Device, method and equipment for evaluating renal function in on-orbit special-cause environment

Abstract

The embodiment of the invention provides a renal function evaluation device, method and equipment in an in-orbit special cause environment. The device comprises an acquisition module used for acquiring ultrasonic data and physiological sign data of a user; the ultrasonic data comprises artery data acquired at the renal artery of the user by ultrasonic data acquisition equipment; the processing module is used for extracting an index value of a target artery index of the user from the ultrasonic data; extracting an index value of a target physiological index of the user from the physiological sign data; determining input information of a pre-trained renal perfusion state classification model according to the index value of the target artery index of the user and the index value of the target physiological index of the user; inputting the input information into a renal perfusion state classification model so as to classify the renal perfusion state of the user by using the renal perfusion state classification model; and evaluating the renal function of the user according to the classification result. According to the technical scheme provided by the embodiment of the invention, kidney function evaluation can be realized in a special scene.

Description

[0001] Cross-references

[0002] This application claims the priority of Chinese patent application No. 2025101269140, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to an apparatus, method and device for evaluating renal function in an on-orbit specific environment. Background Art

[0004] The kidney is an important organ of the human body, responsible for excreting metabolic products and toxic substances from the body and maintaining water, electrolyte and acid-base balance. Kidney dysfunction can cause internal environmental disturbances. Taking the on-orbit special environment as an example, astronauts may be affected by the metabolic and cardiovascular regulation functions of the kidneys in the microgravity environment of the space station, which may cause changes in the role of the kidneys in maintaining water and electrolyte balance in the body, thereby affecting the kidney's filtering function and reabsorption capacity.

[0005] Renal perfusion imaging technology is mainly used to reflect the blood perfusion status of renal tissue. It can restore the actual situation of renal blood vessels as much as possible and assist in the evaluation of renal blood flow and renal function. At present, traditional renal perfusion imaging technology mostly uses large-scale equipment such as computed tomography (CT) and magnetic resonance imaging (MRI) for examination, and then evaluates renal blood flow and renal function based on the examination results.

[0006] However, this type of inspection equipment is often large in size and installed in fixed places such as hospitals. Therefore, in some outdoor emergency scenarios or on-orbit special environments, this technology cannot be used to complete the inspection of renal perfusion status, resulting in the inability to evaluate renal blood flow and renal function status. Therefore, a new solution is needed. Summary of the invention

[0007] In view of the above problems, the present application is proposed to provide an on-orbit renal function assessment device, method and equipment in a special environment that solves the above problems or at least partially solves the above problems.

[0008] In a first aspect of the present application, a renal function assessment device for use in an on-orbit special environment is provided, comprising:

[0009] An acquisition module, used to: acquire ultrasound data and physiological sign data of a user; the ultrasound data includes arterial data acquired by an ultrasound data acquisition device at the renal artery of the user;

[0010] A processing module, configured to: extract an index value of a target artery index of the user from the ultrasound data; extract an index value of a target physiological index of the user from the physiological sign data; determine input information of a pre-trained renal perfusion state classification model according to the index value of the target artery index of the user and the index value of the target physiological index of the user; input the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model; and evaluate the renal function of the user according to the classification result;

[0011] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0012] A second aspect of the present application provides a method for assessing renal function, comprising:

[0013] Acquiring ultrasound data and physiological sign data of the user; the ultrasound data includes arterial data collected by an ultrasound data acquisition device at the renal artery of the user;

[0014] extracting an index value of a target artery index of the user from the ultrasound data;

[0015] Extracting an index value of a target physiological index of the user from the physiological sign data;

[0016] Determining input information of a pre-trained renal perfusion state classification model according to an index value of a target arterial index of the user and an index value of a target physiological index of the user;

[0017] Inputting the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model;

[0018] evaluating the renal function of the user according to the classification result;

[0019] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0020] A third aspect of the present application provides a method for training a renal perfusion state classification model, comprising:

[0021] Acquire a training sample, wherein the training sample includes: an index value of a target artery index of a sample user, an index value of a target physiological index of the sample user, and a real renal perfusion state category of the sample user;

[0022] Determining input information of a renal perfusion state classification model to be trained according to the index value of the target artery index of the sample user and the index value of the target physiological index of the sample user;

[0023] Inputting the input information into the renal perfusion state classification model, so as to classify the renal perfusion state of the user using the renal perfusion state classification model, and obtain the predicted renal perfusion state category of the sample user;

[0024] Optimizing the parameters in the renal perfusion state classification model with the goal of minimizing the difference between the true renal perfusion state category and the predicted renal perfusion state category;

[0025] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0026] A fourth aspect of the present application provides a method for classifying renal perfusion status, comprising:

[0027] Acquiring ultrasound data and physiological sign data of the user; the ultrasound data includes arterial data collected by an ultrasound data acquisition device at the renal artery of the user;

[0028] extracting an index value of a target artery index of the user from the ultrasound data;

[0029] Extracting an index value of a target physiological index of the user from the physiological sign data;

[0030] Determining input information of a pre-trained renal perfusion state classification model according to an index value of a target arterial index of the user and an index value of a target physiological index of the user;

[0031] Inputting the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model;

[0032] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0033] In a fifth aspect of the present application, a device for classifying renal perfusion status is provided, comprising:

[0034] An acquisition module, used to: acquire ultrasound data and physiological sign data of a user; the ultrasound data includes arterial data acquired by an ultrasound data acquisition device at the renal artery of the user;

[0035] A processing module, configured to: extract an index value of a target artery index of the user from the ultrasound data; extract an index value of a target physiological index of the user from the physiological sign data; determine input information of a pre-trained renal perfusion state classification model according to the index value of the target artery index of the user and the index value of the target physiological index of the user; input the input information into the renal perfusion state classification model, so as to classify the renal perfusion state of the user using the renal perfusion state classification model;

[0036] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0037] In a sixth aspect of the present application, an electronic device is provided. The electronic device comprises: a memory and a processor, wherein:

[0038] The memory is used to store programs;

[0039] The processor is coupled to the memory and is used to execute the program stored in the memory to implement the methods provided in the second, third and fourth aspects above.

[0040] In a seventh aspect of the present application, a computer-readable storage medium storing a computer program is provided, and when the computer program is executed by a computer, the methods provided in the second, third and fourth aspects above can be implemented.

[0041] In an eighth aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the methods provided in the second, third and fourth aspects above.

[0042] In the technical solution provided in the embodiment of the present application, the renal perfusion state classification model can classify the user's renal perfusion state using the data collected by the ultrasonic data acquisition device at the user's renal artery and some basic physiological sign data of the user. In other words, when classifying the user's renal perfusion state, the renal perfusion state classification model does not rely on brain magnetic resonance data, but relies on renal artery ultrasound data and basic physiological sign data that are easily obtained in special scenarios. It can be seen that the technical solution provided in the embodiment of the present application can evaluate the user's renal perfusion state in some special scenarios, such as: aerospace scenarios, outdoor first aid scenarios.

[0043] In addition, the technical solution provided in the embodiment of the present application can further evaluate the user's renal function based on the classification results of the renal perfusion state based on the renal perfusion state classification model. It can be seen that the technical solution provided in the embodiment of the present application can evaluate the user's renal function in an on-orbit special environment (or aerospace scene) or an outdoor first aid scene. Note: The on-orbit special environment refers to the special environment faced by astronauts during space flight, mainly including microgravity, radiation, circadian rhythm disorders, confined spaces, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1a A structural block diagram of a renal function assessment device provided in one embodiment of the present application;

[0046] Figure 1b A structural block diagram of a method for evaluating renal function provided in one embodiment of the present application;

[0047] Figure 2 A flowchart of a model training method provided in one embodiment of the present application;

[0048] Figure 3 A schematic diagram of a process flow of a method for classifying renal perfusion status provided in one embodiment of the present application;

[0049] Figure 4 A structural block diagram of a renal perfusion state classification device provided in one embodiment of the present application;

[0050] Figure 5 A schematic diagram of a renal function assessment system provided in one embodiment of the present application;

[0051] Figure 6 A structural block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below according to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0053] In addition, some of the processes described in the specification, claims and the above-mentioned figures of the present application include multiple operations that appear in a specific order, and these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0055] Changes in the kidney's own hemodynamics play an important role in the onset of renal injury. In many disease states, pathogenic factors first cause changes in systemic hemodynamics (such as blood pressure, volume, cardiac output, etc.); changes in systemic hemodynamics will cause changes in renal hemodynamics, thereby causing a decrease in glomerular filtration rate, abnormal renal function and damage. Therefore, the kidney's own hemodynamics should be worthy of attention.

[0056] Renal hemodynamics mainly include two aspects: pressure perfusion and flow perfusion. Flow perfusion is usually measured by renal blood flow (RBF). The magnetic resonance-based pseudo-continuous arterial spin labeling (Pseudo-Continuous ASL, PCASL) sequence is a non-invasive perfusion imaging technique that uses water molecules in the blood as endogenous tracers to evaluate tissue perfusion. In renal perfusion imaging, the PCASL sequence under multiple delay times (Post Label Delay, PLD) can provide important information about renal blood flow and function.

[0057] Taking into account that magnetic resonance data cannot be obtained in special scenarios, the embodiments of the present application provide a solution for predicting renal perfusion status based on ultrasound data and some basic physiological sign data, so as to solve or partially solve the problem that renal perfusion status and renal function cannot be evaluated in current special scenarios.

[0058] Figure 1a: is a structural block diagram of a renal function assessment device provided in one embodiment of the present application. The renal function assessment device may include, but is not limited to: a device integrated in any terminal device such as a smart phone, a tablet computer, a PDA (Personal Digital Assistant), a smart TV, a laptop computer, a desktop computer, a smart wearable device, etc. Figure 1a As shown, the apparatus may include: an acquisition module 101 and a processing module 102. Optionally, the apparatus further includes a display module for displaying the processing result (eg, evaluation result, classification result) of the apparatus, such as a screen in a terminal device.

[0059] The acquisition module 101 is used to: acquire ultrasound data and physiological sign data of the user; the ultrasound data includes arterial data acquired by an ultrasound data acquisition device at the renal artery of the user.

[0060] The ultrasonic data acquisition device acquires the above arterial data in vitro. The ultrasonic data acquisition device may be a portable Doppler ultrasonic device. The ultrasonic data acquisition device may send the acquired arterial data to the acquisition module 101 .

[0061] Exemplarily, the ultrasound data may include ultrasound spectrum data.

[0062] Optionally, the physiological sign data may include physiological sign data collected from the user by a physiological data collection device (eg, an electrocardiogram monitor, a blood pressure monitor, etc.).

[0063] Optionally, physiological sign data may be manually input by the user through the screen, such as heart rate, blood pressure, etc.

[0064] The processing module 102 is used to extract the index value of the target artery index of the user from the ultrasound data, and extract the index value of the target physiological index of the user from the physiological sign data.

[0065] The index value of the target artery index of the user can be obtained by analyzing the ultrasound data, such as ultrasound spectrum data. The index value of the target physiological index of the user can be obtained by analyzing the physiological sign data.

[0066] The target arterial index is an arterial index related to the renal artery, which may include: one or more arterial indexes of vascular inner diameter, vascular elasticity, peak systolic blood flow velocity (Vs), end-diastolic blood flow velocity (Vd), mean blood flow velocity (Vm), resistance index (RI), pulsatility index (PI), systolic / diastolic ratio (S / D), acceleration slope (AS), acceleration time (AT), time to peak velocity (TAmax), and mean acceleration time (T1mean), wherein the peak systolic blood flow velocity (Vs), end-diastolic blood flow velocity (Vd), mean blood flow velocity (Vm), resistance index (RI), pulsatility index (PI), systolic / diastolic ratio (S / D), acceleration slope (AS), acceleration time (AT), time to peak velocity (TAmax), and mean acceleration time (T1mean) may be collectively referred to as hemodynamic parameters. Optionally, in order to improve the classification accuracy of the model, key arterial indexes that affect the renal perfusion state may be screened out from multiple arterial indexes related to the renal artery as target arterial indexes.

[0067] Through research, it is found that renal blood flow is supplied by the renal artery, which is divided into several main segments: the hilar part, the segmental artery and the interlobar artery. There is a certain correlation between the blood flow of each segment and the perfusion of the kidney. In order to improve the classification accuracy of the renal perfusion state, the arterial index of the renal artery can be refined. Exemplarily, the target arterial index includes: the arterial index of the hilar part, the arterial index of the segmental artery, and the arterial index of the interlobar artery. Among them, the arterial index of any segment can include one or more arterial indexes of vascular inner diameter, vascular elasticity, peak systolic blood flow velocity (Vs), end-diastolic blood flow velocity (Vd), mean blood flow velocity (Vm), resistance index (RI), pulsatility index (PI), systolic / diastolic ratio (S / D), acceleration slope (AS), acceleration time (AT), time to reach peak velocity (TAmax), and average acceleration time (T1mean).

[0068] In some embodiments, the ultrasound data includes arterial data acquired by the ultrasound data acquisition device at the hilum, segmental arteries, and interlobar arteries of the user's renal artery, respectively.

[0069] Among them, the target physiological index may include: age, gender, body mass index (BMI), heart rate, systolic blood pressure, diastolic blood pressure, the ratio of systolic blood pressure to diastolic blood pressure, and one or more physiological indicators of the electrocardiogram obtained by analyzing the electrocardiogram data. Among them, systolic blood pressure and diastolic blood pressure can be collectively referred to as blood pressure. These physiological indicators are important indicators for assessing individual health status and monitoring disease progression. Due to the interaction between the heart and the kidneys, multiple electrocardiogram indicators are obtained by performing multiple cardiac function analyses such as heart rate variability (HRV) analysis, atrial fibrillation analysis, QRS complex (Q wave-R wave-S wave complex) analysis, and pacing analysis on the electrocardiogram data. Using these physiological indicators is helpful for evaluating the renal perfusion state. Optionally, in order to improve the classification accuracy of the model, key physiological indicators that affect the renal perfusion state can be screened out from multiple physiological indicators as target physiological indicators.

[0070] In an optional embodiment, the processing module 102 is further used to: extract the index value of the target artery index of the user from the ultrasound data, and extract the index value of the target physiological index of the user from the physiological sign data according to the index screening result; wherein the index screening result includes the target artery index and the target physiological index obtained by index screening.

[0071] The index screening result is obtained by screening from the multiple physiological indicators and the multiple arterial indicators based on the correlation between the renal perfusion index and the multiple physiological indicators and the correlation between the renal perfusion index and the multiple arterial indicators.

[0072] The plurality of arterial indices are related to the renal artery, for example, arterial indices related to the hilum of the kidney, arterial indices related to the segmental arteries of the kidney, and arterial indices related to the interlobar arteries.

[0073] Among them, the correlation relationship is obtained based on sample data statistics.

[0074] The renal perfusion index may include but is not limited to renal blood flow and renal artery transit time.

[0075] The screening process of the above arterial indexes and physiological indexes will be described in detail in the following embodiments.

[0076] In some embodiments, the target physiological index and target arterial index to be extracted may be stored in advance in a storage module (e.g., memory) of the device. In this way, the subsequent processing module 101 may obtain the target physiological index and target arterial index to be extracted from the storage module of the device, and complete data extraction based on the target physiological index and target arterial index.

[0077] The processing module 102 is further configured to determine input information of a pre-trained renal perfusion state classification model according to the index value of the target arterial index of the user and the index value of the target physiological index of the user.

[0078] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0079] In some embodiments, the renal perfusion status classification model can be based on a deep learning model architecture, for example, a deep learning model architecture combining convolutional neural networks (CNN) and fully connected layers.

[0080] The renal perfusion state classification model may be trained based on training samples, which may include: the index value of the target artery index of the sample user, the index value of the target physiological index of the sample user, and the real renal perfusion state category of the sample user.

[0081] In practical applications, multiple renal perfusion state categories can be divided according to the variation range of the renal perfusion index of the sample data, for example, three categories of reduction, normal, and increase can be included, or normal, slightly reduced, moderately reduced, severely reduced, and / or normal, slightly increased, moderately increased, and severely increased. The specific division situation will be set according to the actual data change distribution, and the embodiment of the present application does not make specific limitations on this. Exemplarily, the threshold values ​​corresponding to each of the multiple renal perfusion state categories (for example, the upper and lower limits of the renal perfusion index) can be determined according to the variation range of the renal perfusion index of the sample data, and the sample users can be classified based on the threshold value to determine the user's true renal perfusion state category.

[0082] Structurally, the renal parenchyma (i.e., kidney) is divided into two parts: the renal cortex and the renal medulla. The renal cortex is located in the shallow outer layer of the kidney, and is mainly composed of glomeruli and renal tubules, which are connected to the renal columns located between the renal pyramids. The glomeruli are responsible for the initial filtration of blood, while the renal tubules further process the filtered fluid, recover necessary substances, and excrete waste from the body. The renal medulla is a structure deep in the kidney, which is composed of more than ten renal pyramids and is mainly responsible for filtering impurities and storing urine.

[0083] In practical applications, the renal perfusion state classification model can be trained to classify the renal perfusion state of the entire kidney, and can also be trained to classify the renal perfusion states of the renal cortex and renal medulla, respectively. When the renal perfusion state classification model needs to be trained to classify the renal perfusion state of the entire kidney, the true renal perfusion state category in the training sample refers to the true renal perfusion state category of the entire kidney. When the renal perfusion state classification model needs to be trained to classify the renal perfusion states of the renal cortex and renal medulla, respectively, the true renal perfusion state category in the training sample includes the true renal perfusion state category of the renal cortex and the true renal perfusion state category of the renal medulla. Among them, the true renal perfusion state category is used to indicate the renal perfusion state category of the desired model output, which can also be called a training label.

[0084] The real renal perfusion state category of the renal cortex of the sample user is determined based on the segmentation mask of the renal cortex of the sample user and the target renal blood flow RBF map and target renal artery transmission time ATT map of the sample user. The real renal perfusion state category of the renal medulla of the sample user is determined based on the segmentation mask of the renal medulla of the sample user and the target renal blood flow map and target renal artery transmission time map of the sample user. The segmentation mask of the renal cortex and the segmentation mask of the renal medulla are determined by the trained segmentation model based on the target renal structure map of the sample user. Wherein the segmentation model can be a model based on deep learning. The target renal structure map, target renal blood flow RBF map and target renal artery transmission time ATT map of the sample user are obtained by image registration of the renal structure map, renal blood flow RBF map and renal artery transmission time ATT map of the sample user. That is to say, the same anatomical feature point of the kidney (for example: vascular branch point) has the same position (pixel coordinates) in the three images of the target renal structure map, target renal blood flow RBF map and target renal artery transmission time ATT map of the sample user.

[0085] The multi-delayed ASL data can be processed to obtain an ATT map and a renal perfusion (RBF) map under each PLD, and a corrected RBF map is generated based on the arterial transmission time ATT map and the RBF maps under multiple PLDs. The index value of the renal perfusion index of the sample user is determined based on the corrected RBF and ATT maps. Among them, the renal structural image is obtained by applying T1-weighted imaging to perform magnetic resonance scanning on the kidney to obtain the morphological and structural information of the kidney. In other words, the renal structural image includes the morphological and structural information of the kidney.

[0086] The parameters of the renal perfusion state classification model are optimized with the goal of minimizing the difference between the predicted renal perfusion state category of the sample user and the true renal perfusion state category; the predicted renal perfusion state category is predicted by the renal perfusion state classification model based on the index value of the target artery index of the sample user and the index value of the target physiological index of the sample user. The specific training process of the model will be described in detail in the following embodiments.

[0087] Alternatively, the mean square error (MSE) can be used as the loss function of the model to continuously reduce the difference between the true category and the predicted category through the back propagation of the model. In addition, this loss function converges quickly and has great advantages in practical applications.

[0088] In some embodiments, the input information may include: an index value of a target arterial index of the user and an index value of a target physiological index of the user.

[0089] The processing module 102 is further configured to: input the input information into the renal perfusion state classification model, so as to classify the renal perfusion state of the user using the renal perfusion state classification model.

[0090] Among them, the renal perfusion status classification model can extract features from the input information, and then classify the user's renal perfusion status based on the extracted features.

[0091] When the renal perfusion status classification model is a deep learning model architecture that combines a convolutional neural network and a fully connected layer, the convolutional neural network can be used to extract features from the input information to obtain features, and then the fully connected layer can be used to classify the user's renal perfusion status based on the features.

[0092] The processing module 101 is further used to: evaluate the renal function of the user according to the classification result.

[0093] That is, the user's renal function is evaluated according to the user's renal perfusion status category.

[0094] In some embodiments, evaluating the user's renal function refers to: estimating whether the user's renal function biochemical indicators are abnormal. The renal function biochemical indicators may include one or more of serum creatinine, urea nitrogen, and urine protein.

[0095] In an optional implementation, the evaluation process may include the following steps:

[0096] S11. Obtaining a correspondence between a pre-configured renal perfusion state category and a value range of a renal function biochemical index.

[0097] The corresponding relationship is obtained based on sample data statistics.

[0098] Exemplarily, there are multiple renal perfusion state categories, and for each renal perfusion state category, the index values ​​of the renal function biochemical indicators of multiple sample users belonging to the renal perfusion state category can be obtained from the sample data; for each renal perfusion state category, the index values ​​of the collected renal function biochemical indicators are statistically analyzed, including: calculating the mean, median, standard deviation, minimum value and maximum value, etc., to determine the value distribution of the renal function indicator, and based on the value distribution, determine the value range of the renal function indicator under each renal perfusion state category. For example: the value range of the renal function indicator under each renal perfusion state category is defined by the maximum and minimum values ​​of the renal function indicator obtained by statistics under the renal perfusion state category. It should be noted that the value ranges of the renal function indicators under different renal perfusion state categories are different, and a corresponding relationship between different renal perfusion state categories and the value ranges of the renal function indicators under different renal perfusion state categories is established. The specific form of the corresponding relationship may include but is not limited to a table or a visual atlas.

[0099] Among them, the biochemical indicators of renal function in the sample users can be obtained through blood tests.

[0100] S12. According to the renal perfusion state category in the classification result, the corresponding relationship is searched to determine the value range of the renal function biochemical index of the user.

[0101] The value range of the renal function biochemical index corresponding to the renal perfusion state category in the classification result in the corresponding relationship is determined as the value range of the renal function biochemical index of the user.

[0102] S13. Evaluate the renal function of the user according to the value range of the biochemical index of renal function of the user.

[0103] Optionally, the value range of the user's renal function biochemical index can be compared with the medical standard range of the renal function biochemical index to determine whether the user's renal function biochemical index is abnormal. The medical standard range refers to the normal range of the renal function biochemical index. For example, when the value range of the user's renal function biochemical index is included in the medical standard range of the renal function biochemical index, the user's renal function biochemical index is determined to be normal, otherwise, the user's renal function biochemical index is determined to be abnormal, wherein the abnormality may include: too low, too high, etc.

[0104] In the above embodiment, what is established is the corresponding relationship between the renal perfusion state category and the value range of the renal function biochemical index. As an option, the corresponding relationship between the renal perfusion state category and the evaluation result of the renal function biochemical index can also be established, and the corresponding relationship is obtained based on the statistics of the sample data. Among them, the evaluation result of the renal function biochemical index can be one of normal and abnormal. The evaluation result of the renal function index under each renal perfusion state category is determined by comparing the value range of the renal function index under the renal perfusion state category with the medical standard range of the renal function biochemical index. The specific determination process can refer to the corresponding content in the above embodiment. Establish a corresponding relationship between different renal perfusion state categories and the evaluation results of the renal function index under different renal perfusion state categories. The specific form of the corresponding relationship may include but is not limited to a table or a visual atlas. The determination process of the value range of the renal function index under each renal perfusion state category can refer to the corresponding content in the above embodiment.

[0105] In summary, the technical solution provided in the embodiments of the present application collects the basic physiological indicators of the subjects, the renal function biochemical indicators obtained by blood tests, and the renal artery arterial indicators determined based on ultrasound data, and establishes a mapping relationship between the renal artery arterial indicators and the renal perfusion state, and a mapping relationship between the renal perfusion state and the renal function biochemical indicators. The mapping relationship reveals the relationship between renal artery blood flow and renal perfusion efficiency, and the relationship between renal perfusion efficiency and functional performance, and applies it to special environments to achieve quantitative renal perfusion and renal function evaluation of the human body under special environments, which has the advantages of being non-invasive and highly operable under special environments.

[0106] A method for screening the above-mentioned arterial indexes and physiological indexes is described below. The method may include the following steps:

[0107] S21. Based on the sample data, determine the correlation between the renal perfusion index and multiple physiological indexes and the correlation between the renal perfusion index and multiple arterial indexes.

[0108] In some embodiments, the sample data includes an index value of a renal perfusion index of each sample user among a plurality of sample users, an index value of a plurality of physiological indexes, and an index value of a plurality of arterial indexes.

[0109] In some embodiments, the sample data is obtained based on a public biomedical database, such as the UK Biobank (UKB), and / or a locally constructed biomedical database.

[0110] The sample data can be statistically analyzed by statistical methods to determine the correlation between the renal perfusion index and multiple physiological indexes and the correlation between the renal perfusion index and multiple arterial indexes. For example, the correlation analysis can be performed by multiple statistical or machine learning methods such as multivariate logistic regression and Pearson correlation analysis.

[0111] Among them, the correlation relationship is used to characterize the degree of correlation between indicators.

[0112] S22. Based on the correlation between the renal perfusion index and the multiple physiological indexes and the correlation between the renal perfusion index and the multiple arterial indexes, a target arterial index and a target physiological index are screened from the multiple physiological indexes and the multiple arterial indexes.

[0113] In practical applications, importance ranking or threshold-based judgment can be used for screening.

[0114] Exemplarily, according to the correlation between the renal perfusion index and the multiple physiological indexes and the correlation between the renal perfusion index and the multiple arterial indexes, the multiple physiological indexes and the multiple arterial indexes are ranked by importance, and according to the result of the importance ranking, the target physiological index and the target arterial index are screened from the multiple physiological indexes and the multiple arterial indexes. For example, when the importance ranking is in descending order, the top N indexes are selected as the target physiological index and the target arterial index. Wherein, N is an integer greater than or equal to 1.

[0115] Exemplarily, the physiological index and the arterial index whose correlation with the renal perfusion index is greater than a preset correlation threshold are determined as the target physiological index and the target arterial index.

[0116] Optionally, when the renal perfusion index includes renal blood flow and ATT, since each renal perfusion index is very important for evaluating the renal perfusion state, the target physiological index and target arterial index related to each renal perfusion index can be screened out in the above manner for each renal perfusion index. That is, the index set finally screened includes the target physiological index and target arterial index related to each renal perfusion index.

[0117] Figure 1b A schematic diagram of a renal perfusion status classification method provided in one embodiment of the present application. The execution subject of the method may be a terminal device or a server device, and the present application embodiment does not specifically limit this. In the above-mentioned on-orbit special environment, the above-mentioned execution subject may be a terminal device. Figure 1b As shown, the method may include the following steps:

[0118] S101. Obtain ultrasound data and physiological sign data of a user.

[0119] The ultrasound data includes arterial data collected by an ultrasound data collection device at the user's renal artery.

[0120] S102: Extracting an index value of a target artery index of the user from the ultrasound data.

[0121] S103: extracting the index value of the target physiological index of the user from the physiological sign data.

[0122] S104: Determine input information of a pre-trained renal perfusion state classification model according to the index value of the target arterial index of the user and the index value of the target physiological index of the user.

[0123] S105. Input the input information into the renal perfusion state classification model, so as to classify the renal perfusion state of the user using the renal perfusion state classification model.

[0124] S105. Evaluate the user's renal function according to the classification result.

[0125] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0126] It should be noted here that: for the contents of each step not fully described in detail in the method provided in the embodiment of the present application, please refer to the corresponding contents in the above embodiment, which will not be repeated here. In addition, in addition to the above steps, the method provided in the embodiment of the present application may also include other parts or all of the steps in the above embodiments, which can be specifically referred to the corresponding contents in the above embodiments, which will not be repeated here.

[0127] Figure 2 The flowchart of a method for training a renal perfusion state classification model provided in one embodiment of the present application is shown in FIG. The execution subject of the method may be a terminal device or a server device, and the present application embodiment does not specifically limit this. Figure 2 As shown, the method may include the following steps:

[0128] 201. Obtain training samples.

[0129] The training samples include: the index value of the target artery index of the sample user, the index value of the target physiological index of the sample user, and the real renal perfusion state category of the sample user.

[0130] 202. Determine input information of a renal perfusion state classification model to be trained according to the index value of the target arterial index of the sample user and the index value of the target physiological index of the sample user.

[0131] 203. Input the input information into the renal perfusion state classification model, so as to classify the renal perfusion state of the user using the renal perfusion state classification model to obtain a predicted renal perfusion state category of the sample user.

[0132] 204. Optimize the parameters in the renal perfusion state classification model with the goal of minimizing the difference between the actual renal perfusion state category and the predicted renal perfusion state category.

[0133] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0134] It should be noted here that: for the contents of each step not fully described in detail in the method provided in the embodiment of the present application, please refer to the corresponding contents in the above embodiment, which will not be repeated here. In addition, in addition to the above steps, the method provided in the embodiment of the present application may also include other parts or all of the steps in the above embodiments, which can be specifically referred to the corresponding contents in the above embodiments, which will not be repeated here.

[0135] Figure 3 A schematic diagram of a renal perfusion status classification method provided in one embodiment of the present application. The execution subject of the method may be a terminal device or a server device, and the present application embodiment does not specifically limit this. In the above-mentioned on-orbit special environment, the above-mentioned execution subject may be a terminal device. Figure 3 As shown, the method may include the following steps:

[0136] 301. Obtain ultrasound data and physiological sign data of the user.

[0137] The ultrasound data includes arterial data collected by an ultrasound data collection device at the user's renal artery.

[0138] 302. Extract an index value of a target artery index of the user from the ultrasound data.

[0139] 303. Extract the index value of the target physiological index of the user from the physiological sign data.

[0140] 304. Determine input information of a pre-trained renal perfusion state classification model according to the index value of the target arterial index of the user and the index value of the target physiological index of the user.

[0141] 305. Input the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model.

[0142] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0143] It should be noted here that: for the contents of each step not fully described in detail in the method provided in the embodiment of the present application, please refer to the corresponding contents in the above embodiment, which will not be repeated here. In addition, in addition to the above steps, the method provided in the embodiment of the present application may also include other parts or all of the steps in the above embodiments, which can be specifically referred to the corresponding contents in the above embodiments, which will not be repeated here.

[0144] Figure 4 : is a structural block diagram of a renal perfusion status classification device provided in one embodiment of the present application. The renal perfusion status classification device may include but is not limited to: a device integrated in any terminal device such as a smart phone, a tablet computer, a PDA (Personal Digital Assistant), a smart TV, a laptop computer, a desktop computer, a smart wearable device, etc. Figure 4 As shown, the apparatus may include: an acquisition module 401 and a processing module 402. Optionally, the apparatus further includes a display module for displaying the processing result (eg, evaluation result, classification result) of the apparatus, such as a screen in a terminal device.

[0145] The acquisition module 401 is used to: acquire ultrasound data and physiological sign data of the user; the ultrasound data includes arterial data acquired by an ultrasound data acquisition device at the renal artery of the user;

[0146] The processing module 402 is used to: extract the index value of the target artery index of the user from the ultrasound data; extract the index value of the target physiological index of the user from the physiological sign data; determine the input information of the pre-trained renal perfusion state classification model according to the index value of the target artery index of the user and the index value of the target physiological index of the user; input the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model;

[0147] The renal perfusion status classification model is trained to classify the renal perfusion status.

[0148] It should be noted here that: the specific implementation of each module in the device provided in the embodiment of the present application that is not fully described in detail can refer to the corresponding content in the above embodiment, which will not be repeated here. In addition, in addition to the above modules, the method provided in the embodiment of the present application may also include other modules in the above embodiments, which can be specifically referred to the corresponding content in the above embodiments, which will not be repeated here.

[0149] Figure 5 Schematic diagram of the renal function assessment system provided in the embodiment of the present application. Figure 5As shown, the system includes: an ultrasonic data acquisition device 51 and a renal function assessment device 52, and the ultrasonic data acquisition device 51 and the renal function assessment device 32 are communicatively connected.

[0150] The renal function assessment device 52 may include an acquisition module 521 and a processing module 522. Optionally, the device 52 may also include a display module 523.

[0151] It should be noted here that the specific implementation and interaction of each device in the system provided in the embodiments of the present application can be found in the corresponding contents of the above embodiments, and will not be repeated here.

[0152] Figure 6 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present application. Figure 6 As shown, the electronic device includes a memory 1101 and a processor 1102. The memory 1101 can be configured to store various other data to support operations on the electronic device. Examples of these data include instructions for any application or method for operating on the electronic device. The memory 1101 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read only memory (EEPROM), an erasable programmable read only memory (EPROM), a programmable read only memory (PROM), a read only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0153] The memory 1101 is used to store programs;

[0154] The processor 1102 is coupled to the memory 1101 and is used to execute the program stored in the memory 1101 to implement the method provided by any of the above method embodiments.

[0155] Further, if Figure 6 As shown, the electronic device also includes: a communication component 1103, a display 1104, a power component 1105, an audio component 1106 and other components. Figure 6 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 6 Components shown.

[0156] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, the method provided by any of the above method embodiments can be implemented.

[0157] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, can implement the method provided by any of the above method embodiments.

[0158] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0159] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM (Read Only Memory) / RAM (Random Access Memory), a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A renal function assessment device for use in an on-orbit environment, characterized in that: include: An acquisition module, used to: acquire ultrasound data and physiological sign data of a user; the ultrasound data includes arterial data acquired by an ultrasound data acquisition device at the renal artery of the user; A processing module, used to: extract an index value of a target artery index of the user from the ultrasound data; Extracting the index value of the target physiological index of the user from the physiological sign data; determining the input information of a pre-trained renal perfusion state classification model according to the index value of the target arterial index of the user and the index value of the target physiological index of the user; inputting the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model; and evaluating the renal function of the user according to the classification result; The renal perfusion status classification model is trained to classify the renal perfusion status.

2. The device according to claim 1, characterized in that The ultrasound data includes arterial data collected by the ultrasound data collection device at the renal hilum, renal segmental artery and interlobar artery of the user respectively; The target arterial index includes an arterial index related to the renal hilum, an arterial index related to the renal segmental artery, and an arterial index related to the interlobar artery.

3. The device according to claim 1, characterized in that The processing module is used to: extract the index value of the target artery index of the user from the ultrasound data and extract the index value of the target physiological index of the user from the physiological sign data according to the index screening result; wherein the index screening result includes the target artery index and the target physiological index obtained by the index screening; The index screening result is obtained by screening from the multiple physiological indicators and the multiple arterial indicators based on the correlation between the renal perfusion index and multiple physiological indicators and the correlation between the renal perfusion index and multiple arterial indicators; the multiple arterial indicators are related to the renal artery.

4. The device according to claim 3, characterized in that The renal perfusion indexes include: renal blood flow and renal artery transit time.

5. The device according to any one of claims 1 to 4, characterized in that The training samples of the renal perfusion state classification model include: the index value of the target artery index of the sample user, the index value of the target physiological index of the sample user, and the real renal perfusion state category of the sample user; The parameters of the renal perfusion state classification model are optimized with the goal of minimizing the difference between the predicted renal perfusion state category of the sample user and the true renal perfusion state category; the predicted renal perfusion state category is predicted by the renal perfusion state classification model based on the index value of the target arterial index of the sample user and the index value of the target physiological index of the sample user.

6. The device according to any one of claims 1 to 4, characterized in that The processing module is used to: obtain the correspondence between the pre-configured renal perfusion state category and the value range of the renal function biochemical index; according to the renal perfusion state category in the classification result, search the correspondence to determine the value range of the renal function biochemical index of the user; evaluate the renal function of the user according to the value range of the renal function biochemical index of the user; The corresponding relationship is obtained based on sample data statistics.

7. A method for assessing renal function, characterized in that: include: Acquiring ultrasound data and physiological sign data of the user; the ultrasound data includes arterial data collected by an ultrasound data acquisition device at the renal artery of the user; extracting an index value of a target artery index of the user from the ultrasound data; Extracting an index value of a target physiological index of the user from the physiological sign data; Determining input information of a pre-trained renal perfusion state classification model according to an index value of a target arterial index of the user and an index value of a target physiological index of the user; Inputting the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model; evaluating the renal function of the user according to the classification result; The renal perfusion status classification model is trained to classify the renal perfusion status.

8. A method for training a renal perfusion state classification model, characterized in that: include: Acquire a training sample, wherein the training sample includes: an index value of a target artery index of a sample user, an index value of a target physiological index of the sample user, and a real renal perfusion state category of the sample user; Determining input information of a renal perfusion state classification model to be trained according to the index value of the target artery index of the sample user and the index value of the target physiological index of the sample user; Inputting the input information into the renal perfusion state classification model, so as to classify the renal perfusion state of the user using the renal perfusion state classification model, and obtain the predicted renal perfusion state category of the sample user; Optimizing the parameters in the renal perfusion state classification model with the goal of minimizing the difference between the true renal perfusion state category and the predicted renal perfusion state category; The renal perfusion status classification model is trained to classify the renal perfusion status.

9. A method for classifying renal perfusion status, characterized in that: include: Acquiring ultrasound data and physiological sign data of the user; the ultrasound data includes arterial data collected by an ultrasound data acquisition device at the renal artery of the user; extracting an index value of a target artery index of the user from the ultrasound data; Extracting an index value of a target physiological index of the user from the physiological sign data; Determining input information of a pre-trained renal perfusion state classification model according to an index value of a target arterial index of the user and an index value of a target physiological index of the user; Inputting the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model; The renal perfusion status classification model is trained to classify the renal perfusion status.

10. A renal perfusion status classification device, characterized in that: include: An acquisition module, used to: acquire ultrasound data and physiological sign data of a user; the ultrasound data includes arterial data acquired by an ultrasound data acquisition device at the renal artery of the user; A processing module, used to: extract an index value of a target artery index of the user from the ultrasound data; Extracting an index value of a target physiological index of the user from the physiological sign data; determining input information of a pre-trained renal perfusion state classification model according to the index value of the target arterial index of the user and the index value of the target physiological index of the user; inputting the input information into the renal perfusion state classification model to classify the renal perfusion state of the user using the renal perfusion state classification model; The renal perfusion status classification model is trained to classify the renal perfusion status.

11. An electronic device, characterized in that: include: A memory and a processor, wherein The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the method described in any one of claims 7 to 9.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a computer, the method according to any one of claims 7 to 9 can be implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 7 to 9 is implemented.

Images