Intelligent lumbar anesthesia puncture guiding method and device

Abstract

The invention provides an intelligent lumbar anesthesia puncture guiding method and device, which are applied to a lumbar anesthesia puncture needle, and the method comprises the following steps: obtaining case information of a puncture object, and preprocessing the case information; the preprocessed case information is input into a trained puncture prediction model, a predicted puncture path is obtained, and the predicted puncture path comprises a predicted puncture point position, the predicted puncture depth of each tissue layer, a predicted pressure threshold value and a predicted puncture angle; guiding a spinal anesthesia puncture needle to puncture according to the predicted puncture path; wherein the puncture prediction model is specifically a deep neural network model, and the puncture prediction model is obtained by training an initial model through sample case information marked with a corresponding puncture path prediction result in advance. In combination with the artificial intelligence model, the puncture path is individually recommended based on patients of different ages and body types, the accuracy of the puncture point location and the success rate of one-time puncture are improved, the operation time is shortened, and the patient experience and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of spinal anesthesia puncture, and in particular to an intelligent spinal anesthesia puncture guiding method and device. Background Art

[0002] Spinal anesthesia is a type of anesthesia that is usually performed in the lumbar intervertebral space. The puncture needle needs to pass through the skin, subcutaneous tissue, ligaments and other structures, and finally reach the epidural space or subarachnoid space.

[0003] Clinically, due to the patient's body position or anatomical structure, it is difficult to accurately locate the puncture point, and the puncture needle may not enter the correct position due to improper operation during the puncture process. In addition, the position of the puncture needle tip is often judged empirically in clinical practice, which carries the risk of the puncture needle penetrating the arachnoid membrane and the puncture path failing, causing harm to the patient.

[0004] That is, how to provide an intelligent spinal anesthesia puncture guidance method and device for predicting the puncture path and identifying the tissue layer where the spinal anesthesia puncture needle is located during puncture, so as to improve the accuracy and success rate of puncture, is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] In response to the above-mentioned problems, the present invention aims to provide an intelligent spinal anesthesia puncture guidance method and device to at least solve at least one of the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides an intelligent spinal anesthesia puncture guidance method, which is applied to a spinal anesthesia puncture needle, and the method comprises:

[0007] Acquiring case information of the puncture subject and preprocessing the case information;

[0008] Inputting the pre-processed case information into a trained puncture prediction model to obtain a predicted puncture path, wherein the predicted puncture path includes a predicted puncture point, a predicted puncture depth of each tissue layer, a predicted pressure threshold, and a predicted puncture angle;

[0009] guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path;

[0010] The puncture prediction model is specifically a deep neural network model, and the puncture prediction model is obtained by training an initial model in advance with sample case information marked with corresponding puncture path prediction results.

[0011] Preferably, the case information includes basic information of the puncture subject, imaging image information, and previous medical history related to spinal puncture, and the preprocessing of the case information includes:

[0012] The imaging image information is subjected to image enhancement, noise reduction, and segmentation processing, and the past medical history related to spinal anesthesia puncture is coded.

[0013] Preferably, the basic information includes the age, gender, height and weight of the puncture subject;

[0014] The imaging image information includes CT, MRI or ultrasound images of the spinal column of the puncture target;

[0015] The past medical history includes a history of spinal disease, neurological disease, bleeding tendency or coagulation disorder.

[0016] Preferably, the predicted puncture path includes a predicted puncture point, a predicted pressure threshold of each tissue layer, a predicted puncture depth, and a predicted puncture angle. The spinal anesthesia puncture needle is provided with a sensor array. When guiding the spinal anesthesia puncture needle for puncture according to the predicted puncture path, the method further includes:

[0017] Acquiring pressure data collected by the sensor array and determining real-time position information and puncture depth information of the spinal anesthesia puncture needle during puncture based on the pressure data;

[0018] Inputting the pressure data, the real-time position information, the puncture depth information, and the predicted pressure threshold and predicted puncture depth of each tissue layer into a trained tissue recognition model to obtain the tissue layer where the spinal anesthesia puncture needle is currently located;

[0019] It is determined whether the tissue layer where the spinal anesthesia puncture needle is currently located is the target tissue layer. If so, the puncture preparation is completed.

[0020] Preferably, the method further comprises:

[0021] If the tissue layer currently located by the spinal anesthesia puncture needle is not the target tissue layer, the puncture is continued according to the predicted puncture path until the target tissue layer is reached.

[0022] Preferably, continuing to puncture according to the predicted puncture path until reaching the target tissue layer includes:

[0023] Determining whether an abnormal situation occurs, wherein the abnormal situation includes abnormal fluctuations in pressure data or obstruction of puncture;

[0024] If no abnormality occurs, continue puncturing according to the puncture plan until the target tissue layer is reached;

[0025] If an abnormality occurs, the puncture path is adjusted and the tissue layer identification is performed again based on the adjusted puncture path.

[0026] Preferably, the method further comprises:

[0027] After the spinal anesthesia puncture is completed, the puncture results are obtained, including whether the puncture is successful, whether the puncture point and puncture path deviate from the predicted puncture path, and whether complications occur;

[0028] The parameters of the puncture prediction model are adjusted according to the puncture result.

[0029] In a second aspect, the present invention provides an intelligent lumbar anesthesia puncture guidance device, which includes a lumbar anesthesia puncture needle and a terminal, and the lumbar anesthesia puncture needle and the terminal are communicatively connected; the terminal includes a memory and a processor, and a computer program is stored in the memory. When the computer program is executed by the processor, it can implement the intelligent lumbar anesthesia puncture guidance method according to any one of claims 1 to 7.

[0030] Preferably, the spinal anesthesia puncture needle includes a needle core, a needle body and a needle tail. The needle body is a hollow structure. One end of the needle body is connected to the needle tail. The needle tail has a through channel. An accommodating space that is adapted to the size of the needle core is formed between the through channel and the needle body. The other end of the needle body is a puncture tip, and the puncture tip is provided with a sensor array. The needle tail has a built-in communication module, and the communication module is communicatively connected to the terminal and the sensor array respectively.

[0031] Preferably, a pressure calibration module is also embedded in the needle tail, and the pressure calibration module is communicatively connected to the sensor array.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] Specifically, the present invention provides an intelligent spinal anesthesia puncture guidance method, which is applied to a spinal anesthesia puncture needle. The method includes obtaining case information of the puncture object and processing the case information; inputting the processed case information into a trained puncture prediction model to obtain a predicted puncture path, the predicted puncture path including the predicted puncture point, the predicted puncture depth of each tissue layer, the predicted pressure threshold, and the predicted puncture angle; guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path; wherein the puncture prediction model is specifically a deep neural network model, and the puncture prediction model is obtained by training an initial model in advance with sample case information marked with the corresponding puncture path prediction results. The intelligent spinal anesthesia puncture guidance method provided by the present application, combined with an artificial intelligence model, recommends a personalized puncture path based on patients of different ages and body shapes to improve the accuracy of the puncture point, thereby improving the success rate of a one-time puncture, reducing operation time, reducing the patient's discomfort caused by long-term operation, and improving patient experience and safety.

[0034] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a flow chart of the intelligent spinal anesthesia puncture guidance method in an embodiment of the present application;

[0037] Figure 2 This is a three-dimensional diagram of the spinal anesthesia puncture needle in the embodiment of this application.

[0038] Reference numerals:

[0039] 1. Needle core;

[0040] 2. Needle body;

[0041] 21. Sensor array;

[0042] 3. Needle tail;

[0043] 31. Communication module. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present invention; the "and / or" keywords involved in this implementation represent both and and or. In other words, A and / or B mentioned in the embodiments of this specification represent both A and B, and A or B, and describe the three states of A and B. For example, A and / or B means: only A is included but not B; only B is included but not A; and both A and B are included.

[0045] Meanwhile, in the embodiments of this specification, when a component is considered to be "connected" to another component, it can be directly connected to the other component or there may be an intermediate component. When a component is considered to be "disposed on" another component, it can be directly disposed on the other component or there may be an intermediate component.

[0046] The following describes the embodiments of the present invention through specific examples. Those skilled in the art will readily understand the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention.

[0047] Example 1

[0048] See also Figure 1 Specifically, this embodiment provides an intelligent spinal anesthesia puncture guidance method, which is applied to a spinal anesthesia puncture needle. In an embodiment of the intelligent spinal anesthesia puncture guidance method, the intelligent spinal anesthesia puncture guidance method specifically includes the following steps S110 to S130:

[0049] Step S110: obtaining case information of the puncture subject and preprocessing the case information;

[0050] The case information includes basic information of the puncture subject, imaging image information, and medical history related to spinal anesthesia puncture. The pre-processing of the case information involved in step S110 specifically includes the following:

[0051] The imaging image information is processed by image enhancement, noise reduction and segmentation, and the medical history related to spinal anesthesia puncture is coded.

[0052] Specifically, imaging images are enhanced, denoised, and segmented to highlight key anatomical structures and features, facilitating subsequent model analysis. Medical history related to spinal anesthesia is also encoded to convert it into a feature vector that can be processed by a computer.

[0053] The basic information mentioned above includes the patient's age, gender, height, and weight; imaging information includes CT, MRI, or ultrasound images of the patient's spine; and medical history includes spinal disorders, neurological diseases, bleeding tendencies, coagulation disorders, and other medical conditions related to spinal anesthesia. This medical information can be obtained from the hospital's medical system or manually entered. The imaging information and medical history should only be within the past year to ensure the validity and accuracy of the prediction.

[0054] Step S120: Inputting the pre-processed case information into the trained puncture prediction model to obtain a predicted puncture path, which includes the predicted puncture point, the predicted pressure threshold of each tissue layer, the predicted puncture depth, and the predicted puncture angle;

[0055] Among them, the puncture prediction model is specifically a deep neural network model, and the puncture prediction model is obtained by training the initial model in advance with sample case information marked with corresponding puncture path prediction results.

[0056] Step S130: guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path;

[0057] It is understandable that before puncture, the pressure value of the sensor array needs to be reset to zero to clear any initial pressure or offset inside the sensor, ensuring that the sensor is in the same starting state during each measurement, thereby reducing measurement errors and improving measurement accuracy.

[0058] Considering that different body postures will affect the angle and direction of the puncture needle entering the intervertebral space, the puncture body posture can be used to train the puncture prediction model so that the puncture path prediction result can also include the puncture body posture prediction.

[0059] In one possible embodiment, the predicted puncture path includes predicting the puncture point, the predicted pressure thresholds of each tissue layer, the predicted puncture depth, and the predicted puncture angle. The spinal anesthesia puncture needle is provided with a sensor array. In the process of guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path in step S130, the method involved in the present application further specifically includes the following steps:

[0060] Obtaining pressure data collected by the sensor array and determining real-time position information and puncture depth information of the spinal anesthesia puncture needle during puncture based on the pressure data;

[0061] Inputting the pressure data, real-time position information, puncture depth information, and the predicted pressure threshold and predicted puncture depth of each tissue layer into the trained tissue recognition model to obtain the tissue layer where the spinal anesthesia puncture needle is currently located;

[0062] Determine whether the tissue layer where the spinal anesthesia puncture needle is currently located is the target tissue layer. If so, complete the puncture preparation.

[0063] Among them, the tissue recognition model is specifically a deep neural network model, and the tissue recognition model is obtained by pre-training an initial model with sample pressure information labeled with corresponding tissue layer recognition results.

[0064] Among them, the sensor array can adopt a 9-axis MEMS sensor array with 0.1mm level accuracy, and a thermistor is built into the sensor array, that is, an NTC thermistor is integrated as a temperature sensing element in each or part of the sensor units in the sensor array to eliminate the drift caused by body temperature.

[0065] Generally speaking, the target tissue layer is the subarachnoid space or the epidural space. When the needle tip reaches the target tissue layer, the puncture preparation is complete, the needle core can be removed, and subsequent procedures can be performed according to clinical needs. For example, when the target tissue layer is the subarachnoid space, a spinal needle is inserted into the spinal anesthesia needle; when the target tissue layer is the epidural space, an epidural catheter is inserted into the spinal anesthesia needle.

[0066] In a possible implementation manner, the method involved in this application further specifically includes the following contents:

[0067] If the tissue layer currently located by the spinal anesthesia puncture needle is not the target tissue layer, the puncture continues according to the predicted puncture path until the target tissue layer is reached.

[0068] In a possible embodiment, if the tissue layer currently located by the spinal anesthesia puncture needle is not the target tissue layer, the above step of "continuing puncture according to the predicted puncture path until the target tissue layer is reached" specifically further includes the following:

[0069] Determine whether any abnormal conditions occur, including abnormal fluctuations in pressure data or obstruction of puncture;

[0070] If no abnormalities occur, continue puncturing according to the puncture plan until the target tissue layer is reached;

[0071] If an abnormality occurs, the puncture path is adjusted and the tissue layer identification is performed again based on the adjusted puncture path.

[0072] The adjustment of the puncture path may be made by the doctor according to the patient's condition, or the doctor may adjust the parameters of the puncture prediction model according to the abnormal condition and re-predict the puncture path based on the puncture prediction model.

[0073] In one possible implementation, the method provided in this application further includes:

[0074] After the spinal anesthesia puncture is completed, the puncture results are obtained, including whether the puncture is successful, whether the puncture point and puncture path deviate from the predicted puncture path, and whether complications occur;

[0075] According to the puncture results, the parameters of the puncture prediction model are adjusted using neural network online learning technology.

[0076] Specifically, an embodiment of the present invention provides an intelligent spinal anesthesia puncture guidance method, which is applied to a spinal anesthesia puncture needle. The method includes obtaining case information of the puncture subject and processing the case information; inputting the processed case information into a trained puncture prediction model to obtain a predicted puncture path, which includes a predicted puncture point, a predicted puncture depth of each tissue layer, a predicted pressure threshold, and a predicted puncture angle; guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path; wherein the puncture prediction model is specifically a deep neural network model, which is obtained by training an initial model in advance using sample case information labeled with corresponding puncture path prediction results. The intelligent spinal anesthesia puncture guidance method provided in this application combines an artificial intelligence model to recommend a personalized puncture path based on patients of different ages and body types. At the same time, pressure data during puncture is obtained in real time through a pressure sensor, and the tissue layer currently located by the spinal anesthesia puncture needle is determined based on the pressure data until it reaches the target tissue layer, so as to improve the accuracy of the puncture point, thereby improving the success rate of a one-time puncture, reducing operation time, reducing the patient's discomfort caused by prolonged operation, and improving patient experience and safety.

[0077] Example 2

[0078] An embodiment of the present invention also provides an intelligent lumbar anesthesia puncture guidance device, including a lumbar anesthesia puncture needle and a terminal, wherein the lumbar anesthesia puncture needle and the terminal are communicatively connected; the terminal includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, an intelligent lumbar anesthesia puncture guidance method as described in any one of the first embodiments can be implemented.

[0079] In one possible implementation, Figure 2 As shown, the spinal anesthesia puncture needle includes a needle core 1, a needle body 2 and a needle tail 3. The needle body 2 is a hollow structure. One end of the needle body 2 is connected to the needle tail 3. The needle tail 3 has a through channel. An accommodating space that is adapted to the size of the needle core 1 is formed between the through channel and the needle body 2. The other end of the needle body 2 is a puncture tip, and the puncture tip is provided with a sensor array 21. The needle tail 3 has a built-in communication module 31, and the communication module 31 is respectively connected to the terminal and the sensor array 21 for communication.

[0080] Specifically, a communication module 31 establishes a communication connection between the spinal puncture needle and the terminal, enabling data transmission between the sensor array 21 provided on the spinal puncture needle and the terminal. This allows for puncture guidance and monitoring using the intelligent spinal puncture guidance method configured on the terminal. The sensor array 21 can utilize a 9-axis MEMS sensor array 21 with 0.1mm-level accuracy, and incorporates a built-in thermistor within the sensor array 21. Specifically, each or some of the sensor cells in the sensor array 21 incorporate an NTC thermistor as a temperature sensing element to eliminate drift caused by body temperature.

[0081] The needle body 2 is reinforced with titanium alloy and other materials to ensure the bending resistance of the needle body 2. The puncture needle is sterile packaged for single use or the entire assembly can withstand a sterilization environment of 60°C and 80% humidity to ensure safety during use.

[0082] In a possible embodiment, a pressure calibration module is further embedded in the needle tail 3 , and the pressure calibration module is communicatively connected to the sensor array 21 and the terminal so as to return the pressure of the sensor array 21 to zero before puncture by controlling the pressure calibration module.

[0083] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for understanding and reading by those familiar with this technology, and are not used to limit the conditions for implementation of the present invention. Therefore, they have no substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the efficacy and purpose that can be achieved by the present invention. At the same time, terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments in their relative relationships should also be regarded as the scope of implementation of the present invention without substantially changing the technical content.

[0084] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any technician familiar with this profession can make some changes or modifications to equivalent embodiments of the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent spinal anesthesia puncture guidance method, characterized in that: Applied to a spinal anesthesia needle, the method comprises: Acquiring case information of the puncture subject and preprocessing the case information; Inputting the preprocessed case information into a trained puncture prediction model to obtain a predicted puncture path; guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path; The puncture prediction model is specifically a deep neural network model, and the puncture prediction model is obtained by training an initial model in advance with sample case information marked with corresponding puncture path prediction results.

2. The intelligent spinal anesthesia puncture guidance method according to claim 1, characterized in that: The case information includes basic information of the puncture subject, imaging image information, and previous medical history related to spinal anesthesia puncture. The preprocessing of the case information includes: The imaging image information is subjected to image enhancement, noise reduction, and segmentation processing, and the past medical history related to spinal anesthesia puncture is coded.

3. The intelligent spinal anesthesia puncture guidance method according to claim 2, characterized in that: The basic information includes the age, gender, height and weight of the puncture subject; The imaging image information includes CT, MRI or ultrasound images of the spinal column of the puncture target; The past medical history includes a history of spinal disease, neurological disease, bleeding tendency or coagulation disorder.

4. The intelligent spinal anesthesia puncture guidance method according to claim 1, characterized in that: The predicted puncture path includes a predicted puncture point, a predicted pressure threshold of each tissue layer, a predicted puncture depth, and a predicted puncture angle. The spinal anesthesia puncture needle is provided with a sensor array. When guiding the spinal anesthesia puncture needle to perform puncture according to the predicted puncture path, the method further includes: Acquiring pressure data collected by the sensor array and determining real-time position information and puncture depth information of the spinal anesthesia puncture needle during puncture based on the pressure data; Inputting the pressure data, the real-time position information, the puncture depth information, and the predicted pressure threshold and predicted puncture depth of each tissue layer into a trained tissue recognition model to obtain the tissue layer where the spinal anesthesia puncture needle is currently located; It is determined whether the tissue layer where the spinal anesthesia puncture needle is currently located is the target tissue layer. If so, the puncture preparation is completed.

5. The intelligent spinal anesthesia puncture guidance method according to claim 4, characterized in that: The method further comprises: If the tissue layer currently located by the spinal anesthesia puncture needle is not the target tissue layer, the puncture is continued according to the predicted puncture path until the target tissue layer is reached.

6. The intelligent spinal anesthesia puncture guidance method according to claim 5, characterized in that: The step of continuing to puncture according to the predicted puncture path until reaching the target tissue layer includes: Determining whether an abnormal situation occurs, wherein the abnormal situation includes abnormal fluctuations in pressure data or obstruction of puncture; If no abnormality occurs, continue puncturing according to the puncture plan until the target tissue layer is reached; If an abnormality occurs, the puncture path is adjusted and the tissue layer identification is performed again based on the adjusted puncture path.

7. The intelligent spinal anesthesia puncture guidance method according to claim 1, characterized in that: The method further comprises: After the spinal anesthesia puncture is completed, the puncture results are obtained, including whether the puncture is successful, whether the puncture point and puncture path deviate from the predicted puncture path, and whether complications occur; The parameters of the puncture prediction model are adjusted according to the puncture result.

8. An intelligent spinal anesthesia puncture guiding device, characterized in that: The intelligent lumbar anesthesia puncture guidance device includes a lumbar anesthesia puncture needle and a terminal, and the lumbar anesthesia puncture needle and the terminal are communicatively connected; the terminal includes a memory and a processor, and the memory stores a computer program. When the computer program is executed by the processor, it can implement the intelligent lumbar anesthesia puncture guidance method according to any one of claims 1 to 7.

9. The intelligent spinal anesthesia puncture guiding device according to claim 8, characterized in that: The spinal anesthesia puncture needle includes a needle core, a needle body and a needle tail. The needle body is a hollow structure. One end of the needle body is connected to the needle tail. The needle tail has a through channel. An accommodating space that is adapted to the size of the needle core is formed between the through channel and the needle body. The other end of the needle body is a puncture tip, and the puncture tip is provided with a sensor array. The needle tail has a built-in communication module, and the communication module is respectively communicatively connected to the terminal and the sensor array.

10. The intelligent spinal anesthesia puncture guiding device according to claim 9, characterized in that: A pressure calibration module is also embedded in the needle tail, and the pressure calibration module is communicatively connected with the sensor array.

Images