CN113096793A - Remote medical diagnosis system based on medical images, algorithms and block chains - Google Patents
Remote medical diagnosis system based on medical images, algorithms and block chains Download PDFInfo
- Publication number
- CN113096793A CN113096793A CN202110403455.8A CN202110403455A CN113096793A CN 113096793 A CN113096793 A CN 113096793A CN 202110403455 A CN202110403455 A CN 202110403455A CN 113096793 A CN113096793 A CN 113096793A
- Authority
- CN
- China
- Prior art keywords
- medical image
- medical
- pixel point
- diagnosis
- transaction
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 103
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 33
- 201000010099 disease Diseases 0.000 claims abstract description 40
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims description 31
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 235000005770 birds nest Nutrition 0.000 description 82
- 235000005765 wild carrot Nutrition 0.000 description 82
- 241000544061 Cuculus canorus Species 0.000 description 15
- 238000004171 remote diagnosis Methods 0.000 description 11
- 238000010845 search algorithm Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 7
- 244000000626 Daucus carota Species 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 208000017667 Chronic Disease Diseases 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000005802 health problem Effects 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 230000000717 retained effect Effects 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a remote medical diagnosis system based on medical images, algorithms and block chains, and aims to improve the reliability of remote medical diagnosis. The system comprises a user terminal, an image storage server, a diagnosis server and a block chain network, wherein the diagnosis server is used for: receiving a diagnosis request sent by a user terminal, wherein the diagnosis request carries a transaction ID; acquiring a unique identifier corresponding to the transaction ID from a block chain network according to the transaction ID; acquiring a medical image corresponding to the transaction ID from an image storage server according to the transaction ID; generating a unique identifier of the medical image according to the acquired medical image; comparing the generated unique identifier with the unique identifier acquired from the block chain network; and under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and predicting the disease of the denoised medical image to obtain a disease prediction result.
Description
Technical Field
The invention relates to the field of artificial intelligent medical diagnosis, in particular to a remote medical diagnosis system based on medical images, algorithms and block chains.
Background
Due to the influences of factors such as the acceleration of life rhythm, the improvement of life pressure, the deterioration of ecological environment, the shortage of medical resources and the like, the incidence rate of chronic diseases is on the trend of rising year by year, and the chronic diseases become the social problems of harming health and influencing life quality at present, and more young people have slight or serious health problems. In the related art, a remote medical diagnosis system is provided to facilitate patients to diagnose and treat their own diseases. However, since the current remote medical diagnosis system is a centralized system, there is a risk that medical data (e.g., medical images) of a user is tampered after being stored in the centralized system. Therefore, how to reliably perform telemedicine without tampering with the medical data of the user is a problem to be solved.
Disclosure of Invention
The embodiment of the invention aims to provide a remote medical diagnosis system based on medical images, algorithms and block chains, aiming at improving the reliability of remote medical diagnosis, and the specific technical scheme is as follows:
in a first aspect of embodiments of the present invention, there is provided a remote medical diagnosis system based on medical images, algorithms and blockchains, the system including: the system comprises a user terminal, an image storage server, a diagnosis server and a block chain network, wherein the block chain network comprises a plurality of node devices;
the user terminal is configured to: generating a unique identifier of a medical image according to the medical image of a user; generating a deposit transaction according to the unique identifier, and submitting the deposit transaction to the blockchain network for execution, wherein the deposit transaction carries the unique identifier and a transaction ID;
the user terminal is further configured to: generating a storage request, and sending the storage request to the image storage server, wherein the storage request carries the medical image and the transaction ID;
the node device of the blockchain network is configured to: processing the deposit transaction, so that the unique identifier and the transaction ID carried by the deposit transaction are correspondingly stored in an account book database of a block chain network;
the image storage server is used for: processing the storage request, so that the medical image and the transaction ID carried by the storage request are correspondingly stored in a database;
the user terminal is further configured to: responding to user operation, generating a diagnosis request, and sending the diagnosis request to the diagnosis server, wherein the diagnosis request carries a transaction ID;
the diagnostic server is to: responding to a diagnosis request sent by a user terminal, acquiring a unique identifier corresponding to a transaction ID from the blockchain network according to the transaction ID carried by the diagnosis request, and acquiring a medical image corresponding to the transaction ID from the image storage server; generating a unique identifier of the medical image according to the acquired medical image; comparing the generated unique identifier with the unique identifier acquired from the block chain network; under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and then predicting the disease of the denoised medical image to obtain a disease prediction result; in the case where the two do not coincide, the response to the diagnosis request is terminated.
In a second aspect of the embodiments of the present invention, there is provided a remote medical diagnosis method based on medical images and a blockchain, the method being applied to a diagnosis server, the method including:
receiving a diagnosis request sent by a user terminal, wherein the diagnosis request carries a transaction ID;
acquiring a unique identifier corresponding to the transaction ID from a block chain network according to the transaction ID;
acquiring a medical image corresponding to the transaction ID from an image storage server according to the transaction ID;
generating a unique identifier of the medical image according to the acquired medical image;
comparing the generated unique identifier with the unique identifier acquired from the block chain network;
under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and predicting the disease of the denoised medical image to obtain a disease prediction result;
in the case where the two do not coincide, the response to the diagnosis request is terminated.
In the invention, the medical images of each user are stored by the centralized image storage server, when a certain user needs to carry out remote diagnosis, the diagnosis server can conveniently call the corresponding medical images from the medical image server, thereby carrying out remote diagnosis according to the called medical images.
In addition, in order to prevent medical images stored in a centralized image storage server from being tampered to cause diagnosis errors, the unique identifier of each medical image is stored in the blockchain network, and the blockchain network belongs to a distributed technology and has the characteristic of preventing data tampering, so that the unique identifier of the medical image stored in the blockchain network cannot be tampered. When the diagnosis server calls the medical image from the image storage server, the unique identification of the medical image is calculated, and then the calculated unique identification is compared with the unique identification of the corresponding medical image in the block chain network.
If the two are consistent, the medical image called by the diagnosis server from the centralized image storage server is not tampered, so that intelligent diagnosis can be performed based on the medical image, and the steps of noise reduction and disease prediction are included. If the two are not consistent, the medical image called by the diagnosis server from the centralized image storage server is falsified, so that the remote diagnosis is terminated, and the diagnosis error is prevented. Therefore, the remote medical diagnosis system based on the medical image, the algorithm and the block chain can effectively improve the reliability of remote diagnosis.
It should be noted that, in the present invention, the medical image is not directly stored in the blockchain network, but the medical image is converted into the unique identifier, and then the unique identifier is stored in the blockchain network. Compared with medical images, the unique identifier has smaller data volume and does not occupy too large storage space, so that the account book database of the block chain network is prevented from being exhausted prematurely.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 is a schematic diagram of a remote medical diagnosis system based on medical images, algorithms and blockchains according to an embodiment of the present invention;
fig. 2 is a flowchart of a remote medical diagnosis method based on medical images and a block chain according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Due to the influences of factors such as the acceleration of life rhythm, the improvement of life pressure, the deterioration of ecological environment, the shortage of medical resources and the like, the incidence rate of chronic diseases is on the trend of rising year by year, and the chronic diseases become the social problems of harming health and influencing life quality at present, and more young people have slight or serious health problems. In the related art, a remote medical diagnosis system is provided to facilitate patients to diagnose and treat their own diseases. However, since the current remote medical diagnosis system is a centralized system, there is a risk that medical data (e.g., medical images) of a user is tampered after being stored in the centralized system. Therefore, how to reliably perform telemedicine without tampering with the medical data of the user is a problem to be solved.
In view of the above, the present invention provides a remote medical diagnosis system based on medical images, algorithms and block chains through the following embodiments, aiming to improve the reliability of remote medical diagnosis.
Referring to fig. 1, fig. 1 is a schematic diagram of a remote medical diagnosis system based on medical images, algorithms and blockchains according to an embodiment of the present invention. As shown in fig. 1, the system includes: the system comprises a user terminal, an image storage server, a diagnosis server and a block chain network. Wherein the blockchain network includes a plurality of node devices.
As shown in fig. 1, the user terminal is configured to: generating a unique identifier of a medical image according to the medical image of a user; and generating a deposit transaction according to the unique identifier, and submitting the deposit transaction to the blockchain network for execution, wherein the deposit transaction carries the unique identifier and the transaction ID.
As shown in fig. 1, the user terminal is further configured to: and generating a storage request, and sending the storage request to the image storage server, wherein the storage request carries the medical image and the transaction ID.
The unique identifier of the medical image is equivalent to the identity information of the medical image, and different medical images have different unique identifiers.
Wherein the transaction ID is also unique. In other words, different deposit transactions each have a different transaction ID.
Optionally, in some embodiments, the user terminal may generate the unique identifier for the medical image by: and inputting the image data of the medical image into a preset hash algorithm to obtain a hash value of the medical image, and then taking the hash value as a unique identifier of the medical image. In specific implementation, the binary data of the medical image can be input into a preset hash algorithm, so that a corresponding hash value is obtained, and the hash value is used as the unique identifier of the medical image.
Optionally, in some embodiments, the user terminal may generate the transaction ID for the credentialing transaction by: splicing the unique identifier carried by the deposit transaction, the hardware address of the terminal equipment, the current timestamp and the like into a character string, then calculating the hash value of the character string, and finally taking the first 25 bits of the hash value as the transaction ID of the deposit transaction.
As shown in fig. 1, the node device of the block chain network is configured to: and processing the deposit transaction, so that the unique identifier and the transaction ID carried by the deposit transaction are correspondingly stored in an account book database of the block chain network. To simplify the drawing, only a part of the node devices performing the deposit transaction is schematically shown in fig. 1.
As shown in fig. 1, the image storage server is configured to: and processing the storage request, so that the medical image and the transaction ID carried by the storage request are correspondingly stored in a database.
In the invention, the unique identifier and the transaction ID are correspondingly stored in the account book database of the block chain network, so that the unique identifier corresponding to the transaction ID can be accurately indexed through the transaction ID during remote diagnosis. Medical images and transaction IDs are correspondingly stored in a database of an image storage server, so that the medical images corresponding to the transaction IDs can be accurately indexed through the transaction IDs during remote diagnosis.
As shown in fig. 1, the user terminal is further configured to: and responding to user operation, generating a diagnosis request, and sending the diagnosis request to the diagnosis server, wherein the diagnosis request carries a transaction ID.
In the invention, when a user needs to carry out remote diagnosis, the terminal equipment can be operated to generate a diagnosis request, and the diagnosis request carries the transaction ID of the previous deposit transaction.
As shown in fig. 1, the diagnostic server is configured to: responding to a diagnosis request sent by a user terminal, acquiring a unique identifier corresponding to a transaction ID from the blockchain network according to the transaction ID carried by the diagnosis request, and acquiring a medical image corresponding to the transaction ID from the image storage server; generating a unique identifier of the medical image according to the acquired medical image; comparing the generated unique identifier with the unique identifier acquired from the block chain network; under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and then predicting the disease of the denoised medical image to obtain a disease prediction result; in the case where the two do not coincide, the response to the diagnosis request is terminated.
When the diagnostic server generates the unique identifier for the acquired medical image, the generation mode adopted by the diagnostic server is the same as the generation mode when the terminal device generates the unique identifier for the medical image in advance.
Optionally, in some embodiments, the diagnosis server may generate the unique identifier for the acquired medical image by: and inputting the image data of the medical image into a preset hash algorithm to obtain a hash value of the medical image, and then taking the hash value as a unique identifier of the medical image. In specific implementation, the binary data of the medical image can be input into a preset hash algorithm, so that a corresponding hash value is obtained, and the hash value is used as the unique identifier of the medical image.
In the invention, the medical images of each user are stored by the centralized image storage server, when a certain user needs to carry out remote diagnosis, the diagnosis server can conveniently call the corresponding medical images from the medical image server, thereby carrying out remote diagnosis according to the called medical images.
In addition, in order to prevent medical images stored in a centralized image storage server from being tampered to cause diagnosis errors, the unique identifier of each medical image is stored in the blockchain network, and the blockchain network belongs to a distributed technology and has the characteristic of preventing data tampering, so that the unique identifier of the medical image stored in the blockchain network cannot be tampered. When the diagnosis server calls the medical image from the image storage server, the unique identification of the medical image is calculated, and then the calculated unique identification is compared with the unique identification of the corresponding medical image in the block chain network.
If the two are consistent, the medical image called by the diagnosis server from the centralized image storage server is not tampered, so that intelligent diagnosis can be performed based on the medical image, and the steps of noise reduction and disease prediction are included. If the two are not consistent, the medical image called by the diagnosis server from the centralized image storage server is falsified, so that the remote diagnosis is terminated, and the diagnosis error is prevented. Therefore, the remote medical diagnosis system based on the medical image, the algorithm and the block chain can effectively improve the reliability of remote diagnosis.
It should be noted that, in the present invention, the medical image is not directly stored in the blockchain network, but the medical image is converted into the unique identifier, and then the unique identifier is stored in the blockchain network. Compared with medical images, the unique identifier has smaller data volume and does not occupy too large storage space, so that the account book database of the block chain network is prevented from being exhausted prematurely.
Optionally, in some embodiments, the number of the medical images is two, and the two medical images are two medical images simultaneously captured for the same human tissue at a moment under the same capturing condition. Because the two medical images are simultaneously shot aiming at the same human tissue at one moment under the same shooting condition, and because of the randomness of the noise pixel points, the two medical images are the same except that the distribution of the noise pixel points is different. Thus, when the diagnostic server performs noise reduction processing on the medical image, the following method may be specifically adopted:
regarding the two medical images, taking any one medical image as a positive medical image and taking the other one as a secondary medical image; calculating the difference between the pixel value of each first pixel point in the positive medical image and the pixel value of each second pixel point at the corresponding position in the auxiliary medical image; under the condition that the difference value is smaller than a preset difference value, the first pixel point is reserved in the positive medical image; under the condition that the difference value is not smaller than a preset difference value, determining a noise pixel point from the first pixel point and the second pixel point, if the first pixel point is the noise pixel point, replacing the first pixel point with the second pixel point in the positive medical image, and if the second pixel point is the noise pixel point, keeping the first pixel point in the positive medical image; and finally, taking the processed positive medical image as a noise-reduced medical image. It should be noted that, for convenience of description, each pixel in the primary medical image is referred to as a first pixel, and each pixel in the secondary medical image is referred to as a second pixel.
For convenience of understanding, illustratively, according to an order from left to right and from top to bottom, a pixel value of a first pixel point in the primary medical image is obtained, a pixel value of a second pixel point in the secondary medical image is obtained, and a difference between the two pixel values is calculated. If the difference is smaller than the predetermined difference (for example, the predetermined difference is equal to 20), it indicates that the pixel difference between the two pixels is very small, and both the two pixels are likely not to be noise pixels, so that the first pixel is retained in the positive medical image. If the difference is greater than the preset difference, it is indicated that one pixel point is a noise pixel point in the two pixel points, so that the noise pixel point is determined from the first pixel point and the second pixel point, if the first pixel point is the noise pixel point, the second pixel point is used for replacing the first pixel point in the positive medical image (so that the noise pixel point in the positive medical image can be effectively eliminated), and if the second pixel point is the noise pixel point, the first pixel point is reserved in the positive medical image.
Then, the same operation is executed for the second first pixel point in the positive medical image. And the operation on all the first pixel points in the positive medical image is completed by analogy in sequence. And finally, taking the processed positive medical image as the medical image subjected to noise reduction.
Optionally, in some specific embodiments, the diagnostic server is further configured to, for any one of the two medical images, extract a plurality of noise pixels in the medical image, and calculate an average pixel value of the plurality of noise pixels. The method for extracting the noise pixel points by the diagnostic server can refer to the prior art, and the comparison of the invention is not limited. For example, the diagnostic server may perform gaussian filtering on a medical image by using a gaussian filtering algorithm, and then subtract the original medical image from the filtered medical image, so as to obtain the noise pixel. And then calculating the average pixel value of a plurality of pixel values of a plurality of noise pixel points.
When the diagnostic service determines the noise pixel points from the first pixel points and the second pixel points, specifically, calculating a first difference value between the pixel value of the first pixel point and the average pixel value of the plurality of noise pixel points; calculating a second difference value between the pixel value of the second pixel point and the average pixel value of the plurality of noise pixel points; if the first difference is smaller than the second difference, determining the first pixel point as a noise pixel point; and if the second difference is smaller than the first difference, determining the second pixel point as a noise pixel point. In the invention, the average pixel value of the noise pixel point is determined in advance, and when the noise pixel point needs to be determined from the first pixel point and the second pixel point, the pixel point with the pixel value closest to the average pixel value is determined as the noise pixel point.
For ease of understanding, it is assumed that the average pixel value of the plurality of noise pixels is 36, by way of example. Assume that the difference between the pixel value of the 527 th first pixel of the positive medical image and the pixel value of the 527 th second pixel of the secondary medical image is greater than the predetermined difference, wherein the pixel value of the first pixel is equal to 33, and the pixel value of the second pixel is equal to 105. Thus, a first difference between the pixel value 33 of the first pixel and the average pixel value 36 of the plurality of noise pixels is equal to 3, and a second difference between the pixel value 105 of the second pixel and the average pixel value 36 of the plurality of noise pixels is equal to 69. And determining the first pixel point as a noise pixel point because the first difference value is smaller than the second difference value.
Optionally, in some specific embodiments, when the diagnosis server performs disease prediction on the noise-reduced medical image, the noise-reduced medical image may be specifically input into a BP neural network that is trained and tested in advance, so as to obtain a disease prediction result output by the BP neural network. It should be noted that the diagnosis server may train the BP neural network by itself, or may call the BP neural network trained by other systems in advance.
Preferably, the pre-trained and tested BP neural network is: calling and processing historical diagnosis and treatment data and medical images of a patient, and taking the processed historical diagnosis and treatment data and medical images as input values for training and testing a disease prediction modelTaking the disease type of the patient as an output value for training and testing a disease prediction model, thereby establishing a sample set; training and testing a BP neural network by adopting a sample set, introducing a cuckoo search algorithm to optimize the weight and the threshold of the BP neural network, and defining a fitness function h of the cuckoo search algorithm as follows:
wherein C represents the number of samples used for training, YaRepresents the actual output value of the a-th sample,
indicating the expected value of the a-th sample.
Preferably, in the updating process of the cuckoo search algorithm, the smaller the fitness function value of the bird nest position is, the better the solution represented by the bird nest position is.
Preferably, after the cuckoo algorithm updates the position of the bird nest through the lave flight mode, the method specifically includes:
(1) the global random search is performed in the following manner:
wherein x isi(t +1) represents the position of the ith bird nest in the population in the (t +1) th global random search, Xi(t) represents the position of the ith bird nest in the population after the updating of the t-th Laevi flight, alpha represents the step control quantity of the global random search,
point-to-point multiplication is represented, Lev 'y (lambda) represents random walk of which the step size follows Le' vy distribution, and lambda is a stability index;
(2) and executing selection operation:
let Xi(t +1) represents the position of the ith nest in the population after the (t +1) th Levy flight update, when the nest position xi(t +1) satisfies: h (x)i(t+1))＜hi(t) when the bird nest is at the position Xi(t+1)＝xi(t + 1); when the bird nest is at position xi(t +1) satisfies: h (x)i(t+1))≥hi(t) when the bird nest is at the position Xi(t+1)＝Xi(t) wherein h (x)i(t +1)) represents the bird nest position xiFitness function value of (t +1), hi(t) indicates the bird nest position Xi(t) fitness function value.
Preferably, in the cuckoo search algorithm, after the position of the bird nest is updated through the levey flight mode, the bird nest position is updated according to the discovery probability paSelecting part of bird nest positions for random updating, specifically:
after the (t +1) th time of the Levy flight updating, selecting a bird nest position in the population for random updating, which specifically comprises the following steps:
(1) let B (t +1) denote the set of bird nest positions in the population after the (t +1) th lave flight update, given a threshold value d (t +1), where the value of d (t +1) can take:
wherein the content of the first and second substances,
indicating the distance from the nest position X in the populationi(t +1) the position of the nearest nest, N represents the number of nests in the population;
the division of the subset of bird's nest positions in set B (t + 1): let b1(t +1) represents the 1 st subset obtained by dividing the bird nest positions in the set B (t +1), and the bird nest position with the minimum fitness function value in the set B (t +1) is selected and added into the subset B1(t +1), and adding the bird nest positions in the set B (t +1) and with the Euclidean distance between the bird nest positions being less than or equal to a threshold value d (t +1) to the subset B1(t + 1); let b2(t +1) represents the 2 nd subset obtained by dividing the bird nest positions in the set B (t +1), and the non-divided bird nest position with the minimum fitness function value in the set B (t +1) is selected and added into the subset B2(t +1) and the Euclidean distance between the positions of the bird nests and the position in the set B (t +1)Adding the undivided bird nest positions with the distance less than or equal to the threshold d (t +1) to the subset b2(t + 1); continuing to divide the rest non-divided bird nest positions in the set B (t +1) by adopting the method, and stopping dividing until all bird nest positions in the set B (t +1) are divided;
(2) detecting the position of bird nest in the population, and setting Xi(t +1) represents the position of the ith bird nest in the population after the (t +1) th Levy flight update, Xi(t) represents the position of the ith nest in the population after the updating of the t-th Laevir flight, when the position X of the nest isi(t +1) satisfies: xi(t+1)＝Xi(t) then the bird nest position Xi(t +1) is denoted by 1;
(3) randomly updating the bird nest position marked as 1 in each subset, and setting bj(t +1) denotes the j-th subset obtained by dividing the bird's nest positions in the set B (t +1), and the subset BjThe bird nest positions marked with 1 in (t +1) are sorted according to the fitness function value from small to large to form a sequence
Is provided with
Representing a sequence
The first bird nest position in the table is determined by the following method
And (3) carrying out random updating:
definition of Qj(t +1) denotes the subset bjLocal detection coefficient of (t +1), and QjThe calculation formula of (t +1) is:
wherein m (t +1) represents the position of the bird's nest in the set B (t +1)Number of subsets obtained by dividing, mj(t +1) denotes the subset bjThe number of bird's nest positions in (t +1),
represents a subset bjThe number of bird nest positions, u, marked 1 in (t +1)j(t +1) denotes the subset bj(t +1) and a spatial detection coefficient, and
Xj，k(t +1) denotes the subset bjThe kth bird nest position, X in (t +1)j，g(t +1) denotes the subset bjThe g-th bird nest position in (t +1), hj，k(t +1) represents a bird nest position Xj，kFitness function value of (t +1), hj，g(t +1) represents a bird nest position Xj，gA fitness function value of (t +1), u '(t +1) represents a median of local detection coefficients of a subset obtained by dividing bird's nest positions in the set B (t +1), and
it is indicated that the median function is calculated,
represents a subset bjA first local detection function of (t +1), and
represents a subset bj(t +1) second local detection function,
represents a subset bjA third local detection function of (t +1), and
definition of
Indicating the position of the bird's nest
Probability of random update is performed, and
the expression of (a) is:
wherein the content of the first and second substances,
indicating the position of the bird's nest
A random number between 0 and 1 is generated,
indicating the position of the bird's nest
An attribute value of (2), and
indicating the position of the bird's nest
The corresponding bird nest is updated after the Tth Laevi flightThe position of the bird nest,
indicating the position of the bird's nest
And the position of the bird nest
A judgment function in between, and
when the bird nest is in position
Satisfies the following conditions:
when it is not in the position of bird's nest
Performing random update when the bird nest position
Satisfies the following conditions:
and QjWhen (t +1) ═ 1, the bird nest position is aligned in the following manner
Performing random update to obtain new bird nest position
Wherein rand represents a random number between 0 and 1,
and
is a random slave subset bjTwo bird nest positions selected from (t +1), and
when the bird nest is in position
Satisfies the following conditions:
then, the bird nest is positioned in the following way
And (3) carrying out random updating:
wherein, Xq1(t +1) and Xq2(t +1) are two bird nest positions randomly selected from the population, and Xq1(t+1)≠Xq2(t+1)；
(3) And executing selection operation: only when the new bird nest position
Satisfies the following conditions:
when it is, the bird nest is in position
In place of bird's nest
Otherwise, abandoning new bird nest position
And the original bird nest position is reserved
Wherein the content of the first and second substances,
indicating the position of the bird's nest
The value of the fitness function of (a),
indicating the position of the bird's nest
The fitness function value of (1).
In the preferred embodiment, aiming at the situation that the BP neural network is easy to fall into a local minimum point due to the random initialization of the weight and the threshold of the BP neural network, so that the situations of non-ideal recognition rate and low reliability may occur during the disease prediction, the cuckoo algorithm and the BP neural network are combined, the optimal weight and the threshold of the BP neural network are obtained by using the cuckoo search algorithm, however, the Levy flight mechanism adopted by the traditional cuckoo search algorithm has strong randomness, and the randomness enables the cuckoo search algorithm to only carry out rough search near each bird nest, so that the local search capability of the cuckoo search algorithm is weak, and the adaptivity is lacked, namely, the traditional cuckoo algorithm is adopted to optimize the BP neural network, the optimal weight and the threshold of the BP neural network cannot be effectively obtained, namely, the disease prediction accuracy cannot be effectively improved, aiming at the situation, the preferred embodiment improves the cuckoo algorithm, randomly updates the positions of the bird nests in the population after each time of Levy flight updating, updates the positions of the bird nests in the population in a Levy flight mode, has strong randomness, and can increase the diversity of the population, but on the other hand, after each time of Levy flight updating, partial positions of the bird nests in the population are not effectively updated, so that the convergence speed and the optimization accuracy of the algorithm are influenced, and aiming at the phenomenon, after each time of Levy flight updating, the preferred embodiment randomly updates the positions of the bird nests which are not changed in the population, so that the diversity of the population is ensured, the deficiency of the Levy flight updating can be effectively made up, and the convergence speed and the optimization accuracy of the algorithm are improved; when the bird nest position is randomly updated, comparing a defined probability value for randomly updating the bird nest position with a discovery probability to determine whether to randomly update the bird nest position, wherein a first part of the calculation formula of the probability value reserves the randomness of determining whether to randomly update the bird nest position by generating random numbers, the attribute value is used for measuring the quality of the optimization result of the bird nest position in the area where the bird nest position is located and the iteration number of times that the position of the bird nest position is not changed, and when the optimization result of a bird nest position in the area where the bird nest position is located is worse and not updated for multiple times, the probability value for randomly updating the bird nest position is increased, namely, compared with the conventional way, the preferred embodiment increases the probability for randomly updating the worse bird nest position by the defined probability value and increases the probability for reserving the better bird nest position, thereby ensuring the population quality; in addition, when the position of the bird nest is randomly updated, two updating modes are set, the updating mode adopted by the position of the bird nest is determined through a defined local detection coefficient, when the bird nest is in an area with a better optimizing result, more new bird nest positions exist in the area where the bird nest is located, and the optimizing space between the bird nests is also larger, at the moment, the position of the bird nest is randomly updated in the area where the bird nest is located, so that the optimizing precision of the bird nest is improved, and on the contrary, the position of the bird nest is randomly updated in the global range, so that the diversity of the algorithm is ensured; that is, the preferred embodiment improves the conventional cuckoo search algorithm, thereby improving the convergence rate and the optimization precision of the cuckoo search algorithm, and can effectively obtain the optimal weight and the threshold of the BP neural network when the improved cuckoo algorithm is used for optimizing the BP neural network, thereby improving the accuracy of disease prediction.
Based on the same inventive concept, the invention also provides a remote medical diagnosis method based on the medical image and the block chain, and the method is applied to a diagnosis server. Referring to fig. 2, fig. 2 is a flowchart of a remote medical diagnosis method based on medical images and a blockchain according to an embodiment of the present invention. It should be noted that the method shown in fig. 2 may be cross-referenced with the system shown in fig. 1. The method is therefore briefly described below in connection with fig. 2.
As shown in fig. 2, the remote medical diagnosis method based on medical images and blockchains comprises the following steps:
step S21: receiving a diagnosis request sent by a user terminal, wherein the diagnosis request carries a transaction ID;
step S22: acquiring a unique identifier corresponding to the transaction ID from a block chain network according to the transaction ID;
step S23: acquiring a medical image corresponding to the transaction ID from an image storage server according to the transaction ID;
step S24: generating a unique identifier of the medical image according to the acquired medical image;
step S25: comparing the generated unique identifier with the unique identifier acquired from the block chain network;
step S26: under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and predicting the disease of the denoised medical image to obtain a disease prediction result;
step S27: in the case where the two do not coincide, the response to the diagnosis request is terminated.
Optionally, in some embodiments, the number of the medical images is two, and the two medical images are two medical images simultaneously captured for the same human tissue at a moment under the same capturing condition;
the denoising processing is performed on the medical image to obtain a denoised medical image, and the denoising processing includes: regarding the two medical images, taking any one medical image as a positive medical image and taking the other one as a secondary medical image; calculating the difference between the pixel value of each first pixel point in the positive medical image and the pixel value of each second pixel point at the corresponding position in the auxiliary medical image; under the condition that the difference value is smaller than a preset difference value, the first pixel point is reserved in the positive medical image; under the condition that the difference value is not smaller than a preset difference value, determining a noise pixel point from the first pixel point and the second pixel point, if the first pixel point is the noise pixel point, replacing the first pixel point with the second pixel point in the positive medical image, and if the second pixel point is the noise pixel point, keeping the first pixel point in the positive medical image; and finally, taking the processed positive medical image as a noise-reduced medical image.
Optionally, in some embodiments, the method further comprises: aiming at any one of the two medical images, extracting a plurality of noise pixel points in the medical image, and calculating the average pixel value of the plurality of noise pixel points;
the determining the noise pixel point from the first pixel point and the second pixel point includes: calculating a first difference value between the pixel value of the first pixel point and the average pixel value of the plurality of noise pixel points; calculating a second difference value between the pixel value of the second pixel point and the average pixel value of the plurality of noise pixel points; if the first difference is smaller than the second difference, determining the first pixel point as a noise pixel point; and if the second difference is smaller than the first difference, determining the second pixel point as a noise pixel point.
Optionally, in some embodiments, the unique identifier is generated as follows: and inputting the image data of the medical image into the preset hash algorithm to obtain a hash value of the medical image, and then taking the hash value as a unique identifier of the medical image.
Optionally, in some embodiments, the performing a disease prediction on the noise-reduced medical image to obtain a disease prediction result includes: and inputting the medical image after noise reduction into a pre-trained BP neural network for disease prediction, thereby obtaining a disease prediction result output by the BP neural network.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A remote medical diagnosis system based on medical images, algorithms and blockchains, the system comprising: the system comprises a user terminal, an image storage server, a diagnosis server and a block chain network, wherein the block chain network comprises a plurality of node devices;
the user terminal is configured to: generating a unique identifier of a medical image according to the medical image of a user; generating a deposit transaction according to the unique identifier, and submitting the deposit transaction to the blockchain network for execution, wherein the deposit transaction carries the unique identifier and a transaction ID;
the user terminal is further configured to: generating a storage request, and sending the storage request to the image storage server, wherein the storage request carries the medical image and the transaction ID;
the node device of the blockchain network is configured to: processing the deposit transaction, so that the unique identifier and the transaction ID carried by the deposit transaction are correspondingly stored in an account book database of a block chain network;
the image storage server is used for: processing the storage request, so that the medical image and the transaction ID carried by the storage request are correspondingly stored in a database;
the user terminal is further configured to: responding to user operation, generating a diagnosis request, and sending the diagnosis request to the diagnosis server, wherein the diagnosis request carries a transaction ID;
the diagnostic server is to: responding to a diagnosis request sent by a user terminal, acquiring a unique identifier corresponding to a transaction ID from the blockchain network according to the transaction ID carried by the diagnosis request, and acquiring a medical image corresponding to the transaction ID from the image storage server; generating a unique identifier of the medical image according to the acquired medical image; comparing the generated unique identifier with the unique identifier acquired from the block chain network; under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and then predicting the disease of the denoised medical image to obtain a disease prediction result; in the case where the two do not coincide, the response to the diagnosis request is terminated.
2. The remote medical diagnosis system based on medical images, algorithms and blockchains according to claim 1, wherein the number of the medical images is two, the two medical images being simultaneously taken for the same human tissue at a moment under the same photographing conditions; when the diagnostic server performs denoising processing on the medical image, the diagnostic server is specifically configured to:
regarding the two medical images, taking any one medical image as a positive medical image and taking the other one as a secondary medical image; calculating the difference between the pixel value of each first pixel point in the positive medical image and the pixel value of each second pixel point at the corresponding position in the auxiliary medical image; under the condition that the difference value is smaller than a preset difference value, the first pixel point is reserved in the positive medical image; under the condition that the difference value is not smaller than a preset difference value, determining a noise pixel point from the first pixel point and the second pixel point, if the first pixel point is the noise pixel point, replacing the first pixel point with the second pixel point in the positive medical image, and if the second pixel point is the noise pixel point, keeping the first pixel point in the positive medical image; and finally, taking the processed positive medical image as a noise-reduced medical image.
3. The medical image, algorithm and blockchain based remote medical diagnosis system according to claim 2, wherein said diagnosis server is further configured to: aiming at any one of the two medical images, extracting a plurality of noise pixel points in the medical image, and calculating the average pixel value of the plurality of noise pixel points;
when the diagnosis server is used for determining the noise pixel points from the first pixel points and the second pixel points, the diagnosis server is specifically used for: calculating a first difference value between the pixel value of the first pixel point and the average pixel value of the plurality of noise pixel points; calculating a second difference value between the pixel value of the second pixel point and the average pixel value of the plurality of noise pixel points; if the first difference is smaller than the second difference, determining the first pixel point as a noise pixel point; and if the second difference is smaller than the first difference, determining the second pixel point as a noise pixel point.
4. The medical image, algorithm and blockchain based remote medical diagnosis system according to claim 1, wherein the user terminal, when generating the unique identifier of the medical image according to the medical image of the user, is specifically configured to: inputting the image data of the medical image into a preset hash algorithm to obtain a hash value of the medical image, and then taking the hash value as a unique identifier of the medical image;
when the diagnosis server generates the unique identifier of the medical image according to the acquired medical image, the diagnosis server is specifically configured to: and inputting the image data of the medical image into the preset hash algorithm to obtain a hash value of the medical image, and then taking the hash value as a unique identifier of the medical image.
5. The medical image, algorithm and blockchain based remote medical diagnosis system according to claim 1, wherein the diagnosis server, when used for performing disease prediction on the denoised medical image, is specifically configured to: inputting the medical image after noise reduction into a BP neural network which is trained and tested in advance to predict diseases, so as to obtain a disease prediction result output by the BP neural network;
the pre-trained and tested BP neural network is as follows: calling historical diagnosis and treatment data and medical images of a patient for processing, taking the processed historical diagnosis and treatment data and medical images as input values for training and testing a disease prediction model, and taking the disease type of the patient as an output value for training and testing the disease prediction model, thereby establishing a sample set; and training and testing the BP neural network by adopting a sample set.
6. A remote medical auxiliary diagnosis method based on medical images and block chains is applied to a diagnosis server, and comprises the following steps:
receiving a diagnosis request sent by a user terminal, wherein the diagnosis request carries a transaction ID;
acquiring a unique identifier corresponding to the transaction ID from a block chain network according to the transaction ID;
acquiring a medical image corresponding to the transaction ID from an image storage server according to the transaction ID;
generating a unique identifier of the medical image according to the acquired medical image;
comparing the generated unique identifier with the unique identifier acquired from the block chain network;
under the condition that the two images are consistent, denoising the medical image to obtain a denoised medical image, and predicting the disease of the denoised medical image to obtain a disease prediction result;
in the case where the two do not coincide, the response to the diagnosis request is terminated.
7. The remote medical auxiliary diagnosis method based on medical images and block chains according to claim 6, wherein the number of the medical images is two, and the two medical images are two medical images simultaneously photographed for the same human tissue at a moment under the same photographing condition;
the denoising processing is performed on the medical image to obtain a denoised medical image, and the denoising processing includes: regarding the two medical images, taking any one medical image as a positive medical image and taking the other one as a secondary medical image; calculating the difference between the pixel value of each first pixel point in the positive medical image and the pixel value of each second pixel point at the corresponding position in the auxiliary medical image; under the condition that the difference value is smaller than a preset difference value, the first pixel point is reserved in the positive medical image; under the condition that the difference value is not smaller than a preset difference value, determining a noise pixel point from the first pixel point and the second pixel point, if the first pixel point is the noise pixel point, replacing the first pixel point with the second pixel point in the positive medical image, and if the second pixel point is the noise pixel point, keeping the first pixel point in the positive medical image; and finally, taking the processed positive medical image as a noise-reduced medical image.
8. The medical image and blockchain based remote medical auxiliary diagnosis method according to claim 7, wherein the method further comprises: aiming at any one of the two medical images, extracting a plurality of noise pixel points in the medical image, and calculating the average pixel value of the plurality of noise pixel points;
the determining the noise pixel point from the first pixel point and the second pixel point includes: calculating a first difference value between the pixel value of the first pixel point and the average pixel value of the plurality of noise pixel points; calculating a second difference value between the pixel value of the second pixel point and the average pixel value of the plurality of noise pixel points; if the first difference is smaller than the second difference, determining the first pixel point as a noise pixel point; and if the second difference is smaller than the first difference, determining the second pixel point as a noise pixel point.
9. The medical image and blockchain based remote medical auxiliary diagnosis method according to claim 6, wherein the unique identifier is generated as follows: and inputting the image data of the medical image into the preset hash algorithm to obtain a hash value of the medical image, and then taking the hash value as a unique identifier of the medical image.
10. The remote medical auxiliary diagnosis method based on medical images and block chains as claimed in claim 6, wherein the performing disease prediction on the medical images after noise reduction to obtain a disease prediction result comprises: and inputting the medical image after noise reduction into a pre-trained BP neural network for disease prediction, thereby obtaining a disease prediction result output by the BP neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110403455.8A CN113096793A (en) | 2021-04-15 | 2021-04-15 | Remote medical diagnosis system based on medical images, algorithms and block chains |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110403455.8A CN113096793A (en) | 2021-04-15 | 2021-04-15 | Remote medical diagnosis system based on medical images, algorithms and block chains |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113096793A true CN113096793A (en) | 2021-07-09 |
Family
ID=76677485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110403455.8A Pending CN113096793A (en) | 2021-04-15 | 2021-04-15 | Remote medical diagnosis system based on medical images, algorithms and block chains |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113096793A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114820550A (en) * | 2022-05-11 | 2022-07-29 | 云南升玥信息技术有限公司 | Disease prediction system based on block chain and medical image |
| CN116313021A (en) * | 2023-05-23 | 2023-06-23 | 肇庆市高要区人民医院 | Medical treatment management system and method for hospital |
| CN116821941A (en) * | 2023-08-25 | 2023-09-29 | 建信金融科技有限责任公司 | Data encryption and decryption method, device, equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11126232A (en) * | 1997-10-24 | 1999-05-11 | Fujitsu Ltd | Medical image diagnostic system |
| US20170005804A1 (en) * | 2015-07-02 | 2017-01-05 | Nasdaq, Inc. | Systems and methods of secure provenance for distributed transaction databases |
| CN106411950A (en) * | 2016-11-21 | 2017-02-15 | 江苏通付盾科技有限公司 | Block-chain transaction ID based authentication method, device and system |
| US20180189449A1 (en) * | 2017-01-04 | 2018-07-05 | International Business Machines Corporation | Tracking items used for providing medical services |
| WO2018176484A1 (en) * | 2017-04-01 | 2018-10-04 | 深圳前海达闼云端智能科技有限公司 | Method and apparatus for processing medical image transmission data, and electronic device |
| KR101925463B1 (en) * | 2017-12-27 | 2018-12-05 | 주식회사 뷰노 | Method of record and validation of image hash value and apparatus using the same |
| WO2018221689A1 (en) * | 2017-06-01 | 2018-12-06 | 株式会社ニデック | Medical information processing system |
| CN110164550A (en) * | 2019-05-22 | 2019-08-23 | 杭州电子科技大学 | A kind of congenital heart disease aided diagnosis method based on multi-angle of view conspiracy relation |
| CN110706791A (en) * | 2019-09-30 | 2020-01-17 | 杭州依图医疗技术有限公司 | Medical image processing method and device |
| CN111159651A (en) * | 2019-11-22 | 2020-05-15 | 张鸿 | Block chain online evidence storage method and system |
| CN111340805A (en) * | 2020-04-16 | 2020-06-26 | 张东 | B-ultrasonic image processing device, fatty liver B-ultrasonic image processing device and B-ultrasonic system |
| CN111803107A (en) * | 2020-08-06 | 2020-10-23 | 上海联影医疗科技有限公司 | Metal detection method, device, equipment and storage medium |
| CN111863232A (en) * | 2020-08-06 | 2020-10-30 | 罗春华 | Remote disease intelligent diagnosis system based on block chain and medical image |
| WO2020232998A1 (en) * | 2019-05-22 | 2020-11-26 | 平安国际智慧城市科技股份有限公司 | Medical image evaluation method and apparatus, computer device and storage medium |
| CN112614586A (en) * | 2020-12-15 | 2021-04-06 | 广东德澳智慧医疗科技有限公司 | Remote disease intelligent diagnosis system based on medical images and block chains |
-
2021
- 2021-04-15 CN CN202110403455.8A patent/CN113096793A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11126232A (en) * | 1997-10-24 | 1999-05-11 | Fujitsu Ltd | Medical image diagnostic system |
| US20170005804A1 (en) * | 2015-07-02 | 2017-01-05 | Nasdaq, Inc. | Systems and methods of secure provenance for distributed transaction databases |
| CN106411950A (en) * | 2016-11-21 | 2017-02-15 | 江苏通付盾科技有限公司 | Block-chain transaction ID based authentication method, device and system |
| US20180189449A1 (en) * | 2017-01-04 | 2018-07-05 | International Business Machines Corporation | Tracking items used for providing medical services |
| WO2018176484A1 (en) * | 2017-04-01 | 2018-10-04 | 深圳前海达闼云端智能科技有限公司 | Method and apparatus for processing medical image transmission data, and electronic device |
| WO2018221689A1 (en) * | 2017-06-01 | 2018-12-06 | 株式会社ニデック | Medical information processing system |
| KR101925463B1 (en) * | 2017-12-27 | 2018-12-05 | 주식회사 뷰노 | Method of record and validation of image hash value and apparatus using the same |
| CN110164550A (en) * | 2019-05-22 | 2019-08-23 | 杭州电子科技大学 | A kind of congenital heart disease aided diagnosis method based on multi-angle of view conspiracy relation |
| WO2020232998A1 (en) * | 2019-05-22 | 2020-11-26 | 平安国际智慧城市科技股份有限公司 | Medical image evaluation method and apparatus, computer device and storage medium |
| CN110706791A (en) * | 2019-09-30 | 2020-01-17 | 杭州依图医疗技术有限公司 | Medical image processing method and device |
| CN111159651A (en) * | 2019-11-22 | 2020-05-15 | 张鸿 | Block chain online evidence storage method and system |
| CN111340805A (en) * | 2020-04-16 | 2020-06-26 | 张东 | B-ultrasonic image processing device, fatty liver B-ultrasonic image processing device and B-ultrasonic system |
| CN111803107A (en) * | 2020-08-06 | 2020-10-23 | 上海联影医疗科技有限公司 | Metal detection method, device, equipment and storage medium |
| CN111863232A (en) * | 2020-08-06 | 2020-10-30 | 罗春华 | Remote disease intelligent diagnosis system based on block chain and medical image |
| CN112614586A (en) * | 2020-12-15 | 2021-04-06 | 广东德澳智慧医疗科技有限公司 | Remote disease intelligent diagnosis system based on medical images and block chains |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114820550A (en) * | 2022-05-11 | 2022-07-29 | 云南升玥信息技术有限公司 | Disease prediction system based on block chain and medical image |
| CN116313021A (en) * | 2023-05-23 | 2023-06-23 | 肇庆市高要区人民医院 | Medical treatment management system and method for hospital |
| CN116313021B (en) * | 2023-05-23 | 2023-08-04 | 肇庆市高要区人民医院 | Medical treatment management system and method for hospital |
| CN116821941A (en) * | 2023-08-25 | 2023-09-29 | 建信金融科技有限责任公司 | Data encryption and decryption method, device, equipment and storage medium |
| CN116821941B (en) * | 2023-08-25 | 2023-12-19 | 建信金融科技有限责任公司 | Data encryption and decryption method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110599451B (en) | Medical image focus detection and positioning method, device, equipment and storage medium | |
| CN113096793A (en) | Remote medical diagnosis system based on medical images, algorithms and block chains | |
| CN108615071B (en) | Model testing method and device | |
| CN110852755B (en) | User identity identification method and device for transaction scene | |
| CN112420187B (en) | Medical disease analysis method based on migratory federal learning | |
| CN113096806A (en) | Disease prediction system based on medical image algorithm and block chain | |
| KR102190325B1 (en) | A method for building a computer-implemented computing device for assessment of qualitative features from face images | |
| KR20190132832A (en) | Method and apparatus for predicting amyloid positive or negative based on deep learning | |
| CN112017789B (en) | Triage data processing method, triage data processing device, triage data processing equipment and triage data processing medium | |
| CN111062486B (en) | Method and device for evaluating feature distribution and confidence of data | |
| CN110163844A (en) | Eyeground lesion detection method, device, computer equipment and storage medium | |
| WO2017194514A1 (en) | Diagnosis system | |
| CN113077891A (en) | Big data disease diagnosis system based on algorithm, block chain and medical image | |
| CN108877924A (en) | A kind of asthma method of determining probability and device | |
| CN116936117A (en) | Chronic disease big data identification and analysis processing method based on AI analysis model | |
| CN117079017A (en) | Credible small sample image identification and classification method | |
| CN116630736A (en) | Training method and system for user expression capturing model | |
| CN116302870A (en) | Mechanical hard disk health assessment method, system and storage medium based on evolutionary diagram | |
| CN113537407B (en) | Image data evaluation processing method and device based on machine learning | |
| CN116302874A (en) | Model capability test method and device, electronic equipment, storage medium and product | |
| KR101781174B1 (en) | Method and apparatus for determining constitution based on administration of computerized adaptive tests | |
| CN114912627A (en) | Recommendation model training method, system, computer device and storage medium | |
| CN114399491A (en) | Human face image quality evaluation method and device and computer readable storage medium | |
| CN113935832A (en) | Abnormal behavior detection processing method and device | |
| CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment |
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 |