CN112259238A - Electronic device, disease type detection method, apparatus, and medium - Google Patents
Electronic device, disease type detection method, apparatus, and medium Download PDFInfo
- Publication number
- CN112259238A CN112259238A CN202011127805.4A CN202011127805A CN112259238A CN 112259238 A CN112259238 A CN 112259238A CN 202011127805 A CN202011127805 A CN 202011127805A CN 112259238 A CN112259238 A CN 112259238A
- Authority
- CN
- China
- Prior art keywords
- model
- gradient parameters
- disease type
- type detection
- model gradient
- 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 121
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 121
- 238000001514 detection method Methods 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 36
- 238000012544 monitoring process Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 15
- 230000002779 inactivation Effects 0.000 claims description 15
- 238000007477 logistic regression Methods 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 208000019622 heart disease Diseases 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 206010003130 Arrhythmia supraventricular Diseases 0.000 description 2
- 206010003658 Atrial Fibrillation Diseases 0.000 description 2
- 206010003671 Atrioventricular Block Diseases 0.000 description 2
- 206010029470 Nodal rhythm Diseases 0.000 description 2
- 208000003734 Supraventricular Tachycardia Diseases 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Abstract
The invention relates to a data processing technology, and discloses electronic equipment, a device, a storage medium and a disease type detection method. The method comprises the following steps: the client encrypts and uploads the model gradient parameters trained by using local data to the server, the server decrypts the encrypted model gradient parameters and performs combined operation to obtain updated model gradient data, the client receives the updated model gradient parameters returned by the server and obtains a standard disease type detection model according to the updated model gradient parameters, and the standard disease type detection model is used for detecting image data to be detected to obtain a disease type detection result. The invention also relates to a blockchain technique, and the updated model gradient parameters can be stored in blockchain nodes. The invention can improve the accuracy of the disease type detection model.
Description
Technical Field
The present invention relates to data processing technologies, and in particular, to an electronic device, a method and an apparatus for detecting disease types, and a computer-readable storage medium.
Background
Disease detection and diagnosis is particularly important to reduce patient mortality. For example, heart disease is a common disease in people's lives today, and the heart disease is particularly subdivided into a plurality of categories, so that the rapid and accurate detection of the heart disease category can reduce the mortality rate of heart disease patients. At present, the heart disease type is mainly detected by adopting an electrocardiogram detection means to diagnose the heart disease.
Because of privacy of medical data, the accuracy of the current model for detecting the electrocardiogram is not high enough, the electrocardiogram data used for training the model is limited in several hospitals, and the electrocardiogram data owned by each hospital still has data barriers, so that a large amount of electrocardiogram data cannot be effectively utilized, and the type of heart diseases cannot be accurately judged according to the electrocardiogram.
Disclosure of Invention
The invention provides electronic equipment, a disease type detection method, a disease type detection device and a computer readable storage medium, and mainly aims to solve the problem that the type of heart disease cannot be accurately judged according to an electrocardiogram.
In order to achieve the above object, the present invention provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the steps of:
acquiring initial gradient parameters from a server, constructing a disease type detection model according to the initial gradient parameters, and training the disease type detection model through local image training data to obtain model gradient parameters after the disease type detection model is trained;
accessing a monitoring port of a server, after the monitoring port is successfully connected with the server, uploading the trained model gradient parameters to the server after encryption operation;
receiving updated model gradient parameters transmitted by a server, and obtaining a standard disease type detection model according to the updated model gradient parameters;
and receiving image data to be detected, and sequentially passing the image data to be detected through a convolution layer, a normalization layer, a linear rectification layer, a random inactivation layer, a full connection layer and a logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
Optionally, the encrypting the model gradient parameter and uploading the encrypted model gradient parameter to a server includes:
randomly selecting large prime numbers p and q, so that the maximum common multiple of pq and (p-1) (q-1) is 1;
calculating n ═ p × q, and satisfying λ (n) ═ lcm (p-1, q-1), where lcm is the least common multiple and λ is the kamichael function;
randomly selecting one less than n2And calculating μ ═ L (g) by the positive integer g of (c)λmodn2))-1modn；
Obtaining a public key (n, g) and a private key (lambda, mu) according to the n, g, lambda and mu;
and encrypting the model gradient parameters by using the private key (lambda, mu) to obtain the encrypted model gradient parameters.
Optionally, the image data to be detected and the corresponding annotation data include an electrocardiographic image and a json file corresponding to the electrocardiographic image and containing annotation data of a cardiologist.
In order to achieve the above object, the present invention further provides an electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the steps of:
opening K monitoring ports, wherein K is the number of the clients;
receiving the encrypted model gradient parameters sent by a plurality of clients by using the monitoring port;
decrypting the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client;
performing a joint operation on the model gradient parameters corresponding to each client to obtain updated model gradient parameters;
and distributing the updated model gradient parameters to each client.
Optionally, the performing a joint operation on the model gradient parameter corresponding to each client to obtain an updated model gradient parameter includes:
performing a joint operation by adopting the following method to obtain an updated model gradient parameter:
wherein f (w) is the updated model gradient parameter, fi(w) as a model gradient parameter, Fk(w) represents an intermediate parameter, K is the number of clients, PkRepresenting training data stored in the kth client, nkIs the amount of training data.
Optionally, the decrypting the encrypted model gradient parameter includes:
decrypting the encrypted model gradient parameters according to the following decryption formula:
m＝L(cλmodn2)*μmodn
where m is the decrypted model gradient parameter, c is the encrypted model gradient parameter, mod is the modulus operator, n is p × q, where p, q are large prime numbers satisfying the greatest common multiple of pq and (p-1) (q-1) as 1, λ is the kamichael function, and μ is a preset parameter.
In order to solve the above problem, the present invention also provides a disease type detection apparatus applied to a client, the apparatus including:
the encryption module is used for acquiring a disease type detection model from the server side, training the disease type detection model through local image data training data to obtain a trained model gradient parameter, accessing a monitoring port of the server side, encrypting the model gradient parameter and uploading the encrypted model gradient parameter to the server side after connection is successfully established;
the model updating module is used for receiving the updated model gradient parameters transmitted by the server and obtaining a standard disease type detection model according to the updated model gradient parameters;
and the classification module is used for receiving image data to be detected, and sequentially passing the image data to be detected through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
In order to solve the above problem, the present invention further provides a disease type detection apparatus applied to a server, the apparatus including:
the decryption module is used for opening K monitoring ports, wherein K is the number of the clients, the monitoring ports are used for receiving the encrypted model gradient parameters sent by the clients, and the encrypted model gradient parameters are decrypted to obtain the model gradient parameters corresponding to each client;
and the parameter updating module is used for executing combined operation on the model gradient parameters corresponding to each client to obtain updated model gradient parameters and distributing the updated model gradient parameters to each client.
In order to solve the above problem, the present invention further provides a computer-readable storage medium including a storage data area and a storage program area, the storage data area storing created data, the storage program area storing a computer program; wherein the computer program when executed by a processor implements:
acquiring initial gradient parameters from a server, constructing a disease type detection model according to the initial gradient parameters, training the disease type detection model through local image training data to obtain a trained model, and extracting the trained model gradient parameters;
accessing a monitoring port of the server, after the connection is successfully established, carrying out encryption operation on the model gradient parameters and uploading the model gradient parameters to the server;
receiving updated model gradient parameters transmitted by a server, and obtaining a standard disease type detection model according to the updated model gradient parameters;
and receiving image data to be detected, and sequentially passing the image data to be detected through a convolution layer, a normalization layer, a linear rectification layer, a random inactivation layer, a full connection layer and a logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
In order to solve the above problem, the present invention also provides a disease type detection method performed by the above electronic device.
According to the embodiment of the invention, the disease type detection model is obtained from the server side, the disease type detection model is trained through local image data training data to obtain the trained model gradient parameters, the training capability of the client side is fully utilized, the model gradient parameters are encrypted by the client side, some calculations of the server side are shared, the concurrent calculation pressure of the server side is reduced, meanwhile, the server side performs combined operation on the model gradient parameters corresponding to each client side to obtain the updated model gradient parameters, and the problem of data barrier of the training data is solved, so that the accuracy of the model gradient parameters is improved. Therefore, the electronic device, the apparatus, the computer-readable storage medium and the disease type detection method provided by the embodiments of the present invention can improve the accuracy of disease type detection. In addition, the electronic equipment, the device, the computer readable storage medium and the disease type detection method provided by the invention can be used for type detection and analysis in the field of digital medical treatment.
Drawings
Fig. 1 is a schematic internal structural diagram of an electronic device according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart of a disease type detection method according to a second embodiment of the present invention;
FIG. 3 is a schematic flow chart of a disease type detection method according to a third embodiment of the present invention;
FIG. 4 is a block diagram of a disease type detecting device according to a fourth embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides electronic equipment. The electronic device may be, for example, at least one of a server, a terminal, and the like. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Fig. 1 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a disease type detection program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of the disease type detection program 12, but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (for example, executing a disease type detection program and the like) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 1 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The memory 11 in the electronic device 1 stores a disease type detection program 12 that is a combination of instructions that, when executed in the processor 10, may implement a disease type detection method. In detail, the disease type detection method may refer to the following description with respect to the flowchart shown in fig. 2.
Fig. 2 is a schematic flow chart of a disease type detection method according to a second embodiment of the present invention. The method for detecting a disease type in the second embodiment of this embodiment is applied to a client, and includes:
s11, obtaining initial gradient parameters from a server, constructing a disease type detection model according to the initial gradient parameters, and training the disease type detection model through local image training data to obtain model gradient parameters after the disease type detection model is trained.
In the embodiment of the invention, the local image training data comprises the electrocardio images of the patients stored in the database of the hospital.
According to the embodiment of the invention, the local image training data is used for training the disease type detection model acquired from the server side, so that the trained model gradient parameters are obtained.
And S12, accessing a monitoring port of the server, and after the connection is successfully established, encrypting the trained model gradient parameters and uploading the encrypted model gradient parameters to the server.
In this embodiment of the present invention, the encrypting the model gradient parameter includes:
randomly selecting large prime numbers p and q, so that the maximum common multiple of pq and (p-1) (q-1) is 1;
calculating n ═ p × q, and satisfying λ (n) ═ lcm (p-1, q-1), where lcm is the least common multiple and λ is the kamichael function;
randomly selecting one less than n2And calculating μ ═ L (g) by the positive integer g of (c)λmodn2))-1modn；
Obtaining a public key (n, g) and a private key (lambda, mu) according to the n, g, lambda and mu;
and encrypting the model gradient parameters by using the private key (lambda, mu) to obtain the encrypted model gradient parameters.
The prime number refers to a natural number having no other factors than 1 and itself among natural numbers greater than 1, and the large prime number refers to the largest one or more of the natural numbers satisfying the definition of prime number.
Further, the embodiment of the present invention transmits the public key to the server, and encrypts the model gradient parameter by using the private key (λ, μ) to obtain the encrypted model gradient parameter.
In the embodiment of the invention, the training of the disease type detection model is executed at a plurality of clients, such as a plurality of hospitals, so as to obtain the model gradient parameter corresponding to each client. For example, the plurality of hospitals may include hospital a, hospital B, hospital C, etc., where hospital a corresponds to a model gradient parameter of w1The gradient parameter of the model corresponding to hospital B is w2The gradient parameter of the model corresponding to hospital C is w3And so on. The embodiment of the invention utilizes the private key to encrypt the model gradient parameters, thereby facilitating subsequent uploading and updating and achieving the purposes of expanding data samples and protecting the privacy of patients.
Further, the embodiment of the invention uploads the encrypted model gradient parameters to the server through a monitoring port opened by the server by using an http protocol.
And S13, receiving the updated model gradient parameters transmitted by the server, and obtaining a standard disease type detection model according to the updated model gradient parameters.
The embodiment of the invention updates the disease type detection model by using the updated model gradient parameters transmitted by the server side to obtain a standard disease type detection model.
And S14, receiving image data to be detected, and sequentially passing the image data to be detected through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
In the embodiment of the invention, the image data to be detected is received, and the image data to be detected sequentially passes through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
The convolution layer is used for extracting features of the image data to be detected, the normalization layer is used for preventing gradient explosion and gradient disappearance, the linear rectification layer is used for improving the efficiency of gradient descent and reverse propagation processes, the random inactivation layer is used for realizing regularization of the standard disease type detection model and reducing the structural risk of the standard disease type detection model, the full connection layer is used for assembling the local features extracted by the features, and the logistic regression layer is used for predicting.
Further, the image data to be detected and the corresponding annotation data comprise the electrocardio image and a json file which corresponds to the electrocardio image and contains annotation data of a cardiologist.
For example, in the embodiment of the present invention, the electrocardiographic data of the patient is obtained, the electrocardiographic data is input into the standard disease type detection model, and the diagnosis result is obtained through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model. Wherein the diagnostic result is a specific classification of a heart condition including, but not limited to, atrial fibrillation and flutter, atrioventricular block, bigeminal, ectopic atrial rhythm, junctional rhythm, sinus rhythm, supraventricular tachycardia.
Fig. 3 is a flow chart illustrating a disease type detection method according to a third embodiment of the present invention. The method for detecting disease types according to the third embodiment of this embodiment is applied to a server, and includes:
and S21, opening K monitoring ports, wherein K is the number of the clients.
In the embodiment of the invention, the server opens K monitoring ports according to the number of the clients so as to perform data transmission with each client.
And S22, receiving the encrypted model gradient parameters sent by the plurality of clients by using the monitoring port.
And S23, decrypting the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client.
The embodiment of the invention utilizes the public key (n, g) to decrypt the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client.
Specifically, the decrypting the encrypted model gradient parameter includes:
decrypting the encrypted model gradient parameters according to the following decryption formula:
m＝L(cλmodn2)*μmodn
where m is the decrypted model gradient parameter, c is the encrypted model gradient parameter, mod is the modulus operator, n is p × q, where p, q are large prime numbers satisfying the greatest common multiple of pq and (p-1) (q-1) as 1, λ is the kamichael function, and μ is a preset parameter.
For example, each client includes, but is not limited to, hospital a, hospital B, and hospital C, and each client decrypts the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client.
And S24, performing joint operation on the model gradient parameters corresponding to each client to obtain updated model gradient parameters.
In this embodiment of the present invention, the performing a joint operation on the model gradient parameter corresponding to each client to obtain an updated model gradient parameter includes:
performing a joint operation by adopting the following method to obtain an updated model gradient parameter:
wherein f (w) isNew gradient parameter of model, fi(w) as a model gradient parameter, Fk(w) represents an intermediate parameter, K is the number of clients, PkRepresenting training data stored in the kth client, nkIs the amount of training data.
And S25, distributing the updated model gradient parameters to each client.
In the embodiment of the invention, the client and the server are safely connected to obtain the client and the server which are successfully connected, and the updated model gradient parameter is distributed to each client.
Fig. 4 is a schematic block diagram of a disease type detection apparatus according to a fourth embodiment of the present invention.
The disease type detecting apparatus of the present invention may be divided into a first disease type detecting apparatus 100 and a second disease type detecting apparatus 200. Wherein the first disease type detecting apparatus 100 may be installed in a client and the second disease type detecting apparatus 200 may be installed in a server.
According to the implemented functions, the first disease type detection apparatus 100 may include an encryption module 101, a model update module 102, and a classification module 103; and the second disease type detection apparatus 200 may include a decryption module 201 and a parameter update module 202.
The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In this embodiment, the functions of the modules of the first disease type detection apparatus 100 and the first disease type detection apparatus 200 are as follows:
the encryption module 101 is configured to obtain an initial gradient parameter from a server, construct a disease type detection model according to the initial gradient parameter, train the disease type detection model through local image training data to obtain a trained model gradient parameter of the disease type detection model, access a monitoring port of the server, and encrypt and upload the trained model gradient parameter to the server after connection is successfully established;
the decryption module 201 is configured to open K monitoring ports, where K is the number of clients, receive the encrypted model gradient parameters sent by the clients through the monitoring ports, and decrypt the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client;
the parameter updating module 202 is configured to perform a joint operation on the model gradient parameter corresponding to each client to obtain an updated model gradient parameter, and distribute the updated model gradient parameter to each client.
The model updating module 102 is configured to receive an updated model gradient parameter transmitted by a server, and obtain a standard disease type detection model according to the updated model gradient parameter;
the classification module 103 is configured to receive image data to be detected, and sequentially pass the image data to be detected through a convolution layer, a normalization layer, a linear rectification layer, a random inactivation layer, a full-link layer, and a logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
In detail, the modules of the first disease type detection apparatus 100 perform the following operations in the client:
the method comprises the steps that firstly, an encryption module 101 obtains initial gradient parameters from a server side, a disease type detection model is built according to the initial gradient parameters, the disease type detection model is trained through local image training data, and model gradient parameters after the disease type detection model is trained are obtained; in the embodiment of the invention, the local image training data comprises the electrocardio images of the patients stored in the database of the hospital.
According to the embodiment of the invention, the local image training data is used for training the disease type detection model acquired from the server side, so that the trained model gradient parameters are obtained.
Step two, the encryption module 101 accesses the monitoring port of the server, after the connection is successfully established,
and encrypting the model gradient parameters and uploading the model gradient parameters to a server.
In this embodiment of the present invention, the encrypting module 101 encrypts the model gradient parameter, including:
randomly selecting large prime numbers p and q, so that the maximum common multiple of pq and (p-1) (q-1) is 1;
calculating n ═ p × q, and satisfying λ (n) ═ lcm (p-1, q-1), where lcm is the least common multiple and λ is the kamichael function;
randomly selecting one less than n2And calculating μ ═ L (g) by the positive integer g of (c)λmodn2))-1modn；
Obtaining a public key (n, g) and a private key (lambda, mu) according to the n, g, lambda and mu;
and encrypting the model gradient parameters by using the private key (lambda, mu) to obtain the encrypted model gradient parameters.
The prime number refers to a natural number having no other factors than 1 and itself among natural numbers greater than 1, and the large prime number refers to the largest one or more of the natural numbers satisfying the definition of prime number.
Further, the embodiment of the present invention transmits the public key to the server, and encrypts the model gradient parameter by using the private key (λ, μ) to obtain the encrypted model gradient parameter.
In the embodiment of the invention, the training of the disease type detection model is executed at a plurality of clients, such as a plurality of hospitals, so as to obtain the model gradient parameter corresponding to each client. For example, the plurality of hospitals may include hospital a, hospital B, hospital C, etc., where hospital a corresponds to a model gradient parameter of w1The gradient parameter of the model corresponding to hospital B is w2The gradient parameter of the model corresponding to hospital C is w3And so on. The embodiment of the invention utilizes the private key to encrypt the model gradient parameters, thereby facilitating subsequent uploading and updating and achieving the purposes of expanding data samples and protecting the privacy of patients.
Further, the embodiment of the invention uploads the encrypted model gradient parameters to the server through a monitoring port opened by the server by using an http protocol.
And step three, the model updating module 102 receives the updated gradient parameters transmitted by the server, and obtains a standard disease type detection model according to the updated model gradient parameters.
The model updating module 102 of the embodiment of the present invention updates the disease type detection model by using the updated model gradient parameters transmitted by the server, so as to obtain a standard disease type detection model.
Step four, the classification module 103 receives the image data to be detected, and the image data to be detected sequentially passes through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
The convolution layer is used for extracting features of the image data to be detected, the normalization layer is used for preventing gradient explosion and gradient disappearance, the linear rectification layer is used for improving the efficiency of gradient descent and reverse propagation processes, the random inactivation layer is used for realizing regularization of the standard disease type detection model and reducing the structural risk of the standard disease type detection model, the full connection layer is used for assembling the local features extracted by the features, and the logistic regression layer is used for predicting.
In the embodiment of the present invention, the classification module 103 receives image data to be detected, and passes the image data to be detected through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full-link layer and the logistic regression layer of the standard disease type detection model in sequence to obtain a disease type detection result.
Further, the image data to be detected and the corresponding annotation data comprise the electrocardio image and a json file which corresponds to the electrocardio image and contains annotation data of a cardiologist.
For example, in the embodiment of the present invention, the electrocardiographic data of the patient is obtained, the electrocardiographic data is input into the standard disease type detection model, and the diagnosis result is obtained through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model. Wherein the diagnostic result is a specific classification of a heart condition including, but not limited to, atrial fibrillation and flutter, atrioventricular block, bigeminal, ectopic atrial rhythm, junctional rhythm, sinus rhythm, supraventricular tachycardia.
In detail, the modules of the second disease type detection apparatus 200 perform the following operations in the server:
step one, the decryption module 201 opens K monitoring ports, where K is the number of clients.
In the embodiment of the invention, the server opens K monitoring ports according to the number of the clients so as to perform data transmission with each client.
Step two, the decryption module 201 receives the encrypted model gradient parameters sent by the plurality of clients by using the monitoring port.
And thirdly, the decryption module 201 decrypts the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client.
In the embodiment of the present invention, the decryption module 201 decrypts the encrypted model gradient parameter by using the public key (n, g), so as to obtain the model gradient parameter corresponding to each client.
Specifically, the decrypting the encrypted model gradient parameter includes:
decrypting the encrypted model gradient parameters according to the following decryption formula:
m＝L(cλmodn2)*μmodn
where m is the decrypted model gradient parameter, c is the encrypted model gradient parameter, mod is the modulus operator, n is p × q, where p, q are large prime numbers satisfying the greatest common multiple of pq and (p-1) (q-1) as 1, λ is the kamichael function, and μ is a preset parameter.
For example, each client includes, but is not limited to, hospital a, hospital B, and hospital C, and each client decrypts the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client.
Step four, the parameter updating module 202 executes a joint operation on the model gradient parameter corresponding to each client to obtain an updated model gradient parameter.
In this embodiment of the present invention, the performing, by the parameter updating module 202, a joint operation on the model gradient parameter corresponding to each client to obtain an updated model gradient parameter includes:
performing a joint operation by adopting the following method to obtain an updated model gradient parameter:
wherein f (w) is the updated model gradient parameter, fi(w) as a model gradient parameter, Fk(w) represents an intermediate parameter, K is the number of clients, PkRepresenting training data stored in the kth client, nkIs the amount of training data.
Step five, the parameter updating module 202 distributes the updated model gradient parameters to each client.
In the embodiment of the present invention, the parameter updating module 202 performs secure connection between the client and the server, obtains the client and the server that successfully establish the connection, and distributes the updated model gradient parameter to each client.
Further, the modules/units of the disease type detection apparatus, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any accompanying claims should not be construed as limiting the claim concerned.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the steps of:
acquiring initial gradient parameters from a server, constructing a disease type detection model according to the initial gradient parameters, and training the disease type detection model through local image training data to obtain trained model gradient parameters of the disease type detection model;
accessing a monitoring port of a server, after the monitoring port is successfully connected with the server, uploading the trained model gradient parameters to the server after encryption operation;
receiving updated model gradient parameters transmitted by a server, and obtaining a standard disease type detection model according to the updated model gradient parameters;
and receiving image data to be detected, and sequentially passing the image data to be detected through a convolution layer, a normalization layer, a linear rectification layer, a random inactivation layer, a full connection layer and a logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
2. The electronic device of claim 1, wherein the encrypting the model gradient parameters and uploading the model gradient parameters to a server comprises:
randomly selecting large prime numbers p and q, so that the maximum common multiple of pq and (p-1) (q-1) is 1;
calculating n ═ p × q, and satisfying λ (n) ═ lcm (p-1, q-1), where lcm is the least common multiple and λ is the kamichael function;
randomly selecting one less than n2And calculating μ ═ L (g) by the positive integer g of (c)λmodn2))-1modn；
Obtaining a public key (n, g) and a private key (lambda, mu) according to the n, g, lambda and mu;
and encrypting the model gradient parameters by using the private key (lambda, mu) to obtain the encrypted model gradient parameters.
3. The electronic device of claim 1, wherein the image data to be detected and corresponding annotation data comprise an electrocardiogram and its corresponding json file containing cardiologist annotation data.
4. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the steps of:
opening K monitoring ports, wherein K is the number of the clients;
receiving the encrypted model gradient parameters sent by a plurality of clients by using the monitoring port;
decrypting the encrypted model gradient parameters to obtain the model gradient parameters corresponding to each client;
performing a joint operation on the model gradient parameters corresponding to each client to obtain updated model gradient parameters;
and distributing the updated model gradient parameters to each client.
5. The electronic device of claim 4, wherein the performing a joint operation on the model gradient parameters corresponding to each client to obtain updated model gradient parameters comprises:
performing a joint operation by adopting the following method to obtain an updated model gradient parameter:
wherein f (w) is the updated model gradient parameter, fi(w) as a model gradient parameter, Fk(w) represents an intermediate parameter, K is the number of clients, PkRepresenting training data stored in the kth client, nkIs the amount of training data.
6. The electronic device of claim 4, wherein the decrypting the encrypted model gradient parameters comprises:
decrypting the encrypted model gradient parameters according to the following decryption formula:
m＝L(cλmodn2)*μmodn
where m is the decrypted model gradient parameter, c is the encrypted model gradient parameter, mod is the modulus operator, n is p × q, where p, q are large prime numbers satisfying the greatest common multiple of pq and (p-1) (q-1) as 1, λ is the kamichael function, and μ is a preset parameter.
7. A disease type detection apparatus, wherein the apparatus is applied to a client electronic device, the apparatus comprising:
the encryption module is used for acquiring initial gradient parameters from the server, constructing a disease type detection model according to the initial gradient parameters, training the disease type detection model through local image training data to obtain the trained model gradient parameters of the disease type detection model, accessing a monitoring port of the server, and after connection is successfully established, encrypting the trained model gradient parameters and uploading the encrypted model gradient parameters to the server;
the model updating module is used for receiving the updated model gradient parameters transmitted by the server and obtaining a standard disease type detection model according to the updated model gradient parameters;
and the classification module is used for receiving image data to be detected, and sequentially passing the image data to be detected through the convolution layer, the normalization layer, the linear rectification layer, the random inactivation layer, the full connection layer and the logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
8. A disease type detection apparatus, wherein the apparatus is applied to a server electronic device, the apparatus comprising:
the decryption module is used for opening K monitoring ports, wherein K is the number of the clients, the monitoring ports are used for receiving the encrypted model gradient parameters sent by the clients, and the encrypted model gradient parameters are decrypted to obtain the model gradient parameters corresponding to each client;
and the parameter updating module is used for executing combined operation on the model gradient parameters corresponding to each client to obtain updated model gradient parameters and distributing the updated model gradient parameters to each client.
9. A computer-readable storage medium comprising a storage data area storing created data and a storage program area storing a computer program; wherein the computer program when executed by the processor implements the steps of:
acquiring initial gradient parameters from a server, constructing a disease type detection model according to the initial gradient parameters, and training the disease type detection model through local image training data to obtain trained model gradient parameters of the disease type detection model;
accessing a monitoring port of a server, after the monitoring port is successfully connected with the server, uploading the trained model gradient parameters to the server after encryption operation;
receiving updated model gradient parameters transmitted by a server, and obtaining a standard disease type detection model according to the updated model gradient parameters;
and receiving image data to be detected, and sequentially passing the image data to be detected through a convolution layer, a normalization layer, a linear rectification layer, a random inactivation layer, a full connection layer and a logistic regression layer of the standard disease type detection model to obtain a disease type detection result.
10. A method of disease type detection performed by an electronic device according to any of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011127805.4A CN112259238A (en) | 2020-10-20 | 2020-10-20 | Electronic device, disease type detection method, apparatus, and medium |
| PCT/CN2020/131987 WO2021189907A1 (en) | 2020-10-20 | 2020-11-27 | Electronic device, disease type detection method and apparatus, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011127805.4A CN112259238A (en) | 2020-10-20 | 2020-10-20 | Electronic device, disease type detection method, apparatus, and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112259238A true CN112259238A (en) | 2021-01-22 |
Family
ID=74244023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011127805.4A Pending CN112259238A (en) | 2020-10-20 | 2020-10-20 | Electronic device, disease type detection method, apparatus, and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112259238A (en) |
| WO (1) | WO2021189907A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610205A (en) * | 2021-07-15 | 2021-11-05 | 深圳宇晰科技有限公司 | Two-dimensional code generation method and device based on machine vision and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116913519A (en) * | 2023-07-24 | 2023-10-20 | 东莞莱姆森科技建材有限公司 | Health monitoring method, device, equipment and storage medium based on intelligent mirror |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110444263A (en) * | 2019-08-21 | 2019-11-12 | 深圳前海微众银行股份有限公司 | Disease data processing method, device, equipment and medium based on federation's study |
| CN110795477A (en) * | 2019-09-20 | 2020-02-14 | 平安科技（深圳）有限公司 | Data training method, device and system |
| CN110797124A (en) * | 2019-10-30 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Model multi-terminal collaborative training method, medical risk prediction method and device |
| CN111180061A (en) * | 2019-12-09 | 2020-05-19 | 广东工业大学 | Intelligent auxiliary diagnosis system fusing block chain and federal learning shared medical data |
| CN111190487A (en) * | 2019-12-30 | 2020-05-22 | 中国科学院计算技术研究所 | Method for establishing data analysis model |
| CN111325726A (en) * | 2020-02-19 | 2020-06-23 | 腾讯医疗健康(深圳)有限公司 | Model training method, image processing method, device, equipment and storage medium |
| CN111652863A (en) * | 2020-05-27 | 2020-09-11 | 刘君茹 | Medical image detection method, device, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10698766B2 (en) * | 2018-04-18 | 2020-06-30 | EMC IP Holding Company LLC | Optimization of checkpoint operations for deep learning computing |
| CN109545385A (en) * | 2018-11-30 | 2019-03-29 | 周立广 | A kind of medical big data analysis processing system and its method based on Internet of Things |
-
2020
- 2020-10-20 CN CN202011127805.4A patent/CN112259238A/en active Pending
- 2020-11-27 WO PCT/CN2020/131987 patent/WO2021189907A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110444263A (en) * | 2019-08-21 | 2019-11-12 | 深圳前海微众银行股份有限公司 | Disease data processing method, device, equipment and medium based on federation's study |
| CN110795477A (en) * | 2019-09-20 | 2020-02-14 | 平安科技（深圳）有限公司 | Data training method, device and system |
| CN110797124A (en) * | 2019-10-30 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Model multi-terminal collaborative training method, medical risk prediction method and device |
| CN111180061A (en) * | 2019-12-09 | 2020-05-19 | 广东工业大学 | Intelligent auxiliary diagnosis system fusing block chain and federal learning shared medical data |
| CN111190487A (en) * | 2019-12-30 | 2020-05-22 | 中国科学院计算技术研究所 | Method for establishing data analysis model |
| CN111325726A (en) * | 2020-02-19 | 2020-06-23 | 腾讯医疗健康(深圳)有限公司 | Model training method, image processing method, device, equipment and storage medium |
| CN111652863A (en) * | 2020-05-27 | 2020-09-11 | 刘君茹 | Medical image detection method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610205A (en) * | 2021-07-15 | 2021-11-05 | 深圳宇晰科技有限公司 | Two-dimensional code generation method and device based on machine vision and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021189907A1 (en) | 2021-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6642890B2 (en) | apparatus | |
| Hsieh et al. | A cloud computing based 12-lead ECG telemedicine service | |
| Jin et al. | Telemedicine in the cloud era: Prospects and challenges | |
| Pise et al. | Enabling artificial intelligence of things (AIoT) healthcare architectures and listing security issues | |
| WO2012100219A1 (en) | Systems and methods for collection, organization and display of ems information | |
| WO2019244949A1 (en) | Biological information processing method, biological information processing device, and biological information processing system | |
| WO2022126903A1 (en) | Method and device for image anomaly area detection, electronic device, and storage medium | |
| US11769584B2 (en) | Face reattachment to brain imaging data | |
| CN112259238A (en) | Electronic device, disease type detection method, apparatus, and medium | |
| EP3799052A1 (en) | Providing and receiving medical data records | |
| CN112435755A (en) | Disease analysis method, disease analysis device, electronic device, and storage medium | |
| CN103971063B (en) | Transmission measure for the vital medical image content of safety | |
| CN112398645A (en) | Medical data sharing method based on block chain technology | |
| US20180358131A1 (en) | Assigning patients to hospital beds | |
| Hamood Alsamhi et al. | Advancing Pandemic Preparedness in Healthcare 5.0: A Survey of Federated Learning Applications | |
| Alamri | Big data with integrated cloud computing for prediction of health conditions | |
| CA2978950C (en) | Infection management and control | |
| US20220020491A1 (en) | Systems and methods for ems device communications interface | |
| Fang et al. | Leveraging electronic medical records for passive disease surveillance in a COVID-19 care facility | |
| Ma et al. | Health Information Exchange for Home-Based Chronic Disease Self-Management--A Hybrid Cloud Approach | |
| CN117150562B (en) | Blood glucose monitoring method, device, equipment and storage medium based on blockchain | |
| CN113674840B (en) | Medical image sharing method and device, electronic equipment and storage medium | |
| Smahi et al. | An efficient and secure blockchain-based SVM classification for a COVID-19 healthcare system | |
| Ho | Digitisation of emergency medicine: opportunities, examples and issues for consideration | |
| Pawar et al. | Remote Health Monitoring System using Secure Communication Techniques |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40041516 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210122 |