Brain blood oxygen monitoring method and terminal, brain blood oxygen monitoring system

Abstract

The present invention provides a cerebral blood oxygen monitoring method and terminal, and a cerebral blood oxygen monitoring system. The method is implemented based on a cerebral blood oxygen sensor set on the forehead of a measured user, including: obtaining the physical sign information of the measured user, and predicting the thickness of the covering tissue of the measured user; the covering tissue refers to the tissue covering the cerebral cortex; determining the first distance based on the thickness of the covering tissue, and adjusting the distance between the light source array and the receiver array to the first distance; obtaining the light signal data of the receiver array, processing the light signal data, and obtaining the initial cerebral blood oxygen content of the measured user; obtaining the ambient brightness and light source brightness when the cerebral blood oxygen sensor performs detection, and calculating the correction coefficient of the initial cerebral blood oxygen content based on the ambient brightness, light source brightness and the thickness of the covering tissue; correcting the initial cerebral blood oxygen content based on the correction coefficient to obtain the final cerebral blood oxygen content. The present invention can effectively improve the monitoring accuracy while ensuring simplicity.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and more specifically, relates to a cerebral blood oxygen monitoring method and terminal, and a cerebral blood oxygen monitoring system. Background Art

[0002] The monitoring of cerebral blood oxygen is extremely important, as it directly affects the judgment of brain cognitive ability and brain function. Therefore, many methods for cerebral blood oxygen monitoring have emerged in the prior art. Among them, the cerebral blood oxygen monitoring methods in the prior art are mainly divided into two categories: invasive monitoring and non-invasive monitoring. The invasive monitoring method has a relatively high accuracy rate, but it is not convenient and fast enough. Although the non-invasive monitoring method is relatively simple, it is easily affected by various factors during monitoring, resulting in low monitoring accuracy.

[0003] Therefore, the present application aims to provide a brain blood oxygen monitoring solution to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a cerebral blood oxygen monitoring method and terminal, and a cerebral blood oxygen monitoring system to solve the problem that the cerebral blood oxygen monitoring scheme in the prior art is not simple or accurate enough.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is to provide a cerebral blood oxygen monitoring method, which is implemented based on a cerebral blood oxygen sensor arranged on the forehead of a user to be measured; the cerebral blood oxygen sensor includes a light source array and a receiver array arranged in parallel, and the distance between the light source array and the receiver array is adjustable; the cerebral blood oxygen monitoring method includes:

[0006] Acquiring physical sign information of the user being measured, and predicting the thickness of the covering tissue of the user being measured according to the physical sign information; the covering tissue refers to the tissue covering the cerebral cortex;

[0007] Determine a first distance based on the thickness of the covering tissue, and adjust the distance between the light source array and the receiver array to the first distance; control the brain blood oxygen sensor to detect the brain of the user being measured, and obtain light signal data of the receiver array, and process the light signal data based on the Lambert-Beer law to obtain the initial brain blood oxygen content of the user being measured;

[0008] Acquiring the ambient brightness and light source brightness when the cerebral blood oxygen sensor performs detection, and calculating a correction coefficient for the initial cerebral blood oxygen content based on the ambient brightness, light source brightness and the thickness of the covering tissue;

[0009] The initial cerebral blood oxygen content is corrected based on the correction coefficient to obtain the final cerebral blood oxygen content.

[0010] In a possible implementation, the physical sign information includes height, weight, age, gender, head circumference, and brain injury information; and predicting the thickness of the covering tissue of the measured user according to the physical sign information includes:

[0011] Generate a feature vector for describing the physical signs of the user being measured according to the height, weight, age, gender, head circumference and brain injury information of the user being measured;

[0012] The feature vector is input into a pre-trained first deep learning model to predict the thickness of the covering tissue of the measured user.

[0013] In a possible implementation manner, determining the first distance based on the thickness of the covering tissue includes:

[0014] determining a thickness range to which the thickness of the covering tissue belongs;

[0015] The first distance is determined based on a correspondence between a pre-calibrated thickness range and the first distance.

[0016] In a possible implementation, the cerebral blood oxygen monitoring method further includes:

[0017] To set multiple thickness ranges for covered tissues, perform the following steps for any thickness range you set:

[0018] Obtaining a first brain blood oxygen content of a target user; the target user is a user who meets the thickness range and has just undergone an invasive brain blood oxygen test, and the first brain blood oxygen content is the brain blood oxygen content measured when the target user undergoes the invasive brain blood oxygen test;

[0019] The distance between the light source array and the receiver array is adjusted to different distances; and after each distance adjustment, the brain of the target user is detected based on the brain blood oxygen sensor after the distance adjustment, and the brain blood oxygen content of the target user is calculated according to the brain detection result to obtain a second brain blood oxygen content;

[0020] The difference between the first cerebral blood oxygen content and each second cerebral blood oxygen content is calculated, and the distance corresponding to the second cerebral blood oxygen content having the smallest difference with the first cerebral blood oxygen content is determined as the first distance corresponding to the thickness range.

[0021] In a possible implementation, the calculation of the correction coefficient of the cerebral blood oxygen content based on the ambient brightness, the light source brightness and the thickness of the covering tissue includes:

[0022] The ambient brightness, light source brightness and the thickness of the covering tissue are input into a pre-trained second deep learning model to obtain a correction coefficient for cerebral blood oxygen content.

[0023] In a possible implementation, the cerebral blood oxygen monitoring method further includes:

[0024] Obtaining a first brain blood oxygen content of a target user; the target user is a user who meets the thickness range and has just undergone an invasive brain blood oxygen test, and the first brain blood oxygen content is the brain blood oxygen content measured when the target user undergoes the invasive brain blood oxygen test;

[0025] Taking the target user as a measured user, performing brain detection on the target user based on the brain blood oxygen sensor and obtaining an initial brain blood oxygen content corresponding to the target user;

[0026] determining a theoretical correction coefficient based on a ratio of the first cerebral blood oxygen content to the initial cerebral blood oxygen content;

[0027] Acquire the ambient brightness and light source brightness when the brain of the target user is detected based on the brain blood oxygen sensor, and acquire the thickness of the covering tissue of the target user;

[0028] The ambient brightness and light source brightness when performing brain detection on the target user, the thickness of the target user's covering tissue, and the theoretical correction coefficient are used as a training set, and the second deep learning model is obtained through training based on the training set.

[0029] In a possible implementation, the correcting the initial cerebral blood oxygen content based on the correction coefficient to obtain the final cerebral blood oxygen content includes:

[0030] The product of the correction coefficient and the initial cerebral blood oxygen content is determined as the final cerebral blood oxygen content.

[0031] In a possible implementation, the cerebral blood oxygen sensor further includes a bendable fixing device, and the light source array and the receiver array are arranged on the fixing device; when the cerebral blood oxygen sensor performs brain detection, the fixing device is closely attached to the forehead of the user being measured; before adjusting the distance between the light source array and the receiver array to the first distance, the cerebral blood oxygen monitoring method further includes:

[0032] Get the forehead curvature of the user being measured;

[0033] The first distance is increased based on the curvature of the forehead of the measured user.

[0034] In another aspect of the present invention, a cerebral blood oxygen monitoring terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned cerebral blood oxygen monitoring method when executing the computer program.

[0035] In another aspect of the present invention, a cerebral blood oxygen monitoring system is provided, comprising:

[0036] A cerebral blood oxygen sensor and the above-described cerebral blood oxygen monitoring terminal electrically connected to the cerebral blood oxygen sensor;

[0037] The cerebral blood oxygen sensor comprises a fixing device and a light source array and a receiver array arranged in parallel on the fixing device, wherein the distance between the light source array and the receiver array is adjustable; the light source array comprises a plurality of near-infrared light sources arranged in sequence, and the receiver array comprises a plurality of light source receivers arranged in sequence, wherein the near-infrared light sources and the light source receivers correspond to each other one by one;

[0038] When the brain blood oxygen sensor performs brain detection, the fixing device is closely attached to the forehead of the user being measured, and the near-infrared light source on the fixing device emits near-infrared light. After the near-infrared light is scattered in the brain of the user being measured, the light source receiver on the fixing device receives the scattered near-infrared light signal, and the near-infrared light signal is used to calculate the brain blood oxygen content of the user being measured.

[0039] The beneficial effects of the cerebral blood oxygen monitoring method, terminal, and cerebral blood oxygen monitoring system provided by the present invention are:

[0040] The inventor of the present application has analyzed and verified the factors that affect the accuracy of non-invasive monitoring of cerebral blood oxygen and found that the thickness of the covering tissue, the ambient brightness, and the brightness of the light source itself will affect the accuracy of monitoring. Therefore, based on this finding, the embodiment of the present invention provides a cerebral blood oxygen monitoring solution.

[0041] In the first aspect, an embodiment of the present invention provides a brain blood oxygen sensor, in which the distance between the light source array and the receiver array is adjustable. On this basis, the embodiment of the present invention can predict the thickness of the covered tissue of the measured user according to the physical sign information of the measured user, and then adjust the distance between the light source array and the receiver array according to the thickness of the covered tissue to ensure that the light emitted by the light source array can be fully scattered and absorbed in the brain of the measured user, thereby improving the monitoring accuracy of brain blood oxygen.

[0042] Secondly, after determining the cerebral blood oxygen content, the embodiment of the present invention will also calculate the correction coefficient based on internal factors (i.e., the thickness of the covering tissue) and external factors (i.e., the ambient brightness and the brightness of the light source), and on this basis, correct the initial cerebral blood oxygen content obtained by the preliminary calculation to obtain the final cerebral blood oxygen content. Based on the scheme of the embodiment of the present invention, the influence of internal and external factors on cerebral blood oxygen monitoring can be effectively reduced, thereby improving the accuracy of cerebral blood oxygen monitoring.

[0043] In summary, the embodiment of the present invention proposes a new non-invasive brain blood oxygen monitoring solution. Based on the solution of the embodiment of the present invention, the monitoring accuracy can be effectively improved while ensuring simplicity. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0045] Figure 1 A schematic diagram of a process for monitoring cerebral blood oxygen levels according to an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of the arrangement of a light source array and a receiver array provided in one embodiment of the present invention;

[0047] Figure 3 A schematic diagram of the structure of a brain blood oxygen sensor provided by an embodiment of the present invention;

[0048] Figure 4 A schematic diagram of a module composed of a light source array and a receiver array provided in one embodiment of the present invention;

[0049] Figure 5 A schematic diagram of an application of a brain blood oxygen sensor provided by an embodiment of the present invention;

[0050] Figure 6 A schematic diagram of a first distance and a second distance provided by an embodiment of the present invention;

[0051] Figure 7 A schematic diagram of the structure of a cerebral blood oxygen monitoring terminal provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0054] The cerebral blood oxygen monitoring method provided by the embodiment of the present invention is implemented based on a cerebral blood oxygen sensor arranged on the forehead of the user being measured. The cerebral blood oxygen sensor includes a light source array and a receiver array arranged in parallel, and the distance between the light source array and the receiver array is adjustable. Among them, when the cerebral blood oxygen sensor is on the forehead of the user being measured, each light source in the light source array will emit near-infrared light. After the near-infrared light is absorbed and scattered by the brain of the user being measured, the scattered near-infrared light will be received by the receiver in the receiver array. On this basis, the cerebral blood oxygen content of the user being measured can be calculated according to the near-infrared light received by the receiver. Specifically, the absorption of near-infrared light by the brain can be judged based on the near-infrared light received by the receiver, and the cerebral blood oxygen content of the user being measured can be judged based on the absorption.

[0055] Based on the above description, you can refer to Figure 1 , Figure 1 The flowchart of the cerebral blood oxygen monitoring method provided by one embodiment of the present invention is as follows:

[0056] S101: Obtaining physical sign information of the user under test, and predicting the thickness of the covering tissue of the user under test according to the physical sign information. The covering tissue refers to the tissue covering the cerebral cortex.

[0057] In this embodiment, considering that there are other structures outside the human brain (i.e., the covering tissue described in this embodiment) that also absorb near-infrared light, thereby affecting the monitoring accuracy of cerebral blood oxygen content, the embodiment of the present invention considers eliminating the interference of the aforementioned other structures from two aspects:

[0058] First, the thickness of the covering tissue is predicted using the vital signs information, so as to select the appropriate receiving and transmitting distance to ensure that the near-infrared light has a suitable optical path, so that it can reach the deep layers of the brain, and will not be excessively scattered / absorbed due to the long optical path, which will cause the receiver to be unable to effectively receive the near-infrared light and affect the monitoring. Figure 2 , Figure 2 The d in the equation is the transmit-receive distance, which is the distance between the light source array and the receiver array.

[0059] Secondly, the embodiment of the present invention also generates a correction coefficient according to the thickness of the covering tissue to correct the calculated initial cerebral blood oxygen content, thereby eliminating the interference of the covering tissue and improving the monitoring accuracy.

[0060] In this embodiment, considering that the thickness of the covering tissue is related to the personal physical signs of the user being measured, the embodiment of the present invention may consider obtaining the physical sign information of the user being measured, predicting the thickness of the covering tissue of the user being measured based on the physical sign information of the user being measured, and then adjusting the receiving and transmitting distance of the brain blood oxygen sensor based on the thickness and calculating the subsequent correction coefficient.

[0061] In the embodiment of the present invention, the covering tissue includes but is not limited to the scalp, skull, meninges, cerebrospinal fluid and the like.

[0062] S102: Determine a first distance based on the thickness of the covering tissue, and adjust the distance between the light source array and the receiver array to the first distance. Control the brain blood oxygen sensor to detect the brain of the user being tested, and obtain light signal data from the receiver array, and process the light signal data based on the Lambert-Beer law to obtain the initial brain blood oxygen content of the user being tested.

[0063] In this embodiment, as described above, the purpose of adjusting the distance between the light source array and the receiver array to the first distance is to select a suitable transmitting and receiving distance to ensure that the near-infrared light has a suitable optical path, so that it can reach deep into the brain, and will not be overly scattered / absorbed due to a long optical path, thereby causing the receiver to be unable to effectively receive the near-infrared light and affect monitoring.

[0064] On this basis, after adjusting the distance between the light source array and the receiver array in the brain blood oxygen sensor to the first distance, the brain of the user under test can be detected based on the brain blood oxygen sensor after the distance adjustment, that is, the brain blood oxygen sensor after the distance adjustment is covered and set on the forehead of the user under test to detect the brain of the user under test. After the detection of the brain blood oxygen sensor is completed, the near-infrared light signal received by the receiver array that is not "absorbed by the brain of the user under test" can be obtained, and the brain blood oxygen content of the user under test can be calculated based on the light signal data received by the receiver array. Specifically, the light signal data can be processed according to the Lambert-Beer law to calculate the brain blood oxygen content of the user under test, and the brain blood oxygen content calculated at this time is used as the initial brain blood oxygen content.

[0065] In this embodiment, "processing the optical signal data based on the Lambert-Beer law to calculate the cerebral blood oxygen content" can be achieved based on existing means, which will not be elaborated in this embodiment.

[0066] S103: Obtaining the ambient brightness and light source brightness when the cerebral blood oxygen sensor performs detection, and calculating a correction coefficient of the initial cerebral blood oxygen content based on the ambient brightness, light source brightness, and thickness of the covering tissue.

[0067] In this embodiment, the inventors of the present application discovered that the accuracy of cerebral blood oxygen content monitoring under different ambient brightness is different, because the relative size of ambient brightness and light source brightness will affect the propagation and detection of near-infrared light to a certain extent. Therefore, the embodiment of the present invention uses ambient brightness and light source brightness as external factors affecting the accuracy of cerebral blood oxygen content monitoring, and uses the thickness of the covering tissue as an internal factor affecting the accuracy of cerebral blood oxygen content monitoring. The correction coefficient is determined based on the internal and external factors to achieve the correction of the initial cerebral blood oxygen content, so as to eliminate the influence of internal and external factors on cerebral blood oxygen content monitoring as much as possible.

[0068] S104: Correcting the initial cerebral blood oxygen content based on the correction coefficient to obtain a final cerebral blood oxygen content.

[0069] In this embodiment, the correction coefficient is in the range of 0.7 to 1.3. The correction of the initial cerebral blood oxygen content based on the correction coefficient can be described in detail as follows:

[0070] The final cerebral blood oxygen content was determined by multiplying the correction factor by the initial cerebral blood oxygen content.

[0071] The inventor of the present application has analyzed and verified the factors that affect the accuracy of non-invasive monitoring of cerebral blood oxygen and found that the thickness of the covering tissue, the ambient brightness, and the brightness of the light source itself will affect the accuracy of monitoring. Therefore, based on this finding, the embodiment of the present invention provides a cerebral blood oxygen monitoring solution.

[0072] In the first aspect, an embodiment of the present invention provides a brain blood oxygen sensor, in which the distance between the light source array and the receiver array is adjustable. On this basis, the embodiment of the present invention can predict the thickness of the covered tissue of the measured user according to the physical sign information of the measured user, and then adjust the distance between the light source array and the receiver array according to the thickness of the covered tissue to ensure that the light emitted by the light source array can be fully scattered and absorbed in the brain of the measured user, thereby improving the monitoring accuracy of brain blood oxygen.

[0073] Secondly, after determining the cerebral blood oxygen content, the embodiment of the present invention will also calculate the correction coefficient based on internal factors (i.e., the thickness of the covering tissue) and external factors (i.e., the ambient brightness and the brightness of the light source), and on this basis, correct the initial cerebral blood oxygen content obtained by the preliminary calculation to obtain the final cerebral blood oxygen content. Based on the scheme of the embodiment of the present invention, the influence of internal and external factors on cerebral blood oxygen monitoring can be effectively reduced, thereby improving the accuracy of cerebral blood oxygen monitoring.

[0074] In summary, the embodiment of the present invention proposes a new non-invasive brain blood oxygen monitoring solution. Based on the solution of the embodiment of the present invention, the monitoring accuracy can be effectively improved while ensuring simplicity.

[0075] In a possible implementation, the physical sign information includes height, weight, age, gender, head circumference, and brain injury information. Predicting the thickness of the covered tissue of the measured user based on the physical sign information includes:

[0076] A feature vector for describing the physical signs of the user being measured is generated according to the height, weight, age, gender, head circumference and brain injury information of the user being measured.

[0077] The feature vector is input into a pre-trained first deep learning model to predict the thickness of the covered tissue of the measured user.

[0078] In this embodiment, considering that the thickness of the covering tissue varies with the height, weight, age, gender, and head circumference of the human body, the embodiment of the present invention considers pre-constructing a mapping relationship between physical sign information and the thickness of the covering tissue, training a first deep learning model, and on this basis, generating a feature vector according to the physical sign information of the measured user, and inputting the feature vector into the pre-trained deep learning model, the thickness of the covering tissue of the measured user can be predicted, and the thickness of the covering tissue can be obtained without sensor detection. Among them, the first deep learning model is constructed based on the principle of deep learning, which is not elaborated in this embodiment.

[0079] In a possible implementation, determining the first distance based on the thickness of the covering tissue includes:

[0080] Determine the thickness range into which the thickness of the overlying tissue falls.

[0081] The first distance is determined based on a correspondence between a pre-calibrated thickness range and the first distance.

[0082] In this embodiment, multiple thickness ranges can be pre-set, and a first distance can be calibrated for each thickness range. On this basis, after the thickness of the covering tissue is determined, the thickness range corresponding to the thickness of the covering tissue can be determined, and the first distance corresponding to the thickness range can be determined as the first distance corresponding to the thickness of the covering tissue. For example, the thickness ranges s1-s2, s2-s3, and s3-s4 are pre-set, and the first distance corresponding to the thickness range s1-s2 is d1, the first distance corresponding to the thickness range s2-s3 is d2, and the first distance corresponding to the thickness range s3-s4 is d3. On this basis, the thickness of the covering tissue of the measured user is ss, and ss belongs to the thickness range s2-s3, then the first distance is d2.

[0083] In a possible implementation, the cerebral blood oxygen monitoring method further includes: calibrating the correspondence between the thickness range and the first distance. The correspondence between the calibrated thickness range and the first distance can be described in detail as follows:

[0084] To set multiple thickness ranges for covered tissues, perform the following steps for any thickness range you set:

[0085] The first cerebral blood oxygen content of the target user is obtained. The target user is a user who meets the thickness range (that is, the thickness of the target user's covering tissue is within the thickness range) and has just undergone invasive cerebral blood oxygen testing. The first cerebral blood oxygen content is the cerebral blood oxygen content measured when the target user undergoes invasive cerebral blood oxygen testing.

[0086] The distance between the light source array and the receiver array is adjusted to different distances. After each distance adjustment, the brain of the target user is detected based on the brain blood oxygen sensor after the distance adjustment, and the brain blood oxygen content of the target user is calculated according to the brain detection result to obtain a second brain blood oxygen content.

[0087] The difference between the first cerebral blood oxygen content and each second cerebral blood oxygen content is calculated, and the distance corresponding to the second cerebral blood oxygen content having the smallest difference with the first cerebral blood oxygen content is determined as the first distance corresponding to the thickness range.

[0088] In this embodiment, each time the distance between the light source array and the receiver array is adjusted, the brain of the target user is detected based on the brain blood oxygen sensor after the distance adjustment, and the second brain blood oxygen content is calculated. Therefore, multiple distance adjustments can be performed to obtain multiple second brain blood oxygen contents, and each distance adjustment corresponds to a second brain blood oxygen content.

[0089] In this embodiment, the cerebral blood oxygen content obtained by invasive detection is a more accurate cerebral blood oxygen content, which can be used as a criterion for judging the monitoring accuracy of the embodiment of the present invention, that is, the cerebral blood oxygen sensor provided by the embodiment of the present invention can be used to detect the brain of the target user, and the cerebral blood oxygen content of the target user is calculated according to the brain detection result combined with the Lambert-Beer law, that is, the second cerebral blood oxygen content. On this basis, the difference between the first cerebral blood oxygen content and each second cerebral blood oxygen content is calculated. The larger the difference, the more inappropriate the distance between the current light source array and the receiver array; the smaller the difference, the more appropriate the distance between the current light source array and the receiver array. Therefore, the distance corresponding to the second cerebral blood oxygen content with the smallest difference can be selected as the first distance corresponding to the current thickness range.

[0090] In a possible implementation, the correction coefficient of cerebral blood oxygen content is calculated based on the ambient brightness, the light source brightness and the thickness of the covering tissue, including:

[0091] The ambient brightness, light source brightness, and thickness of the covering tissue are input into a pre-trained second deep learning model to obtain a correction coefficient for cerebral blood oxygen content.

[0092] In this embodiment, the second deep learning model can be pre-trained to learn the intrinsic relationship between the ambient brightness, the light source brightness, the thickness of the covering tissue and the correction coefficient. On this basis, the ambient brightness, the light source brightness and the thickness of the covering tissue can be input into the pre-trained second deep learning model to obtain the correction coefficient of the cerebral blood oxygen content. The second deep learning model is constructed based on the principle of deep learning, which is not described in detail in this embodiment.

[0093] In this embodiment, the ambient brightness, light source brightness, and thickness of the covering tissue are input into the pre-trained second deep learning model to obtain a correction coefficient for the cerebral blood oxygen content, which can be described in detail as follows:

[0094] The ratio of ambient brightness to light source brightness is used as the first eigenvector, and the thickness of the covering tissue is used as the second eigenvector. The first eigenvector and the second eigenvector are combined to obtain a eigenvector for describing internal and external influencing factors. On this basis, the eigenvector for describing internal and external influencing factors is input into the pre-trained second deep learning model to obtain the correction coefficient of cerebral blood oxygen content.

[0095] In a possible implementation, the cerebral blood oxygen monitoring method further includes: training a second deep learning model. Training the second deep learning model can be described in detail as follows:

[0096] The first cerebral blood oxygen content of the target user is obtained. The target user is a user who meets the thickness range and has just undergone invasive cerebral blood oxygen testing. The first cerebral blood oxygen content is the cerebral blood oxygen content measured when the target user undergoes invasive cerebral blood oxygen testing.

[0097] The target user is taken as the user to be measured, and the brain of the target user is detected based on the brain blood oxygen sensor to obtain the initial brain blood oxygen content corresponding to the target user (that is, the target user is taken as the user to be measured, and the aforementioned steps S101 and S102 are executed to obtain the initial brain blood oxygen content corresponding to the target user).

[0098] A theoretical correction factor is determined based on the ratio of the first cerebral blood oxygen content to the initial cerebral blood oxygen content.

[0099] The ambient brightness and light source brightness when the brain of the target user is detected based on the brain blood oxygen sensor are obtained, and the thickness of the covering tissue of the target user is obtained.

[0100] The ambient brightness and light source brightness when the target user's brain is detected, the thickness of the target user's covering tissue, and the theoretical correction coefficient are used as a training set, and a second deep learning model is obtained based on the training set.

[0101] In this embodiment, the second deep learning model is obtained based on the training set training, which can be described in detail as follows:

[0102] S1: Input the ambient brightness and light source brightness when performing brain detection on the target user, and the thickness of the target user's covering tissue into the second deep learning model to obtain the correction coefficient output by the second deep learning model.

[0103] S2: Calculate the difference between the correction coefficient output by the second deep learning model and the theoretical correction coefficient. If the difference is less than the preset difference, the training of the second deep learning model is completed. If the difference is not less than the preset difference, update the weight coefficient in the second deep learning model and return to execute step S1.

[0104] In one possible implementation, Figure 3 As shown, the brain blood oxygen sensor also includes a bendable fixing device, and the light source array and the receiver array are arranged on the fixing device. Figure 3 In the embodiment, the module consisting of the light source array and the receiver array is clamped on the fixing device. The other side of the aforementioned module can be referred to Figure 4 , Figure 4 Each light source and each light source receiver can be snapped into the hole of the fixing device, wherein the specific shapes of the light source, the light source receiver, and the hole can be defined according to actual needs. In the embodiment of the present invention, Figure 3 and Figure 4 This is only for illustration and is not intended to limit the shape. Figure 5 When the brain blood oxygen sensor performs brain detection, the fixing device can be close to the forehead of the user being tested. At this time, each light source in the light source array will emit near-infrared light. After the near-infrared light is absorbed and scattered by the brain of the user being tested, the scattered near-infrared light will be received by the receiver in the receiver array. On this basis, the brain blood oxygen content of the user being tested can be calculated based on the near-infrared light received by the receiver. Specifically, the brain's absorption of near-infrared light can be judged based on the near-infrared light received by the receiver, and the brain blood oxygen content of the user being tested can be judged based on the absorption.

[0105] Based on the above description, before adjusting the distance between the light source array and the receiver array to the first distance, the cerebral blood oxygen monitoring method further includes:

[0106] Get the forehead curvature of the measured user.

[0107] The first distance is increased based on the curvature of the forehead of the measured user.

[0108] In this embodiment, it is assumed that the first distance calculated according to the thickness of the covering tissue is L, that is, the distance between the light source array and the receiver array in the cerebral blood oxygen sensor is L. Since the forehead of the user being measured has a certain curvature, when the cerebral blood oxygen sensor is close to the forehead of the user being measured, the distance between the light source array and the receiver array will be less than L, resulting in an impact on the monitoring accuracy. Therefore, the curvature of the forehead of the user being measured can be obtained, and the first distance is increased according to the curvature of the forehead of the user being measured and the first distance to obtain the second distance. On this basis, the distance between the light source array and the receiver array is adjusted to the aforementioned second distance. After the distance between the light source array and the receiver array is adjusted to the aforementioned second distance, since the forehead of the user being measured has a certain curvature, when the cerebral blood oxygen sensor is close to the forehead of the user being measured, the distance between the light source array and the receiver array is exactly the first distance.

[0109] The first distance is increased based on the curvature of the forehead of the measured user, including:

[0110] like Figure 6 As shown, the forehead curvature of the measured user is equivalent to a circular arc (that is, Figure 6 The arc between AB in the middle is located on the upper side of the circle), then the second distance is the length of the arc, and the first distance is the straight-line distance between the two endpoints of the arc (that is, the straight-line distance between AB). This problem is converted to finding the second distance L2 based on the first distance L1 and the forehead arc α. The calculation method of the second distance is:

[0111]

[0112] Please refer to Figure 7In another aspect of the present invention, a cerebral blood oxygen monitoring terminal 300 is provided, comprising: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processor 301, input device 302, output device 303 and memory 304 communicate with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the steps of the above-mentioned method embodiments. It should be understood that in the embodiment of the present invention, the processor 301 may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc. The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type. In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiment of the present invention may execute the implementation described in the first embodiment and the second embodiment of the cerebral blood oxygen monitoring method provided in the embodiment of the present invention.

[0113] In another aspect of the present invention, a cerebral blood oxygen monitoring system is provided, comprising:

[0114] A cerebral blood oxygen sensor and the above-described cerebral blood oxygen monitoring terminal electrically connected to the cerebral blood oxygen sensor.

[0115] The cerebral blood oxygen sensor comprises a fixing device and a light source array and a receiver array which are arranged in parallel on the fixing device, and the distance between the light source array and the receiver array is adjustable.

[0116] The light source array includes a plurality of near-infrared light sources arranged in sequence, and the receiver array includes a plurality of light source receivers arranged in sequence, and the near-infrared light sources and the light source receivers correspond to each other one by one.

[0117] When the brain blood oxygen sensor performs brain detection, the fixing device is close to the forehead of the user being measured, and the near-infrared light source on the fixing device emits near-infrared light. After the near-infrared light is scattered in the brain of the user being measured, the light source receiver on the fixing device receives the scattered near-infrared light signal, and the near-infrared light signal is used to calculate the brain blood oxygen content of the user being measured.

[0118] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for monitoring cerebral blood oxygen, characterized in that: The cerebral blood oxygen monitoring method is implemented based on a cerebral blood oxygen sensor arranged on the forehead of the user being measured; the cerebral blood oxygen sensor includes a light source array and a receiver array arranged in parallel, and the distance between the light source array and the receiver array is adjustable; The cerebral blood oxygen monitoring method comprises: Acquiring physical sign information of the user being measured, and predicting the thickness of the covering tissue of the user being measured according to the physical sign information; the covering tissue refers to the tissue covering the cerebral cortex; Determine a first distance based on the thickness of the covering tissue, and adjust the distance between the light source array and the receiver array to the first distance; control the brain blood oxygen sensor to detect the brain of the user being measured, and obtain light signal data of the receiver array, and process the light signal data based on the Lambert-Beer law to obtain the initial brain blood oxygen content of the user being measured; Acquiring the ambient brightness and light source brightness when the cerebral blood oxygen sensor performs detection, and calculating a correction coefficient for the initial cerebral blood oxygen content based on the ambient brightness, light source brightness and the thickness of the covering tissue; Correcting the initial cerebral blood oxygen content based on the correction coefficient to obtain a final cerebral blood oxygen content; The physical sign information includes height, weight, age, gender, head circumference and brain injury information; and predicting the thickness of the covering tissue of the measured user according to the physical sign information includes: Generate a feature vector for describing the physical signs of the user being measured according to the height, weight, age, gender, head circumference and brain injury information of the user being measured; The feature vector is input into a pre-trained first deep learning model to predict the thickness of the covering tissue of the measured user.

2. The method for monitoring cerebral blood oxygenation according to claim 1, characterized in that: The determining the first distance based on the thickness of the covering tissue comprises: determining a thickness range to which the thickness of the covering tissue belongs; The first distance is determined based on a correspondence between a pre-calibrated thickness range and the first distance.

3. The method for monitoring cerebral blood oxygenation according to claim 2, characterized in that: The cerebral blood oxygen monitoring method further comprises: To set multiple thickness ranges for covered tissues, perform the following steps for any thickness range you set: Obtaining a first brain blood oxygen content of a target user; the target user is a user who meets the thickness range and has just undergone an invasive brain blood oxygen test, and the first brain blood oxygen content is the brain blood oxygen content measured when the target user undergoes the invasive brain blood oxygen test; The distance between the light source array and the receiver array is adjusted to different distances; and after each distance adjustment, the brain of the target user is detected based on the brain blood oxygen sensor after the distance adjustment, and the brain blood oxygen content of the target user is calculated according to the brain detection result to obtain a second brain blood oxygen content; The difference between the first cerebral blood oxygen content and each second cerebral blood oxygen content is calculated, and the distance corresponding to the second cerebral blood oxygen content having the smallest difference with the first cerebral blood oxygen content is determined as the first distance corresponding to the thickness range.

4. The method for monitoring cerebral blood oxygenation according to claim 1, characterized in that: The correction coefficient of the cerebral blood oxygen content is calculated based on the ambient brightness, the light source brightness and the thickness of the covering tissue, including: The ambient brightness, light source brightness and the thickness of the covering tissue are input into a pre-trained second deep learning model to obtain a correction coefficient for cerebral blood oxygen content.

5. The method for monitoring cerebral blood oxygenation according to claim 4, characterized in that: The cerebral blood oxygen monitoring method further comprises: Obtaining a first brain blood oxygen content of a target user; the target user is a user who meets the thickness range and has just undergone an invasive brain blood oxygen test, and the first brain blood oxygen content is the brain blood oxygen content measured when the target user undergoes the invasive brain blood oxygen test; Taking the target user as a measured user, performing brain detection on the target user based on the brain blood oxygen sensor and obtaining an initial brain blood oxygen content corresponding to the target user; determining a theoretical correction coefficient based on a ratio of the first cerebral blood oxygen content to the initial cerebral blood oxygen content; Acquire the ambient brightness and light source brightness when the brain of the target user is detected based on the brain blood oxygen sensor, and acquire the thickness of the covering tissue of the target user; The ambient brightness and light source brightness when performing brain detection on the target user, the thickness of the target user's covering tissue, and the theoretical correction coefficient are used as a training set, and the second deep learning model is obtained through training based on the training set.

6. The method for monitoring cerebral blood oxygenation according to any one of claims 1 to 5, characterized in that: The correcting the initial cerebral blood oxygen content based on the correction coefficient to obtain the final cerebral blood oxygen content includes: The product of the correction coefficient and the initial cerebral blood oxygen content is determined as the final cerebral blood oxygen content.

7. The method for monitoring cerebral blood oxygenation according to any one of claims 1 to 5, characterized in that: The brain blood oxygen sensor also includes a bendable fixing device, on which the light source array and the receiver array are arranged; when the brain blood oxygen sensor performs brain detection, the fixing device is closely attached to the forehead of the user being tested; Before adjusting the distance between the light source array and the receiver array to a first distance, the cerebral blood oxygen monitoring method further includes: Get the forehead curvature of the user being measured; The first distance is increased based on the curvature of the forehead of the measured user.

8. A cerebral blood oxygen monitoring terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A brain blood oxygen monitoring system, characterized in that: include: A cerebral blood oxygen sensor and a cerebral blood oxygen monitoring terminal as claimed in claim 8 which is electrically connected to the cerebral blood oxygen sensor; The cerebral blood oxygen sensor comprises a fixing device and a light source array and a receiver array arranged in parallel on the fixing device, wherein the distance between the light source array and the receiver array is adjustable; The light source array comprises a plurality of near-infrared light sources arranged in sequence, the receiver array comprises a plurality of light source receivers arranged in sequence, and the near-infrared light sources and the light source receivers correspond one to one; When the brain blood oxygen sensor performs brain detection, the fixing device is closely attached to the forehead of the user being measured, and the near-infrared light source on the fixing device emits near-infrared light. After the near-infrared light is scattered in the brain of the user being measured, the light source receiver on the fixing device receives the scattered near-infrared light signal, and the near-infrared light signal is used to calculate the brain blood oxygen content of the user being measured.

Images