CN108154914B - Method for accurately storing and retrieving medical images anonymously - Google Patents
Method for accurately storing and retrieving medical images anonymously Download PDFInfo
- Publication number
- CN108154914B CN108154914B CN201810074300.2A CN201810074300A CN108154914B CN 108154914 B CN108154914 B CN 108154914B CN 201810074300 A CN201810074300 A CN 201810074300A CN 108154914 B CN108154914 B CN 108154914B
- Authority
- CN
- China
- Prior art keywords
- data
- index
- database
- information
- dicom
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A method for accurate anonymous storage and retrieval of medical images, comprising the steps of, in a first part, building a database of patient medical images, comprising the steps of: collecting big data of patient information, collecting medical images of a large number of patients through a cooperative hospital, and performing data analysis on human body characteristics and diseases reflected by the medical image information of the patients by using a statistical method; generating an index, and generating an index head from the information in the human body characteristics and disease preparation database in the step one according to an irreversible compression algorithm; step three, anonymization treatment; and step four, storing the data into an anonymous database. And the second part is used for collecting information from the anonymous database by searching according to the patient information required by research and development work, so that the medical data query efficiency is improved, and the method comprises two steps of generating indexes and acquiring data. The invention has the characteristics of safety, applicability and the like, has good popularization and practical values, and can generate good economic benefits after being widely popularized and applied.
Description
Technical Field
The invention belongs to the technical field of anonymization processing for saving and transmitting a medical image data set of a patient, and particularly relates to a method for accurately anonymizing, storing and retrieving a medical image.
Background
There are strict rules for image preservation security in the healthcare field that preclude the possibility of storing such data in an external data center. The prior art can adapt to the rule by using a preservation method with some anonymization, but has the following problems: with the prior art, data is not well classified for processing, i.e. similar data cannot be obtained from managed data, and this requirement is important for large data processing.
With the development of the economic society, medical image diagnosis is accepted by more and more people, the diversity and the utilization rate of diagnosis modes and treatment methods are increased, so that the problem that the data storage amount of patient image data is continuously increased and image cases are difficult to retrieve by doctors becomes more severe, an anonymization database is established, secondary indexes are established according to acquired doctor retrieval information and then image retrieval is carried out, and the method is a mode for improving the image retrieval efficiency.
Disclosure of Invention
The invention aims to provide a method for accurately storing and retrieving medical images anonymously, which solves the problems of complicated process and long time consumption of the prior art for processing patient information; the method aims to provide a method for more quickly and accurately acquiring the data of the patient for scientific research units.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for accurately anonymously storing and retrieving medical images, comprising the steps of,
a first part, establishing a patient medical image database, comprising the steps of:
step one, collecting big data of patient information: collecting a large number of patient cases through a cooperative hospital, performing data analysis on human body characteristics and symptoms reflected by patient case information by using a statistical method, respectively establishing a prepared database of the human body characteristics and symptoms according to an analysis result, defining security protection obligations of the prepared database of a service object which is not anonymized through a legal agreement, and signing a clear data confidentiality obligation agreement;
generating an index, namely generating an index head from the information in the human body characteristic and disease preparation database in the step one according to an irreversible compression algorithm;
step three, anonymization treatment: anonymizing the patient information;
step four, storing the data into an anonymous database;
and a second part, obtaining information from the anonymous database by searching according to patient information required by research and development work, comprising the following steps:
step one, generating an index: generating index information from patient information required by research and development work through an irreversible compression algorithm;
step two, acquiring data: and importing the index information into an anonymous database, searching and acquiring the required data information.
Further preferably, the preliminary database of step one in the first part is a TAG value database of patient medical images.
Further, the index header in the first part of step two at least includes an index header length field and a data entry total number field, the index header length field represents the length of the index header, and the data entry total number field represents the total number of data entries stored in the data folder.
Further, the first part of the second step comprises the following steps:
step a, acquiring an index type dictionary to be generated according to a patient medical image TAG value database;
b, searching corresponding DICOM attribute numbers according to the index type dictionary, wherein the DICOM is a standard for defining the format attribute of the medical image, and the specification is patient or existing;
step c, acquiring an attribute value from the DICOM image according to the DICOM attribute number;
d, generating DICOM data with index heads by the attribute values acquired in the step c through an irreversible encryption algorithm;
and e, storing the DICOM data with the index header.
In addition, the anonymization processing procedure in step three in the first part comprises the following steps:
step 1, acquiring an attribute name needing anonymity;
step 2, searching a corresponding DICOM attribute number according to the index type dictionary;
step 3, acquiring an attribute value from the DICOM image according to the DICOM attribute number;
step 4, positioning the attribute position in the DICOM image according to the DICOM attribute value;
and 5, covering the data of the attribute position in the step 4 according to anonymization standards.
More preferably, the patient medical image is a cardiothoracic contour image or a bone map.
Compared with the prior art, the invention has the following characteristics and beneficial effects:
the invention can refine the medical image data information of the patient, and provides a method which can simplify the complexity of data processing and can store the patient information in a standardized, normalized and scientific manner while ensuring the protection of the patient information; the technical problem that data cannot be well classified for processing, namely similar data cannot be obtained from managed data is solved.
According to the invention, the DICOM data with the index head is generated through the irreversible compression algorithm, the input is simple and quick during the retrieval, and a method for acquiring the patient data more quickly and accurately is provided for scientific research units;
the invention has the characteristics of safety, applicability and the like, has good popularization and practical values, and can generate good economic benefits after being widely popularized and applied.
Drawings
Fig. 1 is a flow chart illustrating a method for accurately anonymously storing and retrieving medical images according to the present invention.
FIG. 2 is a flow chart of the present invention relating to generating an index.
Fig. 3 is a schematic flow chart of the anonymization processing according to the present invention.
Detailed Description
In order to make the technical means, innovative features, objectives and functions realized by the present invention easy to understand, the present invention is further described below.
The examples described herein are specific embodiments of the present invention, are intended to be illustrative and exemplary in nature, and are not to be construed as limiting the scope of the invention. In addition to the embodiments described herein, those skilled in the art will be able to employ other technical solutions which are obvious based on the disclosure of the claims and the specification of the present application, and these technical solutions include technical solutions which make any obvious replacement or modification for the embodiments described herein.
A method for accurately anonymously storing and retrieving medical images, comprising the steps of,
the first part, establishing a patient medical database, comprises the following steps:
step one, collecting big data of patient information: the method comprises the steps of collecting patient cases through a cooperative hospital, carrying out quantity analysis on patient case information by applying a statistical method, respectively establishing a prepared database of the human body characteristics and the disease symptoms according to analysis results, defining the security protection obligation of the prepared database of a service object which is not anonymized through a legal agreement, and signing a clear data security obligation agreement, wherein the prepared database is a TAG value database of a patient medical image, and the patient medical image is a heart and chest contour image or a skeleton image.
And step two, generating an index, namely generating an index head from the information in the human body characteristic and disease preparation database in the step one according to an irreversible compression algorithm, wherein the index head at least comprises an index head length field and a data entry total number field, the index head length field represents the length of the index head, and the data entry total number field represents the total number of the data entries stored in the data folder.
The method specifically comprises the following steps:
step a, acquiring an index type dictionary to be generated according to a patient medical image TAG value database;
b, searching a corresponding DICOM attribute number according to the index type dictionary;
step c, acquiring an attribute value from the DICOM image according to the DICOM attribute number;
d, generating DICOM data with index heads by the attribute values acquired in the step c through an irreversible encryption algorithm;
and e, storing the DICOM data with the index header.
Step three, anonymization treatment: anonymizing the patient information.
The method specifically comprises the following steps:
step 1, acquiring an attribute name needing anonymity;
step 2, searching a corresponding DICOM attribute number according to the index type dictionary;
step 3, acquiring an attribute value from the DICOM image according to the DICOM attribute number;
step 4, positioning the attribute position in the DICOM image according to the DICOM attribute number;
and 5, covering the data of the attribute position in the step 4 according to anonymization standards.
Step four, storing the data into an anonymous database;
and a second part, obtaining information from the anonymous database by searching according to patient information required by research and development work, comprising the following steps:
step one, generating an index: generating index information from patient information required by research and development work through an irreversible compression algorithm;
step two, acquiring data: and importing the index information into an anonymous database, searching and acquiring the required data information.
As shown in table 1, the present invention obtains an index generated by an irreversible encryption algorithm according to the attribute value obtained from the DICOM image.
Table 1 example of an index generated by an irreversible encryption algorithm from the acquired attribute values in the DICOM image.
As shown in tables 2 and 3, the patient information is anonymized and the patient information is re-protected.
Table 2 patient information anonymization pre-processing example.
Table 3 example after anonymization of patient information.
The above description is only exemplary of the present invention and should not be taken as limiting the invention, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A method for accurately anonymously storing and retrieving medical images, comprising the steps of,
a first part, establishing a patient medical image database, comprising the steps of:
step one, collecting big data of patient information: collecting medical images of a large number of patients through a cooperative hospital, performing data analysis on the human body characteristics and symptoms of the patients by applying a statistical method to the medical image information of the patients, respectively establishing a prepared database of the human body characteristics and symptoms according to the analysis result, defining the security protection obligation of the prepared database of a service object which is not anonymized through a legal agreement, and signing a clear data confidentiality obligation agreement;
generating an index, namely generating an index head from the information in the human body characteristic and disease preparation database in the step one according to an irreversible compression algorithm, wherein the index head in the step two at least comprises an index head length field and a data entry total number field, the index head length field represents the length of the index head, and the data entry total number field represents the total number of data entries stored in a data folder;
step three, anonymization treatment: anonymizing the patient information;
step four, storing the data into an anonymous database;
and a second part, obtaining information from the anonymous database by searching according to patient information required by research and development work, comprising the following steps:
step one, generating an index: generating index information from patient information required by research and development work through an irreversible compression algorithm;
step two, acquiring data: and importing the index information into an anonymous database, searching and acquiring the required data information.
2. A method for accurate anonymous storage and retrieval of medical images as defined in claim 1, wherein: the preliminary database described in step one of the first section is a TAG value database of patient medical images.
3. A method for accurate anonymous storage and retrieval of medical images as defined in claim 2, wherein: the first part of the second step comprises the following steps:
step a, acquiring an index type dictionary to be generated according to a patient medical image TAG value database;
b, searching a corresponding DICOM attribute number according to the index type dictionary;
step c, acquiring an attribute value from the DICOM image according to the DICOM attribute number;
d, generating DICOM data with index heads by the attribute values acquired in the step c through an irreversible encryption algorithm;
and e, storing the DICOM data with the index header.
4. A method for accurate anonymous storage and retrieval of medical images as defined in claim 3, wherein: the anonymization processing process in the third step in the first part comprises the following steps:
step 1, acquiring an attribute name needing anonymity;
step 2, searching a corresponding DICOM attribute number according to the index type dictionary;
step 3, acquiring an attribute value from the DICOM image according to the DICOM attribute number;
step 4, positioning the attribute position in the DICOM image according to the DICOM attribute value;
and 5, covering the data of the attribute position in the step 4 according to anonymization standards.
5. The method for accurately anonymously storing and retrieving medical images according to any one of claims 1 to 4, wherein: the medical image of the patient is a cardiothoracic contour image or a skeleton image.
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 CN108154914A (en) | 2018-06-12 |
| CN108154914B true 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) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243584B (en) * | 2018-07-09 | 2020-07-07 | 研境信息科技(上海)有限公司 | Medical image desensitization data management method and system 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 |
| 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 |
Citations (6)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150095070A1 (en) * | 2013-10-01 | 2015-04-02 | Mitchell Jay NewDelman | System, Process and Article of Manufacture for Human Health and Longevity Data Analysis |
-
2018
- 2018-01-25 CN CN201810074300.2A patent/CN108154914B/en not_active Expired - Fee Related
Patent Citations (6)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108154914A (en) | 2018-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Johnson et al. | MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs | |
| CN111414393B (en) | Semantic similar case retrieval method and equipment based on medical knowledge graph | |
| US10818383B2 (en) | Hospital matching of de-identified healthcare databases without obvious quasi-identifiers | |
| CN108154914B (en) | Method for accurately storing and retrieving medical images anonymously | |
| Johnson et al. | Mimic-cxr-jpg-chest radiographs with structured labels | |
| CN112883157A (en) | Method and device for standardizing multi-source heterogeneous medical data | |
| US11769584B2 (en) | Face reattachment to brain imaging data | |
| US20180276248A1 (en) | Systems and methods for storing and selectively retrieving de-identified medical images from a database | |
| CN109448811B (en) | Prescription auditing improvement method and device, electronic equipment and storage medium | |
| CN111292814A (en) | Medical data standardization method and device | |
| US20170132372A1 (en) | Integrating and/or adding longitudinal information to a de-identified database | |
| Ceusters et al. | Clinical data wrangling using ontological realism and referent tracking | |
| CN112002413B (en) | Intelligent cognitive system, equipment and storage medium for cardiovascular system infection | |
| CN112507138B (en) | Method and device for constructing special disease knowledge map, medium and electronic equipment | |
| CN106844325B (en) | Medical information processing method and medical information processing apparatus | |
| CN109522331B (en) | Individual-centered regionalized multi-dimensional health data processing method and medium | |
| WO2023240837A1 (en) | Service package generation method, apparatus and device based on patient data, and storage medium | |
| CN114154514B (en) | Traditional Chinese medicine syndrome type identification method and system | |
| US20230032180A1 (en) | Method and system for empowering cancer patient(s) | |
| CN109063507A (en) | A kind of general design model for hospital information system analysis | |
| Berry et al. | Standardizing data from the dead | |
| CN111079021B (en) | Method, device, server and storage medium for recommending medical information content | |
| CN108170828B (en) | Structured clinical diagnosis term set construction method and system | |
| CN113380424A (en) | Automatic generation method and automatic generation device for follow-up plan and storage medium | |
| US20160371457A1 (en) | System and Method for Data Analyzing of Health-Related Data |
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 |