CN109461494A - A kind of RIS platform and image assistant diagnostic system example method of data synchronization - Google Patents
A kind of RIS platform and image assistant diagnostic system example method of data synchronization Download PDFInfo
- Publication number
- CN109461494A CN109461494A CN201811271360.XA CN201811271360A CN109461494A CN 109461494 A CN109461494 A CN 109461494A CN 201811271360 A CN201811271360 A CN 201811271360A CN 109461494 A CN109461494 A CN 109461494A
- Authority
- CN
- China
- Prior art keywords
- ris
- image
- platform
- case
- diagnostic system
- 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
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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Data Mining & Analysis (AREA)
- Radiology & Medical Imaging (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention provides a kind of RIS platforms and image assistant diagnostic system example method of data synchronization, the method comprise the steps that obtaining operation interface RIS platform real-time operation image;Extract RIS character features information;According to RIS character features Information locating RIS character information;Extract case feature number;The case data in image assistant diagnostic system are obtained according to case feature number, and are shown in image assistant diagnostic system.The present invention realizes in operation, there is the case feature number of patient in the operation interface of RIS platform, it can then be transferred in real time in image assistant diagnostic system and show case data corresponding with the case feature number, so that doctor is to the analysis and diagnosis of the case data quickly checked or pass through AI, doctor is improved to the efficiency of the analysis and diagnosis of patient cases' data, case data recall display automatically, easy to be quick, provide convenience for the clinical analysis diagnostic work of doctor.
Description
Technical field
The present invention relates to Medical Imaging Technology fields, are more specifically to a kind of RIS platform and Image-aided diagnosis
System example method of data synchronization.
Background technique
With the high speed development of artificial intelligence, the development of hospital information and manual intelligent, in modern hospital management and
Have the function of becoming more and more important in actual clinical, be of great significance for quality of medical care, medical data, Hospital Decision making etc..
Radiology information management system, RIS (Radiology Information System), be dept. of radiology registration,
It point examines, the management system of the work such as diagnostic imaging report and the every terms of information inquiry of dept. of radiology, statistics, RIS system and PACS
System is closely coupled, constitutes the solution of hospital digital Medical Devices, image and report management.It is the medical information of dept. of radiology
System, while being the Integrated Management Information System and Gao Shui with all patient datas and department's routine work in Administration and Registration Division
Flat high efficiency carries out scientific research, teaching, academic exchange, improves the modernization information platform of department's medical level comprehensively.And image is auxiliary
Diagnostic system is helped, it is more and more aobvious in clinical diagnosis as a kind of artificial intelligence diagnosis' system based on AI machine learning techniques
Now and play an important role in.The first step of auxiliary diagnosis can pass through natural language processing (Natural Language
Processing, abbreviation NLP) study, understanding and conclusion medical information, including authoritative medical book document, practice guidelines and disease
It the massive informations such as goes through, constructs one large-scale " medical knowledge map ", " medical knowledge base " of similar machine brain automatically;The
Two steps go study magnanimity clinical diagnosis case with leading depth learning technology, then compare hundreds of thousands of machines and the diagnosis number of expert
According to rear Continuous optimization model, its diagnosis capability is constantly promoted, obtains based on medical image, check that inspection result and medical history etc. are multiple
The depth of dimension diagnoses, and provides specific illness prediction.This provides better decision basis for doctor, can assist they faster,
More effectively understand medical record, promotes diagnosis and treatment efficiency.
In clinical practice operation, user (doctor) generally requires RIS platform and image assistant diagnostic system is carried out across flat
The operation of platform, it is necessary first to the case data including medical image etc. of target patient be checked on RIS platform, in turn
It needs export and import in corresponding image assistant diagnostic system by the case number of target patient, in order in shadow
Obtain using the medical data of artificial intelligence as numbering corresponding case data to the case of patient in assistant diagnosis system
With the diagnosis for being directed to the case data.
To sum up, the existing side that by image assistant diagnostic system patient cases are carried out with diagnostic analysis based on RIS platform
In method, when practical operation, doctor is needed to carry out cross-platform importing to the case number of obtained patient in RIS platform and lead
Out, such as duplication is pasted, and is needed to open different windows when carrying out analyzing and diagnosing and is carried out cross-platform operation, operating procedure fiber crops
Tired, diagnosis efficiency is low, poor user experience, to the analysis and diagnosis of the case data including medical image for patient of doctor
It makes troubles.
Summary of the invention
In view of this, the present invention provides a kind of RIS platform and image assistant diagnostic system example method of data synchronization and its dress
It sets so as to solve the deficiencies in the prior art.
To solve the above problems, the present invention provides a kind of RIS platform and image assistant diagnostic system to current case data
Synchronous method is applied between RIS platform and image assistant diagnostic system, comprising:
Obtain the RIS platform real-time operation image of operation interface;
Extract the RIS character features information in the RIS platform real-time operation image;
Go out the RIS character information in the real-time operation image according to the RIS character features Information locating;
The RIS character information is identified, the case feature number in the RIS character information is extracted;
According to the case feature number obtain in the image assistant diagnostic system with the case feature number pair
The case data answered, and the case data are shown in the image assistant diagnostic system.
Preferably, described " the RIS platform real-time operation image for obtaining operation interface " includes:
Obtain the operation screenshot image of operation interface;
Extract the characteristics of image in the operation screenshot image;
Described image feature is identified based on default RIS interface feature database;
If in described image feature including RIS interface feature, using the operation screenshot image as the RIS platform
Real-time operation image.
Preferably, described " extracting the RIS character features information in the RIS platform real-time operation image " includes:
The processing of image grayscale hierarchical cluster is carried out to the RIS platform real-time operation image, obtains hierarchical cluster image;
The hierarchical cluster image is handled by preprocess method, obtains the RIS character features information;Its
In,
The preprocess method includes figure detection of connectivity, resistance to corrosion detection, pondization operation and mean filter
Denoising.
Preferably, described " the RIS character in the real-time operation image to be gone out according to the RIS character features Information locating
Information " includes:
The real-time operation image is expanded by proximity search algorithm, obtains into word expansion area;
Extract it is each at word expansion area at word feature, and according to it is described at word feature by it is described at word expansion area into
Row integration, obtains uniline feature text;
Based on character width feature, the uniline feature text is cut, RIS character information is obtained.
Preferably, described " the RIS character information to be identified, the case extracted in the RIS character information is special
Assemble-publish number " includes:
Using the convolutional neural networks model trained in advance by high frequency Chinese characters, OCR knowledge is carried out to the RIS character information
Not, the case feature number in the RIS character information is extracted.
Preferably, described " according to the case feature number obtain in the image assistant diagnostic system with the disease
The corresponding case data of example feature number, and the case data are shown in the image assistant diagnostic system " before, also
Include:
Judge the case feature number in the RIS character information gone out by the RIS platform real-time operation image zooming-out
Number whether be greater than 1;
If so, determining that current state compares state for multiple-case, in the image assistant diagnostic system described in foundation
The hyperlink corresponding relationship of case feature number and case data corresponding with the case feature number, according to the hyperlink
Corresponding relationship generates a hyperlink inventory interface comprising each case feature number, in order to be based on the hyperlink pair
It should be related to, according to the case feature number in the hyperlink inventory interface, be shown in the image assistant diagnostic system
Show the case data corresponding with the case feature number selected;
If it is not, then determining current state for single case diagnosis state, in order to execute described " compile according to the case feature
Number obtain the case data corresponding with the case feature number in the image assistant diagnostic system ".
In addition, to solve the above problems, the present invention also provides a kind of RIS platforms and image assistant diagnostic system number of cases according to same
Walk device, comprising: obtain module, extraction module, locating module and display module;
The acquisition module, for obtaining the RIS platform real-time operation image of operation interface;
The extraction module, for extracting the RIS character features information in the RIS platform real-time operation image;
The locating module, for going out the RIS in the real-time operation image according to the RIS character features Information locating
Character information;
The extraction module is also used to identify the RIS character information, extract in the RIS character information
Case feature number;
The display module, be also used to be obtained according to the case feature number in the image assistant diagnostic system with
The corresponding case data of the case feature number, and the case data are shown in the image assistant diagnostic system.
In addition, to solve the above problems, the present invention also provides a kind of user terminal, including memory and processor, institute
Memory is stated for storing RIS platform and image assistant diagnostic system number of cases according to synchronization program, the processor runs the RIS
Platform is with image assistant diagnostic system number of cases according to synchronization program so that the user terminal executes RIS platform and shadow as described above
As assistant diagnosis system example method of data synchronization.
In addition, to solve the above problems, the present invention also provides a kind of computer readable storage medium, it is described computer-readable
RIS platform and image assistant diagnostic system number of cases are stored on storage medium according to synchronization program, the RIS platform and Image-aided
Diagnostic system number of cases realizes RIS platform as described above and image assistant diagnostic system example when being executed by processor according to synchronization program
Method of data synchronization.
A kind of RIS platform provided by the invention and image assistant diagnostic system example method of data synchronization, comprising: obtain operation
The RIS platform real-time operation image at interface;Extract the RIS character features information in the RIS platform real-time operation image;According to
The RIS character features Information locating goes out the RIS character information in the real-time operation image;To the RIS character information into
Row identification, extracts the case feature number in the RIS character information;The image is obtained according to the case feature number
Case data corresponding with the case feature number in assistant diagnosis system, and the case data are shown in the shadow
As in assistant diagnosis system.The present invention carries out screenshot to operation interface after passing through prefixed time interval, obtains RIS platform and grasps in real time
Make image, case feature number therein is extracted by image recognition technology, and according to the number, diagnose system in Image-aided
Real-time display case data corresponding with pathological characters number are carried out in system, to carry out in practical operation in doctor, RIS platform
Operation interface there is the case feature number of patient, then image assistant diagnostic system can transfer in real time and show with should
The corresponding case data of case feature number, for doctor's quickly checking or further by the analysis of AI to the case data
And diagnosis, doctor is substantially increased to the efficiency of the lookup analysis and diagnosis of patient cases' data, and case data recall simultaneously automatically
It has been shown that, implementation method is easy quickly, provides convenience for the clinical analysis diagnostic work of doctor, improves user experience;It avoids
In existing method, it is still necessary to which doctor carries out cross-platform importing to the case number of obtained patient in RIS platform, leads
Out, it replicates and pastes, and need to open different windows when carrying out analyzing and diagnosing and carry out cross-platform operation, operating procedure fiber crops
It is tired, the problem of diagnosis efficiency is low, poor user experience.
Detailed description of the invention
Fig. 1 is related to for RIS platform of the present invention with image assistant diagnostic system example method of data synchronization example scheme hard
The structural schematic diagram of part running environment;
Fig. 2 is that RIS platform of the present invention and the process of image assistant diagnostic system example method of data synchronization first embodiment are shown
It is intended to;
Fig. 3 is that RIS platform of the present invention and the process of image assistant diagnostic system example method of data synchronization second embodiment are shown
It is intended to;
Fig. 4 is that RIS platform of the present invention and the process of image assistant diagnostic system example method of data synchronization 3rd embodiment are shown
It is intended to;
Fig. 5 is that RIS platform of the present invention and the process of image assistant diagnostic system example method of data synchronization fourth embodiment are shown
It is intended to;
Fig. 6 is the functional block diagram of RIS platform of the present invention and image assistant diagnostic system example data synchronization unit.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, in which the same or similar labels are throughly indicated same or like
Element or element with the same or similar functions.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more of the features.In the description of the present invention, the meaning of " plurality " is two or more,
Unless otherwise specifically defined.
In the present invention unless specifically defined or limited otherwise, term " installation ", " connected ", " connection ", " fixation " etc.
Term shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral;It can be mechanical connect
It connects, is also possible to be electrically connected;It can be directly connected, can also can be in two elements indirectly connected through an intermediary
The interaction relationship of the connection in portion or two elements.It for the ordinary skill in the art, can be according to specific feelings
Condition understands the concrete meaning of above-mentioned term in the present invention.
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the structural schematic diagram of the hardware running environment for the terminal that the embodiment of the present invention is related to.
The PC that the terminal of that embodiment of the invention can be, being also possible to smart phone, tablet computer, portable computer etc. has
The packaged type terminal device of certain operational capability.
As shown in Figure 1, the terminal may include: processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen, input unit such as keyboard, remote controler, and optional user interface 1003 can also include
Standard wireline interface and wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as
WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to stable memory, such as magnetic disk storage.
Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.Optionally, terminal can also include
RF (Radio Frequency, radio frequency) circuit, voicefrequency circuit, WiFi module etc..In addition, mobile terminal can also configure gyro
The other sensors such as instrument, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal shown in Fig. 1, may include ratio
More or fewer components are illustrated, certain components or different component layouts are perhaps combined.
As shown in Figure 1, as may include operating system, number in a kind of memory 1005 of computer readable storage medium
According to interface control program, network attachment procedure and RIS platform and image assistant diagnostic system number of cases according to synchronization program.
A kind of RIS platform provided by the invention and image assistant diagnostic system example method of data synchronization.The method is realized
In image assistant diagnostic system case data corresponding with the case feature number can be transferred and shown in real time, for doctor
Raw quickly checking or further by the analysis and diagnosis of AI, substantially increase doctor to disease number of cases to the case data
According to lookup analysis and diagnosis efficiency, it is the clinic of doctor that case data, which recall and show automatically, and implementation method is easy quickly
Analyzing and diagnosing work provides convenience, and improves user experience.
Embodiment 1:
Referring to Fig. 2, first embodiment of the invention provides a kind of RIS platform with image assistant diagnostic system number of cases according to synchronous side
Method, comprising:
Step S10 obtains the RIS platform real-time operation image of operation interface;
Above-mentioned, synchronous method provided in the present embodiment is directed to the case number of patient, in addition it is also possible to be it
His number corresponding with the case data of patient, coding, two dimensional code, image, image character etc. mark.
Above-mentioned, doctor carries out the management of medical image data, patient image by RIS platform when being operated on the spot
The work such as comparison, the retrieval of image pass through the automatic diagnosis of AI technology if necessary to further progress, then need RIS platform
In, the case of the patient checked number carries out the importing to another platform, such as by by the case in the platform
Number is replicated, then is pasted in another platform (image assistant diagnostic system), then further identify and
Retrieval, so operates time-consuming and laborious, causes operational inconvenience, and causing, which influences doctor, diagnose to patient cases' data
Working efficiency.
In the present embodiment, acquisition for screenshot can be real-time, or timing, such as by interval of default
Time carries out the screenshot to operation interface, in order to carry out further identifying operation.
Wherein, operation interface, for the interface for the operating system that user (doctor) is operated in terminal;
It is above-mentioned, if obtain opportunity be timing, the preset time, for interval progress image acquisition time, this
It can be 1 second in embodiment, i.e., the detection for carrying out the operation interface once operated for doctor in terminal each second.
Above-mentioned, RIS platform real-time operation image is doctor in RIS platform, the case data of patient are transferred,
The image intercepted when operation such as edit, check, managing.
Step S20 extracts the RIS character features information in the RIS platform real-time operation image;
Step S30 goes out the RIS character information in the real-time operation image according to the RIS character features Information locating;
Step S40 identifies that the case feature extracted in the RIS character information is compiled to the RIS character information
Number;
Above-mentioned, RIS character features information can be the region with character features occurred in the picture.
Above-mentioned, RIS character information as includes the text screenshot of character information.
It is above-mentioned, by image recognition technology, RIS platform real-time operation image is identified, in the presence of having obtained it
RIS character features information, and go out RIS character information therein according to RIS character features Information locating, and then to the character
Information is identified, the case feature number in all character informations is extracted.
Step S50 is obtained special with the case in the image assistant diagnostic system according to the case feature number
The corresponding case data of assemble-publish number, and the case data are shown in the image assistant diagnostic system.
Above-mentioned, image assistant diagnostic system is the diagnostic system for being different from RIS platform, when carrying out practical operation, image
Assistant diagnosis system can be synchronous for real-time holding with the case data of the patient in RIS platform.Also, according to patient cases spy
Assemble-publish number can find out corresponding case data in image assistant diagnostic system, in order to be based further on AI's
Analysis and diagnosis.
It is above-mentioned, after obtaining case feature number, it is corresponding that case feature number is got in image assistant diagnostic system
Case data, and real-time display is carried out in image assistant diagnostic system.
The present embodiment carries out screenshot to operation interface after passing through prefixed time interval, obtains RIS platform real-time operation image,
Extract case feature number therein by image recognition technology, and according to the number, in image assistant diagnostic system into
Row real-time display case data corresponding with pathological characters number, to be carried out in practical operation in doctor, the operation of RIS platform
There is the case feature number of patient in interface, then can transfer and show and case spy in real time in image assistant diagnostic system
The corresponding case data of assemble-publish number, for doctor's quickly checking or further by the analysis of AI and examining to the case data
It is disconnected, doctor is substantially increased to the efficiency of the lookup analysis and diagnosis of patient cases' data, case data are recalled and are shown automatically,
Implementation method is easy quickly, provides convenience for the clinical analysis diagnostic work of doctor, improves user experience;It avoids existing
Method in, it is still necessary to doctor carries out cross-platform importing to the case number of obtained patient in RIS platform, export, answers
System and stickup, and need to open different windows when carrying out analyzing and diagnosing and carry out cross-platform operation, operating procedure trouble is examined
The problem of disconnected low efficiency, poor user experience.
Embodiment 2:
Referring to Fig. 3, second embodiment of the invention provides a kind of RIS platform with image assistant diagnostic system number of cases according to synchronous side
Method, is based on above-mentioned first embodiment shown in Fig. 2, and the step S10 " obtains the RIS platform real-time operation figure of operation interface
Picture " includes:
Step S11 obtains the operation screenshot image of operation interface;
It is above-mentioned, screenshot image is operated, for the screenshot operated in the operating system of user (doctor) in the terminal.
The acquisition for wherein operating screenshot image, can be by carrying out the screenshot according to preset time in an operating system.
In addition it is also possible to carry out Image Acquisition by the external image capture device connecting with terminal, in order to get doctor in real time
Raw terminal operation interface, and the operation of relative program is reduced in systems for the occupancy of system resource.
Step S12 extracts the characteristics of image in the operation screenshot image;
Step S13 identifies described image feature based on default RIS interface feature database;
Step S14, if in described image feature including RIS interface feature, using the operation screenshot image as institute
State RIS platform real-time operation image.
In the present embodiment, before the acquisition for carrying out RIS platform real-time operation image, arrived firstly for real-time or timing acquisition
User judge in the operation screenshot image of operation interface, if the image be RIS platform operation figure, can carry out
Further for whether including that the case feature number of patient extracts in image.Image recognition is being carried out to carry out disease
Before the extraction of example feature number, the image obtained firstly for institute's screenshot is screened, if it is the operation of RIS operating platform
The image at interface then can be identified further, to improve the working efficiency of further image recognition work, reduction pair
In the identification of the useless picture largely without containing case feature number, the workload that system carries out image recognition is reduced, is reduced
Occupancy of the redundant work for system resource.
Embodiment 3:
Referring to Fig. 4, third embodiment of the invention provides a kind of RIS platform with image assistant diagnostic system number of cases according to synchronous side
Method, is based on above-mentioned second embodiment shown in Fig. 3, and the step S20 " is extracted in the RIS platform real-time operation image
RIS character features information " includes:
Step S21 carries out the processing of image grayscale hierarchical cluster to the RIS platform real-time operation image, obtains cluster point
Tomographic image;
It is above-mentioned, the image grayscale hierarchical cluster of image is handled, it can be for based on layer clustering procedure (hierarchical
Cluster method) it is realized.A kind of method of clustering.Its way be each sample as a kind of when starting,
Then hithermost sample (i.e. apart from the smallest group's product) is gathered first for group, then by the group having polymerize by its between class distance
It remerges, constantly continues, all subclasses are all finally aggregated to a major class.
Step S22 handles the hierarchical cluster image by preprocess method, obtains the RIS character features
Information;Wherein, the preprocess method includes figure detection of connectivity, resistance to corrosion detection, pondization operation and mean filter
Device denoising.
Above-mentioned, connectivity refers to a kind of topological property of space or set.Intuitively, connection is exactly to join together not having
Interruption.Section on number axis is connection.Connectivity analysis is according to specified starting and to terminate node, and analyzing between two o'clock is
No connection;Or according to multiple points are specified, analyze between multiple points whether intercommunication.
Above-mentioned, corrosion is one of two basic operations of morphological image, another is expansion (Dilate).Binary map
As upper corrosion is to corrode most typical utilization, but etching operation can equally apply to gray level image.In this life embodiment,
By the bianry image etching operation carried out for gray level image, thus in corrosion image foreground region edge.So that preceding
Scape image-region becomes smaller, and the background area inside foreground image is amplified.To remove useless region, noise is reduced.
It is above-mentioned, pondization operation is carried out for image, wherein the benefit in pond has: 1, substantially reducing calculation amount, reduce w's
Quantity;2, certain invariance (rotation, translation, flexible etc.) can be kept, so that the picture made greatly reduces later period identification
For the occupancy of system resource, recognition efficiency is improved.
Above-mentioned, mean filter is typical linear filtering algorithm, it refers on the image to object pixel to a template,
The template include surrounding adjacent pixels (8 pixels, constitute a Filtering Template around centered on object pixel,
Remove object pixel itself), then original pixel value is replaced with the average value of the entire pixels in template.Pass through mean filter
Processing, reaches and removes dryness purpose for image, improve the accuracy rate of identification.
The step S30 " goes out the RIS character in the real-time operation image according to the RIS character features Information locating
Information " includes:
Step S31 expands the real-time operation image by proximity search algorithm, obtains into word expansion area;
Step S32, extract it is each at word expansion area at word feature, and according to it is described will be described swollen at word at word feature
Swollen region is integrated, and uniline feature text is obtained;
Step S33 is based on character width feature, cuts to the uniline feature text, obtain RIS character information.
It is above-mentioned, expanded using proximity search algorithm, may at the region (at word expansion area) " bonding " of word rise
Come, so that integration characteristics region fragment, obtains the uniline feature text of uniline.
In existing recognition methods, it is normally applied uniform cutting method and carries out cutting and identification to image, and in
The text or character of English mixing, then recognition effect is poor, and recognition accuracy is low, in the present embodiment, by utilizing front and back to count
Uniline feature text is cut in method progress, so that RIS character information can be obtained, accuracy is more compared with the prior art
It is high.Wherein, the method for front and back statistics is as based on kinds of characters, such as width shared by Chinese and each character (letter) of English
(character width feature) is different, is based on the character width feature, is cut, if it is determined that it is English, then it cuts spacing and is less than
The cutting spacing of Chinese, to be respectively cut to obtain RIS character information.Specifically, the uniline feature text can be calculated
Kind has how many English alphabet and Chinese character, calculates the spacing that can respectively obtain each Chinese and English character.
The step S40 " identifies the RIS character information, extracts the case in the RIS character information
Feature number " includes:
Step S41, using the convolutional neural networks model trained in advance by high frequency Chinese characters, to the RIS character information
OCR identification is carried out, the case feature number in the RIS character information is extracted.
It is above-mentioned, after obtaining RIS character information, by carrying out further light using convolutional neural networks (CNN) technology
It learns character recognition (OCR).
Optical identification is being carried out, when extracting the case feature number in RIS character information, may include steps of:
1, training data is made, including characters such as high frequency Chinese character, English alphabet, numbers, quantity can be 3000
It is a, training and in data include 45 kinds of different common fonts, also, increase man made noise, to enhance the extensive energy of model
Power;
2, CNN network is designed, convolutional neural networks model is as obtained by preparatory trained CNN network training;
3, using the model, RIS character information is identified, to extract case feature number therein.
Its network structure can be with are as follows: and [Conv2D- > relu- > MaxPool2D- > Dropout] * 2- > Flatten- >
Dense->Dropout->
Dense->Softmax。
In the present embodiment, using CNN nerual network technique, the screenshot of the operation interface of doctor is identified, if doctor
Include RIS character information in raw operation interface, then the RIS character information is known by CNN neural network model
Not, to extract case feature number therein, image recognition accuracy is high, and recognition efficiency is done, and recognition result is accurate.
Embodiment 4:
Referring to Fig. 5, fourth embodiment of the invention provides a kind of RIS platform with image assistant diagnostic system number of cases according to synchronous side
Method, is based on above-mentioned first embodiment shown in Fig. 2, and the step S50 " obtains the image according to the case feature number
Case data corresponding with the case feature number in assistant diagnosis system, and the case data are shown in the shadow
As in assistant diagnosis system " before, further includes:
Step S60 judges the case in the RIS character information gone out by the RIS platform real-time operation image zooming-out
Whether the number of feature number is greater than 1;
It is above-mentioned, it may be to be directed to a trouble when user (doctor) operate in the operating system of terminal
The case data of person are checked, are edited, can also be by comparing for case data corresponding to multiple and different patients
To, check and edit.At this point, multiple and different case feature numbers in image may be obtained if carrying out image acquisition,
If necessary to further respectively for different case feature numbers carry out based on image assistant diagnostic system automatically analyzing and
Diagnosis, then need to select the case feature number wherein identified, thus separately or concurrently carry out automatically analyzing and
Diagnosis.
In the present embodiment, for identifying that the quantity of the case feature number in obtained RIS character information judges,
Judge whether it is greater than 1, if it is greater than 1, then multiple-case occurs and compare state, if being equal to 1, single case diagnosis shape occur
State, if it is less than 1, then not retrieve case feature number therein.
Step S70, if so, determining that current state compares state for multiple-case, in the image assistant diagnostic system
The hyperlink corresponding relationship for establishing the case feature number and case data corresponding with the case feature number, according to institute
It states hyperlink corresponding relationship and generates a hyperlink inventory interface comprising each case feature number, in order to based on described
Hyperlink corresponding relationship is diagnosed according to the case feature number in the hyperlink inventory interface in the Image-aided
The case data corresponding with the case feature number selected are shown in system;
Step S80, if it is not, then determine current state for single case diagnosis state, it is described " according to the disease in order to execute
Example feature number obtains the case data corresponding with the case feature number in the image assistant diagnostic system ".
It is above-mentioned, when multiple-case compares state, in image assistant diagnostic system, construct obtained case feature number
With the hyperlink corresponding relationship of corresponding case data, and a hyperlink inventory interface is constructed, may include having in interface
All case feature numbers identified are then selected when doctor, which needs to number case therein, to be analyzed and diagnosed
The case feature number, then image assistant diagnostic system calls corresponding case data by hyperlink corresponding relationship, goes forward side by side one
Step analyzes and diagnoses the case data.
In addition it is also possible in the interface, equipped with carry out simultaneously the button that each case feature number is transferred or
Option, such setting can be transferred simultaneously for the corresponding case data of all case feature numbers in interface, thus real
It is now compared simultaneously for all corresponding case data and carries out automatically analyzing based on AI simultaneously and diagnose.
In the present embodiment, it is contemplated that the real work situation of doctor, the intersection that often there are more patient's multiple-cases compare feelings
Condition, so the case where there are the case feature numbers of multiple and different patients in the operation interface of current RIS is certainly existed,
If there is above situation, then all case feature numbers are identified, and construct and facilitate intuitive hyperlink, so as to facilitate doctor
It is raw to carry out a key further intellectual analysis is carried out for acquisition of the case data in image assistant diagnostic system and a key
And diagnosis is doctor for different patients' to analyze work for the clinical diagnosis of doctor, data and provide convenience significantly
Compare analysis provide convenience, improve the working efficiency of diagnostic analysis, realize more most patients according to pathological characters number
Synchronization.
In addition, the present invention also provides a kind of RIS platforms and image assistant diagnostic system example data synchronization unit, comprising: obtain
Modulus block 10, extraction module 20, locating module 30 and display module 40;
The acquisition module 10, for obtaining the RIS platform real-time operation image of operation interface;
The extraction module 20, for extracting the RIS character features information in the RIS platform real-time operation image;
The locating module 30, for being gone out in the real-time operation image according to the RIS character features Information locating
RIS character information;
The extraction module 20 is also used to identify the RIS character information, extracts the RIS character information
In case feature number;
The display module 40 is also used to be obtained in the image assistant diagnostic system according to the case feature number
Case data corresponding with the case feature number, and the case data are shown in the image assistant diagnostic system
In.
In addition, the present invention also provides a kind of user terminal, including memory and processor, the memory is for storing
According to synchronization program, the processor runs the RIS platform and examines with Image-aided for RIS platform and image assistant diagnostic system number of cases
Disconnected system number of cases is according to synchronization program so that the user terminal executes RIS platform as described above and image assistant diagnostic system example
Method of data synchronization.
In addition, being stored on the computer readable storage medium the present invention also provides a kind of computer readable storage medium
There are RIS platform and image assistant diagnostic system number of cases according to synchronization program, the RIS platform and image assistant diagnostic system number of cases evidence
RIS platform as described above and image assistant diagnostic system example method of data synchronization are realized when synchronization program is executed by processor.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (9)
1. a kind of RIS platform and image assistant diagnostic system example method of data synchronization, are applied to RIS platform and Image-aided diagnoses
Between system characterized by comprising
Obtain the RIS platform real-time operation image of operation interface;
Extract the RIS character features information in the RIS platform real-time operation image;
Go out the RIS character information in the real-time operation image according to the RIS character features Information locating;
The RIS character information is identified, the case feature number in the RIS character information is extracted;
It is obtained according to the case feature number corresponding with the case feature number in the image assistant diagnostic system
Case data, and the case data are shown in the image assistant diagnostic system.
2. RIS platform as described in claim 1 and image assistant diagnostic system example method of data synchronization, which is characterized in that described
" the RIS platform real-time operation image for obtaining operation interface " includes:
Obtain the operation screenshot image of operation interface;
Extract the characteristics of image in the operation screenshot image;
Described image feature is identified based on default RIS interface feature database;
It is if in described image feature including RIS interface feature, the operation screenshot image is real-time as the RIS platform
Operate image.
3. RIS platform as described in claim 1 and image assistant diagnostic system example method of data synchronization, which is characterized in that described
" extracting the RIS character features information in the RIS platform real-time operation image " includes:
The processing of image grayscale hierarchical cluster is carried out to the RIS platform real-time operation image, obtains hierarchical cluster image;
The hierarchical cluster image is handled by preprocess method, obtains the RIS character features information;Wherein,
The preprocess method includes figure detection of connectivity, resistance to corrosion detection, pondization operation and mean filter denoising.
4. RIS platform as described in claim 1 and image assistant diagnostic system example method of data synchronization, which is characterized in that described
" the RIS character information gone out in the real-time operation image according to the RIS character features Information locating " includes:
The real-time operation image is expanded by proximity search algorithm, obtains into word expansion area;
Extract it is each at word expansion area at word feature, and according to it is described at word feature will it is described at word expansion area carry out it is whole
It closes, obtains uniline feature text;
Based on character width feature, the uniline feature text is cut, RIS character information is obtained.
5. RIS platform as described in claim 1 and image assistant diagnostic system example method of data synchronization, which is characterized in that described
" identifying to the RIS character information, extract the case feature number in the RIS character information " includes:
Using the convolutional neural networks model trained in advance by high frequency Chinese characters, OCR identification is carried out to the RIS character information,
Extract the case feature number in the RIS character information.
6. RIS platform as described in claim 1 and image assistant diagnostic system example method of data synchronization, which is characterized in that described
" case corresponding with the case feature number in the image assistant diagnostic system is obtained according to the case feature number
Data, and the case data are shown in the image assistant diagnostic system " before, further includes:
Judge of the case feature number in the RIS character information gone out by the RIS platform real-time operation image zooming-out
Whether number is greater than 1;
If so, determining that current state compares state for multiple-case, the case is established in the image assistant diagnostic system
The hyperlink corresponding relationship of feature number and case data corresponding with the case feature number, it is corresponding according to the hyperlink
Relationship generates a hyperlink inventory interface comprising each case feature number, in order to based on the corresponding pass of the hyperlink
System, according to the case feature number in the hyperlink inventory interface, in the image assistant diagnostic system display with
The corresponding case data of the case feature number selected;
If it is not, then determining current state for single case diagnosis state, in order to execute described " obtain according to the case feature number
Take the case data corresponding with the case feature number in the image assistant diagnostic system ".
7. a kind of RIS platform and image assistant diagnostic system example data synchronization unit characterized by comprising obtain module, mention
Modulus block, locating module and display module;
The acquisition module, for obtaining the RIS platform real-time operation image of operation interface;
The extraction module, for extracting the RIS character features information in the RIS platform real-time operation image;
The locating module, for going out the RIS character in the real-time operation image according to the RIS character features Information locating
Information;
The extraction module is also used to identify the RIS character information, extracts the disease in the RIS character information
Example feature number;
The display module, be also used to be obtained according to the case feature number in the image assistant diagnostic system with it is described
The corresponding case data of case feature number, and the case data are shown in the image assistant diagnostic system.
8. a kind of user terminal, which is characterized in that including memory and processor, the memory is for storing RIS platform
With image assistant diagnostic system number of cases according to synchronization program, the processor runs the RIS platform and image assistant diagnostic system
Number of cases is according to synchronization program so that the user terminal executes RIS platform and Image-aided as described in any one of claim 1-6
Diagnostic system example method of data synchronization.
9. a kind of computer readable storage medium, which is characterized in that be stored with RIS platform on the computer readable storage medium
With image assistant diagnostic system number of cases according to synchronization program, the RIS platform and image assistant diagnostic system number of cases are according to synchronization program
Realize that RIS platform and image assistant diagnostic system number of cases are according to same as described in any one of claim 1-6 when being executed by processor
One step process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811271360.XA CN109461494A (en) | 2018-10-29 | 2018-10-29 | A kind of RIS platform and image assistant diagnostic system example method of data synchronization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811271360.XA CN109461494A (en) | 2018-10-29 | 2018-10-29 | A kind of RIS platform and image assistant diagnostic system example method of data synchronization |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109461494A true CN109461494A (en) | 2019-03-12 |
Family
ID=65608708
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811271360.XA Pending CN109461494A (en) | 2018-10-29 | 2018-10-29 | A kind of RIS platform and image assistant diagnostic system example method of data synchronization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109461494A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110147791A (en) * | 2019-05-20 | 2019-08-20 | 上海联影医疗科技有限公司 | Character recognition method, device, equipment and storage medium |
CN110473621A (en) * | 2019-07-24 | 2019-11-19 | 上海联影智能医疗科技有限公司 | Diagnostic data display methods, computer equipment and storage medium |
CN110910991A (en) * | 2019-11-21 | 2020-03-24 | 张军 | Medical automatic image processing system |
CN111292837A (en) * | 2020-01-13 | 2020-06-16 | 上海杏脉信息科技有限公司 | Medical image auxiliary diagnosis system and triggering method, device, medium and equipment thereof |
CN111681739A (en) * | 2020-06-15 | 2020-09-18 | 杭州依图医疗技术有限公司 | Pathological information display method and computer-readable storage medium |
CN112992334A (en) * | 2020-12-14 | 2021-06-18 | 中国科学院大学宁波生命与健康产业研究院 | Femoral head necrosis auxiliary diagnosis system based on artificial intelligence |
CN113407841A (en) * | 2021-06-25 | 2021-09-17 | 陈亮 | Method and system for automatically recommending AI (artificial intelligence) scheme based on performance analysis of structured report |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060236247A1 (en) * | 2005-04-15 | 2006-10-19 | General Electric Company | Interface to display contextual patient information via communication/collaboration application |
CN102883660A (en) * | 2010-09-20 | 2013-01-16 | 德克萨斯州大学系统董事会 | Advanced multimedia structured reporting |
CN105264568A (en) * | 2013-04-04 | 2016-01-20 | 日本电气株式会社 | Identification system, identification method, matching device, and program |
CN106529115A (en) * | 2015-09-09 | 2017-03-22 | 佳能株式会社 | Information processing device, information processing method, and information processing system |
CN107341331A (en) * | 2016-11-18 | 2017-11-10 | 张益群 | A kind of medical information processing system and medical information processing method |
-
2018
- 2018-10-29 CN CN201811271360.XA patent/CN109461494A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060236247A1 (en) * | 2005-04-15 | 2006-10-19 | General Electric Company | Interface to display contextual patient information via communication/collaboration application |
CN102883660A (en) * | 2010-09-20 | 2013-01-16 | 德克萨斯州大学系统董事会 | Advanced multimedia structured reporting |
CN105264568A (en) * | 2013-04-04 | 2016-01-20 | 日本电气株式会社 | Identification system, identification method, matching device, and program |
CN106529115A (en) * | 2015-09-09 | 2017-03-22 | 佳能株式会社 | Information processing device, information processing method, and information processing system |
CN107341331A (en) * | 2016-11-18 | 2017-11-10 | 张益群 | A kind of medical information processing system and medical information processing method |
Non-Patent Citations (1)
Title |
---|
何东健: "《数字图像处理》", 28 February 2015 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110147791A (en) * | 2019-05-20 | 2019-08-20 | 上海联影医疗科技有限公司 | Character recognition method, device, equipment and storage medium |
CN110473621A (en) * | 2019-07-24 | 2019-11-19 | 上海联影智能医疗科技有限公司 | Diagnostic data display methods, computer equipment and storage medium |
CN110473621B (en) * | 2019-07-24 | 2022-12-20 | 上海联影智能医疗科技有限公司 | Diagnostic data display method, computer device, and storage medium |
CN110910991A (en) * | 2019-11-21 | 2020-03-24 | 张军 | Medical automatic image processing system |
CN111292837A (en) * | 2020-01-13 | 2020-06-16 | 上海杏脉信息科技有限公司 | Medical image auxiliary diagnosis system and triggering method, device, medium and equipment thereof |
CN111681739A (en) * | 2020-06-15 | 2020-09-18 | 杭州依图医疗技术有限公司 | Pathological information display method and computer-readable storage medium |
CN112992334A (en) * | 2020-12-14 | 2021-06-18 | 中国科学院大学宁波生命与健康产业研究院 | Femoral head necrosis auxiliary diagnosis system based on artificial intelligence |
CN113407841A (en) * | 2021-06-25 | 2021-09-17 | 陈亮 | Method and system for automatically recommending AI (artificial intelligence) scheme based on performance analysis of structured report |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109461494A (en) | A kind of RIS platform and image assistant diagnostic system example method of data synchronization | |
Nichols et al. | Machine learning: applications of artificial intelligence to imaging and diagnosis | |
CN112329964B (en) | Method, device, equipment and storage medium for pushing information | |
CN113892148A (en) | Interpretable AI (xAI) platform for computational pathology | |
CN104298983B (en) | Tongue fur image with distributed user terminal obtains and analysis system | |
Liu et al. | A framework of wound segmentation based on deep convolutional networks | |
CN111932482A (en) | Method and device for detecting target object in image, electronic equipment and storage medium | |
CN111445440B (en) | Medical image analysis method, device and storage medium | |
US11967181B2 (en) | Method and device for retinal image recognition, electronic equipment, and storage medium | |
CN110767283B (en) | Mental disease imaging automatic reporting system and method thereof | |
CN112507701A (en) | Method, device, equipment and storage medium for identifying medical data to be corrected | |
WO2020118152A1 (en) | Heat map based medical image diagnostic mechanism | |
WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
CN112334070A (en) | Medical image processing apparatus and method, machine learning system, program, and storage medium | |
CN110489577B (en) | Medical image management method and device, fundus image processing method and electronic equipment | |
CN113744845A (en) | Medical image processing method, device, equipment and medium based on artificial intelligence | |
CN117237351A (en) | Ultrasonic image analysis method and related device | |
CN112614570A (en) | Sample set labeling method, pathological image classification method and classification model construction method and device | |
CN113792740B (en) | Artery and vein segmentation method, system, equipment and medium for fundus color illumination | |
Amruthalingam et al. | Objective hand eczema severity assessment with automated lesion anatomical stratification | |
CN114020926A (en) | Data processing method and device and electronic equipment | |
CN113808731A (en) | Intelligent medical diagnosis system and method | |
CN111915615A (en) | Image segmentation method and device, electronic equipment and computer readable storage medium | |
CN110889836A (en) | Image data analysis method and device, terminal equipment and storage medium | |
CN115578370B (en) | Brain image-based metabolic region abnormality detection method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |