CN113470818A - Disease prediction method, device, system, electronic device and computer readable medium - Google Patents
Disease prediction method, device, system, electronic device and computer readable medium Download PDFInfo
- Publication number
- CN113470818A CN113470818A CN202110775911.1A CN202110775911A CN113470818A CN 113470818 A CN113470818 A CN 113470818A CN 202110775911 A CN202110775911 A CN 202110775911A CN 113470818 A CN113470818 A CN 113470818A
- Authority
- CN
- China
- Prior art keywords
- disease
- infrared
- disease prediction
- determining
- sample
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 201
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 201
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001931 thermography Methods 0.000 claims abstract description 96
- 208000023504 respiratory system disease Diseases 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000007477 logistic regression Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 abstract description 10
- 230000007613 environmental effect Effects 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 14
- 238000009529 body temperature measurement Methods 0.000 description 10
- 210000003800 pharynx Anatomy 0.000 description 10
- 230000036760 body temperature Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 210000002345 respiratory system Anatomy 0.000 description 5
- 238000012886 linear function Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 206010061218 Inflammation Diseases 0.000 description 2
- 201000007100 Pharyngitis Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 208000030270 breast disease Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003759 clinical diagnosis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000004054 inflammatory process Effects 0.000 description 2
- 230000036285 pathological change Effects 0.000 description 2
- 231100000915 pathological change Toxicity 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 1
- 206010068319 Oropharyngeal pain Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a disease prediction method, a disease prediction device, a disease prediction system, electronic equipment and a computer readable medium, and relates to the technical field of artificial intelligence. One embodiment of the method comprises: acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph; determining a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value; determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases. The embodiment reduces the influence of environmental factors and reduces the misjudgment rate, thereby improving the accuracy of the screening result.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a system, an electronic device, and a computer-readable medium for disease prediction.
Background
Infrared thermography, a non-contact body temperature detection method, has been widely used, and has important significance for early screening and diagnosis of diseases.
At present, for body temperature screening by using infrared thermography, people with abnormal body temperature are screened mainly by comparing the body temperature value of a single point in an infrared thermography with a preset high temperature threshold value, so that suspected patients are detected.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the image acquisition of the infrared thermal imaging is easily influenced by environmental factors, so that the screening is only carried out by comparing the single-point body temperature value with the high-temperature threshold value, the accuracy of the screening result is low, and the possibility of misjudgment is high.
Disclosure of Invention
In view of this, embodiments of the present invention provide a disease prediction method, apparatus, system, electronic device, and computer readable medium, which can determine a plurality of second temperature values corresponding to a plurality of pixel points in an infrared thermography according to a first temperature value of a feature point in the infrared thermography of a disease prediction object and a gray value of the infrared thermography, so as to reduce an influence of an environmental factor in an image acquisition process and/or a temperature measurement process of the infrared thermography and improve accuracy of a temperature measurement result. Furthermore, according to the second temperature values of the multiple pixel points, the disease prediction model is used for predicting the disease probability of the disease prediction object, the misjudgment rate can be effectively reduced, and the accuracy of the screening result is improved.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a disease prediction method including:
acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph;
determining a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value;
determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
Optionally, the determining, according to the gray value of the infrared thermography and the first temperature value, a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography includes:
determining the corresponding relation between the gray value and the temperature value in the infrared thermography;
and determining the plurality of second temperature values respectively corresponding to the plurality of pixel points according to the gray values of the plurality of pixel points in the infrared thermography, the corresponding relation, the first temperature value and the gray value of the characteristic point.
Optionally, the determining a corresponding relationship between a gray value and a temperature value in the infrared thermography includes:
acquiring infrared thermographs of a plurality of samples;
determining sample detection points, and sample gray values and sample temperature values corresponding to the sample detection points in each sample infrared thermograph;
and determining the corresponding relation according to the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs.
Optionally, the determining the corresponding relationship according to the sample gray values and the sample temperature values respectively corresponding to the multiple sample infrared thermographs includes:
and performing two-dimensional fitting on the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs, and taking the fitting result as the corresponding relation.
Optionally, the determining, according to the gray values of the plurality of pixel points in the infrared thermography, the correspondence, the first temperature value, and the gray values of the feature points, the plurality of second temperature values respectively corresponding to the plurality of pixel points includes:
updating the intercept in the fitting result according to the slope in the fitting result, the first temperature value and the gray value of the characteristic point; and determining the plurality of second temperature values according to the updated fitting result and the gray values of the plurality of pixel points.
Optionally, the central pixel point of the infrared thermography is used as the feature point.
Optionally, the disease prediction model is constructed based on a logistic regression algorithm.
Optionally, the weight vector corresponding to the logistic regression algorithm is trained according to the historical temperature value and the illness result corresponding to one or more diseases, so as to obtain the disease prediction model.
Optionally, when the probability of the target disease is greater than a preset threshold, a prompt message is output.
Optionally, the infrared thermography comprises: a laryngeal image of the subject for the disease prediction;
the target disease is a respiratory disease.
According to a second aspect of embodiments of the present invention, there is provided a disease prediction apparatus including: the device comprises an acquisition module, a determination module and a prediction module; wherein,
the acquisition module is used for acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph;
the determining module is used for determining a plurality of second temperature values corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value;
the prediction module is used for determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
According to a third aspect of embodiments of the present invention, there is provided a disease prediction system including: the system comprises an infrared thermal imager, a display and a disease prediction device based on infrared thermal image recognition; wherein,
the infrared thermal imager is used for collecting an infrared thermal image of a disease prediction object;
the disease prediction device is used for predicting the disease probability of the disease prediction object corresponding to the target disease according to the infrared thermography;
the display is used for displaying the prediction result of the disease prediction device.
According to a fourth aspect of the embodiments of the present invention, there is provided an electronic device for disease prediction, including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method as in any one of the disease prediction methods provided above in the first aspect.
According to a fifth aspect of embodiments of the present invention, there is provided a computer readable medium, on which a computer program is stored, which program, when executed by a processor, implements the method of any one of the disease prediction methods provided above in the first aspect.
One embodiment of the above invention has the following advantages or benefits: the method and the device can determine a plurality of second temperature values corresponding to a plurality of pixel points in the infrared thermography according to the first temperature values of the characteristic points in the infrared thermography of the disease prediction object and the gray values of the infrared thermography, thereby reducing the influence of environmental factors in the image acquisition process and/or the temperature measurement process of the infrared thermography and improving the accuracy of the temperature measurement result. Furthermore, according to the second temperature values of the multiple pixel points, the disease prediction model is used for predicting the disease probability of the disease prediction object, the misjudgment rate can be effectively reduced, and the accuracy of the screening result is improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic flow chart of a disease prediction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a disease prediction apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a disease prediction system according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments of the present invention and the technical features of the embodiments may be combined with each other without conflict.
Fig. 1 is a disease prediction method based on infrared thermography identification according to an embodiment of the present invention, which may include the following steps S101 to S103:
step S101: acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph.
Step S102: and determining a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value.
One possible implementation of step S102 includes: determining the corresponding relation between the gray value and the temperature value in the infrared thermography; and determining a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography according to the corresponding relation, the first temperature value and the gray value of the characteristic point.
The corresponding relation can also be a single-point corresponding mode of an RGB value and a temperature value of the image, a model training determination mode and a fitting determination mode.
The correspondence may be expressed as a correspondence table, a curve, a straight line.
In a preferred embodiment of the present invention, the correspondence between the gray scale value and the temperature value in the infrared thermography can be determined by: acquiring infrared thermographs of a plurality of samples; determining sample detection points, and sample gray values and sample temperature values corresponding to the sample detection points in each sample infrared thermograph; and determining the corresponding relation according to the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs.
When a sample detection point is determined from a sample infrared thermograph, a characteristic region is determined, for example, in a scene of predicting respiratory diseases, a characteristic region corresponding to the laryngeal part of the pharynx is generally determined from a sample infrared image, and then the sample detection point is determined from the characteristic region, so as to improve the accuracy of later-stage disease prediction. For many epidemic respiratory diseases, in addition to fever, their clinical manifestations are accompanied by symptoms of the upper respiratory tract, such as sore throat, cough, etc. In fact, the throat tissues may have been pathologically changed during the latent period of respiratory diseases, the body temperature of the throat inflammation part may be changed, the infrared thermal imaging technology is sensitive to the temperature change, and the temperature change can be captured when the pathological change is slightly generated at the beginning of the pathological change. Therefore, the accuracy of the screening result of the respiratory system diseases can be improved by analyzing the infrared thermography of the characteristic region corresponding to the throat.
When the sample detection point is determined from the feature region, any one pixel point corresponding to the feature region can be randomly selected as the sample detection point, and a fixed pixel point can also be selected as the sample detection point according to actual test requirements. In a preferred embodiment of the present invention, a central pixel point of a feature region in an infrared thermography may be used as a sample detection point, that is, the sample detection point may be the central pixel point of the infrared thermography. Therefore, the central pixel point is used as the sample detection point, and compared with the edge pixel point used as the sample detection point, the temperature value corresponding to the central pixel point is less influenced by the environment, so that the accuracy of temperature measurement is improved conveniently.
In an embodiment of the present invention, the determining the corresponding relationship according to the sample gray-scale values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs includes: and performing two-dimensional fitting on the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs, and taking the fitting result as the corresponding relation.
It can be understood that the gray value and the temperature value of the infrared thermal imager generally have a linear relationship, so that a corresponding linear function can be fitted by using a least square method through the gray values and the temperature values of a plurality of sample points to determine the corresponding relationship.
For example, the correspondence between the gray value and the temperature value of each infrared thermal imager may be different, and at this time, the correspondence may be fitted by obtaining a plurality of sample pictures taken by the infrared thermal imager. That is, a set of data [ (x) is obtained by obtaining gray values (x) of a plurality of sample pixel points corresponding to a plurality of sample infrared thermographs and corresponding temperature values (t), respectively1,t1),(x2,t2)…(xi，ti)]. Plotting these data into x-t coordinates, one can find that these points are near a straight line, and the formula of the linear function is: t is ti＝kxi+ b. In this case, it can be determined by a two-dimensional fitting methodThe slope k and the intercept b of the straight line, i.e. the correspondence is determined.
After a two-dimensional fitting result is obtained, that is, after the k and b are determined, since the b value is subject to the difference between the environmental factor and the individual, the b values of the infrared thermographs of different disease prediction objects may be different, and in order to improve the accuracy of temperature measurement, after the infrared thermograph of the disease prediction object is obtained, the b value needs to be updated according to the infrared thermograph of the disease prediction object. Thus, in one embodiment of the invention: updating the intercept in the fitting result according to the slope in the fitting result, the first temperature value and the gray value of the characteristic point; and determining the plurality of second temperature values according to the updated fitting result and the gray values of the plurality of pixel points.
The feature points may be fixed points selected according to requirements. In a preferred embodiment of the present invention, the center pixel point in the infrared thermography is used as the feature point. The formula of the linear function of the first temperature value of the characteristic point and the gray value of the characteristic point is as follows: t is t0＝kx0+ b. According to the gradient k and the gray value (x) of the characteristic point in the formula0) And a first temperature value (t) corresponding to the characteristic point0) Obtaining the formula b ═ t of intercept0-kx0And determining the value of the intercept b according to a formula, thereby updating the value b in the fitting result.
And after the b value in the fitting result is updated, determining the plurality of second temperature values according to the updated fitting result and the gray values of the plurality of pixel points. For example, the formula of the linear function of the gray value and the temperature value of the ith pixel point is as follows: t is ti＝kxi+ b, then according to b and k in the fitting result, and the gray value (x) of the ith pixel pointi) Then the second temperature value (t) corresponding to the ith pixel point can be determinedi)。
In an embodiment of the present invention, after the second temperature values corresponding to the pixel points are determined, the second temperature values may be added to the infrared thermographyIn a set of temperature values, e.g. each calculated second temperature value tiAnd adding the temperature value to a temperature value set corresponding to the thermal image.
Step S103: determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
The predictive models may be constructed according to different machine learning algorithms, such as Support Vector Machines (SVMs), logistic regression, decision trees, and the like.
In one embodiment of step S103, the disease prediction model is constructed based on a logistic regression algorithm, and the disease prediction model needs to be obtained by pre-training.
The prediction result of the logistic regression algorithm is in an S shape, the probability change at two ends is small, the logistic regression algorithm is not easily influenced by marginal values, and the change of the middle probability is large and sensitive. Because the body temperature of a human is constant, and the body temperature difference change is mainly concentrated in a small range of the middle section, the logistic regression algorithm for analyzing the body temperature and predicting diseases is sensitive, and a good prediction effect is achieved.
In one embodiment of the present invention, further comprising: and training the weight vector corresponding to the logistic regression algorithm according to the historical temperature value and the ill result corresponding to one or more diseases to obtain the disease prediction model.
The historical temperature value can be obtained from a plurality of infrared thermographic images corresponding to one or more diseases in an infrared thermographic image library, or can be obtained from a plurality of infrared thermographic images corresponding to one or more diseases based on clinical data. Wherein the clinical data is determined based on clinical diagnostic results. In a preferred embodiment of the present invention, a plurality of sets of historical second temperature values are determined from the plurality of infrared thermographic images corresponding to one or more diseases based on clinical data. And training a logistic regression algorithm by using the plurality of historical second temperature value sets and the corresponding plurality of infrared thermographs corresponding to the disease results of clinical diagnosis of the target diseases, so as to obtain the weight vector corresponding to the logistic regression algorithm.
The logistic regression algorithm is trained by using the infrared thermography corresponding to the target disease based on clinical data, so that the weight vector obtained by training is more reasonable, and the accuracy of a prediction result can be improved.
Taking a prediction model of respiratory system diseases as an example, when the prediction model is pre-trained, the infrared thermography comprises a throat image of a disease prediction object, and the target disease is the respiratory system disease. Wherein, the infrared thermal image is selected from the infrared thermal image which comprises the throat part and corresponds to the clinical data of the respiratory system; the plurality of historical second temperature value sets are a plurality of second temperature value sets corresponding to the infrared thermography of the plurality of laryngeal portions clinically. For the plurality of thermographic images, the diseased result of the respiratory disease corresponding to each infrared thermographic image is determined based on clinical diagnosis. That is, with certain inputs and outputs, the weight vectors in the logistic regression algorithm are trained to obtain a respiratory system prediction model.
In this example, the formula of the logistic regression algorithm is:
wherein v is an input instance, which in this embodiment is a set of historical second temperature values; y is the output, i.e., the outcome of the disease, Y ∈ (0, 1), in this example, 1 indicates inflammation of the throat, i.e., respiratory disease, and 0 indicates no inflammation of the throat, i.e., no respiratory disease; w is the weight vector; thus, p (Y ═ 1| v, w) indicates the probability that the disease outcome Y equals 1. And setting a threshold, judging that Y is 1 when P is larger than the threshold, and judging that Y is 0 when P is smaller than the threshold.
It can be understood that, in the training process, the weight vector w is determined by fitting according to a plurality of input instances v and a plurality of corresponding output results Y, so as to obtain a respiratory system prediction model.
In one embodiment of step S103, after determining the prediction model, determining a prevalence probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and the pre-trained disease prediction model.
Taking the prediction of respiratory system diseases as an example, firstly, acquiring an infrared thermograph of the throat of a prediction object, thereby determining a plurality of second temperature values of the infrared thermograph, inputting the plurality of second temperature values into a prediction model as a temperature value set (input example v), calculating the illness probability P of the prediction object through the prediction model according to a weight vector w determined by the prediction model, and further determining whether the illness result Y of the respiratory system is 1 or 0 according to P, namely whether the prediction object suffers from the respiratory system diseases. For example, the threshold value is set to 0.5, and when the prediction model calculates the disease probability P of the prediction target to be 0.8, the disease outcome Y is determined to be 1, that is, the prediction target is suffering from the respiratory disease. When the prediction model calculates that the disease probability P of the prediction object is 0.3, the disease result Y is judged to be 0, namely, the prediction object does not suffer from the respiratory system disease.
In one embodiment of the invention, when the probability of the target disease is greater than a preset threshold value, prompt information is output.
It can be understood that when the prediction model determines that the disease probability of the prediction object is greater than the preset threshold, the prediction object is determined to have the target disease, and prompt information can be output at the moment. Outputting the prompt message may include: sending an alarm prompt to a voice terminal, and simultaneously marking a red warning identifier on the infrared thermography on a display terminal to remind field personnel to arrange a predicted object for further medical observation; the prediction result can also be sent to other remote terminals, for example, for a certain epidemic respiratory system disease needing to be reported in the community, the prediction result can be sent to the terminals of the community to inform community personnel to perform follow-up treatment actions; the prediction result may also be transmitted to the terminal device of the prediction object.
When the prediction model determines that the disease probability of the prediction object is smaller than a preset threshold value, the prediction object is judged not to have the target disease, at the moment, a release prompt can be sent to the voice terminal, and meanwhile, a green passage identifier is marked on the infrared thermal image in the display terminal.
In an embodiment of the present invention, the breast disease can be predicted based on infrared thermography identification, that is, the probability of the breast disease to be predicted is determined according to a plurality of temperature values of the breast characteristic region and a pre-trained disease prediction model, and the process is similar to the prediction process of the respiratory system disease, and is not described herein again.
As shown in fig. 2, an embodiment of the present invention provides a disease prediction apparatus 200 based on infrared thermography recognition, including: an acquisition module 201, a determination module 202 and a prediction module 203; wherein,
the acquiring module 201 is configured to acquire an infrared thermography of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermography;
the determining module 202 is configured to determine, according to the gray-scale value of the infrared thermography and the first temperature value, a plurality of second temperature values corresponding to a plurality of pixel points in the infrared thermography respectively;
the prediction module 203 is configured to determine a disease probability that the disease prediction object corresponds to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
In an embodiment of the present invention, the obtaining module 201 is configured to obtain a laryngeal image of a subject with a respiratory disease; and taking the central pixel point of the infrared thermography of the throat part as the characteristic point, and acquiring a first temperature value of the characteristic point.
In an embodiment of the present invention, the determining module 202 is configured to determine a corresponding relationship between a gray value and a temperature value in the infrared thermography; and determining the plurality of second temperature values respectively corresponding to the plurality of pixel points according to the gray values of the plurality of pixel points in the infrared thermography, the corresponding relation, the first temperature value and the gray value of the characteristic point.
In an embodiment of the present invention, the determining module 202 is configured to obtain a plurality of infrared thermographic images of samples; determining sample detection points, and sample gray values and sample temperature values corresponding to the sample detection points in each sample infrared thermograph; and determining the corresponding relation according to the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs.
In an embodiment of the present invention, the determining module 202 is configured to perform two-dimensional fitting on the sample gray-scale values and the sample temperature values respectively corresponding to the multiple sample infrared thermographs, and use a fitting result as the corresponding relationship.
In an embodiment of the present invention, the determining module 202 is configured to update an intercept in the fitting result according to a slope in the fitting result, the first temperature value, and a gray value of the feature point; and determining the plurality of second temperature values according to the updated fitting result and the gray values of the plurality of pixel points.
In an embodiment of the present invention, the determining module 202 is configured to use a central pixel point of the infrared thermography as the feature point.
In an embodiment of the present invention, the prediction module 203 is configured to construct the disease prediction model according to a logistic regression algorithm.
In an embodiment of the present invention, the prediction module 203 is configured to train a weight vector corresponding to the logistic regression algorithm according to the historical temperature value and a disease result corresponding to one or more diseases, so as to obtain the disease prediction model.
In an embodiment of the present invention, the predicting module 203 is configured to output a prompt message when the probability of the target disease is greater than a preset threshold.
According to the disease prediction device based on infrared thermography identification provided by the embodiment of the invention, a plurality of second temperature values corresponding to a plurality of pixel points in the infrared thermography can be determined according to the first temperature values of the characteristic points in the infrared thermography of the disease prediction object and the gray values of the infrared thermography, so that the influence of environmental factors in the image acquisition process and/or the temperature measurement process of the infrared thermography is reduced, and the accuracy of the temperature measurement result is improved. Furthermore, according to the second temperature values of the multiple pixel points, the disease prediction model is used for predicting the disease probability of the disease prediction object, the misjudgment rate can be effectively reduced, and the accuracy of the screening result is improved.
In addition, as shown in fig. 3, an embodiment of the present invention further provides a disease prediction system based on infrared thermography identification, including: the infrared thermal imaging system 301, the display 302 and the disease prediction device 200 based on infrared thermal image recognition provided in any of the above embodiments; wherein,
the infrared thermal imager 301 is used for acquiring an infrared thermal image of a disease prediction object;
the disease prediction device 200 is used for predicting the disease probability of the disease prediction object corresponding to the target disease according to the infrared thermography;
the display 302 is configured to display the prediction result of the disease prediction apparatus 200.
Taking the above disease prediction system for predicting respiratory diseases as an example, in this scenario, an infrared thermal imaging image of the throat of a person and a temperature value of a central pixel point of the image may be collected by the infrared thermal imager 301; the disease prediction device 200 based on infrared thermography identification provided by the embodiment of the invention is responsible for calculating the temperature values of a plurality of pixel points of an infrared thermography, and predicting the disease probability of a disease prediction object corresponding to a respiratory system disease according to the obtained plurality of temperature values; the predicted result is finally displayed via the display 302.
Based on the disease prediction system based on infrared thermographic identification as shown in fig. 3, fig. 4 shows an exemplary system architecture 400 to which the disease prediction method based on infrared thermographic identification or the disease prediction system based on infrared thermographic identification according to the embodiments of the present invention can be applied.
As shown in fig. 4, system architecture 400 may include terminal devices 401, 402, 403, a network 404, a server 405, and an infrared thermal imager 406. Network 404 is the medium used to provide communication links between terminal devices 401, 402, 403, infrared thermal imager 406, and server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few. The disease prediction device provided by the embodiment of the invention is deployed in a server 405, and an infrared thermal imager 406 can send the acquired infrared thermal image to the server 405 through a network 404.
A user may use terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may be various electronic devices having displays and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. The display on the terminal device 401, 402, 403 may display the prediction result of the disease prediction means.
The server 405 may be a server providing various services, and the background management server may analyze and perform other processing on the acquired data such as the infrared thermography, and feed back a processing result (a disease probability that a disease prediction object corresponds to a target disease) to the terminal device.
It should be noted that the disease prediction method based on infrared thermography recognition provided by the embodiment of the present invention is generally executed by the server 405, and accordingly, a disease prediction apparatus based on infrared thermography recognition is generally disposed in the server 405.
It should be understood that the number of terminal devices, infrared thermal imagers, networks and servers in fig. 4 are merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
It can be understood that, in the system architecture shown in fig. 4, the disease prediction device based on infrared thermography recognition is arranged in the server at the cloud end, in other words, the disease prediction device based on infrared thermography recognition provides cloud service, the system architecture is suitable for a scene with a heavy calculation task, the infrared thermography sends the acquired infrared thermography to the server at the cloud end, and the server at the cloud end returns a calculation result to the terminal through the network after calculating the disease probability that the disease prediction object corresponds to the target disease according to the infrared thermography. In addition to the system architecture shown in fig. 4, the disease prediction apparatus based on infrared thermography recognition according to the embodiment of the present invention may also be deployed locally, for example, for a scene with a high real-time requirement, the disease prediction apparatus based on infrared thermography recognition may be deployed locally at the terminal, and after the disease probability of the disease prediction object corresponding to the target disease is calculated by the local disease prediction apparatus based on infrared thermography recognition, the disease probability is directly displayed by the display of the terminal.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an acquisition module, a determination module, and a prediction module. The names of the modules do not limit the modules themselves in some cases, and for example, the acquisition module may be further described as a "module for acquiring an infrared thermography".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph; determining a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value; determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
According to the technical scheme of the embodiment of the invention, the plurality of second temperature values corresponding to the plurality of pixel points in the infrared thermography can be determined according to the first temperature values of the characteristic points in the infrared thermography of the disease prediction object and the gray values of the infrared thermography, so that the influence of environmental factors in the image acquisition process and/or the temperature measurement process of the infrared thermography is reduced, and the accuracy of the temperature measurement result is improved. Furthermore, according to the second temperature values of the multiple pixel points, the disease prediction model is used for predicting the disease probability of the disease prediction object, the misjudgment rate can be effectively reduced, and the accuracy of the screening result is improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (14)
1. A method of disease prediction, comprising:
acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph;
determining a plurality of second temperature values respectively corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value;
determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
2. The method of claim 1, wherein the determining a plurality of second temperature values corresponding to a plurality of pixel points in the infrared thermography according to the gray-level value of the infrared thermography and the first temperature value comprises:
determining the corresponding relation between the gray value and the temperature value in the infrared thermography;
and determining the plurality of second temperature values respectively corresponding to the plurality of pixel points according to the gray values of the plurality of pixel points in the infrared thermography, the corresponding relation, the first temperature value and the gray value of the characteristic point.
3. The method of claim 2, wherein determining the correspondence between the gray scale values and the temperature values in the infrared thermography comprises:
acquiring infrared thermographs of a plurality of samples;
determining sample detection points, and sample gray values and sample temperature values corresponding to the sample detection points in each sample infrared thermograph;
and determining the corresponding relation according to the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs.
4. The method according to claim 3, wherein the determining the corresponding relationship according to the sample gray-scale values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographic images comprises:
and performing two-dimensional fitting on the sample gray values and the sample temperature values respectively corresponding to the plurality of sample infrared thermographs, and taking the fitting result as the corresponding relation.
5. The method of claim 4, wherein determining the plurality of second temperature values respectively corresponding to the plurality of pixel points according to the gray values of the plurality of pixel points in the infrared thermography, the correspondence, the first temperature value, and the gray values of the feature points comprises:
updating the intercept in the fitting result according to the slope in the fitting result, the first temperature value and the gray value of the characteristic point;
and determining the plurality of second temperature values according to the updated fitting result and the gray values of the plurality of pixel points.
6. The method according to any one of claims 1 to 5,
and taking the central pixel point of the infrared thermography as the characteristic point.
7. The method of claim 1,
the disease prediction model is constructed based on a logistic regression algorithm.
8. The method of claim 7, further comprising:
and training the weight vector corresponding to the logistic regression algorithm according to the historical temperature value and the ill result corresponding to one or more diseases to obtain the disease prediction model.
9. The method of claim 1, further comprising:
and when the probability of the target disease is greater than a preset threshold value, outputting prompt information.
10. The method of claim 1,
the infrared thermography comprises: a laryngeal image of the subject for the disease prediction;
the target disease is a respiratory disease.
11. A disease prediction apparatus, comprising: the device comprises an acquisition module, a determination module and a prediction module; wherein,
the acquisition module is used for acquiring an infrared thermograph of a disease prediction object and a first temperature value corresponding to a feature point in the infrared thermograph;
the determining module is used for determining a plurality of second temperature values corresponding to a plurality of pixel points in the infrared thermography according to the gray value of the infrared thermography and the first temperature value;
the prediction module is used for determining the disease probability of the disease prediction object corresponding to the target disease according to the plurality of second temperature values and a pre-trained disease prediction model; the disease prediction model is trained based on historical temperature values and disease outcomes corresponding to one or more diseases.
12. A disease prediction system, comprising: an infrared thermography, a display and the infrared thermography identification based disease prediction device of claim 11; wherein,
the infrared thermal imager is used for collecting an infrared thermal image of a disease prediction object;
the disease prediction device is used for predicting the disease probability of the disease prediction object corresponding to the target disease according to the infrared thermography;
the display is used for displaying the prediction result of the disease prediction device.
13. An electronic device for disease prediction, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-10.
14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110775911.1A CN113470818A (en) | 2021-07-08 | 2021-07-08 | Disease prediction method, device, system, electronic device and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110775911.1A CN113470818A (en) | 2021-07-08 | 2021-07-08 | Disease prediction method, device, system, electronic device and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113470818A true CN113470818A (en) | 2021-10-01 |
Family
ID=77879301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110775911.1A Pending CN113470818A (en) | 2021-07-08 | 2021-07-08 | Disease prediction method, device, system, electronic device and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113470818A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024025489A1 (en) * | 2022-07-28 | 2024-02-01 | İstanbul Geli̇şi̇m Üni̇versi̇tesi̇ | Health status analysis system on historical data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107588854A (en) * | 2016-07-08 | 2018-01-16 | 杭州新瀚光电科技有限公司 | High precision measuring temperature method based on built-in reference body |
| CN109872821A (en) * | 2019-04-24 | 2019-06-11 | 北京信息科技大学 | A method and device for constructing a blood glucose prediction model |
| CN111341461A (en) * | 2020-02-24 | 2020-06-26 | 中国船舶重工集团公司第七一七研究所 | Infrared epidemic situation intelligent comprehensive detection and identification system |
| CN111738132A (en) * | 2020-06-17 | 2020-10-02 | 银河水滴科技（北京）有限公司 | Method and device for measuring human body temperature, electronic equipment and readable storage medium |
| CN112155520A (en) * | 2020-07-24 | 2021-01-01 | 北京微芯区块链与边缘计算研究院 | Monitoring device and method based on body temperature data, electronic equipment and storage medium |
| WO2021117013A1 (en) * | 2019-12-13 | 2021-06-17 | Hearthcore S.A.P.I. De C.V. | Determination of medical condition risk using thermographic images |
-
2021
- 2021-07-08 CN CN202110775911.1A patent/CN113470818A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107588854A (en) * | 2016-07-08 | 2018-01-16 | 杭州新瀚光电科技有限公司 | High precision measuring temperature method based on built-in reference body |
| CN109872821A (en) * | 2019-04-24 | 2019-06-11 | 北京信息科技大学 | A method and device for constructing a blood glucose prediction model |
| WO2021117013A1 (en) * | 2019-12-13 | 2021-06-17 | Hearthcore S.A.P.I. De C.V. | Determination of medical condition risk using thermographic images |
| CN111341461A (en) * | 2020-02-24 | 2020-06-26 | 中国船舶重工集团公司第七一七研究所 | Infrared epidemic situation intelligent comprehensive detection and identification system |
| CN111738132A (en) * | 2020-06-17 | 2020-10-02 | 银河水滴科技（北京）有限公司 | Method and device for measuring human body temperature, electronic equipment and readable storage medium |
| CN112155520A (en) * | 2020-07-24 | 2021-01-01 | 北京微芯区块链与边缘计算研究院 | Monitoring device and method based on body temperature data, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张杰: "红外热成像测温技术及其应用研究", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024025489A1 (en) * | 2022-07-28 | 2024-02-01 | İstanbul Geli̇şi̇m Üni̇versi̇tesi̇ | Health status analysis system on historical data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349156B (en) | Method and device for identifying lesion characteristics in fundus picture and storage medium | |
| US20190096060A1 (en) | Method and apparatus for annotating medical image | |
| AU2014271202B2 (en) | A system and method for remote medical diagnosis | |
| EP3992851A1 (en) | Image classification method, apparatus and device, storage medium, and medical electronic device | |
| US10755410B2 (en) | Method and apparatus for acquiring information | |
| US20200185073A1 (en) | System and method for providing personalized health data | |
| CN110660484B (en) | Bone age prediction method, device, medium, and electronic apparatus | |
| US20170061608A1 (en) | Cloud-based pathological analysis system and method | |
| US12118739B2 (en) | Medical image processing method, apparatus, and device, medium, and endoscope | |
| CN108491823B (en) | Method and device for generating human eye recognition model | |
| WO2020062493A1 (en) | Image processing method and apparatus | |
| US11301995B2 (en) | Feature identification in medical imaging | |
| CN109887077B (en) | Method and apparatus for generating three-dimensional model | |
| CN108509921B (en) | Method and apparatus for generating information | |
| CN111227789A (en) | Human health monitoring method and device | |
| US20210345955A1 (en) | Portable real-time medical diagnostic device | |
| CN115862831B (en) | Intelligent online reservation diagnosis and treatment management system and method | |
| JP7253152B2 (en) | Information processing device, information processing method, and program | |
| CN113470818A (en) | Disease prediction method, device, system, electronic device and computer readable medium | |
| CN112397195A (en) | Method, apparatus, electronic device, and medium for generating physical examination model | |
| CN111914744A (en) | Temperature measurement method and system for portable temperature inspection | |
| CN114937178B (en) | Multi-modality-based image classification method and device, readable medium and electronic equipment | |
| CN111192679B (en) | Method, device and storage medium for processing image data abnormality | |
| CN114783594A (en) | Recommendation information determination method, device, equipment, storage medium and program product | |
| JP2020190913A (en) | Image-reading supporting device and method for supporting image-reading |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211001 |