Wearable non-invasive lung function monitoring equipment, system and device based on impedance imaging and medium

Abstract

The invention provides wearable non-invasive lung function monitoring equipment, system and device based on impedance imaging and a medium. The wearable non-invasive lung function monitoring equipment, system and device based on impedance imaging have the advantages that limitation of traditional equipment is overcome, complex operation of a patient is not needed, subjective interference is reduced, and imaging and function testing can be integrated to complete comprehensive lung function evaluation; 2, the device is highly portable and wearable, is extremely miniaturized and is suitable for multiple scenes, and the flexible sensor belt is comfortable and stable to wear; intelligence and interconnection are achieved, real-time remote medical treatment can be achieved through cloud data sharing, and the early diagnosis and management efficiency of diseases is improved in combination with the AI technology; the method can be applied to multiple scenes, and a high-value scheme is provided for chronic disease management, postoperative rehabilitation, health screening and the like; intelligent interaction and platform integration are supported, real-time online communication between doctors and patients is facilitated, and the hospital is assisted to improve diagnosis and treatment efficiency; and 6, personalized health management and diagnosis optimization are promoted, precise health prediction and intervention suggestions are given by depending on an AI algorithm, and a dynamic analysis tool is also provided to jointly manage the health trend and improve the treatment effect.

Description

Technical Field

[0001] The present application relates to the fields of medical equipment, respiratory diagnosis and telemedicine technology, and in particular to wearable non-invasive lung function monitoring equipment, systems, devices and media based on impedance imaging. Background Art

[0002] In the field of clinical application, traditional pulmonary function instruments have exposed a series of quite significant technical defects. When conducting the critical link of the breath test, it requires the test subject to cooperate highly and complete a series of complex exhalation action processes. This is undoubtedly a very challenging task for the elderly and children with relatively weak physical functions and limited understanding and cooperation ability, as well as critically ill patients with serious illnesses and physical exhaustion. In the actual operation process, these special groups often find it difficult to accurately complete the exhalation action according to the standard requirements, which frequently causes the test results to be unable to truly and objectively reflect the actual functional status of their lungs, greatly affecting the accuracy and reliability of clinical diagnosis.

[0003] From the perspective of the physical characteristics of the equipment, traditional pulmonary function testing equipment generally has the problem of large size and bulky structure. This characteristic severely limits the use of the equipment, making it confined to relatively fixed places within medical institutions for placement and operation, greatly restricting the application of the equipment in scenarios such as out-of-hospital scenarios, emergency treatment sites, and patient home health monitoring.

[0004] Although lung imaging technology has made certain progress in recent years, taking electrical impedance tomography (EIT) technology as an example, it can achieve continuous lung ventilation imaging, providing a new technical means for visual monitoring of lung function. However, this technology also has limitations. It lacks the ability to obtain traditional lung function parameters and cannot effectively obtain a series of clinically commonly used and critical lung function parameters such as lung capacity, ventilation, and diffusion function. This limits its comprehensive assessment of the patient's overall lung function status to a certain extent. At the same time, EIT equipment also has the disadvantage of being large in size, making it difficult to meet the needs of portability and wearable applications, and unable to achieve the ideal goal of patients performing lung function tests anytime and anywhere, and it is difficult to effectively meet the growing demand for personalized and convenient medical care. Summary of the invention

[0005] In view of the shortcomings of the prior art mentioned above, the purpose of this application is to provide a wearable non-invasive lung function monitoring device, system, apparatus and medium based on impedance imaging, which is used to solve the technical problem that the prior art cannot achieve the ideal goal of patients performing lung function testing anytime and anywhere, and it is difficult to effectively meet the growing personalized and convenient medical needs.

[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a wearable non-invasive lung function monitoring device based on impedance imaging, which includes: a wearable sensor belt module, which is equipped with an impedance sensor array for collecting lung impedance signals of a subject; the wearable sensor belt module is also integrated with a lung function parameter collection sensor, and the collected lung function parameters include peak expiratory flow, vital capacity, forced vital capacity and forced expiratory volume in one second; a data processing module, which is electrically connected to the wearable sensor belt module and is used to convert the collected lung impedance signal into a digital signal through an analog-to-digital conversion circuit. The digital signal converted by the analog-to-digital conversion circuit is processed by a firmware algorithm to generate a lung ventilation image after lung imaging calculation; a display and interaction module is electrically connected to the data processing module, and is used to display lung function parameter data and lung ventilation image data in real time; a wireless transmission module is electrically connected to the data processing module, and is used to transmit the lung function parameter data and lung ventilation image data to a remote medical diagnosis platform based on a wireless transmission protocol, so that the remote medical diagnosis platform can build a deep learning model architecture for judging the health status of the lungs; a battery management module is connected to the data processing module for power supply.

[0007] In some embodiments of the first aspect of the present application, the wearable sensor belt module includes a shell structure that can fit and cover the lung area of ​​the test person; the formation process of the shell structure includes: measuring the surface shape of the human lung area through three-dimensional scanning technology, and the measurement objects include the contour of the chest cavity, the distribution of ribs, and the expansion and contraction range of the lungs during breathing; and generating the shell structure based on the measurement data.

[0008] In some embodiments of the first aspect of the present application, the wireless transmission module uses a compression algorithm based on wavelet transform to compress signal and image data, and the compression processing process includes: decomposing the signal or image to be transmitted into wavelet coefficients of different frequencies and spatial positions; quantizing the wavelet coefficients according to their importance; encoding the quantized wavelet coefficients to generate compressed data; calculating the ratio of the amount of compressed data to the amount of original data to obtain the compression ratio, and evaluating whether the expected compression effect is achieved.

[0009] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a remote medical diagnosis system based on wearable non-invasive pulmonary function monitoring, including: a wearable non-invasive pulmonary function monitoring device; a remote medical diagnosis platform, which establishes a communication connection with the wearable non-invasive pulmonary function monitoring device.

[0010] In some embodiments of the second aspect of the present application, the telemedicine diagnosis platform includes multiple service entities participating in telemedicine services, and a blockchain node is embedded in the information management system of each of the service entities. The blockchain node is used to add new blocks to the entire blockchain network for adding medical data in accordance with the format and rules of the blockchain; and the blockchain node receives data synchronized from other nodes.

[0011] In some embodiments of the second aspect of the present application, the remote medical diagnosis platform constructs a deep learning model architecture based on the received lung function parameter data and lung ventilation image data, and the process includes: preprocessing the received lung function parameter data and lung ventilation image data to remove outliers and noise data; based on a deep learning model architecture that is a mixture of convolutional neural networks and recurrent neural networks, feature fusion of the lung function parameter data and lung ventilation image data, and model training.

[0012] In some embodiments of the second aspect of the present application, a spatiotemporal attention module is configured in the deep learning model architecture; the spatiotemporal attention module focuses on data changes at key time points of lung function sensor data based on the attention mechanism, and highlights prominent lesion areas of lung image data to enable the model to pay more attention to areas where problems may exist.

[0013] In some embodiments of the second aspect of the present application, the remote medical diagnosis platform is also configured with a generative adversarial network, which is used to supplement scarce lung image data; the generator in the generative adversarial network is used to generate simulated lung images, and the discriminator is used to distinguish between true and false images; the scarce lung image data includes but is not limited to: rare lung disease images, early lesion images, special types of infection images, and critical stages of disease progression images.

[0014] In some embodiments of the second aspect of the present application, when performing feature fusion, the deep learning model architecture dynamically adjusts the fusion weights of the lung function parameter data and the lung ventilation image data according to the output feedback of the model.

[0015] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a remote medical diagnosis method based on wearable non-invasive lung function monitoring, which is applied to a remote medical diagnosis platform; the method comprises: receiving lung function parameter data and lung ventilation image data from a wearable non-invasive lung function monitoring device, preprocessing the received data, and removing outliers and noise data; based on a deep learning model architecture that is a mixture of convolutional neural networks and recurrent neural networks, feature fusion of lung function parameter data and lung ventilation image data, and model training.

[0016] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the remote medical diagnosis method based on wearable non-invasive lung function monitoring is implemented.

[0017] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides a computer device, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the remote medical diagnosis method based on wearable non-invasive lung function monitoring.

[0018] As described above, the wearable non-invasive lung function monitoring equipment, system, device and medium based on impedance imaging of the present application have the following beneficial effects: First, it overcomes the limitations of traditional equipment, does not require complicated operations by patients, reduces subjective interference, and can integrate imaging and functional tests to complete comprehensive lung function assessment; second, it has highly portable and wearable characteristics, extreme miniaturization is suitable for multiple scenarios, and the flexible sensor belt is comfortable and stable to wear; third, it realizes intelligence and interconnection, and can share data in the cloud to achieve real-time telemedicine, and combine AI technology to improve the efficiency of early diagnosis and management of diseases; fourth, it can be applied to multiple scenarios to provide high-value solutions for chronic disease management, postoperative rehabilitation and health screening; fifth, it supports intelligent interaction and platform integration, facilitates real-time online communication between doctors and patients, and helps hospitals improve diagnosis and treatment efficiency; sixth, it promotes personalized health management and diagnosis optimization, relies on AI algorithms to give accurate health predictions and intervention recommendations, and also provides dynamic analysis tools to jointly manage health trends and improve treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Shown is a schematic structural diagram of a wearable non-invasive lung function monitoring device based on impedance imaging in one embodiment of the present application.

[0020] Figure 2 Shown is a schematic diagram of a human body using a wearable sensor belt module in one embodiment of the present application.

[0021] Figure 3 Shown is a structural schematic diagram of an analog-to-digital conversion circuit in an embodiment of the present application.

[0022] Figure 4 Shown is a structural schematic diagram of a remote medical diagnosis system based on wearable non-invasive lung function monitoring in one embodiment of the present application.

[0023] Figure 5 Shown is a flowchart of a remote medical diagnosis platform constructing a deep learning model in one embodiment of the present application.

[0024] Figure 6Shown is a schematic diagram of the structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] The technical solutions of the embodiments of the present application have a wide range of application scenarios. In hospitals, the emergency room can help to quickly diagnose respiratory emergencies, the respiratory ward is used to monitor the condition of hospitalized patients in real time, the operating room can evaluate surgical tolerance and ensure surgical safety, and the rehabilitation department assists in evaluating the effectiveness of rehabilitation training. In community clinics, it is used for daily diagnosis and treatment and health examinations, and can also provide long-term follow-up management for patients with chronic diseases. In home scenarios, it is suitable for daily health monitoring, helping chronic patients manage their conditions and monitoring the recovery of postoperative rehabilitation patients. In terms of Internet hospitals, it supports remote diagnosis and health consultation. Doctors can use the platform to follow up on chronic patients for a long time, adjust treatment plans based on uploaded data, and improve patients' quality of life. Due to the wide range of application scenarios, they are not listed here one by one.

[0027] like Figure 1 As shown, a schematic diagram of the structure of a wearable non-invasive lung function monitoring device based on impedance imaging in an embodiment of the present application is shown. The wearable non-invasive lung function monitoring device based on impedance imaging 1 includes a shell structure that fits and covers the lung area of ​​the subject; the shell structure is provided with the following multiple electrical modules: a wearable sensor band module 101, a data processing module 102, a display and interaction module 103, a wireless transmission module 104, and a battery management module 105.

[0028] The wearable sensor belt module 101 is configured with an impedance sensor array for collecting lung impedance signals of the subject; the wearable sensor belt module 101 is also integrated with a lung function parameter collection sensor, and the collected lung function parameters include peak expiratory flow, vital capacity, forced vital capacity and forced expiratory volume in the first second.

[0029] In terms of the layout of the impedance sensor array, the wearable sensor belt module can be equipped with 4 to 128 high-precision impedance sensors. Figure 2In the human body diagram shown in the figure, there are multiple small dots evenly distributed in the lung area, each of which represents an impedance sensor. The number of sensors in the figure is only an example and not a limitation. These high-precision sensors are core components that obtain information by measuring changes in the electrical impedance of human tissues and organs. Specifically, when the lungs breathe, the internal gas content, tissue morphology, etc. will change, which will cause changes in electrical impedance. High-precision sensors can accurately capture these subtle changes and provide a data basis for subsequent accurate analysis of lung function.

[0030] It should be understood that the impedance sensor measures the lung impedance signal based on the lung impedance imaging technology (EIT). When the alternating current passes through the human tissue, the tissue's resistance to the current is not only the resistance part, but also the reactance part. The reactance is mainly the resistance to the alternating current caused by the capacitance and inductance effects. In the EIT system, a weak alternating current is applied to the human body, and the human tissue (such as lung tissue) will show capacitive and inductive characteristics under the action of this alternating current. For example, the cell membrane of a cell can be regarded as a capacitor, and the ion distribution inside and outside the cell will produce a capacitive effect. When the alternating current passes through, this capacitive effect will produce reactance. Moreover, the inductive effect in the human tissue (although relatively weak) will also hinder the alternating current, which is also part of the reactance. The relationship between the measured body surface voltage and the injected alternating current is described by the impedance. According to the complex form of Ohm's law Z=U / I (where Z is the impedance, U is the voltage, and I is the current). The impedance sensor in the embodiment of the present application can select a resistive impedance sensor, a capacitive impedance sensor or an inductive impedance sensor, which is not limited in this embodiment.

[0031] It is worth noting that the wearable sensor belt module in the embodiment of the present application is designed to be wearable and is specifically worn in the lung area. It is close to the human lung position, convenient for real-time data collection and portable, and will not affect the user's daily activities too much, and can achieve long-term continuous monitoring. In addition, the wearable sensor belt module implements non-invasive monitoring, and does not require invasive methods such as surgery and intubation for monitoring, reducing harm and pain to the patient's body. There is no need for the test subject to deliberately cooperate to complete complex breathing movements, which is suitable for patients of different ages and health conditions.

[0032] Preferably, a shell structure that can closely fit the lung area of ​​the person being tested can be manufactured in the following manner: using three-dimensional scanning technology to accurately measure the surface shape of the human lung area, including the outline of the chest cavity, the distribution of the ribs, and the expansion and contraction range of the lungs during breathing; based on these data, a shell shape that can fit the lung area is designed, such as using an arc-shaped shell structure or a shell structure that matches the chest cavity curve, so that it can closely fit the chest and cover the lung area without causing compression to the chest cavity and lungs or hindering breathing movement.

[0033] Preferably, the shell structure of the wearable non-invasive pulmonary function monitoring device in the embodiment of the present application adopts flexible materials, such as elastic fabrics, soft silicone or stretchable composite materials, which can automatically adjust the shape according to the ups and downs of the lungs when the human body breathes. For example, an elastic fabric is used on the outer shell of the device, and when the user inhales, the fabric can stretch accordingly, and return to its original state when exhaling, ensuring that the device does not restrict the normal physiological process of breathing. Furthermore, the wearable non-invasive pulmonary function monitoring device is equipped with an adjustable fixing device, such as an adjustable length chest strap or shoulder strap, which can adapt to users of different body shapes and chest sizes. The chest strap can use adjustment methods such as Velcro, buckles or elastic bands to ensure that the device is firmly fixed in the lung area while ensuring comfort.

[0034] Preferably, the shell structure of the wearable non-invasive pulmonary function monitoring device in the embodiment of the present application is designed with a buffer structure at the part in contact with the human body, such as adding an air cushion, sponge or soft gel pad between the chest strap and the device shell, so as to evenly distribute the weight of the device on the chest, reduce local pressure, and avoid discomfort and skin damage caused by long-term wearing. In addition, the center of gravity distribution of the device can be optimized, and the heavier components, such as the battery, are placed as close to the center of gravity of the human body as possible, so that the device is more stable and comfortable when worn, and does not cause a sense of falling or discomfort due to uneven weight distribution.

[0035] In addition, considering the two different breathing modes of chest breathing and abdominal breathing, in order to more comprehensively understand the breathing condition of the test subject, the embodiment of the present application also integrates a pulmonary function parameter acquisition sensor in the wearable sensor belt module 101. For example, a flow sensor is integrated in the wearable sensor belt module 101, which measures the peak expiratory flow (PEF) by detecting the heat taken away during the gas flow process. The air inlet and outlet of the flow sensor are usually connected to the respiratory channel, and good air tightness is maintained to ensure accurate measurement of the flow of respiratory gas. For another example, a pressure sensor is integrated in the wearable sensor belt module 101, which uses the piezoresistive effect of the material to convert pressure changes into electrical signal changes, thereby collecting parameters such as vital capacity (VC), forced vital capacity (FVC) and forced expiratory volume in the first second (FEV1). The installation position of the pressure sensor is usually near the respiratory channel to accurately sense the pressure changes during lung breathing; in terms of hardware connection, the pressure sensor also needs to be connected to the signal acquisition circuit through a signal line.

[0036] The data processing module 102 is electrically connected to the wearable sensor belt module 101, and is used to convert the collected lung impedance signal into a corresponding digital signal through an analog-to-digital conversion circuit, and to process the digital signal converted by the analog-to-digital conversion circuit through a firmware algorithm to perform lung imaging calculations to generate a lung ventilation image.

[0037] The purpose of the analog-to-digital conversion circuit (also referred to as A / D conversion circuit) in this application is to convert the analog signal from the impedance sensor array into a digital signal. The structure of the analog-to-digital conversion circuit is as follows: Figure 3 As shown, it includes a sampling module 301, a quantization module 302 and an encoding module 303. The sampling module 301 samples the analog signal within a certain time interval, and this time interval determines the sampling frequency; for example, for respiratory monitoring, a higher sampling frequency (such as dozens or even hundreds of times per second) may be required to accurately capture changes in the respiratory cycle. The quantization module 302 is electrically connected to the sampling module 301, and is used to convert the amplitude of the sampled analog signal into a discrete digital value. This is done by dividing the amplitude range of the analog signal into multiple quantization levels, and representing it as a corresponding digital code according to which quantization level it falls into. The encoding module 303 is electrically connected to the quantization module 302, and is used to represent the quantized result as a binary number for subsequent digital processing.

[0038] Firmware algorithms refer to a series of calculation rules and logic programs embedded in the firmware of a hardware device. Firmware is usually software stored in the non-volatile memory (such as ROM, EEPROM or flash memory) of a hardware device. It is a part of the hardware device and provides basic operating functions and features for the device. Firmware algorithms are algorithms contained in these firmware to complete specific tasks or achieve specific functions.

[0039] The digital signal converted by the analog-to-digital conversion circuit is processed by a firmware algorithm to perform lung imaging calculations. The process includes: first, filtering the signal output by the analog-to-digital conversion circuit to remove noise and interference. For example, for a respiratory signal, a low-pass filter can be used to remove high-frequency noise because the respiratory signal is a relatively low-frequency signal. Secondly, key features are extracted from the preprocessed signal. For example, for lung monitoring, features such as respiratory frequency, respiratory depth, respiratory pattern (normal breathing, rapid breathing, gasping, etc.), and lung sound frequency can be extracted. Finally, a lung image is generated using a computer graphics algorithm by mapping the extracted features to the pixel value or grayscale value of the image. For example, the state of the lungs is displayed on the image according to different respiratory features (such as different respiratory frequency ranges corresponding to different colors or grayscales).

[0040] The display and interaction module 103 is electrically connected to the data processing module 102 and is used for displaying lung function parameter data and lung ventilation image data in real time.

[0041] In some examples, the display and interaction module 103 has a built-in high-resolution screen. High resolution means that the screen can display more pixels, thereby showing clearer and more delicate images and text information. For lung monitoring equipment, a high-resolution screen can clearly display the details of lung ventilation images, such as the texture of the lungs, subtle changes in ventilation areas, etc., which helps doctors or operators to observe and analyze lung conditions more accurately. At the same time, for the display of real-time parameters such as respiratory rate, tidal volume, oxygen saturation and other numerical values, a high-resolution screen can ensure that the numbers are clear and readable, reducing the possibility of misreading.

[0042] High-resolution screens can preferably be OLED screens, which can present brighter colors and higher contrast when displaying lung ventilation images, making different areas of the lungs and ventilation changes more clearly identifiable. For example, when displaying low-ventilation areas of the lungs, the OLED screen can clearly distinguish them from normal ventilation areas through high contrast, which helps doctors to more keenly detect potential problems. In addition, a high refresh rate can be introduced, and a high refresh rate screen can update the screen at a faster speed, which is particularly important for the display of dynamic lung ventilation images. For example, increasing the screen refresh rate to 120Hz or even higher can more smoothly display the dynamic process of lung ventilation and reduce the freeze and smear phenomenon of the screen. This is of great significance for observing rapid ventilation changes in the lungs, such as the condition of the lungs during strenuous exercise or shortness of breath.

[0043] The real-time parameters described here refer to the data related to lung function that changes over time during the monitoring process. These parameters are collected in real time through the connected sensors, then transmitted to the processing unit of the device for analysis and processing, and finally displayed on the screen. For example, the flow and pressure data during the breathing process are obtained through the respiratory flow sensor and the pressure sensor, and the parameters such as tidal volume and minute ventilation are calculated and updated in real time. The lung ventilation image presents the dynamic process of lung ventilation in a visual form through specific imaging technology (such as the generation using computer graphics algorithms mentioned above). This can help doctors intuitively understand the ventilation of the lungs and determine whether there are problems such as uneven ventilation and local obstruction.

[0044] The wireless transmission module 104 is electrically connected to the data processing module 102 and is used to transmit the lung function parameter data and the lung ventilation image data to the outside based on the wireless transmission protocol for providing telemedicine services.

[0045] Exemplarily, the wireless transmission module 104 can transmit data to the PC, mobile phone and cloud of the telemedicine diagnosis platform via Bluetooth or Wi-Fi, thereby supporting telemedicine services. Bluetooth is a short-range wireless communication technology used to transmit data collected by the device (such as real-time parameters of lung monitoring, imaging data, etc.) to a close PC or mobile phone. Its advantages are low power consumption, convenient connection, and simple pairing between devices. For example, when a patient uses a portable lung monitoring device, it can quickly connect to a mobile phone around it via Bluetooth, and transmit the monitoring data to the mobile phone application in real time, so that the patient can check his health status at any time. Wi-Fi can provide a higher data transmission rate and a relatively large transmission range, and can stably transmit a large amount of complex lung monitoring data (such as high-resolution lung imaging, long-term monitoring data records) to a PC or upload it to the cloud. For example, in a hospital environment, a doctor can quickly transfer the patient's lung monitoring device data to his own PC through the Wi-Fi network in the ward for detailed analysis and diagnosis. At the same time, the data is uploaded to the cloud, which is convenient for subsequent long-term storage, big data analysis, and data sharing between different medical institutions. Telemedicine services can be realized through wireless transmission, and doctors can make remote diagnoses and provide patients with timely medical advice and treatment plans. For example, patients in remote areas collect data through monitoring devices at home, and after transmitting it to the cloud, experts in big cities can log in to the corresponding platform through mobile phones or PCs, view the data and make diagnoses, thus optimizing the allocation of medical resources.

[0046] Preferably, it is considered that when transmitting a large amount of signal data and imaging results in real time, data transmission delays and bandwidth limitations may be encountered. Especially in remote monitoring scenarios. A large amount of signal data and imaging results need to be transmitted from the data acquisition end to the receiving end (such as the terminal where the doctor views the data). Due to factors such as long transmission distance and many network nodes, the data will take a certain amount of time during the transmission process, resulting in the receiving end being unable to obtain the latest data in time, causing delays. For example, the transmission of lung imaging data from medical monitoring equipment in remote areas to the doctor's workstation in an urban hospital may cause a delay of several seconds or even longer due to many network transfer links, affecting the real-time judgment of the patient's condition. In addition, the amount of signal data and imaging results is usually large. For example, high-resolution lung CT imaging data, a single picture may reach several MB or even larger. When a large amount of such data is transmitted simultaneously, the existing network bandwidth cannot meet the data transmission rate requirements, and data congestion, packet loss, etc. will occur. It's like a narrow road, but a large number of vehicles have to pass through it at the same time, causing traffic jams.

[0047] In view of this, the wireless transmission module 104 in the embodiment of the present application adopts a compression algorithm based on wavelet transform to compress the signal and image data. The specific process includes: decomposing the signal or image to be transmitted into wavelet coefficients of different frequencies and spatial positions; quantizing the wavelet coefficients according to their importance; encoding the quantized wavelet coefficients to generate compressed data; calculating the ratio of the compressed data volume to the original data volume to obtain the compression ratio, and evaluating whether the expected compression effect is achieved.

[0048] Specifically, each wavelet coefficient represents the characteristics of the image at a specific frequency and position. For example, for lung imaging, low-frequency wavelet coefficients reflect the general outline of the lungs, while high-frequency wavelet coefficients reflect details such as lung texture. Quantification is performed according to the importance of the wavelet coefficients, with the aim of removing those wavelet coefficients that have little impact on the overall data and retaining only key information. The amount of data of the encoded wavelet coefficients is greatly reduced compared to the original data, which is convenient for subsequent transmission. Calculating the compression ratio can evaluate whether the expected compression effect has been achieved. At the same time, check the similarity between the decompressed data and the original data to ensure that no key information is lost during the compression process. For example, by calculating indicators such as the peak signal-to-noise ratio (PSNR) of the image, it is determined whether the image quality meets the application requirements of medical diagnosis.

[0049] The battery management module 105 is electrically connected to the data processing module 102 for power supply.

[0050] Preferably, the battery management module 105 has a built-in long-life battery, which is designed to reduce the frequency of frequent charging of the device and ensure that the device can continue to operate stably for a long time. Long-life batteries usually have a higher energy density, that is, they can store more electrical energy in a smaller volume and weight. For example, some devices that use new lithium polymer battery technology have a higher energy density than traditional lithium-ion batteries and can provide more lasting power support for the device. This is crucial for devices that need to be used for a long time, such as wearable lung monitoring devices. It allows patients to avoid frequent interruptions in monitoring to charge in their daily lives, thereby ensuring the continuity and integrity of data collection.

[0051] Preferably, the battery management module 105 uses wireless charging technology for charging. Wireless charging technology allows the device to be charged without using a traditional charging cable connection. Its principle is mainly based on electromagnetic induction, magnetic resonance or radio wave transmission. Taking electromagnetic induction as an example, there is a transmitting coil in the charging base. When the device is placed on the charging base, the receiving coil inside the device will generate a magnetic field coupling with the transmitting coil, thereby generating an induced current in the receiving coil to charge the battery. This charging method avoids the inconvenience and wear caused by plugging and unplugging the charging cable, and improves the convenience of charging the device.

[0052] It should be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0053] Above, Figures 1 to 3 The structure and implementation principle of a wearable non-invasive lung function monitoring device based on impedance imaging are demonstrated; below, the wearable non-invasive lung function monitoring device is applied to a telemedicine diagnosis system and further explained.

[0054] Figure 4 The structural schematic diagram of a telemedicine diagnosis system based on wearable non-invasive pulmonary function monitoring is shown. The telemedicine diagnosis system of the present application includes a wearable non-invasive pulmonary function monitoring device 1 and a telemedicine diagnosis platform 2 with which a communication connection is established. The wearable non-invasive pulmonary function monitoring device 1 transmits pulmonary function parameter data and pulmonary ventilation image data to the telemedicine diagnosis platform 2 based on Bluetooth transmission or WiFi transmission. It should be understood that the principle of the wearable non-invasive pulmonary function monitoring device 1 in the present system has been explained above and will not be repeated here.

[0055] In the embodiments of the present application, it should be noted that the telemedicine diagnosis platform 2 in the present application has a high degree of flexibility and diversity from the architectural implementation level. Its physical carrier can be a fully functional computer device. By integrating various medical applications, communication modules and data storage units, it independently undertakes the core tasks of telemedicine services and completes the whole process from patient data collection and transmission to interaction with medical experts. In other scenarios, the telemedicine diagnosis platform 2 can also be expressed as a system in which multiple computer devices operate in coordination. These devices are interconnected through an internal high-speed network and are responsible for different functional modules. For example, some devices focus on patient information management and storage, some are used for real-time video communication, and some are responsible for the processing and analysis of complex medical images. They cooperate with each other to provide comprehensive and efficient telemedicine services for medical institutions. In some other scenarios, the telemedicine diagnosis platform can also cross the boundaries of different medical institutions and is composed of multiple computer devices distributed in various medical institutions. With the help of wide area network technology and standardized data communication protocols, these devices scattered in different geographical locations break geographical restrictions and realize functions such as real-time sharing of medical data and remote consultation. Experts from different medical institutions can log in to the platform through computer equipment within their respective institutions and jointly participate in the diagnosis and treatment plan formulation for patients with difficult diseases, greatly improving the collaborative efficiency and application scope of medical resources.

[0056] Preferably, during the data transmission process, the pulmonary function parameter data and the pulmonary ventilation image data are uploaded to the telemedicine diagnosis platform 2 after end-to-end encryption, ensuring the privacy of the patient while also supporting real-time sharing. The end-to-end encryption refers to the encryption of the pulmonary function parameter data and the pulmonary ventilation image data and converting them into ciphertext, and the receiving end uses a specific decryption key to restore the ciphertext to the original data. Therefore, during the entire transmission process, even if the data is intercepted by a third party, the third party cannot obtain the true content of the data due to the lack of a decryption key, thereby ensuring the privacy and security of the patient. This allows the patient's medical records, imaging materials and other sensitive information to be strictly protected during network transmission. Once the patient's data is encrypted and uploaded to the telemedicine diagnosis platform, authorized medical personnel can obtain these data immediately to achieve real-time synchronization of information. For example, in a remote consultation, multiple experts can view the patient's latest test results at the same time, discuss the condition, and formulate a timely and effective treatment plan for the patient.

[0057] Preferably, a blockchain node is set up inside the medical institutions such as hospitals and clinics that participate in telemedicine services in the telemedicine diagnosis platform 2. For example, a blockchain module can be embedded in the hospital's information management system, which is responsible for organizing and encrypting the patient medical data generated by the hospital, and then trying to add new blocks to the entire blockchain network according to the format and rules of the blockchain. At the same time, the node can also receive data synchronized from other nodes, so that medical staff within the hospital can view the patient's diagnosis and treatment history in other medical institutions with authorization, achieve a comprehensive understanding of the condition, and provide a reference for subsequent treatment.

[0058] Furthermore, the implementation process of blockchain technology in the embodiment of the present application includes:

[0059] First, build a data structure: build a storage system for patient medical data based on the chain structure of blockchain. Each "block" can contain various medical data records of patients within a certain time range, including sensor collection data and lung imaging data. These blocks are linked in chronological order to form a chain, and the newly generated data will be continuously added to the end of the chain, thus building a complete and orderly data storage structure, which is convenient for tracing the order and history of data generation.

[0060] Secondly, use encryption algorithms: Use appropriate encryption algorithms to encrypt patient medical data before storing it on the blockchain. For example, use an asymmetric encryption algorithm to generate a pair of public and private keys for each patient. The patient's private key is kept by the patient (it can be stored in a secure digital wallet, etc.), and the public key is used to encrypt the data. When medical data is to be uploaded to the blockchain, it is encrypted using the public key, and only the corresponding private key can be used to decrypt and view the specific content. This ensures the confidentiality of the data during storage and transmission, and prevents the data from being obtained by unauthorized third parties.

[0061] Thirdly, deploy distributed nodes: establish multiple distributed nodes to jointly maintain the blockchain. These nodes can be distributed in different medical institutions (such as the hospital where the patient first visited, the specialist hospital that participated in the consultation, other hospitals that may receive referrals, etc.), medical regulatory departments, and professional third-party data storage service providers. Each node stores a complete or partial copy of the blockchain data. When a new data block is generated, through a specific consensus mechanism (such as proof of work, proof of equity, or practical Byzantine fault tolerance, etc., choose the appropriate one according to the specific application scenario), each node reaches a consensus and jointly adds the new block to the blockchain to ensure data consistency and reliability.

[0062] Finally, write and execute smart contracts: Write smart contracts to define the rules for medical data operations, such as stipulating that only medical institutions authorized by patients can obtain their complete medical records, or under what circumstances data can be updated or supplemented. When the conditions set in the smart contract are met, the corresponding operations are automatically executed without human intervention, and the execution process and results are recorded on the blockchain, further ensuring the standardization and traceability of data operations.

[0063] Preferably, after receiving the lung function parameter data and lung ventilation image data, the remote medical diagnosis platform 2 integrates them into the hospital information system to perform automatic updating and management of the electronic health record.

[0064] It should be understood that the hospital information system (HIS) is a comprehensive information management system covering all aspects of the hospital's business, including outpatient registration, hospitalization management, pharmacy management, financial management and other subsystems. Integrating the data generated by telemedicine and intelligent interaction into HIS means seamlessly integrating various types of data generated by patients during remote diagnosis and treatment, such as remote diagnosis results, remote monitoring data, and patient-doctor intelligent interaction records, into the hospital's existing information management system. For example, a patient monitors physiological indicators such as blood pressure and heart rate through telemedicine equipment. These data will be collected and transmitted to the hospital information system and stored together with other medical records generated by the patient during the hospital visit.

[0065] In the embodiment of the present application, the remote medical diagnosis platform 2 performs multimodal data fusion based on the received lung function parameter data and lung ventilation image data, and performs deep learning modeling based on the data, thereby improving the diagnostic accuracy of complex respiratory diseases. The specific execution steps are as follows: Figure 5 As shown, including the following:

[0066] Step S51: pre-processing the received lung function parameter data and lung ventilation image data to remove abnormal values ​​and noise data.

[0067] Specifically, for the collected lung function sensor data, data points that are obviously beyond the normal physiological range can be filtered out by setting a reasonable parameter range. For lung images, image enhancement, denoising, normalization and other processing are performed, such as using histogram equalization to enhance image contrast, using Gaussian filtering to remove noise in the image, and normalizing all image data to the same size and grayscale range for subsequent feature extraction and model training.

[0068] When fusing features, all features can be combined into a long vector, or a fusion method based on the attention mechanism can be used to allow the model to automatically learn the importance of different modal features in diagnosis, assign different weights to different features, and then perform weighted fusion.

[0069] Step S52: Based on a deep learning model architecture that is a mixture of a convolutional neural network and a recurrent neural network, feature fusion is performed on the lung function parameter data and the lung ventilation image data, and model training is performed.

[0070] Specifically, the convolutional neural network (CNN) is used to process lung image data to extract image features, and the recurrent neural network (RNN) is used to process the time series data of the lung function sensor. The extracted features are then fused and input into the fully connected layer for further learning and classification to determine the health status of the lungs, the type of disease, and the severity of the disease.

[0071] Preferably, a spatiotemporal attention module is added to the deep learning model architecture; the spatiotemporal attention module focuses on data changes at key time points of the lung function sensor data based on the attention mechanism, and highlights prominent lesion areas of the lung image data so that the model pays more attention to areas where problems may exist. That is, for lung function sensor data, the attention mechanism can focus on data changes at key time points, such as parameter fluctuations at the moment of disease onset; for lung image data, the attention mechanism can highlight lesion areas, so that the model pays more attention to areas where problems may exist, and improves the model's ability to capture important information.

[0072] Preferably, a generative adversarial network is used to expand scarce lung image data; the generator in the generative adversarial network is used to generate simulated lung images, and the discriminator is used to distinguish between true and false images; the scarce lung image data includes but is not limited to: rare lung disease images, early lesion images, special types of infection images, and critical stages of disease progression images. Therefore, for relatively scarce lung disease image data, more similar image data can be generated through GAN for training, while ensuring the authenticity and diversity of the generated data. During the training process, the generator and the discriminator compete with each other to jointly improve the model's understanding and processing capabilities of lung images.

[0073] It should be understood that rare lung disease images, such as idiopathic pulmonary fibrosis and lymphangioleiomyomatosis, have low incidence and limited number of patients, so there is little relevant high-quality image data that can be collected. Taking idiopathic pulmonary fibrosis as an example, its pathogenesis is still unclear, and the image manifestations are diverse. The number of image samples corresponding to each manifestation is small, which is not conducive to comprehensive learning and accurate recognition of deep learning models. Early lesion images, such as early lung cancer images, are often not obvious in the early stages of the disease. They may be only very small nodules or ground-glass shadows, and many patients have no obvious symptoms in the early stages, making them difficult to detect and diagnose. Therefore, the images of early lung cancer that can be obtained and confirmed by pathology are relatively scarce. These early images are crucial for the early diagnosis and treatment of the disease, but because they are difficult to obtain, they account for a small proportion of the data set. Special types of infection images, such as lung images infected by special pathogens such as Pneumocystis pneumonia and pulmonary aspergillosis, are more common in specific populations (such as immunodeficient patients), but the overall number of patients is relatively small, and the image performance also varies due to individual differences and the stage of the disease. It is difficult to collect a large amount of representative image data covering various stages of the disease. The key stage images of the disease progression refer to the different image performances of lung diseases at different stages. Some key stages, such as the transition from the stable stage to the acute exacerbation stage, are very important for studying the development mechanism of the disease and predicting the changes in the disease. However, since it is difficult to accurately capture the patient's examination at this critical time point, this type of image data is relatively scarce.

[0074] Preferably, when performing feature fusion in the deep learning model architecture of the present application, the traditional way of performing data fusion at the model input stage is changed, and a dynamic fusion strategy is adopted. Specifically, in different training stages of the model, the fusion weights of the lung function parameter data and the lung ventilation image data are dynamically adjusted according to the output feedback of the model. For example, in the initial learning stage of the model, the weight of the image data is made larger so that the overall structure of the lungs can be clearly understood first; as the training deepens, the weight of the lung function sensor data is increased, and attention is paid to the dynamic changes of lung function, so that the model can adapt to different data characteristics more flexibly and improve the modeling effect.

[0075] It is worth noting that the embodiment of the present application preferably adopts a dynamic fusion strategy in order to adapt to different data characteristics. The pulmonary function sensor data is dynamic and time-series data, reflecting the changes in pulmonary function over time; while the pulmonary image data presents the static structural information of the lungs at a certain moment. The requirements for these two types of characteristic data are different at different stages. For example, in the early stage of model training, a clear understanding of the overall structure of the lungs is helpful for subsequent analysis of functional changes, so the image data weight is greater at this time. As the training progresses, it is more critical to understand the dynamic changes of pulmonary function at different times. Increasing the weight of pulmonary function sensor data can enable the model to better handle the advantages of each of these two types of data. In addition, the flexibility of the model is also improved accordingly, and the traditional fixed fusion method cannot be flexibly adjusted according to the model training situation. The dynamic fusion strategy can change the fusion weight in real time based on the model output feedback, so that the model can flexibly adjust the degree of dependence on different data when facing different data characteristics and training stages. For example, when the model is identifying certain disease characteristics, it is found that the detailed information in the image is not fully utilized, and the image data weight can be appropriately increased in subsequent training to optimize the model's learning of the feature.

[0076] By building a deep learning model architecture, the telemedicine diagnosis platform of this application can focus on personalized health record management and has powerful automatic recognition capabilities. It can accurately identify abnormal lung trends with advanced algorithms. In the process of accumulating patient data, the system quickly captures the changing trend of lung health through in-depth mining and analysis of long-term data. Once an abnormal trend is found, it will issue early warning information in time to gain valuable time for medical intervention. Not only that, this application also innovatively integrates AI algorithms. Through this cutting-edge technology, the system can conduct a comprehensive and detailed trend analysis of the patient's long-term data. On this basis, a highly targeted personalized health report is generated. This report not only provides doctors with clear and intuitive patient health dynamics, helping doctors to develop more scientific and optimized treatment plans, but also allows patients to have a deeper understanding of their own health status, so that patients can actively cooperate and participate in health management together, thereby achieving more effective health intervention.

[0077] The present application also provides a remote medical diagnosis method based on wearable non-invasive pulmonary function monitoring, which is applied to a remote medical diagnosis platform. The method includes: first, receiving pulmonary function parameter data and pulmonary ventilation image data from a wearable non-invasive pulmonary function monitoring device, preprocessing the received data, and removing outliers and noise data. Based on a deep learning model architecture that is a mixture of convolutional neural networks and recurrent neural networks, feature fusion is performed on the pulmonary function parameter data and pulmonary ventilation image data, and model training is performed. It should be noted that the implementation process and principle of the remote medical diagnosis method based on wearable non-invasive pulmonary function monitoring are similar to the remote medical diagnosis system based on wearable non-invasive pulmonary function monitoring mentioned above, and will not be repeated here.

[0078] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0079] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0080] Figure 6 is a schematic block diagram of a computer device / equipment / system provided in an embodiment of the present application. Figure 6 As shown in FIG. 6 , the computer device includes: at least one processor 601, a memory 602, at least one network interface 603, and a user interface 605. The various components in the device are coupled together via a bus system 604. It can be understood that the bus system 604 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 604 is not described in detail. Figure 6 In the specification, various buses are labeled as bus systems.

[0081] The user interface 605 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0082] It is understood that the memory 602 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0083] The memory 602 in the embodiment of the present invention is used to store various types of data to support the operation of the computer device 600. Examples of these data include: any executable program for operating on the computer device 600, such as an operating system 6021 and an application 6022; the operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 6022 can include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The implementation of the XX method provided in the embodiment of the present invention can be included in the application 6022.

[0084] The method disclosed in the above embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 601 or the instruction in the form of software. The above processor 601 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 601 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 601 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0085] In an exemplary embodiment, the computer device 600 may be one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0086] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: a computer program code, when the computer program code is run on a computer, the computer executes the method.

[0087] According to the method provided in an embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program code. When the program code is run on a computer, the computer executes the above-mentioned remote medical diagnosis method based on wearable non-invasive lung function monitoring.

[0088] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes according to signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0089] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0094] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When loading and executing computer program instructions (programs) on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs), etc.).

[0095] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0096] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0097] In summary, the present application provides wearable non-invasive lung function monitoring equipment, systems, devices and media based on impedance imaging. The present application first overcomes the limitations of traditional equipment, does not require complicated patient operations, reduces subjective interference, and can integrate imaging and functional testing to complete comprehensive lung function assessment; second, it has highly portable and wearable characteristics, extreme miniaturization is suitable for multiple scenarios, and the flexible sensor belt is comfortable and stable to wear; third, it realizes intelligence and interconnection, can share data in the cloud to achieve real-time telemedicine, and combines AI technology to improve the efficiency of early diagnosis and management of diseases; fourth, it can be applied to multiple scenarios, providing high-value solutions for chronic disease management, postoperative rehabilitation and health screening; fifth, it supports intelligent interaction and platform integration, facilitates real-time online communication between doctors and patients, and helps hospitals improve diagnosis and treatment efficiency; sixth, it promotes personalized health management and diagnosis optimization, relies on AI algorithms to give accurate health predictions and intervention suggestions, and also provides dynamic analysis tools to jointly manage health trends and improve treatment effects. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0098] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A wearable non-invasive lung function monitoring device based on impedance imaging, characterized in that: It includes a shell structure that fits and covers the lung area of ​​the tested person; the shell structure is provided with: A wearable sensor belt module is configured with an impedance sensor array for collecting lung impedance signals of the subject; the wearable sensor belt module is also integrated with a lung function parameter collection sensor, and the collected lung function parameters include peak expiratory flow, vital capacity, forced vital capacity and forced expiratory volume in one second; A data processing module, electrically connected to the wearable sensor belt module, for converting the collected lung impedance signal into a corresponding digital signal through an analog-to-digital conversion circuit, and processing the digital signal converted by the analog-to-digital conversion circuit through a firmware algorithm to perform lung imaging calculations to generate a lung ventilation image; A display and interaction module, electrically connected to the data processing module, for displaying lung function parameter data and lung ventilation image data in real time; A wireless transmission module, electrically connected to the data processing module, for transmitting lung function parameter data and lung ventilation image data to a remote medical diagnosis platform based on a wireless transmission protocol, so that the remote medical diagnosis platform can construct a deep learning model architecture for determining the health status of the lungs; The battery management module and the data processing module are used for power supply.

2. The wearable non-invasive lung function monitoring device based on impedance imaging according to claim 1, characterized in that: The wearable non-invasive lung function monitoring device includes a shell structure that can fit and cover the lung area of ​​the tested person; the formation process of the shell structure includes: measuring the surface shape of the human lung area through three-dimensional scanning technology, and the measurement objects include the outline of the chest cavity, the distribution of ribs, and the expansion and contraction range of the lungs during breathing; and generating the shell structure based on the measurement data.

3. The wearable non-invasive lung function monitoring device based on impedance imaging according to claim 1, characterized in that: The wireless transmission module uses a compression algorithm based on wavelet transform to compress signal and image data. The compression process includes: decomposing the signal or image to be transmitted into wavelet coefficients of different frequencies and spatial positions; quantizing the wavelet coefficients according to their importance; encoding the quantized wavelet coefficients to generate compressed data; calculating the ratio of the compressed data volume to the original data volume to obtain the compression ratio, and evaluating whether the expected compression effect is achieved.

4. A remote medical diagnosis system based on wearable non-invasive lung function monitoring, characterized in that: include: A wearable non-invasive lung function monitoring device as claimed in any one of claims 1 to 3; A remote medical diagnosis platform establishes a communication connection with the wearable non-invasive lung function monitoring device.

5. The remote medical diagnosis system based on wearable non-invasive lung function monitoring according to claim 4 is characterized in that: The telemedicine diagnosis platform includes multiple service entities participating in telemedicine services. A blockchain node is embedded in the information management system of each of the service entities. The blockchain node is used to add new blocks to the entire blockchain network according to the format and rules of the blockchain for medical data; and the blockchain node receives data synchronized from other nodes.

6. The remote medical diagnosis system based on wearable non-invasive lung function monitoring according to claim 4 is characterized in that: The remote medical diagnosis platform constructs a deep learning model architecture based on the received lung function parameter data and lung ventilation image data, and the process includes: Preprocessing the received lung function parameter data and lung ventilation image data to remove abnormal values ​​and noise data; Based on the deep learning model architecture that is a mixture of convolutional neural networks and recurrent neural networks, the lung function parameter data and lung ventilation image data are feature fused and the model is trained.

7. The remote medical diagnosis system based on wearable non-invasive lung function monitoring according to claim 6, characterized in that: The deep learning model architecture is configured with a spatiotemporal attention module; the spatiotemporal attention module focuses on data changes at key time points of lung function sensor data based on an attention mechanism, and highlights prominent lesion areas of lung image data to enable the model to pay more attention to areas where problems may exist.

8. The remote medical diagnosis system based on wearable non-invasive lung function monitoring according to claim 6, characterized in that: The remote medical diagnosis platform is also configured with a generative adversarial network, which is used to supplement scarce lung image data; the generator in the generative adversarial network is used to generate simulated lung images, and the discriminator is used to distinguish between true and false images; the scarce lung image data includes but is not limited to: rare lung disease images, early lesion images, special types of infection images, and critical stages of disease progression images.

9. The remote medical diagnosis system based on wearable non-invasive lung function monitoring according to claim 6, characterized in that: When performing feature fusion, the deep learning model architecture dynamically adjusts the fusion weights of the lung function parameter data and the lung ventilation image data according to the output feedback of the model.

10. A remote medical diagnosis method based on wearable non-invasive lung function monitoring, characterized in that: Applied to a remote medical diagnosis platform; the method comprises: receiving lung function parameter data and lung ventilation image data from a wearable non-invasive lung function monitoring device, and preprocessing the received data to remove outliers and noise data; Based on the deep learning model architecture that is a mixture of convolutional neural networks and recurrent neural networks, the lung function parameter data and lung ventilation image data are feature fused and the model is trained.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the remote medical diagnosis method based on wearable non-invasive lung function monitoring as described in claim 10 is implemented.

12. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the remote medical diagnosis method based on wearable non-invasive lung function monitoring as described in claim 10.

Images