optionally, the risk labeling output unit includes: Device Risk Classification Subunit: This subunit receives motion anomaly flags output by the device motion analysis unit and generates a corresponding risk level based on the number of abnormal parameters exceeding limits. The risk level is determined using the following mapping function: ;in, This indicates the number of instrument speed, acceleration, and angular velocity parameters that exceed the threshold within the current time window; Labels indicating the risk level of instrument operation; Fetal Risk Scoring Subunit: Used to receive heart rate variability output from the fetal physiological status assessment unit. and late deceleration magnitude Calculate fetal risk score ; Tag generation subunit: used to score fetal risk The mapping is to fetal risk level labels, and the mapping function is: ;in, A score used to classify the risk level of the fetus; This indicates the risk level of the fetus's physiological state.

[0011] Optionally, the collaborative early warning module includes a rule matching unit, a joint judgment unit, and an instruction generation unit; wherein: Rule matching unit: Used to receive device risk labels and fetal risk levels, and retrieve matching rule entries from the pre-loaded operation-physiology association rule base; Joint Judgment Unit: Used to perform joint condition evaluation on the matched rule entries, determine whether the current surgical status triggers the warning mechanism of level 1, 2 or 3 risk level, and extract the response elements specified in the rule accordingly, including the high-risk instrument movement area, the corresponding surgical field image coordinate area and the risk propagation path; Instruction generation unit: Based on the response elements output by the joint judgment unit, it generates structured multi-level early warning instructions, including risk level identifiers, location coordinates of risk sites in image space, recommended intervention operation prompts, and time sequence annotations of the target surgical stage.

[0012] Optionally, the rule matching unit includes: Tag Combination Parsing Subunit: Used to receive device risk tags Fetal risk level The two are combined into a joint risk index key according to a preset format. ; Index locator subunit: used to receive the joint risk index key Search for related rules in the operation-physiology association rule base. The corresponding rule index entries; Rule invocation subunit: used to extract the corresponding rule content based on the index results. The rule content includes joint risk level, associated site number, response strategy level and surgical stage adaptation conditions.

[0013] Optionally, the joint determination unit includes: Stage matching subunit: Used to receive the current surgical status information and extract the surgical stage identifier. Compare the applicable surgical stages recorded in the rule entries. ,when If the current rule is deemed valid, the warning level assessment can continue; otherwise, the corresponding rule entry is ignored. Condition-triggered discrimination subunit: Under the premise that the stage match is met, compare the current device risk labels. Fetal risk level Whether it falls within the scope of the joint risk combination set in the rule entry; if it matches, it is determined to be in a triggered state. Risk Level Confirmation Subunit: When a rule is triggered, the joint risk level field in the rule entry is read and the current warning level is determined according to the following mapping method: When the combined risk level is low risk, the warning level is confirmed as Level 1 warning. When the combined risk level is medium risk, the warning level is confirmed as Level II warning. When the combined risk level is high risk or extremely high risk, the warning level is confirmed as Level III warning.

[0014] Optionally, the decision output module includes a boundary generation unit, a layer overlay unit, and a terminal output unit; wherein: Boundary generation unit: Receives multi-level early warning instructions and current surgical stage information, combines the risk coordinate range corresponding to the early warning level with the stage operation specifications, generates a safe operation boundary map, and updates its spatial area and color markings in real time; Layer overlay unit: used to map the safety operation boundary map as a transparent layer and overlay it onto the surgical field video stream according to the image coordinate alignment, so that the boundary display is synchronized with the real-time picture; Terminal output unit: Encodes and outputs the superimposed video stream to the display terminal for real-time reference by the operator during the operation.

[0015] The beneficial effects of this invention are: This invention, by constructing a multi-source sensing module, enables real-time acquisition of surgical instrument movement trajectories, intrauterine pressure waveforms, fetal electrocardiogram signals, and surgical field video streams. Combined with a feature fusion module and a pattern recognition module, it can achieve unified perception and risk identification of intraoperative operations and physiological states, solving the problem of single data sources and inability to make collaborative judgments in traditional surgical monitoring.

[0016] This invention, through the linkage mechanism of the collaborative early warning module and the decision output module, dynamically generates multi-level early warning instructions by combining the operation-physiology association rule base, and overlays and displays the safe operation boundary map onto the surgical field video stream, thereby realizing real-time visual prompts for high-risk areas and effectively improving the timeliness and accuracy of intraoperative risk intervention. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of an intelligent monitoring system for obstetric and gynecological surgeries according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the collaborative early warning module according to an embodiment of the present invention. Detailed Implementation

[0019] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0020] It should be noted that the use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0021] Generally, terms can be understood at least partly from their use in context. For example, depending at least partly on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood not necessarily to convey an exclusive set of factors, but rather, alternatively, depending at least partly on the context, to allow for the presence of other factors that are not necessarily explicitly described.

[0022] like Figures 1-2 As shown, a sensor-based intelligent monitoring system for obstetric and gynecological surgery includes a multi-source sensing module, a feature fusion module, a pattern recognition module, a collaborative early warning module, and a decision output module; wherein: Multi-source sensing module: includes sensor arrays configured on surgical instruments and the patient's body surface, which respectively output instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream; Feature fusion module: used to receive instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream, and synchronously map various types of information to a unified spatiotemporal coordinate system through spatiotemporal stamp alignment to generate a multi-dimensional feature matrix; Pattern recognition module: used to receive a multi-dimensional feature matrix, identify abnormal movement patterns of the device and fetal distress characteristics based on a preset threshold, and output device risk labels and fetal risk levels; Collaborative early warning module: Receives device risk labels and fetal risk levels, and generates multi-level early warning instructions containing the coordinates of risk sites based on a pre-loaded operation-physiology association rule base; Decision output module: It is used to receive multi-level early warning instructions, combine the current surgical stage information to generate a dynamically updated safety operation boundary map, overlay it on the surgical field video stream and output it to the display terminal.

[0023] The multi-source sensing module includes a transmission status sensing unit, a uterine pressure detection unit, a fetal electrocardiogram monitoring unit, and a surgical field video acquisition unit: where: Transmission state sensing unit: It is configured at each motion node of the surgical instrument and collects the acceleration, angular velocity and attitude angle change data of the instrument through an integrated inertial measurement unit (IMU), and outputs the instrument motion trajectory after coordinate fusion calculation; Intrauterine pressure detection unit: It is attached to the patient's intrauterine catheter interface and collects changes in intrauterine pressure in real time through an embedded micro-pressure sensor, and outputs a standardized intrauterine pressure waveform sequence; Fetal ECG monitoring unit: It is used to adhere to the surface of the pregnant woman's abdomen and collect fetal ECG signals through a multi-lead electrode array; Surgical field video acquisition unit: It is fixedly installed near the surgical lighting device, and uses a high-definition wide-angle camera to acquire surgical field images in real time and output a time-synchronized surgical field video stream. Through the collaborative work of the above units, high-precision real-time perception of key physiological parameters and operational behaviors during the operation is achieved, providing structured raw data support for subsequent feature fusion and risk identification, and improving the system's ability to accurately perceive complex surgical conditions.

[0024] The feature fusion module includes a data preprocessing unit, a spatiotemporal alignment unit, and a feature matrix generation unit; wherein: Data preprocessing unit: used to receive instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream respectively, and to perform noise reduction, completion and time series standardization processing on different types of data to ensure the consistency of various types of data in the time dimension; Spatiotemporal alignment unit: used to introduce timestamps and spatial markers in a unified format into the preprocessed data, realize the temporal alignment of multimodal data through interpolation and synchronous resampling, and map all data to a unified spatiotemporal coordinate system based on the spatial coordinate reference of the surgical field video stream; Feature matrix generation unit: This unit receives aligned data, encodes it into multi-dimensional feature vectors according to a preset format, and combines them in chronological order to generate a multi-dimensional feature matrix with a unified structure. Each row of the feature matrix represents the fusion state of four types of perceptual information at the same time point. The output is a standardized input dataset for subsequent recognition and analysis. Through the collaborative processing of the above units, efficient fusion of multi-source heterogeneous perceptual data at a unified spatiotemporal scale is achieved, enhancing the system's overall perception capability of complex surgical dynamic states and ensuring the accurate extraction of surgical risk features by the subsequent recognition module.

[0025] The spatiotemporal alignment unit includes: The time interpolation and completion subunit is used to perform linear interpolation on data segments with missing timestamps or inconsistent sampling in the received instrument motion trajectory, intrauterine pressure waveform, and fetal electrocardiogram signal to construct a complete time series. The interpolation function satisfies the following expression: ,in, Indicates the time point to be interpolated Physiological or operational data values ​​below; Representing time points The adjacent known data values ​​below; Given a timestamp, satisfying ; Synchronous resampling subunit: Used to uniformly sample multi-source data after interpolation according to a set sampling period. Perform synchronous resampling to generate timestamp-aligned data sequences, ensuring that all data types have synchronous observations at each time point; Spatial mapping subunit: Used to map three-dimensional spatial points in the instrument movement trajectory to image plane coordinates based on the image coordinates in the surgical field video stream, through a coordinate transformation function. The transformation process uses the following projection formula: ; in, The coordinates of the device at a certain moment in its motion trajectory; These are the corresponding image plane coordinates after mapping; This is the intrinsic parameter matrix of the surgical field camera; This is the rotation matrix of the camera relative to the surgical area; This is the translation vector of the camera relative to the surgical area. Through the division of labor and cooperation of the above sub-units, it is possible to achieve precise synchronization of different types of data in the time dimension, and to complete the position mapping by uniformly referring to the surgical field image reference coordinate system in the spatial dimension, so as to provide a unified spatiotemporal structure input basis for subsequent multimodal fusion.

[0026] The pattern recognition module includes a device motion analysis unit, a fetal physiological state assessment unit, and a risk labeling output unit; among which: Instrument Motion Analysis Unit: Receives feature sub-vectors related to the instrument's motion trajectory from the multi-dimensional feature matrix, extracts continuous changes in velocity, acceleration, and angular velocity, and compares them with corresponding safety thresholds to determine if there is any violent operation, abnormal shaking, or angular deviation. Abnormal motion is determined if one of the following conditions is met: ;in, These represent the current velocity, acceleration, and angular velocity of the instrument, respectively. The preset corresponding motion safety threshold; Fetal physiological state assessment unit: used to extract fetal electrocardiogram signal features from a multidimensional feature matrix, including heart rate variability. Late deceleration characteristics The fetal distress is determined to exist if it is compared with the preset normal reference range and deceleration threshold; if any of the following conditions are met. Condition 1, ; Condition 2, ;in, Indicates current heart rate variability; Indicates the total deceleration rate during the evening period per unit time; These represent the upper and lower limits of the normal variation range; The threshold for determining deceleration; Risk Labeling Output Unit: Used to map the identification results of the device motion analysis unit and the fetal physiological status assessment unit into device risk labels, respectively. and fetal risk level Through the collaborative processing of the above units, the risk of instrument operation and the abnormal physiological state of the fetus can be accurately determined based on real-time data during the operation, providing criterion support for the subsequent generation of multi-level early warning instructions and dynamic decision-making, and ensuring that the monitoring system has real-time and sensitivity.

[0027] The risk labeling output unit includes: Device Risk Classification Subunit: This subunit receives motion anomaly flags output by the device motion analysis unit and generates corresponding risk levels based on the number of abnormal parameters exceeding limits. The risk level is determined using the following mapping function: ;in, This indicates the number of instrument speed, acceleration, and angular velocity parameters that exceed the threshold within the current time window; The label indicates the risk level of the instrument operation; the higher the value, the more improper the operation. Fetal Risk Scoring Subunit: Used to receive heart rate variability output from the fetal physiological status assessment unit. and late deceleration magnitude Calculate fetal risk score The formula is as follows: ,in, This indicates the fetal heart rate variability at the current moment. This is a normal reference value; Indicates the magnitude of late-stage deceleration; Weighting factors set for experience; This represents the fetal risk score; a higher score indicates a greater potential risk. Tag generation subunit: used to score fetal risk The mapping is to fetal risk level labels, and the mapping function is: ;in, A score used to classify the risk level of the fetus; The risk level of the fetus's physiological state is indicated, with higher levels indicating more severe physiological abnormalities. Through the structured division of labor among the above sub-units, risk labels can be assigned to both instrument operation behavior and fetal physiological state, completing the entire process from quantitative assessment to level mapping, and providing a stable and clearly structured risk input data foundation for the system's early warning module.

[0028] The collaborative early warning module includes a rule matching unit, a joint judgment unit, and an instruction generation unit; among which: Rule matching unit: Used to receive device risk labels and fetal risk levels, and retrieve and combine matching rule entries in the pre-loaded operation-physiology association rule base. The rule entries include device risk level ranges, fetal risk level ranges and their corresponding joint response strategies, ensuring that rule matching is based on risk collaborative judgment logic in the context of dynamic surgery. Joint Judgment Unit: Used to perform joint condition evaluation on the matched rule entries, determine whether the current surgical status triggers the warning mechanism of level 1, 2 or 3 risk level, and extract the response elements specified in the rule accordingly, including the high-risk instrument movement area, the corresponding surgical field image coordinate area and the risk propagation path; Instruction generation unit: Based on the response elements output by the joint decision unit, it generates structured multi-level early warning instructions, including risk level identifiers, location coordinates of risk sites in image space, recommended intervention operation prompts, and time sequence annotations of the target surgical stage, and outputs them uniformly to the decision output module. Through the synergistic effect of the above units, the collaborative early warning module can efficiently generate visualized risk prompts based on real-time data and established rules in complex surgical scenarios, providing doctors with clear, intuitive, and hierarchical auxiliary decision-making information and improving the safety control capabilities during the surgical process.

[0029] The rule matching unit includes: Tag Combination Parsing Subunit: Used to receive device risk tags Fetal risk level The two are combined into a joint risk index key according to a preset format. This index key is used to uniquely identify the risk intersection between the operation and the physiological state, and serves as the query entry point for subsequent rule retrieval. Index locator subunit: used to receive the joint risk index key Search for related rules in the operation-physiology association rule base. The corresponding rule index entries are organized using a multi-dimensional hash structure in the rule base to ensure efficient retrieval; Rule Invocation Subunit: Used to extract the corresponding rule content based on the index results. The rule content includes the joint risk level, associated site number, response strategy level and surgical stage adaptation conditions, and outputs the rule content to the joint decision unit.

[0030] Table 1 Operation-Physiological Association Rule Base In Table 1 above, the joint risk index key Device risk label and fetal risk level Combined generation, used to uniquely index a rule; medical device risk label The range of values ​​is This represents the risk level of the operational behavior; fetal risk level. The range of values ​​is This indicates the risk level of the fetal physiological state; the combined risk level is based on... and The combined judgment results are classified into low, medium, high, and very high; the risk site number corresponds to the high-risk operation area number marked in the surgical field; the larger the response strategy level value, the stronger the warning strategy (such as whether to interrupt the operation or switch surgical procedures); the applicable surgical stage rule applies to the surgical process node; the risk coordinate range represents the area marked in the image space that needs to be highlighted, with the unit being the pixel coordinate interval.

[0031] The joint decision unit includes: Stage matching subunit: Used to receive the current surgical status information and extract the surgical stage identifier. Compare the applicable surgical stages recorded in the rule entries. ,when If the current rule is deemed valid, the warning level assessment can continue; otherwise, the corresponding rule entry is ignored. Condition-triggered discrimination subunit: Under the premise that the stage match is met, compare the current device risk labels. Fetal risk level Whether it falls within the scope of the joint risk combination set in the rule entry; if it matches, it is determined to be in a triggered state. Risk Level Confirmation Subunit: When a rule is triggered, the joint risk level field in the rule entry is read and the current warning level is determined according to the following mapping method: When the combined risk level is low risk, the warning level is confirmed as Level 1 warning. When the combined risk level is medium risk, the warning level is confirmed as Level II warning. When the combined risk level is high risk or extremely high risk, the warning level is confirmed as Level 3 warning. Through the above sub-unit linkage processing, the joint judgment unit can ensure the consistency of rule adaptation, status recognition and level confirmation, thereby realizing a dynamic warning triggering mechanism driven by multiple risk factors, which helps to improve the system's real-time response capability to complex surgical abnormalities.

[0032] The decision output module includes a boundary generation unit, a layer overlay unit, and a terminal output unit; wherein: Boundary generation unit: Receives multi-level early warning instructions and current surgical stage information, combines the risk coordinate range corresponding to the early warning level with the stage operation specifications, generates a safe operation boundary map, and updates its spatial area and color markings in real time; Layer overlay unit: used to map the safety operation boundary map as a transparent layer and overlay it onto the surgical field video stream according to the image coordinate alignment, so that the boundary display is synchronized with the real-time picture; Terminal output unit: The superimposed video stream is encoded and output to the display terminal for real-time reference by the operator during surgery; through the collaboration of the above units, dynamic visualization prompts of surgical risk areas are realized, improving intuitive perception and operational safety during surgery.

[0033] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0034] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A sensor-based intelligent monitoring system for obstetric and gynecological surgeries, characterized in that, It includes a multi-source sensing module, a feature fusion module, a pattern recognition module, a collaborative early warning module, and a decision output module; among which: Multi-source sensing module: includes sensor arrays configured on surgical instruments and the patient's body surface, which respectively output instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream; Feature fusion module: used to receive instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream, and synchronously map various types of information to a unified spatiotemporal coordinate system through spatiotemporal stamp alignment to generate a multi-dimensional feature matrix; Pattern recognition module: used to receive a multi-dimensional feature matrix, identify abnormal movement patterns of the device and fetal distress characteristics based on a preset threshold, and output device risk labels and fetal risk levels; Collaborative early warning module: Receives device risk labels and fetal risk levels, and generates multi-level early warning instructions containing the coordinates of risk sites based on a pre-loaded operation-physiology association rule base; Decision output module: It is used to receive multi-level early warning instructions, combine the current surgical stage information to generate a dynamically updated safety operation boundary map, overlay it on the surgical field video stream and output it to the display terminal.

2. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 1, characterized in that, The multi-source sensing module includes a transmission state sensing unit, a uterine pressure detection unit, a fetal electrocardiogram monitoring unit, and a surgical field video acquisition unit: wherein: Transmission state sensing unit: It is configured at each motion node of the surgical instrument and collects the acceleration, angular velocity and attitude angle change data of the instrument through an integrated inertial measurement unit, and outputs the instrument motion trajectory after coordinate fusion calculation; Intrauterine pressure detection unit: It is attached to the patient's intrauterine catheter interface and collects changes in intrauterine pressure in real time through an embedded micro-pressure sensor, and outputs a standardized intrauterine pressure waveform sequence; Fetal ECG monitoring unit: It is used to adhere to the surface of the pregnant woman's abdomen and collect fetal ECG signals through a multi-lead electrode array; Surgical field video acquisition unit: It is fixedly installed near the surgical lighting device, and uses a high-definition wide-angle camera to acquire surgical field images in real time and output a time-synchronized surgical field video stream.

3. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 1, characterized in that, The feature fusion module includes a data preprocessing unit, a spatiotemporal alignment unit, and a feature matrix generation unit; wherein: Data preprocessing unit: used to receive instrument movement trajectory, intrauterine pressure waveform, fetal electrocardiogram signal and surgical field video stream respectively, and perform noise reduction, completion and time series standardization processing on different types of data; Spatiotemporal alignment unit: used to introduce timestamps and spatial markers in a unified format into the preprocessed data, realize the temporal alignment of multimodal data through interpolation and synchronous resampling, and map all data to a unified spatiotemporal coordinate system based on the spatial coordinate reference of the surgical field video stream; Feature matrix generation unit: It receives aligned data, encodes it into multi-dimensional feature vectors according to a preset format, and combines them in chronological order to generate a multi-dimensional feature matrix with a unified structure.

4. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 1, characterized in that, The spatiotemporal alignment unit includes: The time interpolation and completion subunit is used to perform linear interpolation on data segments with missing timestamps or inconsistent sampling in the received instrument motion trajectory, intrauterine pressure waveform, and fetal electrocardiogram signal to construct a complete time series. Synchronous resampling subunit: Used to uniformly sample multi-source data after interpolation according to a set sampling period. Perform synchronous resampling to generate timestamp-aligned data sequences, ensuring that all data types have synchronous observations at each time point; Spatial mapping subunit: Used to map three-dimensional spatial points in the instrument motion trajectory to image plane coordinates using the image coordinates in the surgical field video stream as a reference and through a coordinate transformation function.

5. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 1, characterized in that, The pattern recognition module includes a device motion analysis unit, a fetal physiological state assessment unit, and a risk labeling output unit; wherein: Instrument motion analysis unit: used to receive feature sub-vectors of instrument motion trajectory from multi-dimensional feature matrix, extract continuous change values ​​of velocity, acceleration and angular velocity, and compare them with corresponding safety thresholds to determine whether there is violent operation, abnormal shaking or angular deviation. Fetal physiological state assessment unit: used to extract fetal electrocardiogram signal features from a multidimensional feature matrix, including heart rate variability. Late deceleration characteristics The fetal distress is determined to exist if it is compared with the preset normal reference range and deceleration threshold; if any of the following conditions are met. Condition 1, ; Condition 2, ;in, Indicates current heart rate variability; This indicates the total deceleration rate during the evening period per unit time. These represent the upper and lower limits of the normal variation range; The threshold for determining deceleration; Risk Labeling Output Unit: Used to map the identification results of the device motion analysis unit and the fetal physiological status assessment unit into device risk labels, respectively. and fetal risk level .

6. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 5, characterized in that, The risk labeling output unit includes: Device Risk Classification Subunit: This subunit receives motion anomaly flags output by the device motion analysis unit and generates a corresponding risk level based on the number of abnormal parameters exceeding limits. The risk level is determined using the following mapping function: ;in, This indicates the number of instrument speed, acceleration, and angular velocity parameters that exceed the threshold within the current time window; Labels indicating the risk level of instrument operation; Fetal Risk Scoring Subunit: Used to receive heart rate variability output from the fetal physiological status assessment unit. and late deceleration magnitude Calculate fetal risk score ; Tag generation subunit: used to score fetal risk The mapping is to fetal risk level labels, and the mapping function is: ;in, A score used to classify the risk level of the fetus; This indicates the risk level of the fetus's physiological state.

7. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 1, characterized in that, The collaborative early warning module includes a rule matching unit, a joint judgment unit, and an instruction generation unit; wherein: Rule matching unit: Used to receive device risk labels and fetal risk levels, and retrieve matching rule entries from the pre-loaded operation-physiology association rule base; Joint Judgment Unit: Used to perform joint condition evaluation on the matched rule entries, determine whether the current surgical status triggers the warning mechanism of level 1, 2 or 3 risk level, and extract the response elements specified in the rule accordingly, including the high-risk instrument movement area, the corresponding surgical field image coordinate area and the risk propagation path; Instruction generation unit: Based on the response elements output by the joint judgment unit, it generates structured multi-level early warning instructions, including risk level identifiers, location coordinates of risk sites in image space, recommended intervention operation prompts, and time sequence annotations of the target surgical stage.

8. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 7, characterized in that, The rule matching unit includes: Tag Combination Parsing Subunit: Used to receive device risk tags Fetal risk level The two are combined into a joint risk index key according to a preset format. ; Index locator subunit: used to receive the joint risk index key Search for related rules in the operation-physiology association rule base. The corresponding rule index entries; Rule invocation subunit: used to extract the corresponding rule content based on the index results. The rule content includes joint risk level, associated site number, response strategy level and surgical stage adaptation conditions.

9. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 8, characterized in that, The joint determination unit includes: Stage matching subunit: Used to receive the current surgical status information and extract the surgical stage identifier. Compare the applicable surgical stages recorded in the rule entries. ,when If the current rule is deemed valid, the warning level assessment can continue; otherwise, the corresponding rule entry is ignored. Condition-triggered discrimination subunit: Under the premise that the stage match is met, compare the current device risk labels. Fetal risk level Whether it falls within the scope of the joint risk combination set in the rule entry; if it matches, it is determined to be in a triggered state. Risk Level Confirmation Subunit: When a rule is triggered, the joint risk level field in the rule entry is read and the current warning level is determined according to the following mapping method: When the combined risk level is low risk, the warning level is confirmed as Level 1 warning. When the combined risk level is medium risk, the warning level is confirmed as Level II warning. When the combined risk level is high risk or extremely high risk, the warning level is confirmed as Level III warning.

10. The sensor-based intelligent monitoring system for obstetric and gynecological surgery according to claim 1, characterized in that, The decision output module includes a boundary generation unit, a layer overlay unit, and a terminal output unit; wherein: Boundary generation unit: Receives multi-level early warning instructions and current surgical stage information, combines the risk coordinate range corresponding to the early warning level with the stage operation specifications, generates a safe operation boundary map, and updates its spatial area and color markings in real time; Layer overlay unit: used to map the safety operation boundary map as a transparent layer and overlay it onto the surgical field video stream according to the image coordinate alignment, so that the boundary display is synchronized with the real-time picture; Terminal output unit: Encodes and outputs the superimposed video stream to the display terminal for real-time reference by the operator during the operation.

Images