CN109446370A - Pathology mask method and device, the computer readable storage medium of medical image - Google Patents
Pathology mask method and device, the computer readable storage medium of medical image Download PDFInfo
- Publication number
- CN109446370A CN109446370A CN201811260198.1A CN201811260198A CN109446370A CN 109446370 A CN109446370 A CN 109446370A CN 201811260198 A CN201811260198 A CN 201811260198A CN 109446370 A CN109446370 A CN 109446370A
- Authority
- CN
- China
- Prior art keywords
- medical image
- annotation results
- user
- pathology
- users
- 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
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
Abstract
The pathology mask method of medical image disclosed by the embodiments of the present invention, by when receive any user the mobile terminal input into dimension model request when, determine the user whether have pathology mark qualification；When judging the user in pathology mark qualification, random call medical image to be marked is simultaneously shown in the display interface of the mobile terminal；The user is received to the first annotation results of the medical image, and the user is saved to the first annotation results of the medical image, it can be under the premise of guaranteeing to mark quality, so that mark worker can whenever and wherever possible be labeled medical image, job site is unrestricted, the efficiency of mark work can be greatly improved, provides quality height and quantity learning sample abundant for artificial intelligence.
Description
Technical field
The present invention relates to intelligent medical field more particularly to the pathology mask methods and device of a kind of medical image, calculating
Machine readable storage medium storing program for executing.
Background technique
Before machine learning is used for medical image analysis, the labeled data of a large amount of high quality is needed.How to ensure to mark matter
How the reliability and doctor for measuring result under artificial intelligence auxiliary sign and issue medical report, are all the following artificial intelligence applications in facing
It to be faced and be solved the problems, such as in bed practice.Also lack systematicness in terms of the accuracy of continuous verifying and debugging artificial intelligence
Method.By artificial intelligence assistant diagnosis system in scientific research, landing is into clinical treatment practice, it is ensured that diagnostic result can
By property and accuracy, need to have good workflow between doctor and artificial intelligence.It was found that artificial intelligence now it is existing or
When the problem of person will be likely encountered in future, there is the related mechanism for constantly learning and adjusting.
Artificial intelligence is typically chosen full sheet globality mark, the big mark to medium FOV picture, then when marking early period
It can only work on the computer of large capacity, place is limited, cannot achieve the mark work of a large amount of medical images, then can not be people
Work intelligently provides learning sample.
Summary of the invention
The embodiment of the present invention provides the pathology mask method and device, computer readable storage medium of a kind of medical image,
It can effectively solve the limited problem in existing artificial mark job site, improve the efficiency of mark work, provided for artificial intelligence
Quality height and quantity learning sample abundant.
One embodiment of the invention provides a kind of pathology mask method of medical image, comprising steps of
When receive any user the mobile terminal input into dimension model request when, determine the user
Whether there is pathology to mark qualification；
When judging that the user has in pathology mark qualification, random call medical image to be marked and in the movement
The display interface of terminal is shown；
The user is received to the first annotation results of the medical image, and saves the user to the medical image
The first annotation results.
Compared with prior art, the pathology mask method of medical image disclosed by the embodiments of the present invention is received by working as
Any user the mobile terminal input into dimension model request when, determine whether the user has pathology mark
Qualification；When judging the user in pathology mark qualification, random call medical image to be marked is simultaneously described mobile whole
The display interface at end is shown；The user is received to the first annotation results of the medical image, and saves the user
To the first annotation results of the medical image, can under the premise of guaranteeing to mark quality so that mark worker can at any time with
Ground is labeled medical image, and job site is unrestricted, can greatly improve the efficiency of mark work, provide for artificial intelligence
Quality height and quantity learning sample abundant.
As an improvement of the above scheme, the method also includes steps:
When detecting the first annotation results of user there are two any medical image tools, described two users are judged
The first annotation results it is whether consistent；
When the first annotation results for judging described two users are consistent, made with the first annotation results of described two users
Correct mark number for the reference annotation results of the medical image, and respectively two users adds 1.
As an improvement of the above scheme, the method also includes steps:
When the first annotation results for judging described two users are inconsistent, at random to any other users or expert user
Send the mark request of the medical image；
As an improvement of the above scheme, the method also includes steps:
When the first annotation results for judging described two users are inconsistent, at random to any other users or expert user
Send the mark request of the medical image；
It is when receiving the second annotation results of the other users or expert user to the medical image, this is described
The reference annotation results of other users or expert user to the second annotation results of the medical image as the medical image,
And the error label number of first annotation results and the inconsistent user of second annotation results are added 1, by described first
The correct mark number of the annotation results user consistent with second annotation results adds 1.
As an improvement of the above scheme, the method also includes steps:
When the error label number for detecting any user is greater than preset first threshold, cancel the pathology mark of the user
Register capital to lattice.
As an improvement of the above scheme, the method also includes steps:
It, will when receiving the request of the other users or expert user to medical image addition intractable case library
Intractable case library is added in the medical image.
As an improvement of the above scheme, the method also includes steps:
When showing the medical image, the AI annotation results of the medical image are obtained；Wherein, the medical image
AI annotation results include positive findings and negative findings；
When the AI annotation results of the medical image are negative findings, and any user is to the first of the medical image
When annotation results are consistent with the AI annotation results of the medical image, using the AI annotation results of the medical image as the doctor
Learn the reference annotation results of image；
When the AI annotation results of the medical image are positive findings, and any two users are to the of the medical image
When one annotation results are consistent with the AI annotation results of the medical image, using the AI annotation results of the medical image described in
The reference annotation results of medical image；
When the AI annotation results of the medical image are positive findings, and any two users are to the of the medical image
When one annotation results and the inconsistent AI annotation results of the medical image, with any two described users to the medical image
Reference annotation results of first annotation results as the medical image；
When the AI annotation results of the medical image be positive findings when, and in any two users one of user to institute
When the AI annotation results of the first annotation results and the medical image of stating medical image are inconsistent, at random to any other users
Or expert user sends the mark request of the medical image or the request that organizes a discussion；
It is when receiving the second annotation results of the other users or expert user to the medical image, this is described
The reference annotation results of other users or expert user to the second annotation results of the medical image as the medical image；
When receiving any two described users and other users or expert user after discussing to the medical image
When third annotation results, using the third annotation results as the reference annotation results of the medical image.
As an improvement of the above scheme, the medical image is generated by following steps:
After being divided into n small pictures to the original scan image of pathological section, calculate each described in the n small pictures
The pathology index of small picture；Wherein, 10^10 >=n >=10；
The pathology index of each small picture in the n small pictures obtains in the n small pictures pathology index most
Preceding m high small pictures are as the medical image；Wherein, 50 >=m >=5.
Another embodiment of the present invention correspondence provides a kind of pathology annotation equipment of medical image, comprising:
Pathology mark qualification obtain module, for when receive any user the mobile terminal input enter mark
When the request of mode, determine whether the user there is pathology to mark qualification；
Medical image display module, for when judging the user in pathology mark qualification, random call to be to be marked
Medical image and shown in the display interface of the mobile terminal；
First annotation results preserving module, for receiving the user to the first annotation results of the medical image, and
The user is saved to the first annotation results of the medical image.
Another embodiment of the present invention provides a kind of pathology annotation equipment of medical image, including processor, memory with
And the computer program executed by the processor is stored in the memory and is configured as, described in the processor execution
The pathology mask method of medical image described in any of the above-described inventive embodiments is realized when computer program.
Another embodiment of the present invention provides a kind of computer readable storage medium, the computer readable storage medium packet
Include the computer program of storage, wherein where controlling the computer readable storage medium in computer program operation
Equipment executes the pathology mask method of medical image described in any of the above-described inventive embodiments.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the pathology mask method for medical image that one embodiment of the invention provides.
Fig. 2 is the cutting schematic diagram of the original scan image for the pathological section that one embodiment of the invention provides.
Fig. 3 (a) is the unicellular small picture of cutting of cervical cytology, and Fig. 3 (b) is that cervical cytology cell mass cuts small figure
Piece.
Fig. 4 is the display interface schematic diagram for the mobile terminal that one embodiment of the invention provides.
Fig. 5 be another embodiment of the present invention provides mobile terminal display interface schematic diagram.
Fig. 6 is a kind of structural schematic diagram of the pathology annotation equipment for medical image that one embodiment of the invention provides.
Fig. 7 is the structural schematic diagram of the pathology annotation equipment of medical image provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It is a kind of flow diagram of the pathology mask method for medical image that one embodiment of the invention provides referring to Fig. 1,
It is used in a mobile terminal, comprising steps of
S1, when receive any user the mobile terminal input into dimension model request when, described in judgement
Whether user there is pathology to mark qualification；
In step sl, user need to can just authorize the mark qualification of its pathology by special test, such as need random call s
The medical image for testing the user is opened, obtains the user to the annotation results of each medical image, it will be described
The annotation results of each medical image are compared with the correct annotation results by user, obtain the user to described
There is for s (s >=10) the mark accuracy of the medical image of correct labeling result, preset when judging that the mark accuracy is greater than
First threshold when, it is determined that the user have pathology mark qualification.Mark worker is sieved by unified test
Choosing, it is ensured that higher medical level marks the consistency and stability of quality, can guarantee to mark quality, can obtain visitor
The scientific evaluation index for the property seen is conducive to subsequent machine learning model and constructs.
S2, when judging that the user has in pathology mark qualification, random call medical image to be marked and described
The display interface of mobile terminal is shown；
In step sl, it is preferable that the medical image generates in the following manner:
Firstly, as shown in Fig. 2, calculating the n after being divided into n small pictures to the original scan image of pathological section
The pathology index of each small picture in small picture；Wherein, 10^10 >=n >=10；
Then, in the n small pictures each small picture pathology index, obtain pathology in the n small pictures
Highest preceding m small pictures of index are logical as the medical image；Wherein, 50 >=m >=5.
The pathology index of each small picture is completed by artificial intelligence in the above-mentioned calculating n small pictures, such as logical
Crossing artificial intelligence preferential screening and sequencing can be presented 20 images from great amount of images, and the workload of doctor can be greatly lowered.
In general, original scan image is by converting X400 by digital slices scanner for cell pathology slide
Digital picture again, size can reach several G to tens G.If mark worker is worked by being labeled to full sheet
Amount is very big, and can only work on the computer of large capacity, and place is limited, and therefore, there are spill tags for original mark work
Note, the problems such as annotation step is cumbersome and workload is huge.Therefore, after by cutting original digital image, can make to mark
Worker can be labeled whenever and wherever possible, and the image after cutting is not necessarily to load in the computer of large capacity, reduce mark work
The workload of author.It is the unicellular small picture of cutting of cervical cytology as shown in Fig. 3 (a), it is thin for uterine neck as shown in Fig. 3 (b)
Born of the same parents learn cell mass and cut small picture.
It is downloaded under different receiving platforms on the internet in addition, small picture can be convenient, it can be convenient for quick beyond the clouds
It is responsive in mobile end equipment, realizes quickly operation, to complete the process of mark.Therefore, mark worker can be in the leisure
Free time (for example, by bus, wait vehicles process) carry out test mark using mobile terminal (for example, mobile phone etc.), can also be
Family or office are labeled using general PC, synchronism can be operated on different devices, be considerably increased convenience, maximum
The scrappy time operation of time utilization user.
S3, the user is received to the first annotation results of the medical image, and save the user to the medicine
First annotation results of image.
For example, as shown in figure 4, on the display interface of the mobile terminal, other than showing medical image, also in the medicine figure
As surrounding shows the first option button for whether having malignant cell and malignant cell type (including ASC, LSIL, AGC, HSIL
Deng), when receiving selection operation of the user to any first option button, the operation note is saved, and go to automatically next
Open medical image.
In a preferred embodiment, when detecting any medical image tool, there are two the first annotation results of user
When, judge whether the first annotation results of described two users are consistent；
When the first annotation results for judging described two users are consistent, made with the first annotation results of described two users
Correct mark number for the reference annotation results of the medical image, and respectively two users adds 1；
When the first annotation results for judging described two users are inconsistent, at random to any other users or expert user
Send the mark request of the medical image；
It is when receiving the second annotation results of the other users or expert user to the medical image, this is described
The reference annotation results of other users or expert user to the second annotation results of the medical image as the medical image,
And the error label number of first annotation results and the inconsistent user of second annotation results are added 1, by described first
The correct mark number of the annotation results user consistent with second annotation results adds 1.
Two different labeled persons are randomly assigned for same medical image by above scheme, same case is carried out
Line assessment mark, double review systems, also avoid because artificial intelligence in design existing for Systematic Errors, it is ensured that mark
Reliability and accuracy.
In addition, cancelling the user's when the error label number for detecting any user is greater than preset first threshold
Pathology marks qualification.Work supervision mechanism and eliminative mechanism is added, avoids due to personal random operation and diagnosis capability not
Foot loophole that may be present.When the correct mark number for detecting any user is greater than preset second threshold, which is added
Enter in professional mark worker library；When the accurate mark number for detecting any user is greater than preset third threshold value, and judge
When the user has medical practitioner's card, authorizes it and sign and issue report qualification.In addition, can also show correct mark number in display interface
User's ranking.By the above incentives strategy, be conducive to the efficiency for improving user annotation, realize a large amount of medical image mark.
In addition to requesting his user or expert user to be labeled the medical image, also more expert discussions can be organized to reach
At common recognition.In addition, when receiving the request of the other users or expert user to medical image addition intractable case library
When, intractable case library is added as the research of atypia case in the medical image and is used.
In another concrete application, as shown in figure 5, on the display interface of the mobile terminal, other than showing medical picture,
Artificial annotation results early period or machine annotation results are also shown, while whether display agrees to other users or machine to described
The second option button (" YES " and " NO " button i.e. in figure) of the annotation results of FOV picture correctly clicks YES, saves simultaneously
Into next.Mistake clicks NO, re-enters new annotation results.By way of this review, correction mistake is improved
Agility, to greatest extent reduce people operation complexity.
And in another embodiment, the method also includes steps:
When showing the medical image, the AI annotation results of the medical image are obtained；Wherein, the medical image
AI annotation results include positive findings and negative findings；
When the AI annotation results of the medical image are negative findings, and any user is to the first of the medical image
When annotation results are consistent with the AI annotation results of the medical image, using the AI annotation results of the medical image as the doctor
Learn the reference annotation results of image；
When the AI annotation results of the medical image are positive findings, and any two users are to the of the medical image
When one annotation results are consistent with the AI annotation results of the medical image, using the AI annotation results of the medical image described in
The reference annotation results of medical image；
When the AI annotation results of the medical image are positive findings, and any two users are to the of the medical image
When one annotation results and the inconsistent AI annotation results of the medical image, with any two described users to the medical image
Reference annotation results of first annotation results as the medical image；
When the AI annotation results of the medical image be positive findings when, and in any two users one of user to institute
When the AI annotation results of the first annotation results and the medical image of stating medical image are inconsistent, at random to any other users
Or expert user sends the mark request of the medical image or the request that organizes a discussion；
It is when receiving the second annotation results of the other users or expert user to the medical image, this is described
The reference annotation results of other users or expert user to the second annotation results of the medical image as the medical image；
When receiving any two described users and other users or expert user after discussing to the medical image
When third annotation results, using the third annotation results as the reference annotation results of the medical image.
It to sum up, can be under the premise of guaranteeing to mark quality, so that mark worker can be with by implementing the solution of the present invention
When medical image is labeled everywhere, job site is unrestricted, improves inefficient operating mode, hence it is evident that promoted medical treatment clothes
Quality of being engaged in and curative activity efficiency provide quality height and quantity learning sample abundant for artificial intelligence.In addition to this, for every
One user, the medical image got are random, and for each medical image, the user distributed to be also it is random,
Objectifying in medicine natural image interpretation is being realized to the greatest extent, and the diagnosis and treatment for reducing different regions and Different hospital are poor
The opposite sex ensure that more patients are benefited, more Medical Equities.
It is a kind of structural schematic diagram of the pathology annotation equipment of medical image provided in an embodiment of the present invention, packet referring to Fig. 6
It includes:
Pathology marks qualification and obtains module 101, for working as the entrance for receiving any user and inputting in the mobile terminal
When the request of dimension model, determine whether the user there is pathology to mark qualification；
Medical image display module 102, for when judging the user in pathology mark qualification, random call to wait marking
The medical image of note is simultaneously shown in the display interface of the mobile terminal；
First annotation results preserving module 103, for receiving the user to the first annotation results of the medical image,
And the user is saved to the first annotation results of the medical image.
The implementation process and working principle of the pathology annotation equipment of the medical image of the embodiment of the present invention can refer to above-mentioned
The description of one pathology mask method to medical image, details are not described herein.
Another embodiment of the present invention provides a kind of pathology annotation equipment of medical image, including processor, memory with
And the computer program executed by the processor is stored in the memory and is configured as, described in the processor execution
The pathology mask method of medical image described in any of the above-described inventive embodiments is realized when computer program.
Another embodiment of the present invention provides a kind of computer readable storage medium, the computer readable storage medium packet
Include the computer program of storage, wherein where controlling the computer readable storage medium in computer program operation
Equipment executes the pathology mask method of medical image described in any of the above-described inventive embodiments.
It is the schematic diagram of the pathology annotation equipment of medical image provided in an embodiment of the present invention referring to Fig. 7.The medicine figure
The pathology annotation equipment of picture includes: at least one processor 11, such as CPU, at least one network interface 14 or other users
Interface 13, memory 15, at least one communication bus 12, communication bus 12 is for realizing the connection communication between these components.
Wherein, user interface 13 optionally may include USB interface and other standards interface, wireline interface.Network interface 14 is optional
May include Wi-Fi interface and other wireless interfaces.Memory 15 may include high speed RAM memory, it is also possible to also wrap
It includes non-labile memory (non-volatilememory), for example, at least a magnetic disk storage.Memory 15 is optional
It may include at least one storage device for being located remotely from aforementioned processor 11.
In some embodiments, memory 15 stores following element, executable modules or data structures, or
Their subset or their superset:
Operating system 151 includes various system programs, such as battery management system, for realizing various basic businesses
And the hardware based task of processing；
Program 152.
Specifically, processor 11 executes medicine described in above-described embodiment for calling the program 152 stored in memory 15
The pathology mask method of image, such as step S11 shown in FIG. 1.Alternatively, when the processor 11 executes the computer program
Realize the function of each module/unit in above-mentioned each Installation practice, such as medical image display module 102.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor, to complete the present invention.It is one or more
A module/unit can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing institute
State implementation procedure of the computer program in the pathology annotation equipment of the medical image.
The pathology annotation equipment of the medical image may include, but be not limited only to, processor 11, memory 15.This field
Technical staff is appreciated that the schematic diagram is only the example of the pathology annotation equipment of medical image, does not constitute to medicine
The restriction of the pathology annotation equipment of image, may include than illustrating more or fewer components, perhaps combine certain components or
Different components, for example, the medical image pathology annotation equipment can also include input-output equipment, network access equipment,
Bus etc..
Alleged processor 11 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor 11 is the control centre of the pathology annotation equipment of the medical image, utilizes various interfaces and connection
The various pieces of the pathology annotation equipment of entire medical image.
The memory 15 can be used for storing the computer program and/or module, the processor 11 by operation or
Computer program and/or the module stored in the memory is executed, and calls the data being stored in memory, is realized
The various functions of the pathology annotation equipment of the medical image.The memory 15 can mainly include storing program area and storage number
According to area, wherein storing program area can application program needed for storage program area, at least one function (for example sound plays function
Energy, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such as audio data,
Phone directory etc.) etc..In addition, memory 15 may include high-speed random access memory, it can also include nonvolatile memory,
Such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid
State memory device.
Wherein, if the integrated module/unit of the pathology annotation equipment of the medical image is with the shape of SFU software functional unit
Formula realize and when sold or used as an independent product, can store in a computer readable storage medium.It is based on
Such understanding, the present invention realize above-described embodiment method in all or part of the process, can also by computer program come
Relevant hardware is instructed to complete, the computer program can be stored in a computer readable storage medium, the computer
Program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes meter
Calculation machine program code, the computer program code can be source code form, object identification code form, executable file or certain
Intermediate form etc..The computer-readable medium may include: can carry the computer program code any entity or
Device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software
Distribution medium etc..It should be noted that the content that the computer-readable medium includes can be according to making laws in jurisdiction
Requirement with patent practice carries out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, computer
Readable medium does not include electric carrier signal and telecommunication signal.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (11)
1. a kind of pathology mask method of medical image, which is characterized in that it is suitable for a mobile terminal, comprising steps of
When receive any user the mobile terminal input into dimension model request when, whether determine the user
Qualification is marked with pathology；
When judging that the user has in pathology mark qualification, random call medical image to be marked and in the mobile terminal
Display interface shown；
The user is received to the first annotation results of the medical image, and saves the user to the of the medical image
One annotation results.
2. the pathology mask method of medical image as described in claim 1, which is characterized in that the method also includes steps:
When detecting any medical image tool, there are two when the first annotation results of user, judge the of described two users
Whether one annotation results are consistent；
When the first annotation results for judging described two users are consistent, using the first annotation results of described two users as institute
The reference annotation results of medical image are stated, and the correct mark number of respectively two users adds 1.
3. the pathology mask method of medical image as claimed in claim 2, which is characterized in that the method also includes steps:
When the first annotation results for judging described two users are inconsistent, sent at random to any other users or expert user
The mark of the medical image is requested；
When receiving the second annotation results of the other users or expert user to the medical image, by this it is described other
The reference annotation results of user or expert user to the second annotation results of the medical image as the medical image, and will
The error label number of first annotation results and the inconsistent user of second annotation results add 1, and described first is marked
As a result the correct mark number of the user consistent with second annotation results adds 1.
4. the pathology mask method of medical image as claimed in claim 3, which is characterized in that the method also includes steps:
When the error label number for detecting any user is greater than preset first threshold, cancel the pathology mark money of the user
Lattice.
5. the pathology mask method of medical image as claimed in claim 3, which is characterized in that the method also includes steps:
It, will be described when receiving the request of the other users or expert user to medical image addition intractable case library
Intractable case library is added in medical image.
6. the pathology mask method of medical image as described in claim 1, which is characterized in that the method also includes steps:
When showing the medical image, the AI annotation results of the medical image are obtained；Wherein, the AI mark of the medical image
Infusing result includes positive findings and negative findings；
When the AI annotation results of the medical image are negative findings, and any user is to the first mark of the medical image
As a result when consistent with the AI annotation results of the medical image, using the AI annotation results of the medical image as the medicine figure
The reference annotation results of picture；
When the AI annotation results of the medical image are positive findings, and any two users are to the first mark of the medical image
When note result is consistent with the AI annotation results of the medical image, using the AI annotation results of the medical image as the medicine
The reference annotation results of image；
When the AI annotation results of the medical image are positive findings, and any two users are to the first mark of the medical image
Infuse result and the medical image AI annotation results it is inconsistent when, with any two described users to the of the medical image
Reference annotation results of one annotation results as the medical image.
7. the pathology mask method of medical image as claimed in claim 6, which is characterized in that the method also includes steps:
When the AI annotation results of the medical image be positive findings when, and in any two users one of user to the doctor
When the AI annotation results of the first annotation results and the medical image of learning image are inconsistent, at random to any other users or specially
Family user sends the mark request of the medical image or the request that organizes a discussion；
When receiving the second annotation results of the other users or expert user to the medical image, by this it is described other
The reference annotation results of user or expert user to the second annotation results of the medical image as the medical image；
When receiving any two described users and other users or expert user after discussing to the third of the medical image
When annotation results, using the third annotation results as the reference annotation results of the medical image.
8. such as the pathology mask method of medical image of any of claims 1-7, which is characterized in that the medicine figure
As being generated by following steps:
After being divided into n small pictures to the original scan image of pathological section, each small figure in the n small pictures is calculated
The pathology index of piece；Wherein, 10^10 >=n >=10；
It is highest to obtain pathology index in the n small pictures for the pathology index of each small picture in the n small pictures
Preceding m small pictures are as the medical image；Wherein, 50 >=m >=5.
9. a kind of pathology annotation equipment of medical image, which is characterized in that be suitable for a mobile terminal, comprising:
Pathology marks qualification and obtains module, enters dimension model what the mobile terminal inputted for that ought receive any user
Request when, determine the user whether have pathology mark qualification；
Medical image display module judges that the user has in pathology mark qualification for working as, random call doctor to be marked
It learns image and is shown in the display interface of the mobile terminal；
First annotation results preserving module for receiving the user to the first annotation results of the medical image, and saves
First annotation results of the user to the medical image.
10. a kind of pathology annotation equipment of medical image, including processor, memory and storage in the memory and by
It is configured to the computer program executed by the processor, is realized when the processor executes the computer program as right is wanted
Seek the pathology mask method of medical image described in any one of 1-8.
11. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed
Benefit require any one of 1 to 8 described in medical image pathology mask method.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811260198.1A CN109446370A (en) | 2018-10-26 | 2018-10-26 | Pathology mask method and device, the computer readable storage medium of medical image |
| US16/628,683 US11094411B2 (en) | 2018-10-26 | 2019-01-28 | Methods and devices for pathologically labeling medical images, methods and devices for issuing reports based on medical images, and computer-readable storage media |
| PCT/CN2019/073339 WO2020082638A1 (en) | 2018-10-26 | 2019-01-28 | Pathological annotation method and device for medical images, report issuing method and device based on medical images, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811260198.1A CN109446370A (en) | 2018-10-26 | 2018-10-26 | Pathology mask method and device, the computer readable storage medium of medical image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446370A true CN109446370A (en) | 2019-03-08 |
Family
ID=65548638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811260198.1A Pending CN109446370A (en) | 2018-10-26 | 2018-10-26 | Pathology mask method and device, the computer readable storage medium of medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446370A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335251A (en) * | 2019-05-31 | 2019-10-15 | 上海联影智能医疗科技有限公司 | Quantization device, method, equipment and the storage medium of image analysis method |
| CN111028924A (en) * | 2019-10-21 | 2020-04-17 | 西安电子科技大学 | Method and system for labeling medical image data in various forms |
| WO2020082638A1 (en) * | 2018-10-26 | 2020-04-30 | 广州金域医学检验中心有限公司 | Pathological annotation method and device for medical images, report issuing method and device based on medical images, and computer readable storage medium |
| CN111292839A (en) * | 2020-05-13 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN111326263A (en) * | 2020-02-03 | 2020-06-23 | 深圳安泰创新科技股份有限公司 | Method, device and equipment for displaying labeling track and computer readable storage medium |
| CN111739617A (en) * | 2020-06-15 | 2020-10-02 | 中国医学科学院医学信息研究所 | Medical image artificial intelligence quality control marking method, device, equipment and storage medium |
| CN112418263A (en) * | 2020-10-10 | 2021-02-26 | 上海鹰瞳医疗科技有限公司 | Medical image focus segmentation and labeling method and system |
| CN113113118A (en) * | 2021-03-31 | 2021-07-13 | 上海深至信息科技有限公司 | Remote film reading system and method |
| CN113469972A (en) * | 2021-06-30 | 2021-10-01 | 沈阳东软智能医疗科技研究院有限公司 | Method, device, storage medium and electronic equipment for labeling medical slice image |
| CN113689937A (en) * | 2021-07-07 | 2021-11-23 | 阿里巴巴新加坡控股有限公司 | Image annotation method, storage medium and processor |
| CN115801781A (en) * | 2023-01-11 | 2023-03-14 | 杭州广科安德生物科技有限公司 | Biological data collaborative analysis system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103926687A (en) * | 2013-01-16 | 2014-07-16 | 索尼公司 | Image Acquisition Apparatus, Image Acquisition Method, And Information Processing Program |
| CN104462738A (en) * | 2013-09-24 | 2015-03-25 | 西门子公司 | Method, device and system for labeling medical images |
| WO2017101142A1 (en) * | 2015-12-17 | 2017-06-22 | 安宁 | Medical image labelling method and system |
| CN107516005A (en) * | 2017-07-14 | 2017-12-26 | 上海交通大学 | A kind of method and system of digital pathological image mark |
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
-
2018
- 2018-10-26 CN CN201811260198.1A patent/CN109446370A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103926687A (en) * | 2013-01-16 | 2014-07-16 | 索尼公司 | Image Acquisition Apparatus, Image Acquisition Method, And Information Processing Program |
| CN104462738A (en) * | 2013-09-24 | 2015-03-25 | 西门子公司 | Method, device and system for labeling medical images |
| WO2017101142A1 (en) * | 2015-12-17 | 2017-06-22 | 安宁 | Medical image labelling method and system |
| CN108463814A (en) * | 2015-12-17 | 2018-08-28 | 北京安宁福祉科技有限公司 | A kind of medical image mask method and system |
| CN107516005A (en) * | 2017-07-14 | 2017-12-26 | 上海交通大学 | A kind of method and system of digital pathological image mark |
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020082638A1 (en) * | 2018-10-26 | 2020-04-30 | 广州金域医学检验中心有限公司 | Pathological annotation method and device for medical images, report issuing method and device based on medical images, and computer readable storage medium |
| CN110335251A (en) * | 2019-05-31 | 2019-10-15 | 上海联影智能医疗科技有限公司 | Quantization device, method, equipment and the storage medium of image analysis method |
| CN110335251B (en) * | 2019-05-31 | 2021-09-17 | 上海联影智能医疗科技有限公司 | Quantization apparatus, method, device and storage medium for image analysis method |
| CN111028924A (en) * | 2019-10-21 | 2020-04-17 | 西安电子科技大学 | Method and system for labeling medical image data in various forms |
| CN111326263A (en) * | 2020-02-03 | 2020-06-23 | 深圳安泰创新科技股份有限公司 | Method, device and equipment for displaying labeling track and computer readable storage medium |
| CN111326263B (en) * | 2020-02-03 | 2023-09-29 | 深圳安泰创新科技股份有限公司 | Labeling track display method, labeling track display device, labeling track display equipment and computer-readable storage medium |
| CN111292839A (en) * | 2020-05-13 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN111739617A (en) * | 2020-06-15 | 2020-10-02 | 中国医学科学院医学信息研究所 | Medical image artificial intelligence quality control marking method, device, equipment and storage medium |
| CN111739617B (en) * | 2020-06-15 | 2023-07-11 | 中国医学科学院医学信息研究所 | Medical image artificial intelligence quality control labeling method, device, equipment and storage medium |
| CN112418263A (en) * | 2020-10-10 | 2021-02-26 | 上海鹰瞳医疗科技有限公司 | Medical image focus segmentation and labeling method and system |
| CN113113118A (en) * | 2021-03-31 | 2021-07-13 | 上海深至信息科技有限公司 | Remote film reading system and method |
| CN113469972A (en) * | 2021-06-30 | 2021-10-01 | 沈阳东软智能医疗科技研究院有限公司 | Method, device, storage medium and electronic equipment for labeling medical slice image |
| CN113469972B (en) * | 2021-06-30 | 2024-04-23 | 沈阳东软智能医疗科技研究院有限公司 | Method and device for labeling medical slice image, storage medium and electronic equipment |
| CN113689937A (en) * | 2021-07-07 | 2021-11-23 | 阿里巴巴新加坡控股有限公司 | Image annotation method, storage medium and processor |
| CN115801781A (en) * | 2023-01-11 | 2023-03-14 | 杭州广科安德生物科技有限公司 | Biological data collaborative analysis system and method |
| CN115801781B (en) * | 2023-01-11 | 2023-05-30 | 杭州广科安德生物科技有限公司 | Biological data collaborative analysis system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446370A (en) | Pathology mask method and device, the computer readable storage medium of medical image | |
| US11783480B2 (en) | Semi-automated system for real-time wound image segmentation and photogrammetry on a mobile platform | |
| US20150046183A1 (en) | Remote, virtual physical exam acquisition and distribution | |
| CN107622000A (en) | A kind of collection of application crash information and report method, device | |
| WO2021000856A1 (en) | Bone age detection method and system, device, and readable storage medium | |
| CN106373063A (en) | Automatic triage treatment control method based on interactive communication and system | |
| US20220125360A1 (en) | Method and computer program for determining psychological state through drawing process of counseling recipient | |
| WO2020087969A1 (en) | Method for identifying abnormal clinical cases based on data analysis and computing device | |
| CN110266994A (en) | A kind of video call method, video conversation apparatus and terminal | |
| CN109473160A (en) | The mark qualification of medical image determines method and device | |
| CN109460433A (en) | A kind of medical system big data single machine integrated approach and device | |
| CN109102900A (en) | A kind of telemedicine method | |
| CN109509541A (en) | Method and device is signed and issued in report based on medical image | |
| CN111985197A (en) | Template generation method based on medical information | |
| CN109461147B (en) | Pathological labeling method and device applied to FOV picture of mobile terminal | |
| CN109003670A (en) | Big data medical information processing method, system, terminal device and storage medium | |
| WO2020082638A1 (en) | Pathological annotation method and device for medical images, report issuing method and device based on medical images, and computer readable storage medium | |
| CN116030950B (en) | Medical data integration management method | |
| WO2020087970A1 (en) | Neural network-based disease type score verification method and computing device | |
| CN207638698U (en) | Medical history integrated system before one kind is examined | |
| CN114496139A (en) | Quality control method, device, equipment and system of electronic medical record and readable medium | |
| CN107808088A (en) | A kind of fingerprint input method, device, computer installation, readable storage medium storing program for executing | |
| CN112270974A (en) | Intelligent auxiliary medical image workstation based on artificial intelligence | |
| CN115269701A (en) | Structured data generation method and device, storage medium and electronic equipment | |
| CN111192643A (en) | Medical record data processing method and related 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |