CN113724244A - Health monitoring method, device and system, health examination equipment and medium - Google Patents
Health monitoring method, device and system, health examination equipment and medium Download PDFInfo
- Publication number
- CN113724244A CN113724244A CN202111075045.1A CN202111075045A CN113724244A CN 113724244 A CN113724244 A CN 113724244A CN 202111075045 A CN202111075045 A CN 202111075045A CN 113724244 A CN113724244 A CN 113724244A
- Authority
- CN
- China
- Prior art keywords
- health
- human body
- image
- monitoring method
- health examination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 347
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 58
- 238000001931 thermography Methods 0.000 claims abstract description 22
- 230000036285 pathological change Effects 0.000 claims abstract description 21
- 231100000915 pathological change Toxicity 0.000 claims abstract description 21
- 238000012806 monitoring device Methods 0.000 claims abstract description 10
- 230000003902 lesion Effects 0.000 claims description 120
- 238000013499 data model Methods 0.000 claims description 56
- 238000003745 diagnosis Methods 0.000 claims description 47
- 230000000875 corresponding effect Effects 0.000 claims description 45
- 238000004891 communication Methods 0.000 claims description 17
- 238000007726 management method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013523 data management Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000013136 deep learning model Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012502 risk assessment Methods 0.000 claims description 4
- 230000001815 facial effect Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims 1
- 238000012216 screening Methods 0.000 abstract description 18
- 201000010099 disease Diseases 0.000 abstract description 17
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 17
- 206010061218 Inflammation Diseases 0.000 abstract description 10
- 206010028980 Neoplasm Diseases 0.000 abstract description 10
- 230000004054 inflammatory process Effects 0.000 abstract description 10
- 230000005802 health problem Effects 0.000 abstract description 4
- 230000036760 body temperature Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 13
- 238000003062 neural network model Methods 0.000 description 12
- 230000036387 respiratory rate Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 208000006820 Arthralgia Diseases 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 6
- 208000027744 congestion Diseases 0.000 description 6
- 230000005855 radiation Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 210000004243 sweat Anatomy 0.000 description 5
- 230000036772 blood pressure Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000001575 pathological effect Effects 0.000 description 4
- 230000035900 sweating Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Pathology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Epidemiology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the application provides a health monitoring method, a health monitoring device, a health monitoring system, health examination equipment and a storage medium, wherein the health monitoring method comprises the following steps: collecting human body vital sign parameters, and collecting human body infrared images based on infrared thermal imaging detection; judging the human body state according to the human body vital sign parameters; and carrying out characteristic point identification on the human body infrared image which is correspondingly acquired when the human body state is in a health examination state so as to determine whether a pathological change part exists. The human body state is judged by combining the human body vital sign parameters, so that the objectivity of the human body infrared image on which the health risk problem screening is carried out is ensured, and the accuracy of the detection result is improved; the health examination equipment is particularly suitable for being used in a family environment, is used as an efficient self-examination for health problems such as inflammation and tumor concerned in the life of a user, has high detection efficiency, and can meet the requirement of early screening and tracking of diseases by the user at home conveniently.
Description
Technical Field
The present application relates to the field of health self-check technology, and in particular, to a health monitoring method, device and system, a health check device, and a computer-readable storage medium.
Background
Along with the improvement of the level of people, the health consciousness of people is higher and higher, the enthusiasm for timely knowing the health condition and the risk of the body is higher and higher, and the early screening and tracking of diseases through physical examination are vital to the prevention of diseases and the reduction of health risks.
The current mainstream physical examination approach is to go to hospitals or commercial physical examination institutions, which are expensive, time-consuming, high-cost, and inconvenient, and cannot track the change trend of the body's potential disease risk in time. In recent years, health monitoring products which are suitable for being used in family scenes are gradually developed, such as the modes of collecting physiological indexes, blood pressure, respiratory rate and the like of a user are too simple, diseased parts or organ tissues in a human body cannot be reflected, the rear end of the health monitoring products is often matched with doctors to perform manual diagnosis to obtain relatively referential examination results, the detection efficiency is low, and health risk problems which can be examined are limited.
Disclosure of Invention
In order to solve the existing technical problems, the health monitoring method, the health monitoring device and the health monitoring system are high in detection efficiency, more comprehensive in health risk screening and more accurate in detection result, and the health examination equipment and the computer readable storage medium are provided.
In order to achieve the above purpose, the technical solution of the embodiment of the present application is implemented as follows:
in a first aspect, an embodiment of the present application provides a health monitoring method applied to a health check device, including:
collecting human body vital sign parameters, and collecting human body infrared images based on infrared thermal imaging detection;
judging the human body state according to the human body vital sign parameters;
and carrying out characteristic point identification on the human body infrared image which is correspondingly acquired when the human body state is in a health examination state so as to determine whether a pathological change part exists.
In a second aspect, an embodiment of the present application provides a health monitoring method applied to a health check system, including:
the cloud end trains the deep learning model according to the sample set of the human body infrared image marked with the diagnosis result to obtain a trained diagnosis data model and sends the trained diagnosis data model to the health examination equipment;
the health examination equipment acquires human body vital sign parameters and acquires human body infrared images based on infrared thermal imaging detection; judging the human body state according to the human body vital sign parameters; and inputting the human body infrared image which is correspondingly acquired when the human body state is in a health examination state into the diagnosis data model so as to determine whether a pathological change part exists.
In a third aspect, an embodiment of the present application provides a health monitoring device, which is applied to a health check apparatus, and includes:
the acquisition module is used for acquiring human body vital sign parameters and acquiring human body infrared images based on infrared thermal imaging detection;
the judging module is used for judging the human body state according to the human body vital sign parameters;
the identification module is used for carrying out characteristic point identification on the human body infrared image which is correspondingly acquired when the human body state is in the health examination state so as to determine whether a lesion part exists
In a fourth aspect, the present application provides a health check device, which includes a processor, an infrared detector and a radar sensor connected to the processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the health monitoring method according to any of the embodiments of the present application applied to the terminal device side.
In a fifth aspect, an embodiment of the present application provides a health monitoring system, which includes the health check device, a cloud, and a terminal device in the embodiment of the present application; the cloud end trains the deep learning model according to the sample set of the human body infrared image marked with the diagnosis result to obtain a trained diagnosis data model and sends the trained diagnosis data model to the health examination equipment; and the terminal equipment receives the checking result sent by the health checking equipment for management.
In a sixth aspect, this application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when executed by the processor, the computer program implements the health monitoring method according to any embodiment of this application.
In the embodiment, the health examination equipment respectively collects human body vital sign parameters, and collects human body infrared images based on infrared thermal imaging detection, whether a diseased part exists is determined by identifying the characteristic points of the human body infrared images, and the diagnosis based on the infrared images can be used for screening health risks according to the surface temperature distribution of a human body and the characteristics of diseases such as inflammation, arthralgia and tumor, so that the health risk screening problem is more comprehensive; the human body state is judged through the human body vital sign parameters, so that the human body infrared image on which the health risk problem screening is carried out is ensured to be the human body infrared image which is correspondingly acquired when the human body is in a health examination state, and the accuracy of the detection result is improved; the health examination equipment is particularly suitable for being used in a family environment, is used as an efficient self-examination for health problems such as inflammation and tumor concerned in the life of a user, has high detection efficiency, and can meet the requirement of early screening and tracking of diseases by the user at home conveniently.
In the above embodiments, the computer readable storage medium and the corresponding health monitoring method embodiments belong to the same concept, and thus have the same technical effects as the corresponding health monitoring method embodiments, and are not described herein again.
Drawings
Fig. 1 is a schematic view of an optional application scenario of a health monitoring method in an embodiment of the present application;
FIG. 2 is a flow chart of a health monitoring method according to an embodiment of the present application;
FIG. 3 is a flow chart of a health monitoring method in another embodiment of the present application;
FIG. 4 is a flow chart of a health monitoring method in another embodiment of the present application;
FIG. 5 is an architecture diagram of a health monitoring system as an alternative embodiment of the present application;
FIG. 6 is a flow chart of a health monitoring method in an alternative embodiment of the present application
FIG. 7 is a schematic view of a health monitoring device in accordance with an embodiment of the present application;
fig. 8 is a schematic structural diagram of a health check apparatus according to an embodiment of the present application.
Detailed Description
The technical solution of the present application is further described in detail with reference to the drawings and specific embodiments of the specification.
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to the expression "some embodiments" which describe a subset of all possible embodiments, it being noted that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, references to the terms "first, second, and third" are only used to distinguish between similar items and do not denote a particular order, but rather the terms "first, second, and third" are used to indicate that a particular order or sequence of items may be interchanged where appropriate to enable embodiments of the application described herein to be practiced otherwise than as specifically illustrated or described herein.
Referring to fig. 1, a schematic view of an optional application scenario of the health monitoring method provided in the embodiment of the present application is shown, where the health monitoring system includes a terminal device 11, a cloud 12, a gateway 13, and a health check device 14. The terminal device 11 refers to a device having communication and storage functions, for example: the smart phone, the desktop computer, the notebook computer, the tablet computer or other smart communication devices with network connection functions. The cloud 12 may include one or more physical servers, such as a network access server, a database server, a cloud server, and so forth. Optionally, the gateway 13 may be a gateway device built based on a ZigBee protocol, the health check device 14 may access the network through the gateway 13 and be controlled by the terminal device 11, the terminal device 11 is provided with a client capable of managing the health check device 14, and the client may be an application client (such as a mobile phone APP), or a web client, an applet, a wechat public number, or the like, which is not limited herein. The user can control the health check equipment 14 through operating the client, the terminal equipment 11 receives a control instruction, input by the user, for the health check equipment 14 through the client, communicates with the cloud 12, and the cloud 12 forwards the control instruction, input by the user, to the corresponding health check equipment 14 through the gateway 13, so that the remote intelligent control for the health check equipment 14 is realized. The terminal device 11 may also receive, through the client, the operating parameter configuration information for the health check device 14 input by the user, and the health check device 14 determines the current operating mode according to the operating parameter configuration information.
Optionally, the health check device 14 may be a device that is added to the gateway 13 in advance, for example, the health check device 14 may be a device in a suite to which the gateway 13 belongs, which is preset when the gateway leaves a factory; or may be a device that is subsequently connected to the gateway 13 by user operation. The health examination device 14 and the terminal device 11 can both access to the ethernet through the gateway 13, and the gateway 13 can access to the cloud 12 through a wired or wireless communication connection. For example, the health check device 14 and the terminal device 11 may store the acquired information in the cloud 12 through the gateway 13. Optionally, the health check device 14 may also establish a network connection with the cloud end 12 through 2G/3G/4G/5G, WiFi, so as to obtain data sent by the cloud end 12.
The health check device 14 may be various smart home devices in the internet of things system, such as a smart mirror.
Referring to fig. 2, a health monitoring method according to an embodiment of the present application can be applied to the health check apparatus shown in fig. 1. The health monitoring method comprises the following steps:
s101, collecting human body vital sign parameters, and collecting human body infrared images based on infrared thermal imaging detection.
The human vital sign parameters refer to parameters related to human vital signs, such as respiration, pulse, body temperature, and blood pressure. In an optional specific example, the acquiring the human vital signs parameters comprises: and detecting and collecting human body vital sign parameters based on a microwave radar. The health examination equipment can be provided with a radar module, the heart rate and the respiratory rate of the collected object are calculated by utilizing phase change through a microwave or millimeter wave radar, and the heart rate and the respiratory rate are obtained as the collected human body vital sign parameters. In other alternative embodiments, the collecting human vital signs parameters comprises: relevant parameters such as respiration, pulse, body temperature, blood pressure and the like are acquired through other sensors for acquiring relevant parameters of human vital signs. The acquisition of the human body infrared image based on the infrared thermal imaging detection may refer to that the infrared thermal imaging module acquires infrared radiation of each part of a human body, converts the infrared radiation into a digital signal to acquire a target temperature, and forms a visual human body infrared image. The health examination equipment is usually applied to a family environment scene, a user can align a body part which is expected to be subjected to health examination with the health examination equipment, and the health examination equipment acquires a human body infrared image of the corresponding body part; or the user stands at a certain distance in front of the health examination equipment, and the health examination equipment directly acquires the human body infrared image of the whole body of the user.
And S103, judging the human body state according to the human body vital sign parameters.
The body temperature is greatly influenced by the state of a user, for example, the body surface temperature is influenced by sweat generated after the user takes exercise. The health examination equipment judges the human body state by acquiring the human body vital sign parameters so as to determine whether the human body infrared image acquired by the user in the current state can accurately and truly reflect the health state of the user, but not the human body infrared image acquired by the user in the states of sweating and the like, so that the situation that the human body infrared image acquired by the user in the current state of sweating due to exercise and the like cannot truly reflect the health state of the user is avoided. In some optional embodiments, the human body status includes a health examination status currently suitable for health examination and a waiting status currently not suitable for health examination, wherein the health examination status indicates that the user is currently suitable for human body infrared image acquisition to identify whether there is a health risk problem, and the waiting status indicates that the user currently needs to wait until the identity returns to calm, for example, after sweat evaporates until the health examination status can be reached, and then uses the health examination equipment to perform human body infrared image acquisition to identify whether there is a health risk problem.
S105, carrying out feature point identification on the human body infrared image which is correspondingly collected when the human body state is in the health examination state so as to determine whether a pathological change part exists.
The characteristic point identification can be used for identifying an imaging part which shows high body temperature in a human body infrared image, the color depth of the imaging part with high body temperature in the human body infrared image is usually larger than the color depth of other parts, and the part with deep color can be determined by extracting image characteristics so as to determine the characteristic point in the human body infrared image. In other alternative embodiments, the feature point identification may also be to perform analysis processing on the human body infrared image to form a mapping relationship between each part in the human body infrared image and the body temperature value, and identify a corresponding part with a higher body temperature value to determine the feature point in the human body infrared image. The characteristic point recognition is carried out on the human body infrared image, according to the distribution of the human body surface temperature, and by combining the fact that when the human body has some set health risk problems, such as verification, congestion, arthralgia, tumor and other diseases, the temperature of the affected part of the disease and the ambient temperature have obvious difference, whether the part with abnormal body temperature exists in the human body infrared image or not is recognized, and whether the diseased part exists or not is determined.
In the embodiment, the health examination equipment respectively collects human body vital sign parameters, and collects human body infrared images based on infrared thermal imaging detection, whether a diseased part exists is determined by identifying the characteristic points of the human body infrared images, and the diagnosis based on the infrared images can be used for screening health risks according to the temperature distribution of the surface of a human body and the characteristics of diseases such as inflammation, congestion, arthralgia and tumor, so that the health risk screening problem is more comprehensive; the human body state is judged through the human body vital sign parameters, so that the human body infrared image on which the health risk problem screening is carried out is ensured to be the human body infrared image which is correspondingly acquired when the human body is in a health examination state, and the accuracy of the detection result is improved; the health examination equipment is particularly suitable for being used in a family environment, is used as an efficient self-examination for health problems such as inflammation, congestion and tumor concerned in the life of a user, has high detection efficiency, and can meet the requirement that the user conveniently screens and tracks diseases at home in an early stage.
In some embodiments, referring to fig. 3, in step S105, when the human body state is in the health check state, performing feature point recognition on the acquired human body infrared image to determine whether a lesion exists, includes:
s1051, identifying characteristic points of the human infrared image correspondingly collected when the human state is in a health examination state, and identifying the position of a suspected lesion part;
s1052, extracting a suspected lesion part image;
and S1053, inputting the suspected lesion part image into a diagnosis data model, determining the type of the suspected lesion part and returning lesion part prompt information.
The health examination equipment identifies the characteristic points of the human body infrared image, and estimates whether a diseased part exists or not by identifying whether the part with abnormal body temperature in the human body infrared image has a pathological change part or not according to the combination of the surface temperature distribution of the human body and the temperature of the affected part of the disease and the ambient temperature when the human body has some set health risk problems, such as verification, congestion, arthralgia, tumor and the like. In this embodiment, a part determined by feature point recognition according to an infrared image of a human body is used as a suspected lesion part, a suspected lesion part image is extracted, the suspected lesion part image is input into a diagnostic data model, whether misjudgment exists in the suspected lesion part is further determined through the diagnostic data model, if the suspected lesion part is determined to be a lesion part with a health risk problem, the type of the suspected lesion part can be further determined, and corresponding lesion part prompt information is returned. When the diagnostic data model determines that the suspected lesion part is not the lesion part, the returned prompt information of the lesion part can be prompt information representing that no health risk problem exists at present; when it is determined that the suspected lesion site is actually a lesion site, the returned lesion site presentation information may be presentation information indicating what type of lesion exists at what site at present.
The diagnostic data model may be a disease diagnosis database established according to the characteristics of the known lesion site image, in which a large number of sample images including confirmed lesions are stored, and the diagnostic data model receives a suspected lesion site image extracted from the human body infrared image, compares the suspected lesion site image with the sample image, and determines whether or not the suspected lesion site has a lesion and the type of the suspected lesion site if the lesion does exist according to the comparison result.
Optionally, the diagnostic data model may also be a deep learning model obtained by training a sample image including a lesion site that has been diagnosed. The diagnostic data model receives a suspected pathological part image extracted from the human body infrared image, performs feature extraction on the suspected pathological part image to form a feature vector, and determines the type of the suspected pathological part based on the feature vector. The diagnostic data model is pre-trained, and when the method is specifically implemented, an initial classification neural network model, such as a convolutional neural network model, can be constructed first, and the initial classification neural network model is trained in the following way: firstly, obtaining a sample image, and carrying out category marking on the sample image, wherein the sample image refers to various types of diagnosed sample images containing pathological changes, the marking refers to pathological change types represented by the corresponding sample image, the sample image can be subjected to category marking according to label information capable of uniquely representing the pathological change types, if the category marking of an image containing a specified pathological change type 1 in the sample image is corresponding to 1, the category marking of an image containing a specified pathological change type 2 in the sample image is corresponding to 2, and the category marking of an image not containing any specified pathological change type in the sample image is corresponding to 0, so as to obtain a sample image marked with a target category; then inputting the sample image marked with the target class into a classification neural network model, performing class prediction on the sample image through the classification neural network model, comparing the prediction class with the standard target class, determining the value of a loss function of the classification neural network model based on the difference between the prediction class and the standard target class, reversely transmitting the value of the loss function to each layer of the classification neural network model, and updating the model parameters of each layer through a Stochastic Gradient Descent (SGD) method to realize the training of the model.
In the above embodiment, the health check device identifies the characteristic points of the infrared image of the human body to determine the suspected pathological change part, and then further determines the suspected pathological change part through the diagnostic data model to determine the type of the pathological change part, so that the health check device can realize self-check of the set health risk problem in an off-line state, is particularly suitable for early screening and tracking of the set health risk problem in a home environment, and improves the efficiency and accuracy of health monitoring.
In some embodiments, after the extracting the image of the suspected lesion, the method further includes:
and registering the suspected lesion part image with a history extraction image to obtain continuous lesion part image data representing the lesion trend of the suspected lesion part image.
The historical extracted image may be an image of the same position as the suspected lesion extracted from the infrared image of the human body acquired in a previous set time period. For example, a user may perform a health check once a day through a health check device, the health check device may store a human body infrared image of the user acquired every day for a period of time, and after a suspected lesion location is determined according to the human body infrared image acquired every day, the human body infrared image acquired every day for a period of time before the day may be called to perform image extraction on the same location of the suspected lesion location, so as to obtain a history extracted image corresponding to the suspected lesion location. Image registration (Image registration) is a process of matching and superimposing two or more images acquired at different times, different imaging devices or under different conditions (weather, illuminance, camera position and angle, etc.). An alternative procedure for registration may be: extracting the features of the two images to obtain feature points; finding matched characteristic point pairs by carrying out similarity measurement; then obtaining image space coordinate transformation parameters through the matched feature point pairs; and finally, carrying out image registration by the coordinate transformation parameters. And the health examination equipment registers the suspected lesion part image with the history extraction image to form continuous lesion part image data, so that the lesion trend of the suspected lesion part image is conveniently analyzed.
In the above embodiment, the health examination apparatus obtains continuous lesion site image data representing a lesion trend of the suspected lesion site image by registering the suspected lesion site image with the history extracted image, so that the development trend of the lesion site can be analyzed, and a more accurate and referential health examination result can be obtained.
In some embodiments, the inputting the image of the suspected lesion into a diagnostic data model, determining the type of the suspected lesion, and returning lesion prompt information includes:
and inputting continuous image data of the lesion site into a diagnostic data model, determining the type of the suspected lesion site and returning prompt information of the lesion site.
The health examination equipment obtains continuous lesion site image data representing the lesion trend of the suspected lesion site image, inputs the continuous lesion site image data into a diagnosis data model, further judges the lesion type of the suspected lesion site through the diagnosis data model, and returns lesion prompt information.
The diagnostic data model judges the suspected lesion part based on continuous lesion part image data, so that the accuracy of a health result can be improved, and the probability of misjudgment is effectively reduced.
In some embodiments, the health monitoring method further comprises:
acquiring a face image, and determining identity information according to the face image;
and correspondingly storing the detection result for determining whether the lesion part exists or not and the identity information.
When the health check equipment collects human infrared images to screen health risk problems, the human face images can be collected through the visible light image shooting module, the human face images are identified to determine identity information, and the detection result of whether a pathological change part exists or not determined according to the human infrared images at present and the identity information are correspondingly stored. The identity information can be related information which is input in a pre-registered mode and uniquely characterizes the identity of the user. For example, the health check device may support entry of user names and face images corresponding to the user names respectively corresponding to a plurality of family members in a pre-registration manner, and in the health check process executed by the health check device, the collected face images may be used to determine which family member the person currently performing health check is, and the check result obtained by the currently executed health check is stored in correspondence with the user name of the family member, so that the health check device may implement health check on a plurality of different family members. Optionally, the identity information may also be non-preset input, and the health check device may acquire the face image and identify whether the face image is the same person to determine information such as a number indicating the identity of the user. If the health examination equipment acquires a face image of the user A, and an examination result obtained by currently executing health examination is stored in association with the user A; acquiring a face image of a user B, and storing an examination result obtained by currently executing health examination in association with the user B; if the health examination is subsequently performed on the user a again, the examination performed on the user a at the moment can be determined according to the facial image of the user a collected again, and therefore the examination result is automatically associated with the user a for storage.
In the embodiment, the health check equipment can identify the user by acquiring the human face image, so that self-check of health risk problems set by a plurality of family members in a family environment can be realized, and the health check equipment is suitable for being used by a plurality of people in a family.
In some embodiments, the health monitoring method further comprises:
acquiring a video consultation instruction, and sending a video consultation request with a preset medical service system according to the video consultation instruction;
and according to the response instruction of the medical service system based on the video consultation request, establishing video communication with a corresponding terminal of the medical service system.
The health check equipment supports the user to establish video consultation with the associated doctor and medical institution. For example, a consultation button controlling the start of video consultation can be arranged on the health examination device, and the user can trigger the creation of video consultation by clicking the consultation button. The health examination equipment detects the clicking operation of a user on a consultation key to obtain a video consultation instruction, sends a video consultation request with a preset medical service system according to the video consultation instruction, and establishes video communication with a corresponding terminal of the medical service system according to a response instruction of the medical service system based on the video consultation request. The corresponding terminal may refer to a mobile phone terminal, a personal computer terminal, and other terminal devices used by the associated doctor, or may refer to a mobile phone terminal, a personal computer terminal, and other terminal devices preset by the associated medical institution for receiving the video consultation request. The user adopts the health examination equipment to establish video consultation with the associated doctor and medical institution, the video consultation needs to be carried out under the condition that the health examination equipment is networked, and the video consultation is established, and meanwhile, the shooting module of the visible light image is started to shoot the video data of the user.
As an alternative implementation, the health check device obtains the video consultation instruction, or automatically obtains the consultation instruction when a preset trigger condition is met. If the health examination equipment determines that the type of the lesion belongs to the health risk problem needing to be solved by the intervention of associated doctors and medical institutions as much as possible according to the current examination result, the triggering condition of video consultation is met, the video aiming instruction is automatically acquired, and a video consultation request is sent to a preset medical service system.
In the embodiment, the health examination equipment can support the user to establish video consultation with a doctor and a medical institution which are associated in advance according to the user requirement, and the video consultation is used for providing image reference for the doctor, so that the diagnosis convenience based on the health examination result is improved.
In some embodiments, before the establishing video communication with a corresponding terminal of the medical service system according to the response instruction of the medical service system based on the video consultation request, the method includes:
acquiring a face image, and sending the face image to the medical service system in cooperation with the video consultation request; and/or the presence of a gas in the gas,
and sending the human body infrared image and the detection result for determining whether the lesion part exists to the medical service system in cooperation with the video consultation request.
When the health examination equipment sends a video consultation request to the medical service system, the shooting module of the visible light image is started to shoot the face image of the user, or the face image of the user is shot correspondingly when the health examination is carried out on the user, and the face image is sent to the medical service system in cooperation with the video consultation request. The health examination equipment collects the face image and sends the face image to the medical service system in cooperation with the video consultation request, so that the medical service system can conveniently know the identity of the user sending the video consultation request while receiving the video consultation request.
As another optional implementation manner, when the health check device sends a video consultation request to the medical service system, the health check device sends the infrared image of the human body and the detection result of determining whether the lesion exists to the medical service system in cooperation with the video consultation request, so that the medical service system can know what health check result is based on the current video consultation request while receiving the video consultation request.
In the above embodiment, when the health check device sends the video consultation request to the medical service system, the face image is sent to the medical service system in cooperation with the video consultation request, or the human body infrared image and the detection result of determining whether the lesion part exists are sent to the medical service system in cooperation with the video consultation request, so that the medical service system can determine whether to receive the video consultation request or determine the priority when receiving a plurality of video consultation requests at the same time, and provide image reference for a doctor through video consultation, thereby improving the convenience of diagnosis based on the health check result.
In another aspect of the embodiments of the present application, a health monitoring method applied to a health check system is further provided, including the following steps:
s201, the cloud end trains the deep learning model according to the sample set of the human body infrared image marked with the diagnosis result to obtain a trained diagnosis data model and sends the trained diagnosis data model to the health examination equipment;
the diagnostic data model is obtained by training the deep learning model by adopting a sample set, wherein the sample set comprises a human body infrared image marked with a diagnostic result, for example, a diagnosed sample image containing a lesion part can be adopted, the diagnosed lesion part is a sample image of a certain lesion type and is used as a positive sample, and the diagnosed lesion part is used as a negative sample without actually causing a lesion.
The diagnostic data model is pre-trained, and when the method is specifically implemented, an initial classification neural network model, such as a convolutional neural network model, can be constructed first, and the initial classification neural network model is trained in the following way: firstly, obtaining a sample image, and carrying out category marking on the sample image, wherein the sample image refers to various sample images containing lesion parts, the marking refers to lesion types represented by corresponding sample images, the category marking can be carried out on the sample image according to label information capable of uniquely representing the lesion types, if the category marking of the image containing the specified lesion type 1 in the sample image is 1, the category marking of the image containing the specified lesion type 2 in the sample image is 2, and the category marking of the image not containing any specified lesion type in the sample image is 0, so as to obtain the sample image marked with a target category; then inputting the sample image marked with the target class into a classification neural network model, performing class prediction on the sample image through the classification neural network model, comparing the prediction class with the standard target class, determining the value of a loss function of the classification neural network model based on the difference between the prediction class and the standard target class, reversely transmitting the value of the loss function to each layer of the classification neural network model, and updating the model parameters of each layer through a Stochastic Gradient Descent (SGD) method to realize the training of the model.
The cloud acquires the sample set to train the deep learning model, so that the source of the sample set is conveniently expanded, the training speed and precision of the diagnostic data model are favorably accelerated, and then the trained diagnostic data model is issued to the health check equipment through the cloud, so that the health check equipment accessed to the network is conveniently upgraded in a unified manner through the cloud.
S203, the health examination equipment collects human vital sign parameters and collects human infrared images based on infrared thermal imaging detection; judging the human body state according to the human body vital sign parameters; and inputting the human body infrared image which is correspondingly acquired when the human body state is in a health examination state into the diagnosis data model so as to determine whether a pathological change part exists.
The health examination equipment collects the human body vital sign parameters, which can mean that the radar module calculates the heart rate and the respiratory rate of a collected object by using phase change through a microwave or millimeter wave radar to obtain the heart rate and the respiratory rate as the collected human body vital sign parameters; or, other sensors for collecting relevant parameters of human vital signs are used for collecting relevant parameters such as respiration, pulse, body temperature, blood pressure and the like. The acquisition of the human body infrared image based on the infrared thermal imaging detection may refer to that the infrared thermal imaging module acquires infrared radiation of each part of a human body, converts the infrared radiation into a digital signal to acquire a target temperature, and forms a visual human body infrared image. The health examination equipment is usually applied to a family environment scene, a user can align a body part which is expected to be subjected to health examination with the health examination equipment, and the health examination equipment acquires a human body infrared image of the corresponding body part; or the user stands at a certain distance in front of the health examination equipment, and the health examination equipment directly acquires the human body infrared image of the whole body of the user.
The body temperature is greatly influenced by the state of a user, for example, the body surface temperature is influenced by sweat generated after the user takes exercise. The health examination equipment judges the human body state by acquiring the human body vital sign parameters so as to determine whether the human body infrared image acquired by the user in the current state can accurately and truly reflect the health state of the user, but not the human body infrared image acquired by the user in the states of sweating and the like, so that the situation that the human body infrared image acquired by the user in the current state of sweating due to exercise and the like cannot truly reflect the health state of the user is avoided. In some optional embodiments, the human body status includes a health examination status currently suitable for health examination and a waiting status currently not suitable for health examination, wherein the health examination status indicates that the user is currently suitable for human body infrared image acquisition to identify whether there is a health risk problem, and the waiting status indicates that the user currently needs to wait until the identity returns to calm, for example, after sweat evaporates until the health examination status can be reached, and then uses the health examination equipment to perform human body infrared image acquisition to identify whether there is a health risk problem.
The health examination equipment inputs the human body infrared image acquired when the human body state is in the health state into the diagnosis data model, and the diagnosis data model identifies based on the human body infrared image to determine whether the pathological change part exists.
In the embodiment, the health examination equipment respectively collects human vital sign parameters, and collects human infrared images based on infrared thermal imaging detection, whether a diseased part exists is identified and determined through a diagnosis data model, and the diagnosis based on the human infrared images can be used for screening health risks according to the surface temperature distribution of a human body and the characteristics of diseases such as inflammation, congestion, arthralgia and tumor, so that the health risk screening problem is more comprehensive; the human body state is judged through the human body vital sign parameters, so that the human body infrared image on which the health risk problem screening is carried out is ensured to be the human body infrared image which is correspondingly acquired when the human body is in a health examination state, and the accuracy of the detection result is improved; the cloud issues the trained diagnostic data model to the health check equipment, and the health risk screening of the health check equipment through the diagnostic data model can be performed offline, so that the health check equipment is particularly suitable for being used in a family environment, is used as an efficient self-checking self-check for health problems such as concerned inflammation, congestion and tumor in the life of a user, is high in detection efficiency, and can meet the requirement of the user on early screening and tracking of diseases conveniently at home.
In some embodiments, the health monitoring method further comprises:
the health examination equipment sends a detection result for determining whether a lesion part exists and the corresponding human body infrared image to the cloud end, so that the cloud end can update the sample set;
and the cloud end trains and optimizes the diagnostic data model based on the updated sample set, and issues the updated diagnostic data model to the health examination equipment.
The health examination equipment can perform associated storage on the detection result for determining whether the pathological part exists and the corresponding human body infrared image, and when the health examination equipment is connected to the network, the health examination equipment reports and sends the detection result to the cloud end according to a set time period. During the use process of the health examination device, the obtained human body infrared image and the detection result of determining whether the lesion part exists can be formed into a sample image for training a diagnostic data model, so that the historical detection data obtained by the health examination device can be updated to a sample set. The cloud end can utilize the updated sample set to train and optimize the diagnostic data model, and the updated diagnostic data model is issued to the health examination equipment as an upgrade version so as to continuously improve the detection precision of the health examination equipment.
In the above embodiment, the health check device may report the historical detection data obtained in the using process to the cloud end, so that the cloud end updates the sample set, trains and optimizes the diagnostic data model, and the cloud end issues the updated diagnostic data model as an upgrade to the health check device, so as to continuously improve the detection accuracy of the health check device.
In some embodiments, the health monitoring method further comprises:
the health examination equipment acquires a face image, determines identity information according to the face image, and transmits a detection result for determining whether a lesion part exists to corresponding terminal equipment in cooperation with the identity information; and/or the presence of a gas in the gas,
the health examination equipment receives a data management instruction sent by corresponding terminal equipment and executes corresponding action according to the data management instruction; the executing the corresponding action according to the data management instruction comprises at least one of the following: displaying corresponding health file information on a current interface according to a health file viewing instruction, sending a video consultation request to a preset medical service system according to the video consultation instruction, and updating user permission information according to a family member management instruction, wherein the user permission information is used for the health examination equipment to determine a processing scheme for a current detection result.
The health check system comprises a terminal device, the terminal device is provided with a client capable of managing the health check device, the client can be an application program client (such as a mobile phone APP), or a webpage client, an applet, a wechat public number, and the like, and the health check system is not limited herein. The user can manage the health monitoring of the family members by adopting the client on the terminal equipment, such as adding or removing the family members, checking the health file information of each family member, registering, reserving, consulting for medical treatment and the like. Optionally, when the health check device collects the human vital sign parameters and the human infrared image for health monitoring, the method further comprises collecting the human face image, determining identity information according to the human face image, sending the detection result of determining whether the lesion part exists to the corresponding terminal device in cooperation with the identity information, and storing and managing the detection result according to the identity information by the terminal device.
As another optional implementation, the health check device may receive a data management instruction sent by the corresponding terminal device, and execute a corresponding action according to the data management instruction. The data management instruction may be an instruction for viewing health profile information of a specified user, an instruction for initiating a video consultation, an instruction for setting user permission, and the like, which are acquired by the terminal device according to an operation of the user in the application program interface. Correspondingly, the health check equipment executes corresponding actions according to the data management instruction, and the actions comprise: displaying corresponding health file information on a current interface according to the health file viewing instruction, sending a video consultation request to a preset medical service system according to the video consultation instruction, and updating user permission information according to the family member management instruction. The health examination equipment comprises a display module, and the corresponding health record information is displayed on the current interface according to the health record viewing instruction so as to be used for mastering the health dynamic state in real time. The display module can be used for displaying basic life related information such as date and time, local weather conditions and the like in a daily state. The health examination equipment comprises a shooting module, and the shooting module is used for sending a video consultation request to a preset medical service system according to a video consultation instruction, shooting visible light images of collected people after video consultation is established, and providing image reference for doctor consultation. The user permission information may be used by the health check device to determine a processing scheme for the current detection result, for example, if the current detection result is detection data of a user without permission according to the usage permission information configured by the terminal device, the health check device does not perform processing such as local storage and cloud reporting.
In the above embodiment, the health check system includes the terminal device, and the terminal device may interact with the health check device to implement more function expansion and management.
In some embodiments, the health monitoring method further comprises:
the terminal equipment receives health examination data sent by the health examination equipment for management; wherein the management scheme includes at least one of: and forming health files corresponding to different identity information according to the health examination data and forming a health risk assessment report according to the health examination data in a set historical time period.
The health examination data refers to data formed in the process of screening health risk problems of the user by the health examination equipment, such as identity information, human vital sign parameters, human infrared images and examination results of determining whether pathological changes exist. The terminal device receives health check data sent by the health check device for management, which may refer to that the health check data forms health files corresponding to different identity information according to the identity information. The health profile may include the test data for each time within a set time period, and may also include health notes or recommendations generated for each test data. The terminal device receives and manages health check data sent by the health check device, and may also refer to forming a health risk assessment report according to the health check data in a set historical period, where the health risk assessment report may form a graph according to some index values of detection data in the set historical period, and may also include information such as prediction of index value trends and prediction of potential risks.
In the embodiment, the user can realize more management of health detection through the terminal device, and is also convenient to realize the analysis, the arrangement and the application functions of more health data by utilizing the terminal device, and the terminal device is matched with the health examination device to meet more health management scenes.
In order to provide a more general understanding of the health monitoring method provided by the embodiments of the present application, please refer to fig. 5 and 6 in conjunction with the following description, which illustrate an alternative embodiment of the health monitoring method. The health examination system comprises a cloud end, a terminal device, a medical service system and a health examination device. The health examination equipment comprises an acquisition module, a visible light shooting module, an audio module, a display module, a communication module, a processor and a memory.
S11, the cloud end trains the diagnosis data model and then issues the diagnosis data model to the health examination equipment;
and S12, the acquisition module acquires the vital sign parameters of the human body through the radar module and acquires the infrared image of the human body through the infrared thermal imaging module. The acquisition module comprises a radar module and an infrared thermal imaging module; the radar module can be a microwave or millimeter wave radar, and calculates the heart rate and the respiratory rate of a person by utilizing phase change; the infrared thermal imaging module comprises elements such as an infrared detector, an infrared lens, a structural part, a processing circuit and the like, wherein the core element is the infrared detector, such as a long-wave uncooled infrared detector, and other types of infrared detectors are similar. The infrared detector can collect infrared radiation of all parts of a body, convert the infrared radiation into digital signals, acquire target temperature and form visual infrared images.
S13, the processor judges the human body state according to the human body vital sign parameters; wherein, two modules of radar module and infrared thermal imaging module can carry out following cooperation, improve diagnostic accuracy: the diagnosis based on the infrared image is that the medical diagnosis is carried out according to the temperature distribution of the surface of the human body and the characteristics of diseases such as inflammation, arthralgia and tumor (the temperature of the affected part of the disease is obviously different from the temperature around the affected part); however, the body temperature is greatly influenced by the user state, for example, sweat after sports can influence the body surface temperature. Therefore, the heart rate and the respiratory rate of a user can be measured firstly by combining the radar module, the state of the user is judged, and if the heart rate is too fast, the user is prompted to test after calm; if the user continues to test under the condition of excessively high heart rate, the data measured at this time are independently marked, and the diagnostic result is prevented from being influenced.
S14, the processor identifies the feature points according to the human infrared image collected when the human state is in the health examination state, extracts the affected part image and inputs the image into the diagnosis data model to determine whether the diseased part exists.
The processor receives heart rate, respiratory rate, body temperature and infrared image data of the acquisition module, and a) automatically records and generates historical data curves of the heart rate, the respiratory rate and the body temperature; b) processing the infrared image, and automatically extracting an image of an affected part: because the user does not need to pay extra attention to the shooting angle, the position of the affected part is not fixed in the infrared image acquired every time, which is not beneficial to further analyzing and archiving the data; the processor firstly identifies the position of the affected part in the image by using the characteristic point identification, then extracts the image of the affected part, and registers the image of the affected part and the image extracted historically by using the characteristic point to form continuous image data, so that the development trend of the affected part can be conveniently analyzed; the processor is combined with the existing disease diagnosis database to match the images and give a preliminary diagnosis suggestion, for example, the infrared image characteristics of the images of the inflammation at the early stage and the middle and later stages of the development are different, so that the current development situation of the inflammation can be preliminarily judged. In combination with a) b) two, the processor may give off-line diagnostic reports and archive the data before and after analysis by time.
And S15, the visible light shooting module collects a face image, the processor identifies the identity information of the current user according to the face image, and the detection result and the identity information are stored in a correlation mode.
And S16, the processor displays the detection result of determining whether the lesion part exists through the display module. The display module can be used for displaying basic life related information such as date and time, local weather conditions and the like. The display module can be an OLED touch screen, can display an application program interface installed on the health check equipment, and supports a user to execute interactive operations such as clicking and touch control on the application program interface so as to realize human-computer interaction. For example, the finger touch interaction of the user is supported, and health management services such as health examination report consulting, audio and video consultation and the like are carried out.
And S17, the health check equipment sends a video consultation request to a related medical service system according to the operation of establishing video consultation triggered by the user, and establishes video communication with a corresponding terminal of the medical service system according to a response instruction of the medical service system based on the video consultation request. After video communication is established, the visible light shooting module collects human body video data to provide image reference for doctor consultation, and the audio module supports an audio interaction part which is divided into a loudspeaker and a microphone and used for real-time talkback and conversation between a doctor and a user in video consultation or audio consultation, and voice broadcasting of health reports and the like.
The memory may include various storage media, such as an EMMC, an SD card, and the like, for storing data before and after analysis by the processing module. The communication module is composed of communication elements such as Wi-Fi chips and the like, is mainly used for receiving and sending data streams sent by the processor and receiving deep learning models sent by the cloud, and is transmitted to the processor and the like, and is also responsible for carrying out service docking data exchange and the like with a cooperative medical service system.
S18, the health examination equipment reports the detection result to the cloud end; the cloud continuously optimizes the disease diagnosis database according to the acquired infrared images and the diagnosis result of the doctor, updates the diagnosis data model, and sends the diagnosis data model to the health examination equipment, so that the diagnosis accuracy is improved.
The cloud end is provided with a storage module and used for storing original data such as infrared images, heart rate and body temperature and historical diagnosis reports, and data loss caused by damage of health examination equipment due to reasons is avoided. The cloud end is provided with a communication module used for receiving the original data of the health examination module acquisition equipment and transmitting the updated model to the health examination module.
The terminal equipment is provided with applications in forms of small programs, App, WeChat public number web pages and the like, and mainly comprises functional modules for family member management, physical examination data management, health service and the like, so that people can add or remove family members conveniently, and health files, data, health risks, registration appointment, medical consultation and the like can be checked.
The medical service system can comprise various medical institutions such as public hospitals and physical examination institutions, and can be accessed to the medical service system for inquiry, registration, emergency call and the like.
In the above embodiment, the health check device may be an intelligent home device in an internet of things system, such as an intelligent mirror, when a user uses the intelligent mirror, the intelligent mirror automatically identifies and determines the identity of a current person through visible light camera face recognition, then collects heart rate, respiratory rate and infrared images, and generates a report after being analyzed by a processor, the report is displayed on a screen of the intelligent mirror in real time, related data and an analysis result are uploaded to a medical service system or a cloud or a terminal device, and the user can perform operations such as video inquiry to a medical institution through the mirror. The health examination equipment adopts the combination of radar and infrared thermal imaging counting, so that the diagnosis accuracy is improved; the medical examination process does not need remote assistance of medical staff, multi-frame infrared videos are shot, key frames of the same organ or part at the same angle are automatically identified through feature point identification, image identification and processing technologies, infrared image data with the same angle, high matching degree and high quality can be obtained, and the development trend of a patient can be obtained through analysis. The physical examination process is more intelligent and efficient, and the link that the user calibrated shooting gesture and angle, even shoot again is removed from.
Referring to FIG. 7, in another aspect of the present application, a health monitoring device is provided, which in an exemplary embodiment may be implemented using smart mirrors. This health monitoring device includes: the acquisition module 31 is used for acquiring human body vital sign parameters and acquiring human body infrared images based on infrared thermal imaging detection; the judging module 32 is used for judging the human body state according to the human body vital sign parameters; the identification module 33 is configured to perform feature point identification on the human infrared image acquired correspondingly when the human state is in the health examination state, so as to determine whether a diseased part exists.
Optionally, the identification module 33 is specifically configured to perform feature point identification on the human infrared image that is acquired correspondingly when the human state is in the health examination state, and identify a position of a suspected lesion; extracting a suspected lesion part image; and inputting the suspected lesion part image into a diagnosis data model, determining the type of the suspected lesion part and returning lesion part prompt information.
Optionally, the identifying module 33 is further configured to register the suspected lesion position image with a history extracted image, so as to obtain continuous lesion position image data representing a lesion trend of the suspected lesion position image.
Optionally, the identification module 33 is further configured to input continuous image data of the lesion site into a diagnostic data model, determine the type of the suspected lesion site, and return a lesion site prompt message.
Optionally, the acquisition module 31 is further configured to acquire a face image, and determine identity information according to the face image; and the storage module is used for correspondingly storing the detection result for determining whether the lesion part exists and the identity information.
Optionally, the system further comprises a communication module, configured to obtain a video consultation instruction, and send a video consultation request with a preset medical service system according to the video consultation instruction; and according to the response instruction of the medical service system based on the video consultation request, establishing video communication with a corresponding terminal of the medical service system.
Optionally, the acquisition module 31 is further configured to acquire a face image, and send the face image to the medical service system in cooperation with the video consultation request. The communication module is further configured to send the human body infrared image and the detection result of determining whether a lesion site exists to the medical service system in cooperation with the video consultation request.
It should be noted that: in the process of implementing the human health examination, the health monitoring device provided in the above embodiment is exemplified by only the division of the above program modules, and in practical applications, the processing distribution may be completed by different program modules as needed, that is, the internal structure of the device may be divided into different program modules to complete all or part of the above described method steps. In addition, the health monitoring device provided by the above embodiment and the health monitoring method embodiment applied to the health examination device side belong to the same concept, and the specific implementation process thereof is described in the method embodiment, and is not described herein again.
Referring to fig. 8, an optional hardware structure diagram of the health check apparatus provided in the embodiment of the present application is provided, where the health check apparatus includes a processor 111, an infrared detector 113 and a radar sensor 114 connected to the processor 111, and a memory 112, where the memory 112 is used for storing various types of data to support operations of a health monitoring device, and is used for storing a computer program for implementing the health monitoring method provided in any embodiment of the present application, and when the computer program is executed by the processor, the steps of the health monitoring method provided in any embodiment of the present application are implemented, and the same technical effects can be achieved, and are not described herein again to avoid repetition. The health check equipment can be the intelligent household equipment shown in fig. 1.
Optionally, the health check device further includes a shooting module 115 and a display module 116 connected to the processor 111, where the shooting module 115 is configured to shoot a face image and send the face image to the processor to determine identity information; the display module 116 is used for displaying the inspection result information. The health check device may be a smart mirror.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the health monitoring method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (17)
1. A health monitoring method is applied to health examination equipment and is characterized by comprising the following steps:
collecting human body vital sign parameters, and collecting human body infrared images based on infrared thermal imaging detection;
judging the human body state according to the human body vital sign parameters;
and carrying out characteristic point identification on the human body infrared image which is correspondingly acquired when the human body state is in a health examination state so as to determine whether a pathological change part exists.
2. The health monitoring method as claimed in claim 1, wherein the performing feature point recognition on the infrared image of the human body collected when the human body state is in a health examination state to determine whether a lesion exists comprises:
identifying characteristic points of the human body infrared image which is correspondingly collected when the human body state is in a health examination state, and identifying the position of a suspected lesion part;
extracting a suspected lesion part image;
and inputting the suspected lesion part image into a diagnosis data model, determining the type of the suspected lesion part and returning lesion part prompt information.
3. The health monitoring method as set forth in claim 2, further comprising, after the extracting the image of the suspected lesion site:
and registering the suspected lesion part image with a history extraction image to obtain continuous lesion part image data representing the lesion trend of the suspected lesion part image.
4. The health monitoring method as claimed in claim 3, wherein said inputting the image of the suspected lesion into a diagnostic data model, determining the type of the suspected lesion and returning a lesion prompt message comprises:
and inputting continuous image data of the lesion site into a diagnostic data model, determining the type of the suspected lesion site and returning prompt information of the lesion site.
5. The health monitoring method as in claim 1, further comprising:
acquiring a face image, and determining identity information according to the face image;
and correspondingly storing the detection result for determining whether the lesion part exists or not and the identity information.
6. The health monitoring method as in claim 1, further comprising:
acquiring a video consultation instruction, and sending a video consultation request with a preset medical service system according to the video consultation instruction;
and according to the response instruction of the medical service system based on the video consultation request, establishing video communication with a corresponding terminal of the medical service system.
7. The health monitoring method according to claim 6, wherein before establishing video communication with a corresponding terminal of the medical service system according to the response instruction of the medical service system based on the video consultation request, the method comprises:
acquiring a face image, and sending the face image to the medical service system in cooperation with the video consultation request; and/or the presence of a gas in the gas,
and sending the human body infrared image and the detection result for determining whether the lesion part exists to the medical service system in cooperation with the video consultation request.
8. A health monitoring method is applied to a health check system and is characterized by comprising the following steps:
the cloud end trains the deep learning model according to the sample set of the human body infrared image marked with the diagnosis result to obtain a trained diagnosis data model and sends the trained diagnosis data model to the health examination equipment;
the health examination equipment acquires human body vital sign parameters and acquires human body infrared images based on infrared thermal imaging detection; judging the human body state according to the human body vital sign parameters; and inputting the human body infrared image which is correspondingly acquired when the human body state is in a health examination state into the diagnosis data model so as to determine whether a pathological change part exists.
9. The health monitoring method as in claim 8, further comprising:
the health examination equipment sends a detection result for determining whether a lesion part exists and the corresponding human body infrared image to the cloud end, so that the cloud end can update the sample set;
and the cloud end trains and optimizes the diagnostic data model based on the updated sample set, and issues the updated diagnostic data model to the health examination equipment.
10. The health monitoring method as in claim 8, further comprising:
the health examination equipment acquires a face image, determines identity information according to the face image, and transmits a detection result for determining whether a lesion part exists to corresponding terminal equipment in cooperation with the identity information; and/or the presence of a gas in the gas,
the health examination equipment receives a data management instruction sent by corresponding terminal equipment and executes corresponding action according to the data management instruction; the executing the corresponding action according to the data management instruction comprises at least one of the following: displaying corresponding health file information on a current interface according to a health file viewing instruction, sending a video consultation request to a preset medical service system according to the video consultation instruction, and updating user permission information according to a family member management instruction, wherein the user permission information is used for the health examination equipment to determine a processing scheme for a current detection result.
11. The health monitoring method as in claim 8, further comprising:
the terminal equipment receives health examination data sent by the health examination equipment for management; wherein the management scheme includes at least one of: and forming health files corresponding to different identity information according to the health examination data and forming a health risk assessment report according to the health examination data in a set historical time period.
12. A health monitoring device, comprising:
the acquisition module is used for acquiring human body vital sign parameters and acquiring human body infrared images based on infrared thermal imaging detection;
the judging module is used for judging the human body state according to the human body vital sign parameters;
and the identification module is used for carrying out characteristic point identification on the human body infrared image which is correspondingly acquired when the human body state is in the health examination state so as to determine whether a pathological change part exists.
13. A health check device comprising a processor, an infrared detector and a radar sensor connected to the processor, a memory and a computer program stored on the memory and executable by the processor, the computer program when executed by the processor implementing the health monitoring method as claimed in any one of claims 1 to 7.
14. The health check device of claim 13, further comprising a camera module and a display module connected to said processor, said camera module being adapted to capture a facial image for transmission to said processor for determining identity information; the display module is used for displaying the inspection result information.
15. The health check device of claim 13, wherein said health check device is a smart mirror.
16. A health monitoring system comprising the health check device of claim 13, a cloud, and a terminal device; the cloud end trains the deep learning model according to the sample set of the human body infrared image marked with the diagnosis result to obtain a trained diagnosis data model and sends the trained diagnosis data model to the health examination equipment; and the terminal equipment receives the checking result sent by the health checking equipment for management.
17. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by the processor, carries out the health monitoring method as set forth in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111075045.1A CN113724244A (en) | 2021-09-14 | 2021-09-14 | Health monitoring method, device and system, health examination equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111075045.1A CN113724244A (en) | 2021-09-14 | 2021-09-14 | Health monitoring method, device and system, health examination equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113724244A true CN113724244A (en) | 2021-11-30 |
Family
ID=78683620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111075045.1A Pending CN113724244A (en) | 2021-09-14 | 2021-09-14 | Health monitoring method, device and system, health examination equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724244A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115414032A (en) * | 2022-08-03 | 2022-12-02 | 浙江大华技术股份有限公司 | Nursing monitoring system, method and device, monitoring equipment and storage medium |
| CN116821779A (en) * | 2023-08-31 | 2023-09-29 | 中南大学湘雅医院 | Big data identification method for gastrointestinal health |
| CN117594227A (en) * | 2024-01-18 | 2024-02-23 | 微脉技术有限公司 | Health state monitoring method, device, medium and equipment based on wearable equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354429A (en) * | 2015-11-19 | 2016-02-24 | 小红象医疗科技有限公司 | System and method for automatically analyzing health outlier via infrared medical image |
| CN105933454A (en) * | 2016-06-30 | 2016-09-07 | 小红象医疗科技有限公司 | Health monitoring and health service system based on mobile phone infrared |
| CN106407724A (en) * | 2015-11-19 | 2017-02-15 | 小红象医疗科技有限公司 | System and method for automatically analyzing health thermal state based on infrared medical image |
| CN110379523A (en) * | 2019-07-19 | 2019-10-25 | 厦门医管家医疗科技有限公司 | Infrared remote based on cloud platform sees a doctor method and system |
| WO2021174601A1 (en) * | 2020-03-03 | 2021-09-10 | 广州紫川电子科技有限公司 | Infrared thermal imaging-based human body temperature anomaly detection method and apparatus |
-
2021
- 2021-09-14 CN CN202111075045.1A patent/CN113724244A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354429A (en) * | 2015-11-19 | 2016-02-24 | 小红象医疗科技有限公司 | System and method for automatically analyzing health outlier via infrared medical image |
| CN106407724A (en) * | 2015-11-19 | 2017-02-15 | 小红象医疗科技有限公司 | System and method for automatically analyzing health thermal state based on infrared medical image |
| CN105933454A (en) * | 2016-06-30 | 2016-09-07 | 小红象医疗科技有限公司 | Health monitoring and health service system based on mobile phone infrared |
| CN110379523A (en) * | 2019-07-19 | 2019-10-25 | 厦门医管家医疗科技有限公司 | Infrared remote based on cloud platform sees a doctor method and system |
| WO2021174601A1 (en) * | 2020-03-03 | 2021-09-10 | 广州紫川电子科技有限公司 | Infrared thermal imaging-based human body temperature anomaly detection method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| 杨丽 等: "《实用老年疾病诊治护理及对策》", 30 April 2021, 中国纺织出版社有限公司, pages: 84 - 85 * |
| 鞠全勇 等: "《物联网技术与应用》", 30 June 2021, 吉林科学技术出版社, pages: 267 - 268 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115414032A (en) * | 2022-08-03 | 2022-12-02 | 浙江大华技术股份有限公司 | Nursing monitoring system, method and device, monitoring equipment and storage medium |
| CN115414032B (en) * | 2022-08-03 | 2023-10-03 | 浙江大华技术股份有限公司 | Nursing monitoring system, method, device, monitoring equipment and storage medium |
| CN116821779A (en) * | 2023-08-31 | 2023-09-29 | 中南大学湘雅医院 | Big data identification method for gastrointestinal health |
| CN116821779B (en) * | 2023-08-31 | 2023-11-14 | 中南大学湘雅医院 | Big data identification method for gastrointestinal health |
| CN117594227A (en) * | 2024-01-18 | 2024-02-23 | 微脉技术有限公司 | Health state monitoring method, device, medium and equipment based on wearable equipment |
| CN117594227B (en) * | 2024-01-18 | 2024-04-30 | 微脉技术有限公司 | Health state monitoring method, device, medium and equipment based on wearable equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113724244A (en) | Health monitoring method, device and system, health examination equipment and medium | |
| JP7387185B2 (en) | Systems, methods and computer program products for physiological monitoring | |
| US20210145306A1 (en) | Managing respiratory conditions based on sounds of the respiratory system | |
| CN108778097A (en) | Device and method for assessing heart failure | |
| US9152762B2 (en) | System, method, and software for positive patient identification | |
| CN111653368A (en) | Artificial intelligence epidemic situation big data prevention and control early warning system | |
| Ruminski et al. | The data exchange between smart glasses and healthcare information systems using the HL7 FHIR standard | |
| WO2020121308A9 (en) | Systems and methods for diagnosing a stroke condition | |
| CN104382570A (en) | Digitized full-automatic health condition detection device | |
| WO2018204336A1 (en) | Techniques for providing computer assisted eye examinations | |
| CN111863252A (en) | Health monitoring method, system, computer equipment and storage medium | |
| CN104427942A (en) | Measurement assistance device, measurement assistance method, control program, and recording medium | |
| CN111524093A (en) | Intelligent screening method and system for abnormal tongue picture | |
| CN111227789A (en) | Human health monitoring method and device | |
| WO2020133776A1 (en) | Health condition detection method and system based on television, and television | |
| CN112017403B (en) | Community-house integrated intelligent service electronic board | |
| CN113221725A (en) | Risk processing method and system | |
| CN113096811A (en) | Diabetic foot image processing and risk early warning equipment based on infrared thermal imaging | |
| WO2023231654A1 (en) | Archive management method and apparatus, device, storage medium and program product | |
| CN110074759B (en) | Voice data auxiliary diagnosis method, device, computer equipment and storage medium | |
| CN111489477A (en) | Entrance entry register capable of intelligently detecting body temperature and application method thereof | |
| CN114664441A (en) | Coronary heart disease risk assessment system | |
| CN113470818A (en) | Disease prediction method, device, system, electronic device and computer readable medium | |
| CN109640819B (en) | Apparatus, system and method for detecting asthma attack or asthma in a subject | |
| Baskaran et al. | Using facial landmark detection on thermal images as a novel prognostic tool for emergency departments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |