CN108154914A - A kind of accurate anonymization storage and the method for retrieval medical image - Google Patents
A kind of accurate anonymization storage and the method for retrieval medical image Download PDFInfo
- Publication number
- CN108154914A CN108154914A CN201810074300.2A CN201810074300A CN108154914A CN 108154914 A CN108154914 A CN 108154914A CN 201810074300 A CN201810074300 A CN 201810074300A CN 108154914 A CN108154914 A CN 108154914A
- Authority
- CN
- China
- Prior art keywords
- data
- medical image
- anonymization
- information
- patient
- 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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
A kind of accurate anonymization storage and the method for retrieval medical image, include the following steps, first part, establish patient medical image data base, include the following steps：Step 1 collects patient information big data, and the medical image of a large amount of patients is collected by the hospital of cooperation, characteristics of human body reflect with statistical method to patient medical image information and illness progress data analysis；Characteristics of human body in step 1 and the information in illness preliminary date library according to irreversible compression algorithm, are generated indexing head by step 2, generation index；Step 3, anonymization processing；Step 4 stores into anonymous data library.Second part according to the required patient information of research-and-development activity, collects information by retrieval to anonymous data library, improves medical data search efficiency, including generation index and obtains two steps of data.The present invention has the characteristics that safety, is applicable in, and has popularization and practical value well, good economic benefit can be generated after widely promoting and applying.
Description
Technical field
The invention belongs to the preservation to patient medical image data set and transmission carry out anonymization processing technical field, especially
It is related to a kind of method of accurate anonymization storage and retrieval medical image.
Background technology
In medical health field to the preservation security presence hard and fast rule of image, this rule is eliminated these data
It is stored in the possibility at external data center.The prior art can utilize the store method for having existed some anonymizations to adapt to the rule
Then, but the problem is that：It cannot be classified to handle well using data during the prior art, i.e., it can not be from management
Similar data are obtained in data, and this demand is critically important to big data processing.
It is received with the development of economy and society, medical imaging is diagnosed as more and more people, diagnoses mode and treatment
The increase of the diversity and utilization rate of method so that patient's image data storage data quantity is increasing, and doctor retrieves figure
As case difficulty, this problem becomes more severe, establishes anonymization database, and retrieve information according to the doctor of acquisition and establish
Secondary index carries out image retrieval again, is a kind of mode for improving image retrieval efficiency.
Invention content
The object of the present invention is to provide a kind of accurate anonymization storages and the method for retrieval medical image, solve the prior art
The problem of processing patient information, process complicated and time consumption is long；Purpose is that more quick, accurate acquisition patient's number is provided for R＆D institution
According to method.
To achieve the above object, the present invention adopts the following technical scheme that：
A kind of accurate anonymization storage and the method for retrieval medical image, which is characterized in that include the following steps,
First part establishes patient medical image data base, includes the following steps：
Step 1 collects patient information big data：The case of a large amount of patients is collected by the hospital of cooperation, with statistical method
The characteristics of human body reflected to patient cases' information and illness carry out data analysis, and characteristics of human body is established respectively according to analysis result
With the preliminary date library of illness, the preliminary date library handled by the not yet anonymization of the clear and definite service object of legal agreements is protected safely
Shield obligation, and sign specific data confidentiality obligation agreement；
Step 2, generation index:It, will be in characteristics of human body in step 1 and illness preliminary date library according to irreversible compression algorithm
Information generation indexing head；
Step 3, anonymization processing：Patient information anonymization is handled；
Step 4 stores into anonymous data library；
According to the required patient information of research-and-development activity, information is obtained to anonymous data library by retrieval for second part,
Include the following steps：
Step 1, generation index：The required patient information of research-and-development activity is generated into rope by irreversible compression algorithm
Fuse ceases；
Step 2 obtains data：Index information is imported in anonymous data library and scanned for, data information needed for acquisition.
It is further preferred that the preliminary date library in the first part described in step 1 is patient medical image
TAG value database.
Further, the indexing head described in first part's step 2 includes at least indexing head length field and data
Entry Total no field, the indexing head length field characterize the length of the indexing head, the data entry Total no field characterization
The sum of stored data entry in data folder.
Further, first part's step 2 includes the following steps：
Step a, according to patient medical image TAG value database, the index type dictionary for needing to generate is obtained；
Step b, it is numbered according to the corresponding DICOM attribute of index type dictionary lookup, DICOM is to define Medical Image Format category
Property a kind of standard, than being patient or existing with explanation；
Step c, property value is obtained from DICOM images according to DICOM attribute numbers；
Step d, the property value obtained in above-mentioned steps c passes through DICOM data of the irreversible encryption algorithm generation with indexing head；
Step e, the DICOM data with indexing head are stored.
In addition, anonymization processing procedure includes the following steps in step 3 in the first part：
Step 1 obtains the Property Name for needing anonymity；
Step 2 is numbered according to the corresponding DICOM attribute of index type dictionary lookup；
Step 3 obtains property value according to DICOM attribute number from DICOM images；
Step 4 positions the property location in DICOM images according to DICOM attribute value；
Step 5 covers the data of the property location in step 4 according to anonymization standard.
It is further preferred that the patient medical image is ambition contour images or skeletal graph.
Compared with prior art the invention has the characteristics that and advantageous effect：
The present invention can become more meticulous patient medical image data information, and providing a kind of can ensure the same of protection patient information
When, simplify the complexity of data processing, moreover it is possible to standardize, standardize, scientific storage patient information；Solve data
The technical issues of cannot being classified to handle, i.e., can not obtain similar data from the data in management well.
The present invention is by DICOM data of the irreversible compression algorithm generation with indexing head, and in retrieval, input is simple, fast
Victory provides more quick, the accurate method for obtaining patient data for R＆D institution；
The present invention has the characteristics that safety, is applicable in, and has popularization and practical value well, can be generated after widely promoting and applying good
Good economic benefit.
Description of the drawings
Fig. 1 is the flow diagram of the method for a kind of accurate anonymization storage of the present invention and retrieval medical image.
Fig. 2 is that the present invention relates to the flow diagrams of generation index.
The flow diagram of Fig. 3 anonymization processing of the present invention.
Specific embodiment
Technological means, character of innovation, reached purpose and effect to realize the present invention are easy to understand, below to this
Invention further illustrates.
Specific specific embodiment of the embodiment recorded herein for the present invention, for illustrating the design of the present invention,
It is explanatory and illustrative, should not be construed as the limitation to embodiment of the present invention and the scope of the invention.Except what is recorded herein
Outside embodiment, those skilled in the art also be able to based on the application claims and specification disclosure of that using aobvious and
The other technical solutions being clear to, these technical solutions include any obvious using making for the embodiment to recording herein
The technical solution of substitutions and modifications.
A kind of accurate anonymization storage and the method for retrieval medical image, which is characterized in that include the following steps,
First part establishes patient medical data library, includes the following steps：
Step 1 collects patient information big data：The case of patient is collected by the hospital of cooperation, to patient cases' information operating
Statistical method carries out quantitative analysis to patient characteristics of human body and illness, characteristics of human body and disease is established respectively according to analysis result
The preliminary date library of disease, the preliminary date library safeguard protection justice handled by the not yet anonymization of the clear and definite service object of legal agreements
Business, and specific data confidentiality obligation agreement is signed, preliminary date library is the TAG value database of patient medical image, and patient cures
It is ambition contour images or skeletal graph to treat image.
Step 2, generation index:According to irreversible compression algorithm, by characteristics of human body in step 1 and illness preliminary date
Information generation indexing head in library, indexing head includes at least indexing head length field and data entry Total no field, indexing head are long
Spend the length that field characterizes the indexing head, stored data entry in data entry Total no field characterize data file
Sum.
Specifically include following steps：
Step a, the index type dictionary for needing to generate is obtained according to patient medical image TAG value database；
Step b, according to the corresponding DICOM attribute numbers of index type dictionary lookup；
Step c, property value is obtained from DICOM images according to DICOM attribute numbers；
Step d, the property value obtained in above-mentioned steps c passes through DICOM data of the irreversible encryption algorithm generation with indexing head；
Step e, the DICOM data with indexing head are stored.
Step 3, anonymization processing：Patient information anonymization is handled.
Specifically include following steps：
Step 1 obtains the Property Name for needing anonymity；
Step 2 is numbered according to the corresponding DICOM attribute of index type dictionary lookup；
Step 3 obtains property value according to DICOM attribute number from DICOM images；
Step 4, according to according to DICOM attribute number positioning DICOM images in property location；
Step 5 covers the data of the property location in step 4 according to anonymization standard.
Step 4 stores into anonymous data library；
According to the required patient information of research-and-development activity, information is obtained to anonymous data library by retrieval for second part,
Include the following steps：
Step 1, generation index：The required patient information of research-and-development activity is generated into rope by irreversible compression algorithm
Fuse ceases；
Step 2 obtains data：Index information is imported in anonymous data library and scanned for, data information needed for acquisition.
As shown in table 1, the rope that the present invention is generated according to property value is obtained in DICOM images by irreversible encryption algorithm
Draw.
The example of index that table 1 is generated according to property value is obtained in DICOM images by irreversible encryption algorithm.
As shown in table 2 and table 3, patient information is subjected to anonymization processing, weight code insurance shield patient information.
2 patient information anonymization before processing example of table.
Example after the processing of 3 patient information anonymization of table.
Described the foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
With within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention god.
Claims (6)
1. a kind of accurate anonymization storage and the method for retrieval medical image, which is characterized in that include the following steps,
First part establishes patient medical image data base, includes the following steps：
Step 1 collects patient information big data：The medical image of a large amount of patients is collected by the hospital of cooperation, to patient medical
Image information uses statistical method, carries out data analysis to patient characteristics of human body and illness, is established respectively according to analysis result
Characteristics of human body and the preliminary date library of illness, the preliminary date handled by the not yet anonymization of the clear and definite service object of legal agreements
Library safe guarding duties, and sign specific data confidentiality obligation agreement；
Step 2, generation index:It, will be in characteristics of human body in step 1 and illness preliminary date library according to irreversible compression algorithm
Information generation indexing head；
Step 3, anonymization processing：Patient information anonymization is handled；
Step 4 stores into anonymous data library；
According to the required patient information of research-and-development activity, information is obtained to anonymous data library by retrieval for second part,
Include the following steps：
Step 1, generation index：The required patient information of research-and-development activity is generated into rope by irreversible compression algorithm
Fuse ceases；
Step 2 obtains data：Index information is imported in anonymous data library and scanned for, data information needed for acquisition.
2. a kind of accurate anonymization storage as described in claim 1 and the method for retrieval medical image, it is characterised in that：It is described
Preliminary date library in first part described in step 1 is the TAG value database of patient medical image.
3. a kind of accurate anonymization storage as described in claim 1 and the method for retrieval medical image, it is characterised in that：It is described
Indexing head described in first part's step 2 includes at least indexing head length field and data entry Total no field, the index
Head length field characterizes the length of the indexing head, stored number in the data entry Total no field characterize data file
According to the sum of entry.
4. a kind of accurate anonymization storage as claimed in claim 2 and the method for retrieval medical image, it is characterised in that：It is described
First part's step 2 includes the following steps：
Step a, according to patient medical image TAG value database, the index type dictionary for needing to generate is obtained；
Step b, it is numbered according to the corresponding DICOM attribute of index type dictionary lookup；
Step c, property value is obtained from DICOM images according to DICOM attribute numbers；
Step d, the property value obtained in above-mentioned steps c passes through DICOM data of the irreversible encryption algorithm generation with indexing head；
Step e, the DICOM data with indexing head are stored.
5. a kind of accurate anonymization storage as claimed in claim 4 and the method for retrieval medical image, it is characterised in that：It is described
Anonymization processing procedure includes the following steps in step 3 in first part：
Step 1 obtains the Property Name for needing anonymity；
Step 2 is numbered according to the corresponding DICOM attribute of index type dictionary lookup；
Step 3 obtains property value according to DICOM attribute number from DICOM images；
Step 4 positions the property location in DICOM images according to DICOM attribute value；
Step 5 covers the data of the property location in step 4 according to anonymization standard.
6. a kind of method of the accurate anonymization storage and retrieval medical image as described in claim 1 ~ 5 any one, special
Sign is：The patient medical image is ambition contour images or skeletal graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810074300.2A CN108154914B (en) | 2018-01-25 | 2018-01-25 | Method for accurately storing and retrieving medical images anonymously |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810074300.2A CN108154914B (en) | 2018-01-25 | 2018-01-25 | Method for accurately storing and retrieving medical images anonymously |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108154914A true CN108154914A (en) | 2018-06-12 |
| CN108154914B CN108154914B (en) | 2021-07-27 |
Family
ID=62459104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810074300.2A Expired - Fee Related CN108154914B (en) | 2018-01-25 | 2018-01-25 | Method for accurately storing and retrieving medical images anonymously |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108154914B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243584A (en) * | 2018-07-09 | 2019-01-18 | 研靖信息科技（上海）有限公司 | The management method and system of medical imaging desensitization data based on content uniqueness |
| CN111145874A (en) * | 2018-11-02 | 2020-05-12 | 北京赛迈特锐医疗科技有限公司 | Medical image underlying basic data management system and management method thereof |
| CN117153419A (en) * | 2023-10-31 | 2023-12-01 | 湖北福鑫科创信息技术有限公司 | Data integration tool for medical institutions |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102160060A (en) * | 2008-09-19 | 2011-08-17 | 山姆国际医疗运动用品供应商 | Process for accessing nominative data such as customised medical file from local generation agent |
| CN104065631A (en) * | 2013-03-22 | 2014-09-24 | 上海联影医疗科技有限公司 | Local area network PACS service to WADO service system and access method thereto |
| US20150095070A1 (en) * | 2013-10-01 | 2015-04-02 | Mitchell Jay NewDelman | System, Process and Article of Manufacture for Human Health and Longevity Data Analysis |
| CN104680076A (en) * | 2013-11-27 | 2015-06-03 | 埃森哲环球服务有限公司 | System for anonymizing and aggregating protected health information |
| CN106169013A (en) * | 2015-05-19 | 2016-11-30 | 埃森哲环球服务有限公司 | For making protected information anonymization and the system of gathering |
| CN106570322A (en) * | 2016-10-26 | 2017-04-19 | 张景飞 | System for establishing psychological assessment archive based on mobile Internet technology |
| CN107547525A (en) * | 2017-08-14 | 2018-01-05 | 复旦大学 | A kind of method for secret protection of big data query processing |
-
2018
- 2018-01-25 CN CN201810074300.2A patent/CN108154914B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102160060A (en) * | 2008-09-19 | 2011-08-17 | 山姆国际医疗运动用品供应商 | Process for accessing nominative data such as customised medical file from local generation agent |
| CN104065631A (en) * | 2013-03-22 | 2014-09-24 | 上海联影医疗科技有限公司 | Local area network PACS service to WADO service system and access method thereto |
| US20150095070A1 (en) * | 2013-10-01 | 2015-04-02 | Mitchell Jay NewDelman | System, Process and Article of Manufacture for Human Health and Longevity Data Analysis |
| CN104680076A (en) * | 2013-11-27 | 2015-06-03 | 埃森哲环球服务有限公司 | System for anonymizing and aggregating protected health information |
| CN106169013A (en) * | 2015-05-19 | 2016-11-30 | 埃森哲环球服务有限公司 | For making protected information anonymization and the system of gathering |
| CN106570322A (en) * | 2016-10-26 | 2017-04-19 | 张景飞 | System for establishing psychological assessment archive based on mobile Internet technology |
| CN107547525A (en) * | 2017-08-14 | 2018-01-05 | 复旦大学 | A kind of method for secret protection of big data query processing |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243584A (en) * | 2018-07-09 | 2019-01-18 | 研靖信息科技（上海）有限公司 | The management method and system of medical imaging desensitization data based on content uniqueness |
| CN111145874A (en) * | 2018-11-02 | 2020-05-12 | 北京赛迈特锐医疗科技有限公司 | Medical image underlying basic data management system and management method thereof |
| CN117153419A (en) * | 2023-10-31 | 2023-12-01 | 湖北福鑫科创信息技术有限公司 | Data integration tool for medical institutions |
| CN117153419B (en) * | 2023-10-31 | 2024-01-26 | 湖北福鑫科创信息技术有限公司 | Data integration tool for medical institutions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108154914B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Daneshjou et al. | Checklist for evaluation of image-based artificial intelligence reports in dermatology: CLEAR derm consensus guidelines from the international skin imaging collaboration artificial intelligence working group | |
| Safdar et al. | Ethical considerations in artificial intelligence | |
| Kushida et al. | Strategies for de-identification and anonymization of electronic health record data for use in multicenter research studies | |
| Little et al. | Radiographic classification of temporal bone fractures: clinical predictability using a new system | |
| US20190236310A1 (en) | Self-contained system for de-identifying unstructured data in healthcare records | |
| US20190043611A1 (en) | Anonymizing data | |
| US20140379373A1 (en) | Management of Medical Information | |
| US20140372149A1 (en) | Method for processing patient-related data records | |
| CN106295182A (en) | A kind of personal identification method based on patient biological information | |
| KR102113806B1 (en) | Method and system for managing personal medical information data | |
| US20200285682A1 (en) | Systems and methods for dynamic data processing and graphical user interface processing | |
| CN108154914A (en) | A kind of accurate anonymization storage and the method for retrieval medical image | |
| CN104156434B (en) | The date storage method and its control device of a kind of biological sample bank | |
| CN109448811B (en) | Prescription auditing improvement method and device, electronic equipment and storage medium | |
| EP3659150B1 (en) | Device, system, and method for optimizing image acquisition workflows | |
| Ries et al. | Single-source tumor documentation-reusing oncology data for different purposes | |
| Clunie et al. | Report of the Medical Image De-Identification (MIDI) Task Group-Best Practices and Recommendations | |
| Lewis | Health informatics: information and communication | |
| Gibson et al. | Making the most of big data in plastic surgery: improving outcomes, protecting patients, informing service providers | |
| Daneshjou et al. | Checklist for evaluation of image-based AI reports in dermatology: CLEAR derm consensus guidelines from the International Skin Imaging Collaboration artificial intelligence working group | |
| Zhan et al. | Medical record encryption storage system based on Internet of Things | |
| Berry et al. | Standardizing data from the dead | |
| Vijayalakshmi et al. | Blockchain security for artificial intelligence-based clinical decision support tool | |
| Fenz et al. | Recognition and privacy preservation of paper-based health records | |
| Essefi et al. | Sensitive data discovery in care pathways using business process modelling and HL7-CDA |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210727 Termination date: 20220125 |