A method, apparatus, device and medium for assisted stereotactic asphyxia monitoring

Abstract

The present application relates to the technical field of medical devices, and discloses a suffocation monitoring method, device, equipment and medium for assisting stereotactic positioning, which comprises the following steps: monitoring the neck deviation angle of an experimental animal and monitoring the physiological parameters of the experimental animal when performing stereotactic surgery on the experimental animal; fusing the neck deviation angle and the physiological parameters to generate comprehensive monitoring data; and determining whether the comprehensive monitoring data is within a pre-determined multi-modal spatial range, and then determining whether the experimental animal has a suffocation risk. The present application can accurately and reliably determine whether the experimental animal has a suffocation risk during stereotactic surgery by comprehensively monitoring the posture and physiological parameters of the experimental animal and analyzing multi-modal data, thereby reducing the harm to the animal, reducing the mortality rate of the animal, and improving the success rate of the stereotactic surgery.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to a method, device, equipment, and medium for assisting stereotactic asphyxia monitoring. Background Technology

[0002] Stereotypers are common equipment in laboratory animal surgeries. For example, experiments such as implanting electrodes in mouse brain regions and viral injections require stereotypers to determine the implantation coordinates. Stereotype technology is a technique for precisely determining the location of specific brain structures. It is commonly used in experimental neuropsychology and neurosurgery. For instance, it allows for the accurate insertion of microelectrodes or microcatheters or the aiming of X-rays at specific brain regions for stimulation, damage, or drug injection. A stereotyper consists of an ear hook to fix the animal's head, incisor hooks, and a three-dimensionally adjustable electrode frame. In use, the head must first be leveled by adjusting the adapter's height and position. Then, according to the parameters provided by the brain atlas, the location to be studied or operated on is determined in the prescribed reference coordinate system.

[0003] However, after fixing the mouse's head, during the leveling process, changes in body posture, especially changes in head and neck posture, can cause abnormal neck angles and airway obstruction, leading to the risk of suffocation. Existing stereotactic instruments do not have the function of monitoring and preventing this from happening, resulting in a risk of suffocation during mouse surgery. Summary of the Invention

[0004] In view of this, the present invention provides a method, device, equipment and medium for assisting stereotactic asphyxiation monitoring, in order to solve the problem of asphyxiation risk during stereotactic surgery on mice.

[0005] In a first aspect, the present invention provides a method for assisting stereotactic asphyxia monitoring, the method comprising:

[0006] During stereotactic surgery on laboratory animals, the angle of neck displacement and physiological parameters of the laboratory animals are monitored.

[0007] Multimodal data fusion of neck displacement angle and physiological parameters is used to generate comprehensive monitoring data;

[0008] To determine whether the comprehensive monitoring data falls within a predetermined multimodal spatial range, and thus to determine whether the experimental animals are at risk of suffocation.

[0009] This invention provides an assisted stereotactic asphyxia monitoring method. During stereotactic surgery on experimental animals, the method monitors the neck displacement angle and physiological parameters. The neck displacement angle and physiological parameters are fused using multimodal data to generate comprehensive monitoring data. The method then determines whether the comprehensive monitoring data falls within a pre-defined multimodal spatial range, thereby assessing whether the experimental animal is at risk of asphyxia. This invention, through comprehensive monitoring of the posture and physiological parameters of experimental animals and multimodal data analysis, can accurately and reliably determine whether experimental animals are at risk of asphyxia during stereotactic surgery, reducing harm to animals, lowering animal mortality rates, and thus improving the success rate of stereotactic surgery experiments.

[0010] In one optional implementation, the method further includes: if the experimental animal is at risk of suffocation, then a multimodal alarm is triggered, the multimodal alarm including at least one of an audible alarm, an optical alert alarm, and an interface notification alarm.

[0011] This invention can promptly issue an alarm when laboratory animals are detected to be at risk of suffocation, thus alerting operators to potential safety issues and necessitating timely adjustments, thereby preventing experimental failures due to operator unawareness.

[0012] In one optional implementation, the process of monitoring the neck offset angle of an experimental animal includes: acquiring a neck image of the experimental animal; and using a pre-trained posture recognition model to identify the neck posture of the experimental animal in the neck image to obtain the neck offset angle of the experimental animal.

[0013] This invention uses a model to learn the neck offset angle during changes in the posture of experimental animals, which can reflect to some extent whether the experimental animals will experience airway obstruction due to abnormal neck angle, thus leading to suffocation.

[0014] In one optional implementation, the process of constructing a pose recognition model includes: collecting neck images of experimental animals under different scenes, different lighting conditions, different body postures, and different neck offset angles; standardizing the neck images and labeling them with preset labels; constructing an initial convolutional neural network model; and inputting the labeled neck images into the initial convolutional neural network model for training to obtain the pose recognition model.

[0015] This invention uses a convolutional neural network to accurately identify the neck offset angle based on images of experimental animals' necks, thereby improving the accuracy and reliability of asphyxiation risk monitoring.

[0016] In one optional implementation, the process of monitoring the physiological parameters of the experimental animal includes: acquiring the respiratory rate of the experimental animal through a respiratory rate sensor; and acquiring the heart rate of the experimental animal through a heart rate sensor.

[0017] This invention, by monitoring the physiological parameters of experimental animals, can further determine whether there is a risk of suffocation based on the actual physiological condition of the experimental animals, making up for possible errors in external posture monitoring, thereby further improving the accuracy of suffocation risk monitoring.

[0018] In one optional implementation, the process of determining the multimodal spatial range includes: collecting the neck offset angle, respiratory rate, and heart rate of experimental animals known to have experienced asphyxiation in historical experiments; fusing the neck offset angle, respiratory rate, and heart rate into multimodal data to obtain comprehensive monitoring data; learning the comprehensive monitoring data corresponding to known asphyxiation through a preset classification model, and obtaining the multimodal spatial range by determining the asphyxiation risk boundary of the neck offset angle, respiratory rate, and heart rate.

[0019] This invention learns and determines the spatial range in which asphyxiation has not occurred by pre-learning based on the data fusion results of posture parameters and physiological parameters. This can reduce false alarms caused by anomalies in a certain data source, improve the reliability of asphyxiation monitoring, and enhance adaptability to complex scenarios.

[0020] In one optional implementation, the process of determining whether the comprehensive monitoring data is within a predetermined multimodal space range, and then determining whether the experimental animal is at risk of asphyxiation, includes: determining whether the neck offset angle, respiratory rate, and heart rate are within the multimodal space range; if the neck offset angle, respiratory rate, and heart rate are all within the multimodal space, then the experimental animal is not at risk of asphyxiation; if at least one of the neck offset angle, respiratory rate, or heart rate is not within the multimodal space, then the experimental animal is at risk of asphyxiation.

[0021] This invention determines whether a laboratory animal is at risk of suffocation by spatial range, integrates multiple data sources, improves the accuracy of real-time monitoring, enhances the monitoring response speed, achieves information complementarity, provides more comprehensive and specific information for suffocation monitoring, and improves the accuracy and reliability of laboratory animal suffocation risk monitoring.

[0022] Secondly, the present invention provides an assisted stereotactic asphyxia monitoring device, the device comprising:

[0023] The monitoring module is used to monitor the neck displacement angle of experimental animals and the physiological parameters of experimental animals during stereotactic surgery.

[0024] The data fusion module is used to fuse neck displacement angle and physiological parameters into multimodal data to generate comprehensive monitoring data.

[0025] The asphyxiation monitoring module is used to determine whether experimental animals are at risk of asphyxiation based on comprehensive monitoring data and pre-determined multimodal judgment conditions.

[0026] The assisted stereotactic asphyxia monitoring device provided in this invention monitors the neck displacement angle and physiological parameters of experimental animals during stereotactic surgery. It then fuses these parameters using multimodal data to generate comprehensive monitoring data. The device determines whether the comprehensive monitoring data falls within a predetermined multimodal spatial range, thereby assessing whether the experimental animal is at risk of asphyxia. This invention, through comprehensive monitoring of the animal's posture and physiological parameters and multimodal data analysis, can accurately and reliably determine whether an experimental animal is at risk of asphyxia during stereotactic surgery, reducing harm to the animal, lowering mortality rates, and thus improving the success rate of stereotactic surgery experiments.

[0027] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the assisted stereoscopic positioning asphyxiation monitoring method of the first aspect or any corresponding embodiment described above.

[0028] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the assisted stereoscopic positioning asphyxiation monitoring method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0029] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0030] Figure 1 This is a flowchart illustrating an assisted stereotactic asphyxia monitoring method according to an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of the system processing flow of the assisted stereoscopic positioning asphyxiation monitoring method according to an embodiment of the present invention;

[0032] Figure 3 This is a flowchart illustrating another assisted stereotactic asphyxia monitoring method according to an embodiment of the present invention;

[0033] Figure 4This is a flowchart illustrating another assisted stereotactic asphyxia monitoring method according to an embodiment of the present invention;

[0034] Figure 5 This is a structural block diagram of an assisted stereoscopic positioning asphyxiation monitoring device according to an embodiment of the present invention;

[0035] Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] This invention is applicable to scenarios involving stereotactic surgery on laboratory animals. According to this invention, an embodiment of a method for assisting stereotactic asphyxia monitoring is provided. It should be noted that the steps shown in the flowcharts can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0038] This embodiment provides an assisted stereotactic asphyxia monitoring method, which can be used in the aforementioned mobile terminal, such as a computer. Figure 1 This is a flowchart of an assisted stereotactic asphyxia monitoring method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0039] Step S101: During stereotactic surgery on the experimental animal, the neck displacement angle of the experimental animal is monitored, and the physiological parameters of the experimental animal are monitored.

[0040] Specifically, in embodiments of the present invention, such as Figure 2As shown, for example, during stereotactic surgery on mice, to accurately determine whether the mouse is at risk of suffocation, a pre-deployed posture monitoring system is used to monitor the mouse's neck offset angle (i.e., the angle of neck displacement) through a system corresponding to the suffocation monitoring method for assisted stereotactic positioning. This ensures that the mouse's posture remains within a safe range during surgery, but is not a limitation thereof. The posture monitoring system acquires images of the mouse's neck using a camera installed in the surgical area. Then, an image processing module containing a posture recognition model identifies the mouse's neck posture in the neck images to obtain the mouse's neck offset angle. In this embodiment of the invention, a high-resolution camera is used to capture images of the mouse's neck, and the image processing module uses the advanced OpenPose image processing algorithm from the prior art to analyze the mouse's neck angle in the neck images from the camera, but is not limited to this.

[0041] In one optional embodiment, this invention further includes real-time monitoring of the mouse's physiological parameters during stereotactic surgery using a pre-deployed physiological parameter monitoring system's sensor integration module. The monitored physiological parameters include respiratory rate and heart rate. Body temperature and blood oxygen saturation may also be monitored, but this is merely an example and not a limitation. These physiological parameters can accurately reflect the mouse's current physiological condition, compensating for potential errors in external posture detection.

[0042] Step S102: Multimodal data fusion of neck offset angle and physiological parameters to generate comprehensive monitoring data.

[0043] Specifically, in this embodiment of the invention, after acquiring the neck offset angle and physiological parameters of the mouse, the risk of suffocation is not simply determined by whether each parameter falls within a certain range. Instead, a pre-deployed data fusion module fuses the neck offset angle and physiological parameters to generate comprehensive monitoring data. This effectively integrates different technical fields, providing a new layer of surgical safety. In the comprehensive monitoring data, the neck offset angle is a single angle value, while physiological parameters may be a single value or a range of variation over a time period. This embodiment employs a Multimodal Data Fusion Engine (MDFE) for data fusion. MDFE uses a specific algorithm to fuse the neck angle data from the image processing unit with the physiological parameters, forming comprehensive monitoring data with multi-dimensional information, ensuring comprehensive monitoring of the mouse's posture and physiological state. Multimodal data fusion helps reduce false alarm rates. By simultaneously considering image and sensor data, it is possible to more accurately determine whether the mouse is at risk of suffocation, reducing false alarms caused by anomalies in a single data source and improving the reliability of monitoring results. Multimodal data fusion also improves adaptability to complex situations. For example, in a stereotactic surgical environment, factors such as changes in lighting and differences in mouse size may exist. Using data from different modalities can enhance the robustness of the system. Multimodal data fusion can respond and adjust promptly because it integrates multiple data sources, improving both the accuracy and speed of real-time monitoring. Furthermore, image processing and sensor data can complement each other; image processing provides visual information, while sensors provide physiological parameters. Combining the two results in monitoring data containing more comprehensive and specific information, helping to more accurately assess the risk of asphyxiation.

[0044] Step S103: Determine whether the comprehensive monitoring data is within the predetermined multimodal space range, and then determine whether the experimental animal has a risk of suffocation.

[0045] Specifically, in this embodiment of the invention, a multimodal spatial range is pre-determined based on the asphyxia status of mice in historical experiments and corresponding comprehensive monitoring data. Then, during the actual stereotactic surgery, comprehensive monitoring data is obtained in real time, and it is determined in real time whether the comprehensive monitoring data is within the multimodal spatial range. This invention's determination of whether the comprehensive monitoring data is within the pre-determined multimodal spatial range is not simply a matter of judging whether each parameter is within its corresponding range, but rather a comprehensive judgment. For example, when it is determined that the neck offset angle is within the angle range of the multimodal spatial range, it is also determined whether each physiological parameter is within its corresponding physiological parameter range. Moreover, the position of the neck offset angle within the angle range also affects the value of the physiological parameter range. For example, if the neck offset angle is in the middle of the angle range, the corresponding physiological parameter range is relatively broad; if the neck offset angle is at either end of the angle range, the corresponding physiological parameter range is relatively small. The specific determination of the multimodal spatial range is based on the learning results of the classification model.

[0046] This invention provides a method for monitoring asphyxiation during stereotactic surgery. By monitoring the neck displacement angle and physiological parameters of experimental animals during stereotactic surgery, and fusing multimodal data of these parameters to generate comprehensive monitoring data, the method determines whether the comprehensive monitoring data falls within a pre-defined multimodal spatial range, thereby assessing whether the experimental animal is at risk of asphyxiation. This invention, through comprehensive monitoring of the posture and physiological parameters of experimental animals and multimodal data analysis, can accurately and reliably determine whether experimental animals are at risk of asphyxiation during stereotactic surgery, reducing harm to animals, lowering animal mortality rates, and thus improving the success rate of stereotactic surgery experiments.

[0047] This embodiment provides an assisted stereotactic asphyxia monitoring method, which can be used in the aforementioned mobile terminal, such as a computer. Figure 3 This is a flowchart of an assisted stereotactic asphyxia monitoring method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0048] Step S301: During stereotactic surgery on the experimental animal, the neck displacement angle and physiological parameters of the experimental animal are monitored. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0049] Step S302 involves fusing multimodal data of the neck displacement angle and physiological parameters to generate comprehensive monitoring data. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0050] Step S303: Determine whether the comprehensive monitoring data falls within a predetermined multimodal spatial range, and thus determine whether the experimental animal poses a risk of suffocation. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0051] In step S304, if the experimental animal is at risk of suffocation, a multimodal alarm is triggered, which includes at least one of an audible alarm, an optical alert alarm, and an interface notification alarm.

[0052] Specifically, in embodiments of the present invention, such as Figure 2 As shown, during stereotactic surgery, if the mouse is deemed to be at risk of suffocation, an alarm is triggered via a Multimodal Alert Transmitter (MAT). The MAT conveys alarm information to the operator through various means such as sound, light cues, or interface notifications, reminding the operator to take appropriate rescue measures. This is just an example and is not limited to this.

[0053] In some optional implementations, embodiments of the present invention utilize a comprehensive user interface for monitoring asphyxiation during mouse surgery to assist stereotactic surgery. This provides operators with a user-friendly interface, enabling them to easily monitor asphyxiation monitoring results, understand the mouse's physiological condition, and make operational adjustments as needed, thus comprehensively ensuring the safety of the surgical procedure. Furthermore, operators can adjust system parameters according to experimental requirements, such as setting a safe threshold for the neck angle and adjusting alarm sensitivity.

[0054] This invention provides a method for monitoring asphyxiation during stereotactic surgery. By monitoring the neck displacement angle and physiological parameters of experimental animals during stereotactic surgery, and fusing multimodal data of these parameters to generate comprehensive monitoring data, the method determines whether the comprehensive monitoring data falls within a pre-defined multimodal spatial range. This allows for the assessment of whether the experimental animal is at risk of asphyxiation. If so, a multimodal alarm is triggered. This invention, through comprehensive monitoring of the animal's posture and physiological parameters, multimodal data analysis, and multimodal alarms, can accurately and reliably determine whether an experimental animal is at risk of asphyxiation during stereotactic surgery. This allows for timely alerts to the operator, reducing harm to the animal, lowering mortality rates, and improving the success rate of stereotactic surgery experiments.

[0055] This embodiment provides an assisted stereotactic asphyxia monitoring method, which can be used in the aforementioned mobile terminal, such as a computer. Figure 4 This is a flowchart of an assisted stereotactic asphyxia monitoring method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0056] Step S401: During stereotactic surgery on the experimental animal, the neck displacement angle of the experimental animal is monitored, and the physiological parameters of the experimental animal are monitored.

[0057] Specifically, step S401 includes:

[0058] Step S4011: Construct a pose recognition model.

[0059] Specifically, in this embodiment of the invention, neck images of experimental mice under different scenarios, lighting conditions, body postures, and neck offset angles are collected. These neck images cover a variety of complex situations, ensuring dataset diversity and improving the model's generalization ability. The neck images are then standardized, including size standardization, brightness adjustment, and rotation correction, to ensure the consistency and quality of the input data. Simultaneously, preset labels are assigned to the neck images. This embodiment can set labels based on whether the label affects the mouse's breathing; for example, an angle that does not affect breathing is labeled as 1, and an angle that does affect breathing is labeled as 0. Alternatively, the angle of the mouse's neck can be directly labeled, and the degree at which it affects breathing can be determined. This invention learns by constructing an initial convolutional neural network model. The labeled neck images are input into the initial convolutional neural network model, which outputs corresponding labels. The initial convolutional neural network model is trained and adjusted based on the input and output, finally obtaining a pose recognition model. During training, the initial convolutional neural network updates its weights using a backpropagation algorithm to reduce the gap between predicted values ​​and true labels, and an appropriate loss function and optimization algorithm are selected for training. In this embodiment of the invention, a validation set (collected photos of inappropriate neck angles and photos of appropriate neck angles) is established to evaluate the performance of the trained model. Based on the evaluation results, the network architecture and hyperparameters are adjusted to ensure that the model performs well on unseen data, thereby ensuring generalization performance.

[0060] Step S4012: Acquire images of the neck of the experimental animal; use a pre-trained posture recognition model to identify the neck posture of the experimental animal in the neck image and obtain the neck offset angle of the experimental animal.

[0061] Specifically, in this embodiment of the invention, the trained posture recognition model is deployed on a computer. In actual stereotactic surgery, the real-time collected neck images are input into the posture recognition model, which can directly obtain the neck offset angle of the mouse, thereby realizing real-time monitoring of the mouse's neck angle.

[0062] Step S4013: Obtain the respiratory rate of the experimental animal through a respiratory rate sensor; obtain the heart rate of the experimental animal through a heart rate sensor.

[0063] Specifically, in this embodiment of the invention, when performing a stereotactic experiment on a mouse, a sensor integrated module including a respiratory rate sensor and a heart rate sensor is deployed on the mouse to perform time-domain analysis and obtain real-time data of respiratory rate and heart rate.

[0064] Step S402 involves fusing multimodal data of the neck offset angle and physiological parameters to generate comprehensive monitoring data. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0065] Step S403: Determine whether the comprehensive monitoring data is within the predetermined multimodal space range, and then determine whether the experimental animal has a risk of suffocation.

[0066] Specifically, step S403 includes:

[0067] Step S4031: Determine the multimodal space range.

[0068] Specifically, in this embodiment of the invention, the neck offset angle, respiratory rate, and heart rate of mice known to have experienced asphyxiation in historical experiments are collected. The neck offset angle, respiratory rate, and heart rate are fused using a multimodal data fusion engine (MDFE) to obtain comprehensive monitoring data. Then, a preset classification model is used to learn the comprehensive monitoring data corresponding to the known asphyxiation situation, such as a binary classification model, but not limited to this. The multimodal spatial range is obtained by determining the asphyxiation risk boundary of the neck offset angle, respiratory rate, and heart rate, where the asphyxiation risk boundary is the value of a certain parameter when asphyxiation occurs and when asphyxiation does not occur.

[0069] Step S4032: Determine whether the neck offset angle, respiratory rate, and heart rate are within the multimodal space. If the neck offset angle, respiratory rate, and heart rate are all within the multimodal space, the experimental animal is not at risk of suffocation. If at least one of the neck offset angle, respiratory rate, or heart rate is not within the multimodal space, the experimental animal is at risk of suffocation.

[0070] Specifically, in this embodiment of the invention, the multimodal spatial ranges corresponding to the neck offset angle, respiratory rate, and heart rate are not three fixed ranges, but rather a spatial range that influences each other. That is, when one parameter is determined to be within the normal range, the other two parameters must also be within their corresponding normal ranges. Furthermore, the normal ranges corresponding to different parameters will change depending on the position of one of the parameters within the normal range. The specific range distribution can be learned through a classification model, and then the results can be directly obtained by using a specially designed algorithm through an anomaly detection engine (ADE).

[0071] This invention provides a method for monitoring asphyxiation during stereotactic surgery. By monitoring the neck displacement angle and physiological parameters of experimental animals during stereotactic surgery, and fusing multimodal data of these parameters to generate comprehensive monitoring data, the method determines whether the comprehensive monitoring data falls within a pre-defined multimodal spatial range, thereby assessing whether the experimental animal is at risk of asphyxiation. This invention, through comprehensive monitoring of the posture and physiological parameters of experimental animals and multimodal data analysis, can accurately and reliably determine whether experimental animals are at risk of asphyxiation during stereotactic surgery, reducing harm to animals, lowering animal mortality rates, and thus improving the success rate of stereotactic surgery experiments.

[0072] This embodiment also provides an assisted stereotactic asphyxia monitoring device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0073] This embodiment provides an auxiliary stereotactic asphyxia monitoring device, such as... Figure 5 As shown, it includes:

[0074] The monitoring module 501 is used to monitor the neck displacement angle of experimental animals and the physiological parameters of experimental animals during stereotactic surgery.

[0075] The data fusion module 502 is used to perform multimodal data fusion of neck offset angle and physiological parameters to generate comprehensive monitoring data.

[0076] The asphyxiation monitoring module 503 is used to determine whether experimental animals are at risk of asphyxiation based on comprehensive monitoring data and pre-determined multimodal judgment conditions.

[0077] In some alternative implementations, the system further includes an alarm module for triggering a multimodal alarm if the experimental animal is at risk of suffocation. The multimodal alarm includes at least one of an audible alarm, an optical alert alarm, and an interface notification alarm.

[0078] In some alternative implementations, the monitoring module 501 includes:

[0079] The neck offset angle monitoring unit is used to acquire images of the neck of experimental animals; through a pre-trained posture recognition model, it identifies the neck posture of the experimental animals in the neck images and obtains the neck offset angle of the experimental animals.

[0080] The pose recognition model building unit is used to collect neck images of experimental animals under different scenes, lighting conditions, body postures, and neck offset angles; standardize the neck images and label them with preset labels; build an initial convolutional neural network model; and input the labeled neck images into the initial convolutional neural network model for training to obtain the pose recognition model.

[0081] The physiological parameter monitoring unit is used to acquire the respiratory rate of experimental animals through a respiratory rate sensor and the heart rate of experimental animals through a heart rate sensor.

[0082] In some alternative implementations, the asphyxiation monitoring module 503 includes:

[0083] The multimodal spatial range determination unit is used to collect the neck displacement angle, respiratory rate, and heart rate of experimental animals known to have experienced asphyxiation in historical experiments; it fuses the neck displacement angle, respiratory rate, and heart rate into multimodal data to obtain comprehensive monitoring data; it learns the comprehensive monitoring data corresponding to known asphyxiation through a preset classification model, and obtains the multimodal spatial range by determining the asphyxiation risk boundary of the neck displacement angle, respiratory rate, and heart rate.

[0084] The range determination unit is used to determine whether the neck offset angle, respiratory rate, and heart rate are within the multimodal space. If the neck offset angle, respiratory rate, and heart rate are all within the multimodal space, the experimental animal is not at risk of suffocation. If at least one of the neck offset angle, respiratory rate, or heart rate is not within the multimodal space, the experimental animal is at risk of suffocation.

[0085] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0086] In this embodiment, the assisted stereoscopic positioning asphyxiation monitoring device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0087] This invention also provides a computer device having the above-described features. Figure 5 The suffocation monitoring device shown is an auxiliary stereotactic positioning device.

[0088] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0089] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0090] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0091] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0092] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0093] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0094] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0095] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for assisted stereotactic asphyxia monitoring, characterized in that, The method includes: During stereotactic surgery on experimental animals, the neck displacement angle of the experimental animals is monitored, and the physiological parameters of the experimental animals are also monitored. The neck offset angle and the physiological parameters are fused using multimodal data to generate comprehensive monitoring data; To determine whether the comprehensive monitoring data falls within a predetermined multimodal spatial range, and thus to determine whether the experimental animal is at risk of suffocation; The physiological parameters include respiratory rate and heart rate. The process of determining the multimodal spatial range includes: Collect neck deflection angle, respiratory rate, and heart rate of the experimental animals in historical experiments where asphyxiation was known to have occurred. The neck offset angle, respiratory rate, and heart rate are fused using multimodal data to obtain comprehensive monitoring data; The comprehensive monitoring data corresponding to the known occurrence of asphyxiation is learned by a preset classification model. The multimodal spatial range is obtained by determining the asphyxiation risk boundary of the neck offset angle, the respiratory rate and the heart rate. The multimodal spatial ranges corresponding to the neck offset angle, respiratory rate and heart rate are mutually influential spatial ranges. The values ​​of the physiological parameter ranges are affected by the position of the neck offset angle within the angle range.

2. The method according to claim 1, characterized in that, Also includes: If the experimental animal is at risk of suffocation, a multimodal alarm will be triggered, which includes at least one of an audible alarm, an optical alert alarm, and an interface notification alarm.

3. The method according to claim 1, characterized in that, The process of monitoring the neck offset angle of the experimental animal includes: Images of the necks of the experimental animals were acquired; The neck posture of the experimental animal in the neck image is identified by a pre-trained posture recognition model, and the neck offset angle of the experimental animal is obtained.

4. The method according to claim 3, characterized in that, The process of constructing the pose recognition model includes: Collect neck images of the experimental animals under different scenes, lighting conditions, body postures, and neck offset angles; The neck images are standardized and labeled with preset tags. Construct the initial convolutional neural network model; The labeled neck image is input into an initial convolutional neural network model for training to obtain a pose recognition model.

5. The method according to claim 1, characterized in that, The process of monitoring the physiological parameters of the experimental animals includes: The respiratory rate of the experimental animal was obtained using a respiratory rate sensor; The heart rate of the experimental animal was obtained using a heart rate sensor.

6. The method according to claim 1, characterized in that, The process of determining whether the comprehensive monitoring data falls within a predetermined multimodal spatial range, and thus determining whether the experimental animal poses a risk of suffocation, includes: Determine whether the neck offset angle, respiratory rate, and heart rate are within the range of the multimodal space; If the neck offset angle, the respiratory rate, and the heart rate are all within the range of the multimodal space, then the experimental animal is not at risk of suffocation. If at least one of the neck offset angle, the respiratory rate, or the heart rate is not within the range of the multimodal space, the experimental animal is at risk of suffocation.

7. A suffocation monitoring device for assisting three-dimensional positioning, characterized in that, The device includes: The monitoring module is used to monitor the neck displacement angle of the experimental animal and the physiological parameters of the experimental animal during stereotactic surgery. The data fusion module is used to perform multimodal data fusion of the neck offset angle and the physiological parameters to generate comprehensive monitoring data; The asphyxiation monitoring module is used to determine whether the experimental animal is at risk of asphyxiation based on the comprehensive monitoring data and the pre-determined multimodal spatial range. The physiological parameters include respiratory rate and heart rate. The process of determining the multimodal spatial range includes: Collect neck deflection angle, respiratory rate, and heart rate of the experimental animals in historical experiments where asphyxiation was known to have occurred. The neck offset angle, respiratory rate, and heart rate are fused using multimodal data to obtain comprehensive monitoring data; The comprehensive monitoring data corresponding to the known occurrence of asphyxiation is learned by a preset classification model. The multimodal spatial range is obtained by determining the asphyxiation risk boundary of the neck offset angle, the respiratory rate and the heart rate. The multimodal spatial ranges corresponding to the neck offset angle, respiratory rate and heart rate are mutually influential spatial ranges. The values ​​of the physiological parameter ranges are affected by the position of the neck offset angle within the angle range.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the assisted stereoscopic positioning asphyxiation monitoring method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the assisted stereoscopic positioning asphyxiation monitoring method according to any one of claims 1 to 6.

Images