CN107239666A - A kind of method and system that medical imaging data are carried out with desensitization process - Google Patents
A kind of method and system that medical imaging data are carried out with desensitization process Download PDFInfo
- Publication number
- CN107239666A CN107239666A CN201710433608.7A CN201710433608A CN107239666A CN 107239666 A CN107239666 A CN 107239666A CN 201710433608 A CN201710433608 A CN 201710433608A CN 107239666 A CN107239666 A CN 107239666A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- sensitive information
- medical imaging
- file
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioethics (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Image Analysis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of method and system that medical imaging data are carried out with desensitization process, it is characterised in that comprises the following steps:Step 1, using Historical medical's image data as training set, the image-sensitive region identification model corresponding with set image-sensitive region is trained using deep learning convolutional neural networks;The pending medical imaging data of step 2, reading, analyze and determine the file attribute sensitive information in the medical imaging data and determine the picture material sensitive information i.e. image-sensitive region in the medical imaging data by described image sensitizing range identification model;Step 3, desensitization process and record storage are carried out to identified file attribute sensitive information and picture material sensitive information.The form and image information that method of the present invention can retain original medical image data are easy to subsequent analysis to handle, and can remove the sensitive information in text attribute and presentation content.
Description
Technical field
It is more particularly to a kind of that medical imaging data are carried out the present invention relates to medical artificial intelligence and big data process field
The method and system of desensitization process.
Background technology
As the new artificial intelligence technology advantage by kernel of deep learning framework emerges, length is all obtained in every field
The development and propulsion of foot, the people such as AlphaGo, automatic driving car, speech recognition expect technology for many years also when very short
It is interior to be broken through.Among visible future, deep learning is also by the big data analysis for promoting medical industry and artificial intelligence
Applicable development.Therefore deep learning needs the training of substantial amounts of medical imaging data progress model, and to these image numbers
According to the demand of desensitization process just seem extremely urgent.
Wherein, dicom standard is a standard exchanged with managed care image data and related data, can be used for doctor
Communicated between information system or between medical information system and medical equipment.The medical equipment collection generation of hospital
Patient checks that image file is DICOM file.Lived because DICOM image files include such as patient name, patient ID, patient in itself
The information such as location, directly by artificial intelligence fields such as the image file application deep learnings, it is possible to invade the right of privacy of patient.
It is therefore desirable to study a kind of effective and high speed, easily desensitization process method can solve the problem that two above-mentioned
Problem, and patient can be protected again while quickly propelling the artificial intelligence approaches such as deep learning and being applied in medical domain
Privacy method.
The content of the invention
In view of the defect that prior art is present, the invention aims to provide a kind of to desensitize to medical imaging data
The method of processing, the form and image information that this method can retain original medical image data is easy to subsequent analysis to handle, and
The sensitive information in text attribute and presentation content can be removed.
To achieve these goals, technical scheme:
A kind of method that medical imaging data are carried out with desensitization process, it is characterised in that comprise the following steps:
Step 1, using Historical medical's image data as training set, using deep learning convolutional neural networks train with it is set
The corresponding image-sensitive region identification model in fixed image-sensitive region;
The pending medical imaging data of step 2, reading, analyze and determine the file attribute in the medical imaging data
Sensitive information and determine that picture material in the medical imaging data is sensitive by described image sensitizing range identification model
Information is image-sensitive region;
Step 3, desensitization process is carried out to identified file attribute sensitive information and picture material sensitive information and is remembered
Address book stored.
Further, the step 1 includes:
Step 11, obtain from database several DICOM file data samples over the years and with each DICOM file over the years
The corresponding image file data of data sample;
Step 12, determine image-sensitive region and selected in acquired image file data containing having determined image
The image file data of sensitizing range;
Step 13, respectively to it is selected go out image file data carry out image preprocessing, to extract image file number
View data in;
Step 14, respectively to extract view data be marked and by after mark view data generation can be expanded
Tab file;
Step 15, using the tab file and extracted view data as mode input parameter, utilize deep learning
Convolutional neural networks train the image-sensitive region identification model corresponding with set image-sensitive region.
Further, the step 1 also includes:
Step 16, select from database some containing the image file data for having determined image-sensitive region again,
And the image file data are subjected to reliability demonstration as test data to image-sensitive region identification model.
Further, in the step 3 to identified file attribute sensitive information carry out desensitization process refer to really
Fixed file attribute sensitive information carries out erase operation or cryptographic operation;Identified picture material sensitive information is taken off
Quick processing refers to carry out image blurringization processing to the image-region where identified picture material sensitive information.
It is preferred that, described cryptographic operation refers to carry out Hash encryption to identified file attribute sensitive information.
Further, the step in the step 3 corresponding to record storage is:
The data carried out to identified file attribute sensitive information involved by desensitization process are charged into desensitization daily record respectively
Desensitization daily record is charged to the data syn-chronization that identified picture material sensitive information is carried out involved by desensitization process simultaneously;And according to
Data are carried out sub-category storage by file attribute sensitive information and picture material sensitive information.
It is another object of the present invention to provide a kind of system that medical imaging data are carried out with desensitization process, its feature exists
In, including:
Medical imaging data read module, it can read pending medical imaging data from database;
The file attribute sensitive information searching modul being connected with the medical imaging data read module, it can be analyzed
And determine the file attribute sensitive information in the medical imaging data;
The picture material sensitive information searching modul being connected with the medical imaging data read module, it can pass through
Described image sensitizing range identification model determines the picture material sensitive information i.e. image sensitizing range in the medical imaging data
Domain, described image sensitizing range identification model is by using Historical medical's image data as training set, utilizing deep learning convolution
Neural metwork training goes out the identification model corresponding with set image-sensitive region;
At the desensitization being connected with the file attribute sensitive information searching modul, picture material sensitive information searching modul
Module is managed, it can carry out desensitization process to identified file attribute sensitive information and picture material sensitive information;
And the data after desensitization process are carried out with the record storage module of record storage.
Further, the medical imaging data read module includes:
Historical data reading submodule, its can be obtained from database several DICOM file data samples over the years with
And the image file data corresponding with each DICOM file data sample over the years;
Image file data extracting sub-module, it can be according to determined image-sensitive region, from acquired image text
Number of packages is selected in containing the image file data for having determined image-sensitive region;
Image preprocessing submodule, its can respectively to it is selected go out image file data carry out image preprocessing, with
Extract the view data in image file data;
View data marks submodule, and it can be marked and by the image after mark to extracting view data respectively
The tab file that data generation can be expanded;
Model creation submodule, it can be joined using the tab file and extracted view data as mode input
Number, trains the image-sensitive region corresponding with set image-sensitive region using deep learning convolutional neural networks and knows
Other model.
Further, the medical imaging data read module also includes:
Model verifies submodule, and it can select some containing having determined image-sensitive region from database again
Image file data, and the image file data are carried out reliable as test data to image-sensitive region identification model
Property checking.
Further, desensitization process is carried out to identified file attribute sensitive information in the desensitization process module to refer to
Erase operation or cryptographic operation are carried out to identified file attribute sensitive information;To identified picture material sensitive information
Desensitization process is carried out to refer to carry out image blurringization processing to the image-region where identified picture material sensitive information.
It is preferred that, described cryptographic operation refers to carry out Hash encryption to identified file attribute sensitive information.
Further, the record storage module is to the step corresponding to data progress record storage:
The data carried out to identified file attribute sensitive information involved by desensitization process are charged into desensitization daily record respectively
Desensitization daily record is charged to the data syn-chronization that identified picture material sensitive information is carried out involved by desensitization process simultaneously;And according to
Data are carried out sub-category storage by file attribute sensitive information and picture material sensitive information.
Compared with prior art, beneficial effects of the present invention:
The present invention is sensitive to image by using deep learning convolutional neural networks training image sensitizing range identification model
Region is identified and carries out desensitization process;In combination with desensitization daily record, the storage of desensitization data is completed;It being capable of efficiently and accurately
Ground handles medical imaging data, and then protects the privacy of patient to be not leaked.
Brief description of the drawings
Fig. 1 is the corresponding flow chart of steps of the method for the invention;
Fig. 2 is the corresponding structural principle block diagram of system of the present invention.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme is clearly and completely described, it is clear that described embodiment is that a part of the invention is real
Apply example, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
Property work under the premise of the every other embodiment that is obtained, belong to the scope of protection of the invention.
As shown in figure 1, a kind of method that medical imaging data are carried out with desensitization process, it is characterised in that including following step
Suddenly:
Step 1, using Historical medical's image data as training set, using deep learning convolutional neural networks train with it is set
The corresponding image-sensitive region identification model in fixed image-sensitive region;Further, the step 1 includes:Step 11, from
Several DICOM file data samples over the years are obtained in database (it includes PACS thesaurus) and literary with each DICOM over the years
The corresponding image file data of part data sample;Step 12, determine image-sensitive region and in acquired image file number
Selected in containing the image file data for having determined image-sensitive region;Step 13, respectively to it is selected go out image text
Number of packages is according to image preprocessing is carried out, to extract the view data in image file data;Step 14, respectively to extracting image
The tab file that data are marked and can be expanded the view data generation after mark, the mark is needed according to user
Certain image-region be identified and record corresponding coordinate information, the tab file that can be expanded can be xml lattice
The file of formula;Step 15, using the tab file and extracted view data as mode input parameter, utilize deep learning
Convolutional neural networks train the image-sensitive region identification model corresponding with set image-sensitive region and obtain one
The individual reliable model parameter that predicts the outcome, the identification for image-sensitive region;If step 16, selecting again from database
It is dry to contain the image file data for having determined image-sensitive region, and using the image file data as test data, to figure
As sensitizing range identification model carries out reliability demonstration.
Step 2, the initial data of reading medical imaging are pending medical imaging data, analyze and determine the medical treatment
Sensitive information in image data, specifically includes file attribute sensitive information, picture material sensitive information, and wherein picture material is quick
Sense information determines picture material sensitive information in the medical imaging data i.e. by described image sensitizing range identification model
Image-sensitive region;Further, the file attribute sensitive information, picture material sensitive information are needed by user according to use
Sets itself, file attribute sensitive information can be the category such as patient's name and unit one belongs to entrained by DICOM file as described
Property field;Picture material sensitive information can be that some of view data band of position such as has patient's name's age sensitivity
Information, because these information and image combine together, it is therefore desirable to pass through for the sensitive information in these images described
Image recognition model finds the sensitive information.
Step 3, desensitization process is carried out to identified file attribute sensitive information and picture material sensitive information and is remembered
Address book stored, the desensitization information processing includes:The processing of file attribute sensitive information and the processing of picture material sensitive information.
Further, desensitization process is carried out to identified file attribute sensitive information in the step 3 to refer to identified file
Attribute sensitive information carries out erase operation or cryptographic operation;Carrying out desensitization process to identified picture material sensitive information is
Refer to and image blurringization processing is carried out to the image-region where identified picture material sensitive information, such as hide or mosaic
Processing.It is preferred that, described cryptographic operation refers to carry out Hash encryption to identified file attribute sensitive information.
Further, the step in the step 3 corresponding to record storage is:
The data carried out to identified file attribute sensitive information involved by desensitization process are charged into desensitization daily record respectively
Desensitization daily record is charged to the data syn-chronization that identified picture material sensitive information is carried out involved by desensitization process simultaneously;And according to
Data are carried out sub-category storage by file attribute sensitive information and picture material sensitive information, after being carried out to help collection data
It is continuous to utilize.Such as check that the legitimacy of image file after modification is normative, and preserve original of the covering containing sensitive information.Data
Recording process comprises the following steps:1. check processing sensitive information after image file file stream whether legacy specification, if
It is no, then illegal nonstandard attribute information is pointed out, and journal file is write information into, and the processing of current file is skipped, it is right
Next file in list is handled;2. using the mode that saves as, cover the original containing sensitive information;3. save as
Success, the success of current image file desensitization process, other files in sequential processes list.
Such as Fig. 2, it is another object of the present invention to provide a kind of system that medical imaging data are carried out with desensitization process, its
It is characterised by, including:
Medical imaging data read module, it can read pending medical imaging data from database;
The file attribute sensitive information searching modul being connected with the medical imaging data read module, it can be analyzed
And determine the file attribute sensitive information in the medical imaging data;Further, file attribute sensitive information is analyzed and true
Determining process includes 1. loading configuration files, and reading needs file attribute information title to be processed, and selection is actually needed according to user
Need desensitization file attribute information, such as patient information (include patient's relation information, patient identification information, patient statistics,
Patient's medical information), and diagnosis information (comprising medical relation information, identification information of going to a doctor, status information of going to a doctor, medical letter of being admitted to hospital
Breath, discharge information of going to a doctor, arrangement information of going to a doctor).Enumerate part sensitive information in a tabular form below:
Patient information:
Diagnosis information:
The picture material sensitive information searching modul being connected with the medical imaging data read module, it can pass through
Described image sensitizing range identification model determines the picture material sensitive information i.e. image sensitizing range in the medical imaging data
Domain, described image sensitizing range identification model is by using Historical medical's image data as training set, utilizing deep learning convolution
Neural metwork training goes out the identification model corresponding with set image-sensitive region;Further, the file attribute is quick
Information, picture material sensitive information are felt by user according to using sets itself is needed, and file attribute sensitive information can be with as described
It is the attribute fields such as patient's name and unit one belongs to entrained by DICOM file;Picture material sensitive information can be picture number
According to some of the band of position such as there is patient's name's age sensitive information, because these information are combined together with image
, it is therefore desirable to the sensitive information is found by described image recognition model for the sensitive information in these images;Such as H3.
Examination operation is done to information sensing area, because the operation of equipment difference or hospital technician are different, depositing in some image files
Some sensitive informations, the legal name of such as patient, the date of birth of patient, hospital name, hospital can be preserved in storage image information
The sensitive informations such as address are accomplished by carrying out lookup examination to multizone by the image sensitive information searching modul of the present invention.If
There is sensitive information, then the next step sensitizing range result that is detected by identification model of processing is done to sensitizing range and to need
Do hiding or mosaic and operate and enter the image information retrography after processing in the file stream of image file in position to be processed.
At the desensitization being connected with the file attribute sensitive information searching modul, picture material sensitive information searching modul
Module is managed, it can carry out desensitization process to identified file attribute sensitive information and picture material sensitive information;
And the data after desensitization process are carried out with the record storage module of record storage.
Further, the medical imaging data read module includes:
Historical data reading submodule, its can be obtained from database several DICOM file data samples over the years with
And the image file data corresponding with each DICOM file data sample over the years;
Image file data extracting sub-module, it can be according to determined image-sensitive region, from acquired image text
Number of packages is selected in containing the image file data for having determined image-sensitive region;
Image preprocessing submodule, its can respectively to it is selected go out image file data carry out image preprocessing, with
Extract the view data in image file data;
View data marks submodule, and it can be marked and by the image after mark to extracting view data respectively
The tab file that data generation can be expanded;
Model creation submodule, it can be joined using the tab file and extracted view data as mode input
Number, trains the image-sensitive region corresponding with set image-sensitive region using deep learning convolutional neural networks and knows
Other model.
Further, the medical imaging data read module also includes:
Model verifies submodule, and it can select some containing having determined image-sensitive region from database again
Image file data, and the image file data are carried out reliable as test data to image-sensitive region identification model
Property checking.
Further, desensitization process is carried out to identified file attribute sensitive information in the desensitization process module to refer to
Identified file attribute sensitive information is erased or deletion action or cryptographic operation;It is quick to identified picture material
Sense information carries out desensitization process and refers to carry out image blurringization to the image-region where identified picture material sensitive information
Processing.
It is preferred that, described cryptographic operation refers to carry out Hash encryption to identified file attribute sensitive information.
Further, the record storage module is to the step corresponding to data progress record storage:
The data carried out to identified file attribute sensitive information involved by desensitization process are charged into desensitization daily record respectively
Desensitization daily record is charged to the data syn-chronization that identified picture material sensitive information is carried out involved by desensitization process simultaneously;And according to
Data are carried out sub-category storage by file attribute sensitive information and picture material sensitive information.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, technique according to the invention scheme and its
Inventive concept is subject to equivalent substitution or change, should all be included within the scope of the present invention.
Claims (10)
1. a kind of method that medical imaging data are carried out with desensitization process, it is characterised in that comprise the following steps:
Step 1, using Historical medical's image data as training set, using deep learning convolutional neural networks train with it is set
The corresponding image-sensitive region identification model in image-sensitive region;
The pending medical imaging data of step 2, reading, analyze and determine that the file attribute in the medical imaging data is sensitive
Information and the picture material sensitive information in the medical imaging data is determined by described image sensitizing range identification model
That is image-sensitive region;
Step 3, carry out desensitization process to identified file attribute sensitive information and picture material sensitive information and record to deposit
Storage.
2. the method according to claim 1 that medical imaging data are carried out with desensitization process, it is characterised in that:
The step 1 includes:
Step 11, obtain from database several DICOM file data samples over the years and with each DICOM file data over the years
The corresponding image file data of sample;
Step 12, determine image-sensitive region and selected in acquired image file data containing having determined that image is sensitive
The image file data in region;
Step 13, respectively to it is selected go out image file data carry out image preprocessing, to extract in image file data
View data;
Step 14, it is marked and by the mark that can be expanded of view data generation after mark to extracting view data respectively
Remember file;
Step 15, using the tab file and extracted view data as mode input parameter, utilize deep learning convolution
Neural metwork training goes out the image-sensitive region identification model corresponding with set image-sensitive region.
3. the method according to claim 1 that medical imaging data are carried out with desensitization process, it is characterised in that:
The step 1 also includes:
Step 16, select from database some containing the image file data for having determined image-sensitive region again, and will
The image file data carry out reliability demonstration as test data to image-sensitive region identification model.
4. the method according to claim 1 that medical imaging data are carried out with desensitization process, it is characterised in that:
Identified file attribute sensitive information progress desensitization process is referred in the step 3 quick to identified file attribute
Sense information carries out erase operation or cryptographic operation;Desensitization process is carried out to identified picture material sensitive information to refer to institute
Image-region where the picture material sensitive information of determination carries out image blurringization processing.
5. the method according to claim 4 that medical imaging data are carried out with desensitization process, it is characterised in that:
Described cryptographic operation refers to carry out Hash encryption to identified file attribute sensitive information.
6. the method according to claim 1 that medical imaging data are carried out with desensitization process, it is characterised in that:
Step in the step 3 corresponding to record storage is:
The data carried out to identified file attribute sensitive information involved by desensitization process are charged into desensitization daily record simultaneously respectively
Desensitization daily record is charged to the data syn-chronization that identified picture material sensitive information is carried out involved by desensitization process;And according to file
Data are carried out sub-category storage by attribute sensitive information and picture material sensitive information.
7. a kind of system that medical imaging data are carried out with desensitization process, it is characterised in that including:
Medical imaging data read module, it can read pending medical imaging data from database;
The file attribute sensitive information searching modul being connected with the medical imaging data read module, it can be analyzed and true
File attribute sensitive information in the fixed medical imaging data;
The picture material sensitive information searching modul being connected with the medical imaging data read module, it can be by described
Image-sensitive region identification model determines the picture material sensitive information i.e. image-sensitive region in the medical imaging data, institute
It is by using Historical medical's image data as training set, utilizing deep learning convolutional Neural net to state image-sensitive region identification model
Network trains the identification model corresponding with set image-sensitive region;
The desensitization process mould being connected with the file attribute sensitive information searching modul, picture material sensitive information searching modul
Block, it can carry out desensitization process to identified file attribute sensitive information and picture material sensitive information;
And the data after desensitization process are carried out with the record storage module of record storage.
8. the system according to claim 7 that medical imaging data are carried out with desensitization process, it is characterised in that:
The medical imaging data read module includes:
Historical data reading submodule, its can be obtained from database several DICOM file data samples over the years and with
The corresponding image file data of each DICOM file data sample over the years;
Image file data extracting sub-module, it can be according to determined image-sensitive region, from acquired image file number
Selected in containing the image file data for having determined image-sensitive region;
Image preprocessing submodule, its can respectively to it is selected go out image file data carry out image preprocessing, with extract
The view data gone out in image file data;
View data marks submodule, and it can be marked and by the view data after mark to extracting view data respectively
Generate the tab file that can be expanded;
Model creation submodule, it can be using the tab file and extracted view data as mode input parameter, profit
The image-sensitive region identification mould corresponding with set image-sensitive region is trained with deep learning convolutional neural networks
Type.
9. the system according to claim 8 that medical imaging data are carried out with desensitization process, it is characterised in that:
The medical imaging data read module also includes:
Model verifies submodule, and it can select some containing the image for having determined image-sensitive region from database again
File data, and using the image file data as test data, reliability is carried out to image-sensitive region identification model and tested
Card.
10. the system according to claim 7 that medical imaging data are carried out with desensitization process, it is characterised in that:
Desensitization process is carried out in the desensitization process module to identified file attribute sensitive information to refer to identified text
Part attribute sensitive information carries out erase operation or cryptographic operation;Desensitization process is carried out to identified picture material sensitive information
Refer to carry out image blurringization processing, described cryptographic operation to the image-region where identified picture material sensitive information
Refer to carry out Hash encryption to identified file attribute sensitive information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710433608.7A CN107239666B (en) | 2017-06-09 | 2017-06-09 | Method and system for desensitizing medical image data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710433608.7A CN107239666B (en) | 2017-06-09 | 2017-06-09 | Method and system for desensitizing medical image data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107239666A true CN107239666A (en) | 2017-10-10 |
CN107239666B CN107239666B (en) | 2020-10-09 |
Family
ID=59987424
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710433608.7A Active CN107239666B (en) | 2017-06-09 | 2017-06-09 | Method and system for desensitizing medical image data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107239666B (en) |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108563930A (en) * | 2018-04-16 | 2018-09-21 | 深圳市联软科技股份有限公司 | A kind of method, apparatus, medium and the system of confidential document addition watermark |
CN108563929A (en) * | 2018-04-16 | 2018-09-21 | 深圳市联软科技股份有限公司 | It is a kind of only in the method for concerning security matters Area generation watermark, system, device and medium |
CN108922601A (en) * | 2018-07-09 | 2018-11-30 | 成都数浪信息科技有限公司 | A kind of medical image processing system |
CN109284684A (en) * | 2018-08-21 | 2019-01-29 | Oppo广东移动通信有限公司 | A kind of information processing method, device and computer storage medium |
CN109410073A (en) * | 2018-09-26 | 2019-03-01 | 平安健康保险股份有限公司 | Image file desensitization method, device, computer equipment and storage medium |
CN109472705A (en) * | 2018-09-26 | 2019-03-15 | 平安健康保险股份有限公司 | Claims Resolution method, system, computer equipment and storage medium |
CN109598730A (en) * | 2018-12-03 | 2019-04-09 | 鄂珑江 | Rabat segmentation and processing method, system and electronic equipment |
CN109842669A (en) * | 2017-11-24 | 2019-06-04 | 丰田自动车株式会社 | Medical data communication device, server, medical data communication methods and procedures |
CN109872282A (en) * | 2019-01-16 | 2019-06-11 | 众安信息技术服务有限公司 | A kind of image desensitization method based on computer vision and system |
CN109919142A (en) * | 2019-04-19 | 2019-06-21 | 东方网力科技股份有限公司 | Personnel monitoring's method, apparatus, server and storage medium |
CN110110588A (en) * | 2019-03-21 | 2019-08-09 | 平安普惠企业管理有限公司 | The method, apparatus computer equipment of business is handled on line based on recognition of face |
CN110163250A (en) * | 2019-04-10 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Image desensitization process system, method and device based on distributed scheduling |
CN110163218A (en) * | 2019-04-10 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Desensitization process method and device based on image recognition |
CN110175623A (en) * | 2019-04-10 | 2019-08-27 | 阿里巴巴集团控股有限公司 | Desensitization process method and device based on image recognition |
CN110287720A (en) * | 2019-07-01 | 2019-09-27 | 国网内蒙古东部电力有限公司 | A kind of access control method based on image recognition and user gradation |
CN110727643A (en) * | 2019-09-16 | 2020-01-24 | 北京明朝万达科技股份有限公司 | File classification management method and system based on machine learning |
CN110866281A (en) * | 2019-11-20 | 2020-03-06 | 满江(上海)软件科技有限公司 | Safety compliance processing system and method for sensitive data |
CN110865654A (en) * | 2019-12-06 | 2020-03-06 | 河南送变电建设有限公司 | Power grid unmanned aerial vehicle inspection defect processing method |
CN111199050A (en) * | 2018-11-19 | 2020-05-26 | 零氪医疗智能科技(广州)有限公司 | System for automatically desensitizing medical records and application |
WO2020113584A1 (en) * | 2018-12-07 | 2020-06-11 | 深圳市欢太科技有限公司 | Log information processing method and device, mobile terminal and storage medium |
CN111382151A (en) * | 2020-03-23 | 2020-07-07 | 新疆大学 | CT medical image cleaning method based on data desensitization |
US10762607B2 (en) | 2019-04-10 | 2020-09-01 | Alibaba Group Holding Limited | Method and device for sensitive data masking based on image recognition |
CN112330644A (en) * | 2020-11-11 | 2021-02-05 | 复旦大学 | Medical image diagnosis system based on deep learning |
CN112347512A (en) * | 2020-11-13 | 2021-02-09 | 支付宝(杭州)信息技术有限公司 | Image processing method, device, equipment and storage medium |
CN112420214A (en) * | 2019-08-21 | 2021-02-26 | 无锡祥生医疗科技股份有限公司 | Ultrasonic consultation remote sharing method, platform and system |
CN113051600A (en) * | 2019-12-27 | 2021-06-29 | 无锡祥生医疗科技股份有限公司 | Medical image safety multi-stage desensitization method and system |
CN113254967A (en) * | 2021-06-04 | 2021-08-13 | 王兆河 | Standardization method of medical digital image cloud system |
CN113254998A (en) * | 2021-06-04 | 2021-08-13 | 王兆河 | Desensitization processing method for digital image and image inspection report data |
CN113782138A (en) * | 2021-09-29 | 2021-12-10 | 清华大学 | Method and apparatus for medical data transmission control |
CN113779630A (en) * | 2021-09-09 | 2021-12-10 | 新疆大学 | DICOM-based CT medical image reversible desensitization method |
CN113822839A (en) * | 2020-06-18 | 2021-12-21 | 飞依诺科技(苏州)有限公司 | Medical image processing method and device, computer equipment and storage medium |
CN114040223A (en) * | 2021-11-05 | 2022-02-11 | 湖北亿咖通科技有限公司 | Image processing method and system |
CN117150565A (en) * | 2023-10-31 | 2023-12-01 | 山东网安安全技术有限公司 | Medical data desensitization storage method and device, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012107692A1 (en) * | 2011-02-09 | 2012-08-16 | Universite De Lorraine | Movement sensor combined with a diagnostic electrode for applications in medical imaging |
CN104463965A (en) * | 2014-12-17 | 2015-03-25 | 中国科学院自动化研究所 | Training scene simulation system and method for minimally invasive cardiovascular interventional operation |
CN105718952A (en) * | 2016-01-22 | 2016-06-29 | 武汉科恩斯医疗科技有限公司 | Method for focus classification of sectional medical images by employing deep learning network |
CN106203432A (en) * | 2016-07-14 | 2016-12-07 | 杭州健培科技有限公司 | A kind of localization method of area-of-interest based on convolutional Neural net significance collection of illustrative plates |
CN106339917A (en) * | 2016-08-18 | 2017-01-18 | 无锡天脉聚源传媒科技有限公司 | Commodity model training method and device |
CN206100294U (en) * | 2015-12-29 | 2017-04-12 | 重庆安碧捷科技股份有限公司 | Medical treatment desensitization system |
CN106682435A (en) * | 2016-12-31 | 2017-05-17 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image through multi-model fusion |
-
2017
- 2017-06-09 CN CN201710433608.7A patent/CN107239666B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012107692A1 (en) * | 2011-02-09 | 2012-08-16 | Universite De Lorraine | Movement sensor combined with a diagnostic electrode for applications in medical imaging |
CN104463965A (en) * | 2014-12-17 | 2015-03-25 | 中国科学院自动化研究所 | Training scene simulation system and method for minimally invasive cardiovascular interventional operation |
CN206100294U (en) * | 2015-12-29 | 2017-04-12 | 重庆安碧捷科技股份有限公司 | Medical treatment desensitization system |
CN105718952A (en) * | 2016-01-22 | 2016-06-29 | 武汉科恩斯医疗科技有限公司 | Method for focus classification of sectional medical images by employing deep learning network |
CN106203432A (en) * | 2016-07-14 | 2016-12-07 | 杭州健培科技有限公司 | A kind of localization method of area-of-interest based on convolutional Neural net significance collection of illustrative plates |
CN106339917A (en) * | 2016-08-18 | 2017-01-18 | 无锡天脉聚源传媒科技有限公司 | Commodity model training method and device |
CN106682435A (en) * | 2016-12-31 | 2017-05-17 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image through multi-model fusion |
Non-Patent Citations (2)
Title |
---|
HUI LI等: "ECARMI: An Ensemble Based Approach for Medical Images Based Disease Classification and ROIs Recognition", 《2015 7TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY IN MEDICINE AND EDUCATION (ITME)》 * |
倪杭建: "数据挖掘技术在区域医疗影像数据中的应用研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109842669A (en) * | 2017-11-24 | 2019-06-04 | 丰田自动车株式会社 | Medical data communication device, server, medical data communication methods and procedures |
CN109842669B (en) * | 2017-11-24 | 2021-11-09 | 丰田自动车株式会社 | Medical data communication device, server, medical data communication method, and medium |
CN108563930B (en) * | 2018-04-16 | 2020-09-25 | 深圳市联软科技股份有限公司 | Method, device, medium and system for adding watermark to confidential file |
CN108563929A (en) * | 2018-04-16 | 2018-09-21 | 深圳市联软科技股份有限公司 | It is a kind of only in the method for concerning security matters Area generation watermark, system, device and medium |
CN108563930A (en) * | 2018-04-16 | 2018-09-21 | 深圳市联软科技股份有限公司 | A kind of method, apparatus, medium and the system of confidential document addition watermark |
CN108922601A (en) * | 2018-07-09 | 2018-11-30 | 成都数浪信息科技有限公司 | A kind of medical image processing system |
CN109284684A (en) * | 2018-08-21 | 2019-01-29 | Oppo广东移动通信有限公司 | A kind of information processing method, device and computer storage medium |
CN109284684B (en) * | 2018-08-21 | 2021-06-01 | Oppo广东移动通信有限公司 | Information processing method and device and computer storage medium |
CN109410073A (en) * | 2018-09-26 | 2019-03-01 | 平安健康保险股份有限公司 | Image file desensitization method, device, computer equipment and storage medium |
CN109472705A (en) * | 2018-09-26 | 2019-03-15 | 平安健康保险股份有限公司 | Claims Resolution method, system, computer equipment and storage medium |
CN109472705B (en) * | 2018-09-26 | 2024-04-26 | 平安健康保险股份有限公司 | Method, system, computer device and storage medium for claim settlement |
CN109410073B (en) * | 2018-09-26 | 2024-04-30 | 平安健康保险股份有限公司 | Image file desensitizing method, device, computer equipment and storage medium |
CN111199050A (en) * | 2018-11-19 | 2020-05-26 | 零氪医疗智能科技(广州)有限公司 | System for automatically desensitizing medical records and application |
CN111199050B (en) * | 2018-11-19 | 2023-10-17 | 零氪医疗智能科技(广州)有限公司 | System for automatically desensitizing medical records and application |
CN109598730A (en) * | 2018-12-03 | 2019-04-09 | 鄂珑江 | Rabat segmentation and processing method, system and electronic equipment |
WO2020113584A1 (en) * | 2018-12-07 | 2020-06-11 | 深圳市欢太科技有限公司 | Log information processing method and device, mobile terminal and storage medium |
CN112889053A (en) * | 2018-12-07 | 2021-06-01 | 深圳市欢太科技有限公司 | Log information processing method and device, mobile terminal and storage medium |
CN109872282A (en) * | 2019-01-16 | 2019-06-11 | 众安信息技术服务有限公司 | A kind of image desensitization method based on computer vision and system |
CN109872282B (en) * | 2019-01-16 | 2021-08-06 | 众安信息技术服务有限公司 | Image desensitization method and system based on computer vision |
CN110110588A (en) * | 2019-03-21 | 2019-08-09 | 平安普惠企业管理有限公司 | The method, apparatus computer equipment of business is handled on line based on recognition of face |
CN110163250B (en) * | 2019-04-10 | 2023-10-24 | 创新先进技术有限公司 | Image desensitization processing system, method and device based on distributed scheduling |
US10762607B2 (en) | 2019-04-10 | 2020-09-01 | Alibaba Group Holding Limited | Method and device for sensitive data masking based on image recognition |
CN110163218A (en) * | 2019-04-10 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Desensitization process method and device based on image recognition |
CN110163250A (en) * | 2019-04-10 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Image desensitization process system, method and device based on distributed scheduling |
CN110175623A (en) * | 2019-04-10 | 2019-08-27 | 阿里巴巴集团控股有限公司 | Desensitization process method and device based on image recognition |
CN109919142B (en) * | 2019-04-19 | 2021-05-25 | 东方网力科技股份有限公司 | Personnel monitoring method, device, server and storage medium |
CN109919142A (en) * | 2019-04-19 | 2019-06-21 | 东方网力科技股份有限公司 | Personnel monitoring's method, apparatus, server and storage medium |
CN110287720A (en) * | 2019-07-01 | 2019-09-27 | 国网内蒙古东部电力有限公司 | A kind of access control method based on image recognition and user gradation |
CN112420214A (en) * | 2019-08-21 | 2021-02-26 | 无锡祥生医疗科技股份有限公司 | Ultrasonic consultation remote sharing method, platform and system |
CN112420214B (en) * | 2019-08-21 | 2023-11-21 | 无锡祥生医疗科技股份有限公司 | Remote sharing method, platform and system for ultrasonic consultation |
CN110727643B (en) * | 2019-09-16 | 2022-04-19 | 北京明朝万达科技股份有限公司 | File classification management method and system based on machine learning |
CN110727643A (en) * | 2019-09-16 | 2020-01-24 | 北京明朝万达科技股份有限公司 | File classification management method and system based on machine learning |
CN110866281A (en) * | 2019-11-20 | 2020-03-06 | 满江(上海)软件科技有限公司 | Safety compliance processing system and method for sensitive data |
CN110865654A (en) * | 2019-12-06 | 2020-03-06 | 河南送变电建设有限公司 | Power grid unmanned aerial vehicle inspection defect processing method |
CN113051600A (en) * | 2019-12-27 | 2021-06-29 | 无锡祥生医疗科技股份有限公司 | Medical image safety multi-stage desensitization method and system |
CN113051600B (en) * | 2019-12-27 | 2024-02-13 | 无锡祥生医疗科技股份有限公司 | Medical image safety multi-stage desensitizing method and system |
CN111382151A (en) * | 2020-03-23 | 2020-07-07 | 新疆大学 | CT medical image cleaning method based on data desensitization |
CN113822839A (en) * | 2020-06-18 | 2021-12-21 | 飞依诺科技(苏州)有限公司 | Medical image processing method and device, computer equipment and storage medium |
CN113822839B (en) * | 2020-06-18 | 2024-01-23 | 飞依诺科技股份有限公司 | Medical image processing method, medical image processing device, computer equipment and storage medium |
CN112330644A (en) * | 2020-11-11 | 2021-02-05 | 复旦大学 | Medical image diagnosis system based on deep learning |
CN112347512A (en) * | 2020-11-13 | 2021-02-09 | 支付宝(杭州)信息技术有限公司 | Image processing method, device, equipment and storage medium |
CN113254998A (en) * | 2021-06-04 | 2021-08-13 | 王兆河 | Desensitization processing method for digital image and image inspection report data |
CN113254967A (en) * | 2021-06-04 | 2021-08-13 | 王兆河 | Standardization method of medical digital image cloud system |
CN113779630A (en) * | 2021-09-09 | 2021-12-10 | 新疆大学 | DICOM-based CT medical image reversible desensitization method |
CN113782138A (en) * | 2021-09-29 | 2021-12-10 | 清华大学 | Method and apparatus for medical data transmission control |
CN114040223A (en) * | 2021-11-05 | 2022-02-11 | 湖北亿咖通科技有限公司 | Image processing method and system |
CN114040223B (en) * | 2021-11-05 | 2023-11-24 | 亿咖通(湖北)技术有限公司 | Image processing method and system |
CN117150565A (en) * | 2023-10-31 | 2023-12-01 | 山东网安安全技术有限公司 | Medical data desensitization storage method and device, electronic equipment and storage medium |
CN117150565B (en) * | 2023-10-31 | 2024-03-01 | 山东网安安全技术有限公司 | Medical data desensitization storage method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107239666B (en) | 2020-10-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107239666A (en) | A kind of method and system that medical imaging data are carried out with desensitization process | |
Escalante et al. | Modeling, recognizing, and explaining apparent personality from videos | |
US9886758B2 (en) | Annotation of skin image using learned feature representation | |
CN107358157A (en) | A kind of human face in-vivo detection method, device and electronic equipment | |
Yoon et al. | Generalizable feature learning in the presence of data bias and domain class imbalance with application to skin lesion classification | |
US10878570B2 (en) | Knockout autoencoder for detecting anomalies in biomedical images | |
CN101944154A (en) | The shadow system is read in medical imaging | |
JP7082993B2 (en) | Medical image processing equipment, methods and programs, diagnostic support equipment, methods and programs, and medical support systems and methods | |
Li et al. | Patch transformer for multi-tagging whole slide histopathology images | |
CN107992602A (en) | Search result methods of exhibiting and device | |
Sadeghi et al. | How users perceive content-based image retrieval for identifying skin images | |
CN107909088A (en) | Obtain method, apparatus, equipment and the computer-readable storage medium of training sample | |
Domel et al. | A new open-access platform for measuring and sharing mTBI data | |
CN109817297B (en) | Medical report generation method, device, computer equipment and computer storage medium | |
Mukherjee et al. | Monitoring, recognition and attendance automation in online class: combination of image processing, cryptography in IoT security | |
CN112434555A (en) | Key value pair region identification method and device, storage medium and electronic equipment | |
Rudmann et al. | Using deep learning artificial intelligence algorithms to verify N-nitroso-N-methylurea and urethane positive control proliferative changes in Tg-RasH2 mouse carcinogenicity studies | |
Huang et al. | Automatic recognizing of vocal fold disorders from glottis images | |
CN105913024A (en) | Android mobile terminal detecting method based on LAP operator for resisting replay attacks | |
Dimauro et al. | A smartphone-based cell segmentation to support nasal cytology | |
CN109036498A (en) | Information processing unit and information processing method | |
CN112084889A (en) | Image behavior recognition method and device, computing equipment and storage medium | |
AU2021105721A4 (en) | System and method for classifying skin cancer lesions using deep neural networks and transfer learning | |
Liu et al. | Embedded autoencoders: A novel framework for face de-identification | |
Shi et al. | A Multi-task Method for Immunofixation Electrophoresis Image Classification |
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 |