CN107516005A - A kind of method and system of digital pathological image mark - Google Patents
A kind of method and system of digital pathological image mark Download PDFInfo
- Publication number
- CN107516005A CN107516005A CN201710576906.1A CN201710576906A CN107516005A CN 107516005 A CN107516005 A CN 107516005A CN 201710576906 A CN201710576906 A CN 201710576906A CN 107516005 A CN107516005 A CN 107516005A
- Authority
- CN
- China
- Prior art keywords
- pathological image
- digital pathological
- mark
- markup information
- pathology
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
- G06F16/83—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a kind of method and system of digital pathological image mark, including:Using the test pattern annotation tool based on pathology terminology bank, digital pathological image to be marked is labeled;The management being formatted based on XML format to the pathology markup information on the digital pathological image that has marked;The digital pathological image marked is distributed at least three people examination & verification, the digital pathological image marked audited after passing through is stored to mark database, and the data transfer in mark database to machine learning Sample Storehouse is subjected to machine learning.The invention provides the digital pathological image of a kind of specialized, standardization, systematization to mark solution, user can be labeled, retrieve, upload and be downloaded using various terminal equipment, annotating efficiency can be improved, promotes to form the pathological image mark mechanism of unified cooperative cooperating.
Description
Technical field
The present invention relates to technical field of image processing, in particular it relates to a kind of method of digital pathological image mark and be
System.
Background technology
The mark and Data Enter of pathological image are the important tool and channel of pathologist accumulation professional diagnosis experience, its
Abundant, the valuable expert data information contained, can be intelligent pathological diagnosis, pathological information teaching, pathological diagnosis correlation
Scientific research provides a large amount of reference informations.
With the development of informationization technology, the related scientific research of digital pathological diagnosis, deep learning is based especially on
The research of digital pathological image is, it is necessary to substantial amounts of digital pathological image markup information and classification samples data, but digitlization at present
Pathological image markup information it is very rare.Digital pathological image markup information between each medical institutions can not be shared, and lack one
The pathological image mark database of individual system specialty, seriously limits the scientific methods such as deep learning, data mining in intelligent disease
Further applying in reason diagnosis research.
Meanwhile the digital pathological image mask method of each medical institutions generally establishes one's own system, and lacks unified Marking Guidelines,
It is unfavorable for the collaboration and data sharing of digital pathological image mark, should so as to limit the efficiency of mark and the abundant of markup information
With.
What a kind of patent " methods, devices and systems for marking medical image " of Application No. 2013104394563 proposed
In medical image mask method, various marks are freely provided by each user, mark can not add without normative and specialization
The semantic tagger information such as type (professional entry), and marked without proposition derived from the tab area batch data of medical image
Method, markup information can not form the medical image mark database of specialty, can not further play bigger effect and value.
The numeral disease that a kind of patent " mask method and annotation equipment of digital pathological section " of Application No. 2015109671608 proposes
In the mask method for managing section, the available marking types of user only have figure labeling and word description class mark, the patent
The pathological section that major significance is to mark can be easy to other users or user subsequently to check, only be applicable and personal or small range
The use of interior user, it is impossible to carry out the collaborative work and data sharing of digital pathological image mark, while the form marked is more
Arbitrarily, without standardization and specialized feature.
Therefore, develop a set of specialized, standardization, systematization flexible easy-to-use digital pathological image annotation tool and be
System is the active demand of pathology industry.
The content of the invention
For in the prior art the defects of, it is an object of the invention to provide a kind of method of digital pathological image mark and be
System, to realize standardizing, unitizing for pathological image mark, annotating efficiency is improved, is ground for science such as data mining, deep learnings
Study carefully and pathological image mark database is provided.
The method marked according to a kind of digital pathological image provided by the invention, including:
Annotation step:Using the test pattern annotation tool based on pathology terminology bank, to digital pathological image to be marked
It is labeled;
Markup information management process:Based on XML format to the pathology markup information on the digital pathological image that has marked
The management being formatted;
Decision fusion step:The digital pathological image marked is distributed at least three people examination & verification, after examination & verification is passed through
The digital pathological image marked is stored to mark database, and by the data transfer in mark database to machine learning sample
Storehouse carries out machine learning.
Preferably, pathology terminology bank described in annotation step is indicated and stored some subsets using XML format.
Preferably, pathology markup information described in markup information management process include coordinate information, link information, classification and
Statistical information, store and represent with XML texts.
Preferably, the markup information management process also includes:
By the digital pathological image marked according to tab area, mark is exported in a manner of image block adds markup information
Database purchase is noted, and is classified.
Preferably, markup information management process also includes:
According to certain regular partition it is different layers by the pathology markup information on digital pathological image.
The system marked according to a kind of digital pathological image provided by the invention, including:
Labeling module:Using the test pattern annotation tool based on pathology terminology bank, to digital pathological image to be marked
It is labeled;
Markup information management module:Based on XML format to the pathology markup information on the digital pathological image that has marked
The management being formatted;
Decision fusion module:The digital pathological image marked is distributed at least three people examination & verification, after examination & verification is passed through
The digital pathological image marked is stored to mark database, and by the data transfer in mark database to machine learning sample
Storehouse carries out machine learning.
Preferably, pathology terminology bank described in labeling module is indicated and stored some subsets using XML format.
Preferably, pathology markup information described in markup information management module include coordinate information, link information, classification and
Statistical information, store and represent with XML texts.
Preferably, the markup information management module also includes:
By the digital pathological image marked according to tab area, mark is exported in a manner of image block adds markup information
Database purchase is noted, and is classified.
Preferably, the markup information management module also includes:
According to certain regular partition it is different layers by the pathology markup information on digital pathological image.
Compared with prior art, the present invention has following beneficial effect:
The digital pathological image mark solution of a kind of specialized, standardization, systematization is provided, user can utilize each
Kind terminal device is labeled, retrieves, uploads and downloaded, and can improve annotating efficiency, promotes to form the disease of unified cooperative cooperating
Image labeling mechanism is managed, specialty and abundant pathological image mark database is provided for scientific research, promotes data mining, depth
Research meanses further the applying in intelligent pathological diagnosis such as study.
Brief description of the drawings
The detailed description made by reading with reference to the following drawings to non-limiting example, further feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is a kind of mark flow chart of the method for digital pathological image mark provided by the invention;
Fig. 2 is a kind of retrieval flow figure of the method for digital pathological image mark provided by the invention;
Fig. 3 is a kind of auditing flow figure of the method for digital pathological image mark provided by the invention;
Fig. 4 is a kind of mark database Optimizing Flow figure of the method for digital pathological image mark provided by the invention.
Embodiment
With reference to specific embodiment, the present invention is described in detail.Following examples will be helpful to the technology of this area
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill to this area
For personnel, without departing from the inventive concept of the premise, some changes and improvements can also be made.These belong to the present invention
Protection domain.
Fig. 1 is the mark flow chart of digital pathological image mask method, as shown in figure 1, this method includes:
Obtain digital pathological image to be marked.
User can download digital pathology to be marked from digital pathological image database to various subscriber terminal equipments
Image, the digital pathological image to be marked preserved in the equipment that can also open a terminal, and scaling can be carried out in image viewing interface
And drag-and-drop operation.
Subsets are chosen from pathology terminology bank, using the test pattern annotation tool based on pathology terminology bank, are treated
The digital pathological image of mark is labeled.Each user distributes an identification number, all markup informations all subsidiary mark persons
Identification number.
User can read the pathology terminology bank of existing various versions, can also be certainly such as tumor morphology code database
By adding self-defined pathology terminology bank, or retrieved according to demand of specialty from existing terminology bank and select entry to establish new disease
Terminology bank of science, and pathology terminology bank is indicated and stored using XML.Terminology bank is presented with tree-shaped structure, Yong Huke
With according to system and anatomical structure, organ, the level organized, or benign pernicious, tissue origin (cytology, institutional framework, tumour
Interstitial) level applicable subsets are chosen from pathology terminology bank, such as:Can according to brain, chest, belly, on
Limb, the anatomical structure of lower limb or digestive system, nervous system, kinematic system, internal system, urinary system, reproductive system, follow
Loop system, respiratory system, immune system etc. choose needed for subsets, then can according to lung, stomach, liver, gall-bladder, small intestine,
The organs such as bladder, uterus further choose subsets, also can be according to epithelial tissue, connective tissue, musculature, nerve fiber
Subsets are chosen Deng further.
User adds figure labeling according to above-mentioned pathology terminology bank to digital pathological image, and can add class to figure labeling
The semantic information such as type and annotation.Each mark user is correspondingly arranged on personal identification code, to distinguish different user addition
Figure labeling.The classification of figure labeling instrument has free paintbrush tool, navigation paintbrush tool, ruler tool, the rectangle tool, ellipse
Sired results tool, arrow instrument etc..User can add tag class, semantic category and word description class to the figure labeling region of selection afterwards
Markup information.Pictorial symbolization and semantic annotations both face towards the digital slices data structure of image pyramid and built, its coordinate letter
Breath and display scale with the scaling of digital pathological image.
The conventional label of management.User can add various entries as desired and be preserved to conventional tag entry, and by conventional label
Just do not have to repeat to add under personal identification number, when so next time uses.User when being labeled to digital pathological image,
The conventional tag entry of selection can be clicked directly on to add tag class mark, it is convenient and swift, efficiency can be improved, while have mark
There is normative and uniformity.
The management being formatted based on XML format to pathology markup information.
Pathology markup information can be divided into different based on pathology term, user profile, medical domain, application purpose etc.
Layer, and the data message for using statistical function to analyze each layer, such as:Layer 1 is concerned with the other mark of cell grade, and layer 2 is paid close attention to
Be glandular tube rank mark.User can manage mark layer, and each layer is added, deleted, renaming and order adjust
Deng operation;The attribute of each layer can be managed, the operation such as each layer of attribute is added, deletes and changed;Certain can be chosen
One layer, the markup information in individual layer is managed, change marking types, mark coordinate, mark label, mark word description;
It can be established the link between the mark of individual layer or each interlayer;Required image block can be chosen with crop tool to be preserved and led
Go out;May search for having opened the markup information in pathological image, such as search for " cancer ", then show in the form of a list it is all containing
The information of the mark of " cancer " word, click on a selection wherein position that can automatic jump to the mark;It can be pathological image
The identification number of interior part or all of markup information addition mark people;All formatting pathology markup information uses and contains seat
Mark the XML texts storage of information, link information, classification and statistical information and represent.
After digital pathological image mark, all markup informations on digital pathological image and this image can integrally be deposited
Storage can also store some region of digital pathological image, import and checked again when being needed so as to next time to mark database
And modification.The region of output image can be set in user, the way of output of image file, block size, overlaps, pantograph ratio
Example, additional information such as thumbnail, label, grand, file type and the compress mode of image file.Whole pathological image mark is completed
Afterwards, each tab area is stored and exported to mark database in a manner of image block adds markup information, and according to
The semantic information such as type and annotation is classified, and same image-region can be subordinated to different types of semantic information word bank.
Fig. 2 is a kind of retrieval flow figure of the method for digital pathological image mark provided by the invention, as shown in Fig. 2 with
Mark database is logined at family, chooses required retrieval mode, can retrieve the digital pathological image of whole subsidiary markup information,
The data with a certain class markup information can be retrieved.Digital pathological image is retrieved if choosing, digital pathological image can be passed through
Numbering is retrieved, if choosing retrieval markup information, can be carried out sub-category retrieval by marking label or semanteme, retrieved
The data of needs can be chosen into rear user, carry out batch download.
Audit the digital pathological image marked.
Fig. 3 is a kind of auditing flow figure of the method for digital pathological image mark provided by the invention, as shown in figure 3, examining
Core flow is related to three inter-related storehouses:Digital picture pathology storehouse, mark database and machine learning Sample Storehouse.User passes through
Various terminal equipment downloads required digital pathological image from digital pathological image storehouse, and is labeled on the terminal device,
Upload and preserve after the completion of mark.Examination & verification stores labeled data to mark database after passing through.User also can be from mark number simultaneously
The labeled data needed for oneself is downloaded according to storehouse.
Data transfer in mark database to machine learning Sample Storehouse is subjected to machine learning.
One of major function of the present invention is for the related scientific research of the intelligent pathological diagnosis such as data mining, deep learning
Abundant labeled data is provided, so the data of mark database finally reach machine learning Sample Storehouse and carry out machine learning, from
And continue to optimize mark database.
As shown in figure 4, pathology expert 1 is distributed to from digital pathological image storehouse by the digital pathological image not marked, disease
The digital pathological image marked is uploaded to mark database after the completion of the mark of expert 1 of science.Mark database will mark
Digital pathological image distribute to other at least three pathology experts (2,3,4) and carry out secondary review, the disease of secondary review
Two kinds of operations may be selected in each mark of digital pathological image of the expert of science to having marked:Agree to or oppose and add difference
Mark, for the mark of different opinions, decision-making is carried out by Decision fusion mechanism:Including creating confidence scale for each mark
Label, delete the mark that dispute is larger, confidence level is relatively low.To finally the markup information classification storage completed be audited, export to mark
Database and machine learning Sample Storehouse.
One skilled in the art will appreciate that except realizing system provided by the invention in a manner of pure computer readable program code
And its beyond each device, module, unit, completely can be by the way that method and step progress programming in logic be provided come the present invention
System and its each device, module, unit with gate, switch, application specific integrated circuit, programmable logic controller (PLC) and embedding
Enter the form of the controller that declines etc. to realize identical function.So system provided by the invention and its every device, module, list
Member is considered a kind of hardware component, and is used to realize that device, module, the unit of various functions also may be used to what is included in it
To be considered as the structure in hardware component;It both can be real that will can also be considered as device, module, the unit of realizing various functions
The software module of existing method can be the structure in hardware component again.
The specific embodiment of the present invention is described above.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or change within the scope of the claims, this not shadow
Ring the substantive content of the present invention.In the case where not conflicting, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (10)
- A kind of 1. method of digital pathological image mark, it is characterised in that including:Annotation step:Using the test pattern annotation tool based on pathology terminology bank, digital pathological image to be marked is carried out Mark;Markup information management process:The pathology markup information on the digital pathological image that has marked is carried out based on XML format The management of formatting;Decision fusion step:The digital pathological image marked is distributed at least three people examination & verification, the mark after passing through will be audited The digital pathological image of note is stored to mark database, and the data transfer in mark database to machine learning Sample Storehouse is entered Row machine learning.
- 2. the method for digital pathological image mark according to claim 1, it is characterised in that pathology described in annotation step Terminology bank is indicated and stored some subsets using XML format.
- 3. the method for digital pathological image mark according to claim 1, it is characterised in that in markup information management process The pathology markup information includes coordinate information, link information, classification and statistical information, is stored and is represented with XML texts.
- 4. the method for digital pathological image mark according to claim 1, it is characterised in that the markup information management step Suddenly also include:By the digital pathological image marked according to tab area, mark number is exported in a manner of image block adds markup information According to library storage, and classified.
- 5. the method for digital pathological image mark according to claim 1, it is characterised in that markup information management process is also Including:According to certain regular partition it is different layers by the pathology markup information on digital pathological image.
- A kind of 6. system of digital pathological image mark, it is characterised in that including:Labeling module:Using the test pattern annotation tool based on pathology terminology bank, digital pathological image to be marked is carried out Mark;Markup information management module:The pathology markup information on the digital pathological image that has marked is carried out based on XML format The management of formatting;Decision fusion module:The digital pathological image marked is distributed at least three people examination & verification, the mark after passing through will be audited The digital pathological image of note is stored to mark database, and the data transfer in mark database to machine learning Sample Storehouse is entered Row machine learning.
- 7. the system of digital pathological image mark according to claim 6, it is characterised in that pathology described in labeling module Terminology bank is indicated and stored some subsets using XML format.
- 8. the system of digital pathological image mark according to claim 6, it is characterised in that in markup information management module The pathology markup information includes coordinate information, link information, classification and statistical information, is stored and is represented with XML texts.
- 9. the system of digital pathological image mark according to claim 6, it is characterised in that the markup information manages mould Block also includes:By the digital pathological image marked according to tab area, mark number is exported in a manner of image block adds markup information According to library storage, and classified.
- 10. the system of digital pathological image mark according to claim 6, it is characterised in that the markup information management Module also includes:According to certain regular partition it is different layers by the pathology markup information on digital pathological image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710576906.1A CN107516005A (en) | 2017-07-14 | 2017-07-14 | A kind of method and system of digital pathological image mark |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710576906.1A CN107516005A (en) | 2017-07-14 | 2017-07-14 | A kind of method and system of digital pathological image mark |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107516005A true CN107516005A (en) | 2017-12-26 |
Family
ID=60721800
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710576906.1A Pending CN107516005A (en) | 2017-07-14 | 2017-07-14 | A kind of method and system of digital pathological image mark |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107516005A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108682453A (en) * | 2018-05-16 | 2018-10-19 | 四川大学 | A kind of Lung neoplasm labeling system |
CN108766538A (en) * | 2018-05-14 | 2018-11-06 | 宁波江丰生物信息技术有限公司 | A kind of labeling system of digital slices |
CN108830466A (en) * | 2018-05-31 | 2018-11-16 | 长春博立电子科技有限公司 | A kind of image content semanteme marking system and method based on cloud platform |
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 |
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 |
CN109378052A (en) * | 2018-08-31 | 2019-02-22 | 透彻影像(北京)科技有限公司 | The preprocess method and system of image labeling |
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 |
CN109783673A (en) * | 2019-01-11 | 2019-05-21 | 海东市平安正阳互联网中医医院有限公司 | A kind of mask method and device of tongue picture image |
CN109949907A (en) * | 2019-03-29 | 2019-06-28 | 西安交通大学 | Large-scale pathological image cooperation annotation method and system based on cloud |
US10489126B2 (en) | 2018-02-12 | 2019-11-26 | Oracle International Corporation | Automated code generation |
CN110532224A (en) * | 2019-08-13 | 2019-12-03 | 武汉中海庭数据技术有限公司 | A kind of file management system and method for deep learning mark sample |
CN111367445A (en) * | 2020-03-31 | 2020-07-03 | 中国建设银行股份有限公司 | Image annotation method and device |
US10733754B2 (en) | 2017-01-18 | 2020-08-04 | Oracle International Corporation | Generating a graphical user interface model from an image |
US10838699B2 (en) | 2017-01-18 | 2020-11-17 | Oracle International Corporation | Generating data mappings for user interface screens and screen components for an application |
CN112102331A (en) * | 2020-08-26 | 2020-12-18 | 广州金域医学检验中心有限公司 | Pathological section training image set acquisition method, system, equipment and medium |
US11094411B2 (en) | 2018-10-26 | 2021-08-17 | Guangzhou Kingmed Center for Clinical Laboratory Co., Ltd. | Methods and devices for pathologically labeling medical images, methods and devices for issuing reports based on medical images, and computer-readable storage media |
CN113793307A (en) * | 2021-08-23 | 2021-12-14 | 上海派影医疗科技有限公司 | Automatic labeling method and system suitable for multi-type pathological images |
CN116705289A (en) * | 2023-05-23 | 2023-09-05 | 北京透彻未来科技有限公司 | Cervical pathology diagnosis device based on semantic segmentation network |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289598A (en) * | 2011-08-24 | 2011-12-21 | 浙江大学 | Pathological section multi-granularity medical information remarking method and system |
US20140180721A1 (en) * | 2012-12-26 | 2014-06-26 | Volcano Corporation | Data Labeling and Indexing in a Multi-Modality Medical Imaging System |
CN105608319A (en) * | 2015-12-21 | 2016-05-25 | 江苏康克移软软件有限公司 | Digital pathological section labeling method and device |
CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪(厦门)医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
WO2017101142A1 (en) * | 2015-12-17 | 2017-06-22 | 安宁 | Medical image labelling method and system |
-
2017
- 2017-07-14 CN CN201710576906.1A patent/CN107516005A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289598A (en) * | 2011-08-24 | 2011-12-21 | 浙江大学 | Pathological section multi-granularity medical information remarking method and system |
US20140180721A1 (en) * | 2012-12-26 | 2014-06-26 | Volcano Corporation | Data Labeling and Indexing in a Multi-Modality Medical Imaging System |
WO2017101142A1 (en) * | 2015-12-17 | 2017-06-22 | 安宁 | Medical image labelling method and system |
CN105608319A (en) * | 2015-12-21 | 2016-05-25 | 江苏康克移软软件有限公司 | Digital pathological section labeling method and device |
CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪(厦门)医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10733754B2 (en) | 2017-01-18 | 2020-08-04 | Oracle International Corporation | Generating a graphical user interface model from an image |
US11119738B2 (en) | 2017-01-18 | 2021-09-14 | Oracle International Corporation | Generating data mappings for user interface screens and screen components for an application |
US10838699B2 (en) | 2017-01-18 | 2020-11-17 | Oracle International Corporation | Generating data mappings for user interface screens and screen components for an application |
US10489126B2 (en) | 2018-02-12 | 2019-11-26 | Oracle International Corporation | Automated code generation |
CN108766538A (en) * | 2018-05-14 | 2018-11-06 | 宁波江丰生物信息技术有限公司 | A kind of labeling system of digital slices |
CN108682453A (en) * | 2018-05-16 | 2018-10-19 | 四川大学 | A kind of Lung neoplasm labeling system |
CN108830466A (en) * | 2018-05-31 | 2018-11-16 | 长春博立电子科技有限公司 | A kind of image content semanteme marking system and method based on cloud platform |
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 |
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 |
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 |
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 |
CN109378052A (en) * | 2018-08-31 | 2019-02-22 | 透彻影像(北京)科技有限公司 | The preprocess method and system of image labeling |
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 |
US11094411B2 (en) | 2018-10-26 | 2021-08-17 | Guangzhou Kingmed Center for Clinical Laboratory Co., Ltd. | Methods and devices for pathologically labeling medical images, methods and devices for issuing reports based on medical images, and computer-readable storage media |
CN109783673A (en) * | 2019-01-11 | 2019-05-21 | 海东市平安正阳互联网中医医院有限公司 | A kind of mask method and device of tongue picture image |
CN109949907A (en) * | 2019-03-29 | 2019-06-28 | 西安交通大学 | Large-scale pathological image cooperation annotation method and system based on cloud |
CN110532224A (en) * | 2019-08-13 | 2019-12-03 | 武汉中海庭数据技术有限公司 | A kind of file management system and method for deep learning mark sample |
CN111367445A (en) * | 2020-03-31 | 2020-07-03 | 中国建设银行股份有限公司 | Image annotation method and device |
CN111367445B (en) * | 2020-03-31 | 2021-07-09 | 中国建设银行股份有限公司 | Image annotation method and device |
CN112102331A (en) * | 2020-08-26 | 2020-12-18 | 广州金域医学检验中心有限公司 | Pathological section training image set acquisition method, system, equipment and medium |
CN112102331B (en) * | 2020-08-26 | 2024-03-29 | 广州金域医学检验中心有限公司 | Training image set acquisition method, system, equipment and medium for pathological section |
CN113793307A (en) * | 2021-08-23 | 2021-12-14 | 上海派影医疗科技有限公司 | Automatic labeling method and system suitable for multi-type pathological images |
CN116705289A (en) * | 2023-05-23 | 2023-09-05 | 北京透彻未来科技有限公司 | Cervical pathology diagnosis device based on semantic segmentation network |
CN116705289B (en) * | 2023-05-23 | 2023-12-19 | 北京透彻未来科技有限公司 | Cervical pathology diagnosis device based on semantic segmentation network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107516005A (en) | A kind of method and system of digital pathological image mark | |
CN109065110B (en) | Method for automatically generating medical image diagnosis report based on deep learning method | |
Rogers | Visual media analysis for Instagram and other online platforms | |
Cabral et al. | The recent landscape of cancer research worldwide: a bibliometric and network analysis | |
US20070061703A1 (en) | Method and apparatus for annotating a document | |
JPWO2008087738A1 (en) | Disease name input support program, method and apparatus | |
CN101529410A (en) | Report generation with integrated quality management | |
CN104899340B (en) | A kind of IETM technical information fragment retrieval device and its search method based on fragment of most compacting | |
CN107077528A (en) | Picture archiving system with the text image link based on text identification | |
CN113161001B (en) | Improved LDA-based process path mining method | |
CA2883388A1 (en) | Mental modeling method and system | |
Ahmed et al. | Diagnosis recommendation using machine learning scientific workflows | |
Ahmadi et al. | Radiology reporting system data exchange with the electronic health record system: A case study in Iran | |
CN115458108A (en) | Visual diabetes big data intelligent analysis system fusing multivariate technology | |
Schmøkel et al. | FBAdLibrarian and Pykognition: open science tools for the collection and emotion detection of images in Facebook political ads with computer vision | |
Maulana et al. | The scientific progress and prospects of artificial intelligence for cancer detection: a bibliometric analysis | |
Ventakasubbu et al. | Deep learning-based brain tumour segmentation | |
Chen et al. | Treating a genre as a database: a digital research methodology for studying Chinese local gazetteers | |
Ball | Health Informatics | |
CN107016889A (en) | Background is provided for problem | |
CA2906297C (en) | Medical research retrieval engine | |
CN114861646A (en) | Data annotation platform for vertical field of medical science | |
Pinho et al. | Extensible architecture for multimodal information retrieval in medical imaging archives | |
Tran et al. | Scaling out and evaluation of obsecan, an automated section annotator for semi-structured clinical documents, on a large VA clinical corpus | |
Andresen et al. | Knowledge Distribution in German Drama |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |