CN104462738A - Method, device and system for labeling medical images - Google Patents
Method, device and system for labeling medical images Download PDFInfo
- Publication number
- CN104462738A CN104462738A CN201310439456.3A CN201310439456A CN104462738A CN 104462738 A CN104462738 A CN 104462738A CN 201310439456 A CN201310439456 A CN 201310439456A CN 104462738 A CN104462738 A CN 104462738A
- Authority
- CN
- China
- Prior art keywords
- mark
- medical image
- terminal
- subset
- marked
- 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.)
- Granted
Links
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention provides a method for labeling medical images. The method includes the steps of dividing an unlabeled medical image set into at least two unlabeled medical image subsets, distributing the unlabeled medical image subsets to at least two labeling terminals so that each labeling terminal can label the medical images in the corresponding distributed unlabeled medical image subset, and receiving labeling information unloaded by each labeling terminal. Accordingly, the embodiment of the invention further provides a device and system for labeling the medical images. Through the method, device and system, the coordinative medical image labeling solution can be obtained, and the labeling efficiency is improved.
Description
Technical field
The present invention relates to technical field of image processing, particularly relate to a kind of methods, devices and systems marking medical image.
Background technology
The medical image that various radial pattern produces comprises such as anatomy and pathological bulk information, these information can provide a large amount of visual information, and form complementation with non-picture datas such as such as genomics, proteomics, histopathology and clinical laboratory data.In Medical Image Processing process, often need to provide accurate mark to the border of region of interest (ROI).But, the manually mark usual length consuming time of medical image and expense is large, and annotation results varies with each individual.In addition, user has to expend special time and place to perform mark, and is difficult to annotation results and other people to be shared.
Existing medical image annotation tool is generally and is suitable for individual and uses, based on the application of desktop computer.Along with the rise of panel computer, some medical image annotation tools based on panel computer are also there are.Nearly ten years, along with the develop rapidly of mobile technology, have also appeared some medical image annotation tools with locomotive function.
But these medical image annotation tools existing all will mark operation separately as independent task, between each user, the mechanism of ununified cooperative cooperating, this reduces the efficiency of mark.And the annotation results of each user cannot be shared, thus reduce further the efficiency of mark.
Summary of the invention
Embodiment of the present invention proposes a kind of methods, devices and systems marking medical image, can improve the annotating efficiency of medical image.
The technical scheme of embodiment of the present invention comprises:
Mark a method for medical image, the method comprises:
Medical image collection will do not marked be divided at least two and do not mark medical image subset;
Described at least two are not marked medical image subset allocation at least two mark terminals, for each mark terminal, the medical image do not marked in medical image subset be assigned to separately is marked;
Receive the markup information that each mark terminal is uploaded.
The method comprises further: receiving package contains the image labeling request of mark key word, and retrieval is corresponding with this mark key word does not mark medical image;
Described do not mark medical image collection for: by not marking of retrieving, medical image forms does not mark medical image collection.
The described medical image collection that will not mark is divided at least two and does not mark medical image subset and comprise:
Divide based on human anatomic structure and do not mark medical image collection; And/or
Divide based on body system's structure and do not mark medical image collection.
The described medical image subset allocation that do not mark at least two comprises at least two mark terminals:
Medical image subset allocation will do not marked to these at least two mark terminals based on the mark terminal PRI order pre-set;
Terminal processing capacity order based on mark terminal will not mark medical image subset allocation to these at least two mark terminals; And/or
Medical image subset allocation will do not marked to these at least two mark terminals based on load balancing principle.
The markup information that described reception each mark terminal is uploaded comprises: receive labeling operation information and mark coordinate information that each mark terminal uploads; The method comprises further: utilize described mark coordinate information to determine not mark the tab area of medical image subset traditional Chinese medicine image, utilize described labeling operation information to perform mark in this tab area, and the medical image after mark is combined as and marks medical image collection; Or
The markup information that described reception each mark terminal is uploaded comprises: receive the medical image after the mark that each mark terminal uploads; The method comprises further: be combined as by the medical image after mark and mark medical image collection.
The method comprises further:
Receiving package contains the mark image retrieval request of search key;
The retrieval mark image corresponding with this search key is concentrated from marking medical image;
Send the image of mark that this retrieves.
Mark a device for medical image, comprise image subset division unit, allocation units and receiving element, wherein:
Image subset division unit, is divided at least two does not mark medical image subset for marking medical image collection;
Allocation units, for described at least two not being marked medical image subset allocation at least two mark terminals, mark the medical image do not marked in medical image subset be assigned to separately for each mark terminal;
Receiving element, for receiving the markup information that each mark terminal is uploaded.
Described allocation units, specifically for not marking medical image subset allocation at least two mark terminals based on the mark terminal PRI order pre-set by described at least two;
Terminal processing capacity order based on mark terminal does not mark medical image subset allocation at least two mark terminals by described at least two; And/or
Medical image subset allocation is not marked at least two mark terminals by described at least two based on load balancing principle.
Described image subset division unit, is further used for the image labeling request that receiving package contains mark key word, retrieves corresponding with this mark key word not mark medical image, and is formed do not marked medical image collection by the medical image that do not mark retrieved.
The device of described mark medical image comprises further: assembled unit;
Described receiving element, specifically for receiving the labeling operation information and mark coordinate information that each mark terminal uploads; Described assembled unit, for utilizing mark coordinate information to determine not mark the tab area of medical image subset traditional Chinese medicine image, utilizes labeling operation information to perform mark in this tab area, and is combined as by the medical image after marking and marks medical image collection; Or
Described receiving element, specifically for receiving the medical image after mark; Described assembled unit, marks medical image collection for being combined as by the medical image after mark.
The device of described mark medical image comprises mark image retrieval unit further, the mark image retrieval request of search key is contained for receiving package, concentrate the retrieval mark image corresponding with this search key from marking medical image, and send this image of mark retrieved.
Mark a system for medical image, comprise at least two mark terminals and medical images server, wherein:
Medical images server, is divided at least two does not mark medical image subset for marking medical image collection, by the described medical image subset allocation that do not mark at least two mark terminals, and receives the markup information that each mark terminal uploads;
Each mark terminal, for marking the medical image do not marked in medical image subset be assigned to separately, and uploads to medical images server by markup information.
Described mark terminal is: functional mobile phone, smart mobile phone, palm PC, PC, panel computer or personal digital assistant.
As can be seen from technique scheme, embodiment of the present invention proposes a kind of medical image mark solution of collaboration type.After applying this solution, user can make full use of the existing or emerging treatment facility such as various bench device, tablet device or mobile device, carries out Collaborative Tagging easily anywhere, thus improve annotating efficiency with random time to medical image.
And have the unified mechanism of cooperative cooperating between user, the annotation results between user also can be shared.In addition, keyword also can be utilized to retrieve not marking and marking medical image, simplify the acquisition process of image, can further improve annotating efficiency thus.
Accompanying drawing explanation
Fig. 1 is the method flow diagram according to embodiment of the present invention mark medical image;
Fig. 2 is according to embodiment of the present invention, asks based on user the method flow diagram marking medical image;
Fig. 3 is the structure drawing of device according to embodiment of the present invention mark medical image;
Fig. 4 is the system construction drawing according to embodiment of the present invention mark medical image.
Embodiment
In order to make technical scheme of the present invention and advantage clearly understand, below in conjunction with drawings and the embodiments, the present invention is further elaborated.Should be appreciated that embodiment described herein only in order to illustrative explanation the present invention, the protection domain be not intended to limit the present invention.
Fig. 1 is the method flow diagram according to embodiment of the present invention mark medical image.As shown in Figure 1, the method comprises:
Step 101: medical image collection will do not marked and be divided at least two and do not mark medical image subset.
Medical image databases can be set up in advance at network side.Store in medical image databases and do not mark medical image collection and marked medical image collection.Mark medical image and concentrate the medical image comprising and be marked; Do not mark medical image and concentrate the medical image comprising and be not yet marked.Medical image databases can have division center or distributed frame.And the memory capacity of medical image databases can also carry out respective extension along with increasing of medical image number.
After network side receives in medical image databases and does not mark task that medical image collection marks, can be divided into not marking medical image collection multiple (at least two) and do not mark medical image subset, each medical image subset that do not mark can comprise one or more medical image.
Network side initiatively can send to each mark terminal and not mark medical image subset, and indicates each mark terminal to perform concrete mark task.Alternatively, network side also can receive the image labeling request coming from mark terminal, and this image labeling request includes mark key word.Then, network side figure is in response to this image labeling request, and from medical image databases, retrieval is corresponding with this mark key word does not mark medical image, and what these did not mark that medical image is just configured to expect to be marked does not mark medical image collection.Then, this is not marked medical image collection and is specifically divided at least two and does not mark medical image subset by network side again, specifically performs respective mark task for each mark terminal.
In one embodiment, medical image subset can not marked based on biological (such as human body) anatomical structure division.Such as, according to the anatomical structure of human body, can will not mark medical image collection and be specifically divided into: the image subset such as brain, chest, heart, belly, upper limbs, lower limb.
In another embodiment, medical image subset can not marked according to the division of body system's structure yet.Such as, medical image collection will do not marked and be specifically divided into the image subset such as digestive system, nervous system, kinematic system, internal system, urinary system, reproductive system, the circulation system, respiratory system, immune system.
In fact, multi-level refinement differentiation can also be carried out to not marking medical image collection.Such as, for brain image, the image subset such as brain core (Central Core), brain edge system (Limbic System) and cerebral cortex (Cerebral Cortex) can also be divided into.
In one embodiment, can also divide in conjunction with human anatomic structure and system architecture and do not mark medical image subset.
Such as, for cardiocirculatory, cardiac image related to this can be divided into the image subset such as sustainer, atrium sinistrum, left ventricle, atrium dextrum, right ventricle.
In one embodiment, combining medical image subset for the ease of follow-up, can be each medical image subset allocation identifier.All medical images in identical medical image subset share identical identifier.
Step 102: medical image subset allocation will do not marked at least two mark terminals, and for each mark terminal, the medical image do not marked in medical image subset be assigned to separately will be marked.
Mark terminal is positioned at end side, is specifically as follows the entity that functional mobile phone, smart mobile phone, palm PC, PC, panel computer or personal digital assistant etc. have arbitrarily computing ability.Mark terminal also there is the communication function with network side, thus can receive provided by network side do not mark medical image subset and return markup information to network side.
Network side will not mark medical image subset allocation to multiple (at least two) mark terminal.Here, medical image subset can not marked based on multiple-task allocation scheme to each mark terminal distribution.
In one embodiment, medical image subset allocation will can not marked to multiple mark terminal based on the mark terminal PRI order pre-set.
Such as, suppose have three to mark terminal, be respectively mark terminal 1, mark terminal 2 and mark terminal 3, the manageable medical image of each mark terminal is 10.The priority of mark terminal 1 is the highest, and the priority of mark terminal 2 is taken second place, and the priority of mark terminal 3 is minimum.Suppose to need the medical image subset one that do not mark of distributing to have two, be respectively and do not mark medical image subset 1 and do not mark medical image subset 2, each mark in medical image subset includes 10 images.So, task matching result can be: to mark terminal 1 send do not mark medical image subset 1(or do not mark medical image subset 2) in 10 images, send remaining 10 images do not marked in medical image subset to mark terminal 1, and do not send to mark terminal 3 and do not mark image.
In another embodiment, medical image subset allocation will can not marked to mark terminal based on the terminal processing capacity order of mark terminal.
Such as, suppose have three to mark terminal, be respectively mark terminal 1, mark terminal 2 and mark terminal 3.The manageable medical image of mark terminal 1 is 10, and the manageable medical image of mark terminal 2 is 10, and the manageable medical image of mark terminal 3 is 5.Suppose to need the medical image subset one that do not mark of distributing to have two, be respectively and do not mark medical image subset 1 and do not mark medical image subset 2, each mark in medical image subset includes 10 images.So, task matching result can be: to mark terminal 1 send do not mark medical image subset 1(or do not mark medical image subset 2) in 10 images, send remaining 10 images do not marked in medical image subset to mark terminal 1, and do not send to mark terminal 3 and do not mark image.
In another embodiment, can will not mark medical image subset allocation at least two mark terminals based on load balancing principle.By load-balancing algorithm, medical image subset allocation will do not marked and process respectively on multiple stage mark terminal, ensure that the load between each mark terminal is in dynamic balance state.Current existing various load-balancing algorithm can be utilized to execute the task distribution, these algorithms include, but are not limited to: non-standing algorithm (Non-Persistent), Round-Robin Algorithm (RoundRobin), minimum join algorithm (Least Connection), response speed algorithm (Response Time) or continuation algorithm (Persistent), etc.
More than itemized and will not mark medical image subset allocation to the multiple example of mark terminal, these examples can be used alone or in combination.Further, it will be appreciated by those of skill in the art that this enumerating is only purposes of illustration, be not intended to limit the present invention the protection domain of embodiment.
Each mark terminal receive respective do not mark medical image subset after, the respective medical image do not marked in medical image subset is marked.
In one embodiment, by mark terminal, medical image can be presented to user, manually complete mark by user, and record corresponding markup information.Markup information can comprise labeling operation information and mark coordinate information, and mark coordinate information describes the tab area having medical image, and labeling operation information can be concrete dotted line information or colouring information.
In another embodiment, mark terminal and also can carry out automatic marking based on various algorithm to medical image.Such as, cluster (threshold value) can be applied; Statistical method; Deformation wheel profile; Region growing; Mathematical morphology; Nonlinear method (fuzzy partition, neural network, genetic algorithm); Three-dimensional model scheduling algorithm carries out automatic marking to medical image.
Step 103: receive the markup information that each mark terminal is uploaded.
In one embodiment, mark terminal does not directly send the medical image after mark, but sends labeling operation information and mark coordinate information.Now, network side utilizes mark coordinate information to determine the tab area of corresponding medical image to utilize labeling operation information to perform mark in this tab area, and is combined as by the medical image after marking and marks medical image collection and preserved.
In another embodiment, mark terminal and directly can send the medical image after mark.Now, network side receives the medical image after this mark, is combined as by the medical image after mark and marks medical image collection and preserved.
Being combined as in the process marking medical image collection by the medical image after mark, the identifier of medical image can be utilized to select same subsets and to complete anabolic process.
In one embodiment, network side can contain the mark image retrieval request of search key from requesting party's receiving package.Then, network side concentrates the retrieval mark image corresponding with this search key from marking medical image, and sends this image of mark retrieved to requesting party.Requesting party both can be mark terminal, also can be any entity to mark interesting image on network.
Based on above-mentioned labor, according to the change of applied environment and demand, the present invention can have multiple form of implementation.
Fig. 2 is according to embodiment of the present invention, asks based on user the method flow diagram marking medical image.As shown in Figure 2, the method comprises:
Step 200: network side receives image labeling request from mark terminal.
Mark key word is included in this image labeling request.Such as, suppose that the user of certain mark terminal expects that the medical image relevant to cardiocirculatory marks, then marking key word can be " cardiocirculatory ".
Step 210: what retrieval was corresponding with mark key word does not mark medical image.
Network side retrieve from medical image databases with " cardiocirculatory " match do not mark medical image.
Step 220: the medical image that do not mark retrieved is divided into multiple subset.
Such as, the medical image that do not mark retrieved can be divided into the image subset such as sustainer, atrium sinistrum, left ventricle, atrium dextrum, right ventricle.
Step 230: by multiple subset allocation of marking off to multiple mark terminal.
Here, according to the demand of applied environment, can according to the plurality of distribution strategy pre-set to distribute subset.Such as, subset can be distributed based on the mark terminal PRI order pre-set, distribute subset based on the terminal processing capacity order of mark terminal or distribute based on load balancing principle and distribute subset.
Step 240: each mark terminal performs respective image labeling process.
Here, each marks terminal after receiving respective image labeling subset, executed in parallel image labeling process separately.
Step 250: whether each mark terminal judges completes image labeling process, if perform step 270 and subsequent step thereof, otherwise performs step 260 and subsequent step thereof.
Step 260: the mark terminal buffers image labeling process progress not completing image labeling process, and return execution step 240.
Step 270: each mark terminal uploads respective markup information respectively to network side, and network side collects all markup informations.
Step 280: network side judges that whether the markup information that mark terminal is uploaded is complete, if it is performs step 290, otherwise performs step 290.
Step 290: network side abandons incomplete markup information, prompting mark terminal continues to upload, and process ends.
Step 291: markup information and corresponding medical image are combined as and mark medical image by network side, and be saved in mark medical image collection by marking medical image.
Based on above-mentioned labor, embodiment of the present invention also proposed a kind of device marking medical image.
The Plant arrangement of the mark medical image that embodiment of the present invention can be proposed is at network side.Utilize the unified platform of device as Collaborative Tagging of this mark medical image, being distributed in each local mark terminal (no matter being specially functional mobile phone, smart mobile phone, palm PC, PC, panel computer or personal digital assistant) can mark medical image with random time anywhere.
Fig. 3 is the structure drawing of device according to embodiment of the present invention mark medical image.As shown in Figure 3, this device comprises image subset division unit 301, allocation units 302 and receiving element 303, wherein:
Image subset division unit 301, is divided at least two does not mark medical image subset for marking medical image collection;
Allocation units 302, for the described medical image subset allocation that do not mark is marked terminals at least two, mark the medical image do not marked in medical image subset be assigned to separately for each mark terminal;
Receiving element 303, for receiving the markup information that each mark terminal is uploaded.
In one embodiment, allocation units 302, for:
Medical image subset allocation will do not marked at least two mark terminals based on the mark terminal PRI order pre-set;
Terminal processing capacity order based on mark terminal will not mark medical image subset allocation at least two mark terminals; And/or
Medical image subset allocation will do not marked at least two mark terminals based on load balancing principle.
Further, in one embodiment, image subset division unit 301, the image labeling request that receiving package contains mark key word can be further used for, retrieve and corresponding with this mark key word do not mark medical image, and formed do not marked medical image collection by the medical image that do not mark retrieved.
In another embodiment, the device of above-mentioned mark medical image can comprise assembled unit 304 further; Correspondingly:
Receiving element 303, specifically for receiving the labeling operation information and mark coordinate information that each mark terminal uploads; Assembled unit 304, for utilizing mark coordinate information to determine not mark the tab area of medical image subset traditional Chinese medicine image, utilizes labeling operation information to perform mark in this tab area, and is combined as by the medical image after marking and marks medical image collection; Or,
Receiving element 303, specifically for receiving the medical image after mark; Assembled unit 304, marks medical image collection for being combined as by the medical image after mark.
Further, in one embodiment, the device of above-mentioned mark medical image can comprise mark image retrieval unit 305 further, the mark image retrieval request of search key is contained for receiving package, concentrate the retrieval mark image corresponding with this search key from marking medical image, and send this image of mark retrieved.
Based on above-mentioned labor, embodiment of the present invention also proposed a kind of system marking medical image.
Fig. 4 is the system construction drawing according to embodiment of the present invention mark medical image.As shown in Figure 4, this system comprises end side and network side, and end side comprises at least two mark terminals 401, and network side comprises medical images server 402, wherein:
Medical images server 402, be divided at least two do not mark medical image subset for medical image collection will do not marked, described at least two are not marked medical image subset allocation at least two mark terminals 401, and receive the markup information that each mark terminal 401 uploads;
Each mark terminal 401, for marking the medical image do not marked in medical image subset be assigned to separately, and uploads to medical images server 402 by markup information.
In one embodiment, mark terminal 401 can comprise: the treatment facilities such as functional mobile phone, smart mobile phone, palm PC, PC, panel computer and personal digital assistant.Preferably, by installing plug-in unit to realize marking Function in the browser of these treatment facilities, browser such as can comprise Internet Explorer, Firefox, Safari, Opera, GoogleChrome, GreenBrowser etc.Mark terminal 401 can be distributed among different geographic areas.Although exemplarily list some conventional browsers above, those skilled in the art can recognize, embodiment of the present invention is not limited to these browsers, but go for the file that can be used for arbitrarily in display web page server or archives economy and allow the application (App) of user and file interaction, these application can be various browsers common at present, also can be other the application programs with web page browsing function.
Medical images server 402 specifically can comprise image subset division unit 4021, allocation units 4022 and receiving element 4023, wherein: image subset division unit 4021, is divided at least two does not mark medical image subset for not marking medical image collection; Allocation units 4022, for described at least two not being marked medical image subset allocation at least two mark terminals 401, mark the medical image do not marked in medical image subset be assigned to separately for each mark terminal 401; Receiving element 4023, for receiving the markup information that each mark terminal 401 is uploaded.
In addition, medical images server 402 can also comprise medical image databases, stores and do not mark medical image collection and marked medical image collection in this medical image databases.This medical image databases can have division center or distributed frame, appropriately can also expand along with the number of medical image.
In one embodiment, allocation units 4022 can be used for:
Medical image subset allocation will do not marked at least two mark terminals 401 based on the mark terminal PRI order pre-set;
Terminal processing capacity order based on mark terminal will not mark medical image subset allocation at least two mark terminals 401; And/or
Medical image subset allocation will do not marked at least two mark terminals 401 based on load balancing principle.
Further, in one embodiment, image subset division unit 4021, the image labeling request that receiving package contains mark key word can be further used for, retrieve and corresponding with this mark key word do not mark medical image, and formed do not marked medical image collection by the medical image that do not mark retrieved.
In another embodiment, medical images server 402 can comprise assembled unit 4024 further; Correspondingly:
Receiving element 4023, specifically can be used for receiving labeling operation information and mark coordinate information that each mark terminal uploads; Assembled unit 4024, can be used for utilizing mark coordinate information to determine not mark the tab area of medical image subset traditional Chinese medicine image, utilize labeling operation information to perform mark in this tab area, and the medical image after mark is combined as and marks medical image collection; Or,
Receiving element 4023, specifically can be used for the medical image after receiving mark; Assembled unit 4024, marks medical image collection for being combined as by the medical image after mark.
In addition, as mentioned above, medical images server 402 also can comprise mark image retrieval unit 4024 further, the mark image retrieval request of search key is contained for receiving package, concentrate the retrieval mark image corresponding with this search key from marking medical image, and send this image of mark retrieved.
Various aspects described herein can realize by hardware, software, firmware, middleware, microcode or its combination in any.When utilizing software, firmware, middleware, microcode, program code or code segment to realize these devices and/or method, can be stored in machine readable media, such as, be stored in memory unit.For software simulating, technical scheme described herein can realize by the module (such as program, function etc.) realizing function described herein.Software code can be stored in a memory cell, be performed by processor.Memory cell can realize within a processor, or can be positioned at processor outside.In the case of the latter, storer can be connected with processor by various means.
In sum, in invention embodiment, medical image collection will do not marked and be divided at least two and do not mark medical image subset; By the described medical image subset allocation that do not mark at least two mark terminals, by each mark terminal, the medical image do not marked in medical image subset be assigned to separately is marked; Receive the markup information that each mark terminal is uploaded.As can be seen here, embodiment of the present invention proposes a kind of medical image mark solution of collaboration type.After applying this solution, user can make full use of the existing or emerging treatment facility such as various bench device, tablet device or mobile device, carries out Collaborative Tagging easily anywhere, thus improve annotating efficiency with random time to medical image.
And have the unified mechanism of cooperative cooperating between user, the annotation results between user also can be shared.In addition, keyword also can be utilized to retrieve not marking and marking medical image, simplify the acquisition process of image, can further improve annotating efficiency thus.
The foregoing is only better embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (13)
1. mark a method for medical image, the method comprises:
Medical image collection will do not marked be divided at least two and do not mark medical image subset;
Described at least two are not marked medical image subset allocation at least two mark terminals, for each mark terminal, the medical image do not marked in medical image subset be assigned to separately is marked;
Receive the markup information that each mark terminal is uploaded.
2. the method for mark medical image according to claim 1, it is characterized in that, the method comprises further: receiving package contains the image labeling request of mark key word, and retrieval is corresponding with this mark key word does not mark medical image;
Described do not mark medical image collection for: by not marking of retrieving, medical image forms does not mark medical image collection.
3. the method for mark medical image according to claim 1, is characterized in that, the described medical image collection that will not mark is divided at least two and does not mark medical image subset and comprise:
Divide based on human anatomic structure and do not mark medical image collection; And/or
Divide based on body system's structure and do not mark medical image collection.
4. the method for mark medical image according to claim 1, is characterized in that, the described medical image subset allocation that do not mark described at least two comprises at least two mark terminals:
Medical image subset allocation is not marked to these at least two mark terminals by described at least two based on the mark terminal PRI order pre-set;
Terminal processing capacity order based on mark terminal does not mark medical image subset allocation to these at least two mark terminals by described at least two; And/or
Medical image subset allocation is not marked to these at least two mark terminals by described at least two based on load balancing principle.
5. the method for mark medical image according to claim 1, is characterized in that,
The markup information that described reception each mark terminal is uploaded comprises: receive labeling operation information and mark coordinate information that each mark terminal uploads; The method comprises further: utilize described mark coordinate information to determine not mark the tab area of medical image subset traditional Chinese medicine image, utilize described labeling operation information to perform mark in this tab area, and the medical image after mark is combined as and marks medical image collection; Or
The markup information that described reception each mark terminal is uploaded comprises: receive the medical image after the mark that each mark terminal uploads; The method comprises further: be combined as by the medical image after mark and mark medical image collection.
6. the method for mark medical image according to claim 5, it is characterized in that, the method comprises further:
Receiving package contains the mark image retrieval request of search key;
The retrieval mark image corresponding with this search key is concentrated from marking medical image;
Send the image of mark that this retrieves.
7. mark a device for medical image, this device comprises image subset division unit, allocation units and receiving element; Wherein:
Described image subset division unit, is divided at least two does not mark medical image subset for marking medical image collection;
Described allocation units, for described at least two not being marked medical image subset allocation at least two mark terminals, mark the medical image do not marked in medical image subset be assigned to separately for each mark terminal;
Described receiving element, for receiving the markup information that each mark terminal is uploaded.
8. the device of mark medical image according to claim 7, is characterized in that, described allocation units, specifically for:
Medical image subset allocation is not marked at least two mark terminals by described at least two based on the mark terminal PRI order pre-set;
Terminal processing capacity order based on mark terminal does not mark medical image subset allocation at least two mark terminals by described at least two; And/or
Medical image subset allocation is not marked at least two mark terminals by described at least two based on load balancing principle.
9. the device of mark medical image according to claim 7, is characterized in that,
Described image subset division unit, is further used for the image labeling request that receiving package contains mark key word, retrieves corresponding with this mark key word not mark medical image, and is formed do not marked medical image collection by the medical image that do not mark retrieved.
10. the device of mark medical image according to claim 7, is characterized in that, this device comprises assembled unit further;
Described receiving element, specifically for receiving the labeling operation information and mark coordinate information that each mark terminal uploads; Described assembled unit, for utilizing mark coordinate information to determine not mark the tab area of medical image subset traditional Chinese medicine image, utilizes labeling operation information to perform mark in this tab area, and is combined as by the medical image after marking and marks medical image collection; Or
Described receiving element, specifically for receiving the medical image after mark; Described assembled unit, marks medical image collection for being combined as by the medical image after mark.
The device of 11. mark medical images according to claim 10, it is characterized in that, this device comprises further:
Mark image retrieval unit, contains the mark image retrieval request of search key for receiving package, from the image of mark marking medical image and concentrate retrieval corresponding with this search key, and send this image of mark retrieved.
12. 1 kinds of systems marking medical image, this system comprises at least two mark terminals and medical images server, wherein:
Described medical images server, is divided at least two does not mark medical image subset for marking medical image collection, by the described medical image subset allocation that do not mark at least two mark terminals, and receives the markup information that each mark terminal uploads;
Described each mark terminal, for marking the medical image do not marked in medical image subset be assigned to separately, and uploads to described medical images server by markup information.
The system of 13. mark medical images according to claim 12, is characterized in that, described each mark terminal is: functional mobile phone, smart mobile phone, palm PC, PC, panel computer or personal digital assistant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310439456.3A CN104462738B (en) | 2013-09-24 | 2013-09-24 | A kind of methods, devices and systems of mark medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310439456.3A CN104462738B (en) | 2013-09-24 | 2013-09-24 | A kind of methods, devices and systems of mark medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104462738A true CN104462738A (en) | 2015-03-25 |
| CN104462738B CN104462738B (en) | 2018-10-30 |
Family
ID=52908768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310439456.3A Expired - Fee Related CN104462738B (en) | 2013-09-24 | 2013-09-24 | A kind of methods, devices and systems of mark medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104462738B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106339571A (en) * | 2015-07-10 | 2017-01-18 | 西门子保健有限责任公司 | Artificial Neural Network And A Method For The Classification Of Medical Image Data Records |
| DE212015000240U1 (en) | 2015-12-17 | 2017-05-24 | Hefei University Of Technology | System for medical image annotation |
| CN106845068A (en) * | 2016-12-13 | 2017-06-13 | 海纳医信（北京）软件科技有限责任公司 | Picture mask method and device |
| CN106845090A (en) * | 2016-12-30 | 2017-06-13 | 海纳医信（北京）软件科技有限责任公司 | Medical image labeling method and device |
| CN108461129A (en) * | 2018-03-05 | 2018-08-28 | 余夏夏 | A kind of medical image mask method, device and user terminal based on image authentication |
| CN108960297A (en) * | 2018-06-15 | 2018-12-07 | 北京金山云网络技术有限公司 | Mask method, annotation equipment, equipment and the storage medium of picture |
| CN109035187A (en) * | 2018-07-10 | 2018-12-18 | 杭州依图医疗技术有限公司 | A kind of mask method and device of medical image |
| CN109034188A (en) * | 2018-06-15 | 2018-12-18 | 北京金山云网络技术有限公司 | Acquisition methods, acquisition device, equipment and the storage medium of machine learning model |
| CN109215017A (en) * | 2018-08-16 | 2019-01-15 | 腾讯科技（深圳）有限公司 | Image processing method, device, user terminal, server and storage medium |
| CN109446370A (en) * | 2018-10-26 | 2019-03-08 | 广州金域医学检验中心有限公司 | Pathology mask method and device, the computer readable storage medium of medical image |
| CN109461495A (en) * | 2018-11-01 | 2019-03-12 | 腾讯科技（深圳）有限公司 | A kind of recognition methods of medical image, model training method and server |
| CN109492698A (en) * | 2018-11-20 | 2019-03-19 | 腾讯科技（深圳）有限公司 | A kind of method of model training, the method for object detection and relevant apparatus |
| CN109686423A (en) * | 2018-11-06 | 2019-04-26 | 众安信息技术服务有限公司 | A kind of medical imaging mask method and system |
| CN110209849A (en) * | 2019-06-04 | 2019-09-06 | 北京字节跳动网络技术有限公司 | Method and apparatus for marking key point |
| CN110460770A (en) * | 2019-07-25 | 2019-11-15 | 上海晰图信息科技有限公司 | A kind of image processing method and system |
| CN111028953A (en) * | 2019-12-10 | 2020-04-17 | 上海明品医学数据科技有限公司 | Control method for prompting marking of medical data |
| 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 |
| CN111062255A (en) * | 2019-11-18 | 2020-04-24 | 苏州智加科技有限公司 | Three-dimensional point cloud labeling method, device, equipment and storage medium |
| 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 |
| CN111554382A (en) * | 2020-04-30 | 2020-08-18 | 上海商汤智能科技有限公司 | Medical image processing method and device, electronic 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 |
| WO2021155678A1 (en) * | 2020-02-03 | 2021-08-12 | 腾讯科技（深圳）有限公司 | Label marking method and apparatus, and device and readable storage medium |
| CN113298112A (en) * | 2021-04-01 | 2021-08-24 | 安徽继远软件有限公司 | Integrated data intelligent labeling method and system |
| WO2021169122A1 (en) * | 2020-02-25 | 2021-09-02 | 平安科技（深圳）有限公司 | Image annotation management method and apparatus, and computer system and readable storage medium |
| WO2023185805A1 (en) * | 2022-03-30 | 2023-10-05 | 图湃(北京)医疗科技有限公司 | Image processing method and apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1853196A (en) * | 2003-08-29 | 2006-10-25 | 皇家飞利浦电子股份有限公司 | A method, a device and a computer program arranged to develop and execute an executable template of an image processing protocol |
| CN101310687A (en) * | 2007-05-22 | 2008-11-26 | 西门子公司 | Method for data evaluation |
| CN101765843A (en) * | 2007-08-01 | 2010-06-30 | 皇家飞利浦电子股份有限公司 | Accessing medical image detabases using medically relevant terms |
| CN102156715A (en) * | 2011-03-23 | 2011-08-17 | 中国科学院上海技术物理研究所 | Retrieval system based on multi-lesion region characteristic and oriented to medical image database |
| CN102999615A (en) * | 2012-11-29 | 2013-03-27 | 合肥工业大学 | Diversified image marking and retrieving method based on radial basis function neural network |
| CN103116737A (en) * | 2011-11-16 | 2013-05-22 | 北京同步科技有限公司 | Distributed type video image identification system and image identification method thereof |
-
2013
- 2013-09-24 CN CN201310439456.3A patent/CN104462738B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1853196A (en) * | 2003-08-29 | 2006-10-25 | 皇家飞利浦电子股份有限公司 | A method, a device and a computer program arranged to develop and execute an executable template of an image processing protocol |
| CN101310687A (en) * | 2007-05-22 | 2008-11-26 | 西门子公司 | Method for data evaluation |
| CN101765843A (en) * | 2007-08-01 | 2010-06-30 | 皇家飞利浦电子股份有限公司 | Accessing medical image detabases using medically relevant terms |
| CN102156715A (en) * | 2011-03-23 | 2011-08-17 | 中国科学院上海技术物理研究所 | Retrieval system based on multi-lesion region characteristic and oriented to medical image database |
| CN103116737A (en) * | 2011-11-16 | 2013-05-22 | 北京同步科技有限公司 | Distributed type video image identification system and image identification method thereof |
| CN102999615A (en) * | 2012-11-29 | 2013-03-27 | 合肥工业大学 | Diversified image marking and retrieving method based on radial basis function neural network |
Non-Patent Citations (2)
| Title |
|---|
| 何楚 等: "医学图像感兴趣区域的自动提取", 《计算机应用研究》 * |
| 王胜伟 等: "医学图像计算机辅助诊断数据平台研究", 《中国生物医学工程学报》 * |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106339571A (en) * | 2015-07-10 | 2017-01-18 | 西门子保健有限责任公司 | Artificial Neural Network And A Method For The Classification Of Medical Image Data Records |
| CN106339571B (en) * | 2015-07-10 | 2020-09-18 | 西门子保健有限责任公司 | Artificial neural network for classifying medical image data sets |
| DE212015000240U1 (en) | 2015-12-17 | 2017-05-24 | Hefei University Of Technology | System for medical image annotation |
| 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 |
| CN108463814B (en) * | 2015-12-17 | 2022-02-18 | 北京安和福祉科技有限公司 | Medical image labeling method and system |
| CN106845068A (en) * | 2016-12-13 | 2017-06-13 | 海纳医信（北京）软件科技有限责任公司 | Picture mask method and device |
| CN106845068B (en) * | 2016-12-13 | 2020-05-22 | 海纳医信（北京）软件科技有限责任公司 | Picture labeling method and device |
| CN106845090A (en) * | 2016-12-30 | 2017-06-13 | 海纳医信（北京）软件科技有限责任公司 | Medical image labeling method and device |
| CN108461129A (en) * | 2018-03-05 | 2018-08-28 | 余夏夏 | A kind of medical image mask method, device and user terminal based on image authentication |
| CN108461129B (en) * | 2018-03-05 | 2022-05-20 | 余夏夏 | Medical image labeling method and device based on image authentication and user terminal |
| CN109034188B (en) * | 2018-06-15 | 2021-11-05 | 北京金山云网络技术有限公司 | Method and device for acquiring machine learning model, equipment and storage medium |
| CN108960297A (en) * | 2018-06-15 | 2018-12-07 | 北京金山云网络技术有限公司 | Mask method, annotation equipment, equipment and the storage medium of picture |
| CN109034188A (en) * | 2018-06-15 | 2018-12-18 | 北京金山云网络技术有限公司 | Acquisition methods, acquisition device, equipment and the storage medium of machine learning model |
| CN109035187B (en) * | 2018-07-10 | 2021-11-09 | 杭州依图医疗技术有限公司 | Medical image labeling method and device |
| CN109035187A (en) * | 2018-07-10 | 2018-12-18 | 杭州依图医疗技术有限公司 | A kind of mask method and device of medical image |
| CN109215017B (en) * | 2018-08-16 | 2020-06-02 | 腾讯科技（深圳）有限公司 | Picture processing method and device, user terminal, server and storage medium |
| CN109215017A (en) * | 2018-08-16 | 2019-01-15 | 腾讯科技（深圳）有限公司 | Image processing method, device, user terminal, server and storage medium |
| 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 |
| CN109446370A (en) * | 2018-10-26 | 2019-03-08 | 广州金域医学检验中心有限公司 | Pathology mask method and device, the computer readable storage medium of medical image |
| CN109461495A (en) * | 2018-11-01 | 2019-03-12 | 腾讯科技（深圳）有限公司 | A kind of recognition methods of medical image, model training method and server |
| CN109686423A (en) * | 2018-11-06 | 2019-04-26 | 众安信息技术服务有限公司 | A kind of medical imaging mask method and system |
| CN109492698A (en) * | 2018-11-20 | 2019-03-19 | 腾讯科技（深圳）有限公司 | A kind of method of model training, the method for object detection and relevant apparatus |
| CN110209849A (en) * | 2019-06-04 | 2019-09-06 | 北京字节跳动网络技术有限公司 | Method and apparatus for marking key point |
| CN110209849B (en) * | 2019-06-04 | 2022-03-25 | 北京字节跳动网络技术有限公司 | Method and device for marking key points |
| CN110460770A (en) * | 2019-07-25 | 2019-11-15 | 上海晰图信息科技有限公司 | A kind of image processing method and system |
| CN110460770B (en) * | 2019-07-25 | 2021-01-26 | 上海晰图信息科技有限公司 | Image processing method and system |
| 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 |
| CN111062255A (en) * | 2019-11-18 | 2020-04-24 | 苏州智加科技有限公司 | Three-dimensional point cloud labeling method, device, equipment and storage medium |
| CN111028953A (en) * | 2019-12-10 | 2020-04-17 | 上海明品医学数据科技有限公司 | Control method for prompting marking of medical data |
| CN111028953B (en) * | 2019-12-10 | 2023-07-25 | 上海明品医学数据科技有限公司 | Control method for prompting marking of medical data |
| WO2021155678A1 (en) * | 2020-02-03 | 2021-08-12 | 腾讯科技（深圳）有限公司 | Label marking method and apparatus, and device and readable storage medium |
| WO2021169122A1 (en) * | 2020-02-25 | 2021-09-02 | 平安科技（深圳）有限公司 | Image annotation management method and apparatus, and computer system and readable storage medium |
| CN111554382A (en) * | 2020-04-30 | 2020-08-18 | 上海商汤智能科技有限公司 | Medical image processing method and device, electronic equipment and 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 |
| 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 |
| CN113298112A (en) * | 2021-04-01 | 2021-08-24 | 安徽继远软件有限公司 | Integrated data intelligent labeling method and system |
| WO2023185805A1 (en) * | 2022-03-30 | 2023-10-05 | 图湃(北京)医疗科技有限公司 | Image processing method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104462738B (en) | 2018-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104462738A (en) | Method, device and system for labeling medical images | |
| Oliveira et al. | Towards applying content-based image retrieval in the clinical routine | |
| CN108463814A (en) | A kind of medical image mask method and system | |
| CN110377587B (en) | Migration data determination method, device, equipment and medium based on machine learning | |
| CN109887584A (en) | It changes the place of examination method, system and server, computer readable storage medium | |
| Lawanont et al. | Daily stress recognition system using activity tracker and smartphone based on physical activity and heart rate data | |
| CN102999878A (en) | Medical intelligent system | |
| CN111986744A (en) | Medical institution patient interface generation method and device, electronic device and medium | |
| CN111639077B (en) | Data management method, device, electronic equipment and storage medium | |
| CN111985197A (en) | Template generation method based on medical information | |
| CN105446669A (en) | Virtual printer based medical data acquisition and transmission method and system thereof | |
| CN111627541A (en) | Medical information management and feedback service method, system and readable storage medium based on Internet of things technology | |
| Dang et al. | Building ICU in-hospital mortality prediction model with federated learning | |
| CN111382336B (en) | Data acquisition method and system | |
| CN112614579A (en) | Hospital appointment registration method and device and computer equipment | |
| CN109657950A (en) | Hierarchy Analysis Method, device, equipment and computer readable storage medium | |
| CN110097930A (en) | Schizophrenia medical data processing method, device, system, server and medium | |
| CN109656955A (en) | User data query method, system and storage medium | |
| Megalooikonomou et al. | Medical data fusion for telemedicine | |
| CN114373541A (en) | Intelligent traditional Chinese medicine diagnosis method, system and storage medium based on distribution | |
| Shi et al. | Cloud-assisted mood fatigue detection system | |
| CN113241134A (en) | Online consulting doctor distribution method and system and storage medium | |
| Karavatselou et al. | Profile management system in ubiquitous healthcare cloud computing environment | |
| Jin et al. | Content and semantic context based image retrieval for medical image grid | |
| CN114020429A (en) | Task processing method and device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181030 Termination date: 20210924 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |