CN107239666B - Method and system for desensitizing medical image data - Google Patents
Method and system for desensitizing medical image data Download PDFInfo
- Publication number
- CN107239666B CN107239666B CN201710433608.7A CN201710433608A CN107239666B CN 107239666 B CN107239666 B CN 107239666B CN 201710433608 A CN201710433608 A CN 201710433608A CN 107239666 B CN107239666 B CN 107239666B
- Authority
- CN
- China
- Prior art keywords
- image
- data
- file
- sensitive information
- determined
- 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.)
- Active
Links
Images
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
Abstract
The invention discloses a method and a system for desensitizing medical image data, which are characterized by comprising the following steps: step 1, training an image sensitive area identification model corresponding to a set image sensitive area by using historical medical image data as a training set and utilizing a deep learning convolutional neural network; step 2, reading medical image data to be processed, analyzing and determining file attribute sensitive information in the medical image data, and determining image content sensitive information, namely an image sensitive area, in the medical image data through the image sensitive area identification model; and 3, desensitizing the determined file attribute sensitive information and image content sensitive information, and recording and storing. The method can keep the format and the image information of the original medical image data, is convenient for subsequent analysis and processing, and can remove the text attribute and the sensitive information in the image content.
Description
Technical Field
The invention relates to the field of medical artificial intelligence and big data processing, in particular to a method and a system for desensitizing medical image data.
Background
With the rise of the new artificial intelligence technology taking a deep learning framework as an inner core, the development and the promotion of the technology are greatly achieved in various fields, and technologies such as AlphaGo, unmanned vehicles and voice recognition, which are expected to be used for many years, are broken through in a short time. In the visible future, deep learning will also promote the development of big data analysis and artificial intelligence application in the medical industry. Deep learning therefore requires a large amount of medical image data for model training, and the need for desensitization processing of such image data is highly urgent.
The DICOM standard is a standard for exchanging and managing medical image data and related data, and can be used for communication between medical information systems or between a medical information system and medical equipment. The medical equipment of the hospital collects the generated patient examination image file as a DICOM file. Since the DICOM image file itself contains information such as patient name, patient ID, and patient address, the image file can be directly applied to the artificial intelligence field such as deep learning, which may infringe the privacy of the patient.
Therefore, there is a need to develop an effective, fast and convenient desensitization treatment method that can solve the above two problems and protect the privacy of patients while rapidly advancing the application of artificial intelligence methods such as deep learning in the medical field.
Disclosure of Invention
In view of the defects in the prior art, the present invention aims to provide a method for desensitizing medical image data, which can preserve the format and image information of the original medical image data for subsequent analysis and processing, and can remove sensitive information in text attributes and image contents.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a method of desensitizing medical image data, comprising the steps of:
step 1, training an image sensitive area identification model corresponding to a set image sensitive area by using historical medical image data as a training set and utilizing a deep learning convolutional neural network;
step 2, reading medical image data to be processed, analyzing and determining file attribute sensitive information in the medical image data, and determining image content sensitive information, namely an image sensitive area, in the medical image data through the image sensitive area identification model;
and 3, desensitizing the determined file attribute sensitive information and image content sensitive information, and recording and storing.
Further, the step 1 comprises:
step 11, acquiring a plurality of historical DICOM file data samples and image file data corresponding to the historical DICOM file data samples from a database;
step 12, determining an image sensitive area and selecting image file data containing the determined image sensitive area from the acquired image file data;
step 13, respectively carrying out image preprocessing on the selected image file data to extract image data in the image file data;
step 14, marking the extracted image data and generating an extensible mark file from the marked image data;
and step 15, training an image sensitive area recognition model corresponding to the set image sensitive area by using the label file and the extracted image data as model input parameters and using a deep learning convolutional neural network.
Further, the step 1 further includes:
and step 16, selecting a plurality of image file data containing the determined image sensitive areas from the database again, and taking the image file data as test data to carry out reliability verification on the image sensitive area identification model.
Further, the desensitizing process of the determined file attribute sensitive information in step 3 refers to performing an erasing operation or an encrypting operation on the determined file attribute sensitive information; desensitizing the determined image content sensitive information refers to blurring an image in an image area where the determined image content sensitive information is located.
Preferably, the encryption operation is to perform hash encryption processing on the determined file attribute sensitive information.
Further, the step corresponding to the recording and storing in the step 3 is:
respectively logging data related to desensitization processing on the determined file attribute sensitive information into desensitization logs, and synchronously logging data related to desensitization processing on the determined image content sensitive information into desensitization logs; and storing the data in a classified manner according to the file attribute sensitive information and the image content sensitive information.
Another object of the present invention is to provide a system for desensitizing medical image data, comprising:
the medical image data reading module can read medical image data to be processed from a database;
the file attribute sensitive information searching module is connected with the medical image data reading module and can analyze and determine the file attribute sensitive information in the medical image data;
the image sensitive region identification model is an identification model which is trained to correspond to the set image sensitive region by using the historical medical image data as a training set and using a deep learning convolutional neural network;
the desensitization processing module is connected with the file attribute sensitive information searching module and the image content sensitive information searching module and can perform desensitization processing on the determined file attribute sensitive information and the determined image content sensitive information;
and the recording storage module is used for recording and storing the desensitized data.
Further, the medical image data reading module comprises:
the historical data reading sub-module can acquire a plurality of historical DICOM file data samples and image file data corresponding to the historical DICOM file data samples from a database;
the image file data extraction submodule can select image file data containing the determined image sensitive area from the acquired image file data according to the determined image sensitive area;
the image preprocessing submodule can respectively carry out image preprocessing on the selected image file data so as to extract the image data in the image file data;
the image data marking submodule can mark the extracted image data and generate an extensible mark file from the marked image data;
and the model creating sub-module can use the marking file and the extracted image data as model input parameters and train an image sensitive area identification model corresponding to the set image sensitive area by using a deep learning convolutional neural network.
Further, the medical image data reading module further comprises:
and the model verification submodule can reselect a plurality of image file data containing the determined image sensitive areas from the database, and uses the image file data as test data to carry out reliability verification on the image sensitive area identification model.
Furthermore, the desensitization processing of the determined file attribute sensitive information in the desensitization processing module refers to performing an erasing operation or an encrypting operation on the determined file attribute sensitive information; desensitizing the determined image content sensitive information refers to blurring an image in an image area where the determined image content sensitive information is located.
Preferably, the encryption operation is to perform hash encryption processing on the determined file attribute sensitive information.
Further, the step corresponding to the recording and storing module performing recording and storing on the data is:
respectively logging data related to desensitization processing on the determined file attribute sensitive information into desensitization logs, and synchronously logging data related to desensitization processing on the determined image content sensitive information into desensitization logs; and storing the data in a classified manner according to the file attribute sensitive information and the image content sensitive information.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of training an image sensitive area identification model by utilizing a deep learning convolutional neural network to identify an image sensitive area and carrying out desensitization treatment; simultaneously, the desensitization log is combined to finish the storage of desensitization data; the medical image data can be processed efficiently and accurately, and privacy of patients is protected from being leaked.
Drawings
FIG. 1 is a flow chart of the steps corresponding to the method of the present invention;
fig. 2 is a schematic block diagram of a structure corresponding to the system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a method for desensitizing medical image data includes the steps of:
step 1, training an image sensitive area identification model corresponding to a set image sensitive area by using historical medical image data as a training set and utilizing a deep learning convolutional neural network; further, the step 1 comprises: step 11, acquiring a plurality of historical DICOM file data samples and image file data corresponding to the historical DICOM file data samples from a database (which comprises a PACS repository); step 12, determining an image sensitive area and selecting image file data containing the determined image sensitive area from the acquired image file data; step 13, respectively carrying out image preprocessing on the selected image file data to extract image data in the image file data; step 14, respectively marking the extracted image data and generating an extensible mark file from the marked image data, wherein the mark is to identify a certain image area according to the needs of a user and record corresponding coordinate information, and the extensible mark file can be a file in an xml format; step 15, training an image sensitive area recognition model corresponding to the set image sensitive area by using the label file and the extracted image data as model input parameters by using a deep learning convolutional neural network to obtain a model parameter with a reliable prediction result for recognizing the image sensitive area; and step 16, selecting a plurality of image file data containing the determined image sensitive areas from the database again, and taking the image file data as test data to carry out reliability verification on the image sensitive area identification model.
Step 2, reading original data of a medical image, namely medical image data to be processed, analyzing and determining sensitive information in the medical image data, specifically comprising file attribute sensitive information and image content sensitive information, wherein the image content sensitive information determines image content sensitive information, namely an image sensitive area, in the medical image data through the image sensitive area identification model; furthermore, the file attribute sensitive information and the image content sensitive information are set by a user according to the use requirement, for example, the file attribute sensitive information can be the attribute fields of the name and the unit of the patient carried by the DICOM file; the image content sensitive information can be sensitive information of certain position areas in the image data, such as the name and age of a patient, and the sensitive information needs to be found by the image recognition model aiming at the sensitive information in the images because the information is integrated with the images.
Step 3, desensitizing the determined file attribute sensitive information and image content sensitive information, and recording and storing the desensitized information, wherein the desensitizing information processing comprises the following steps: and processing the file attribute sensitive information and processing the image content sensitive information. Further, the desensitizing process of the determined file attribute sensitive information in step 3 refers to performing an erasing operation or an encrypting operation on the determined file attribute sensitive information; desensitizing the determined image content sensitive information refers to performing image blurring processing, such as concealment or mosaic processing, on an image area where the determined image content sensitive information is located. Preferably, the encryption operation is to perform hash encryption processing on the determined file attribute sensitive information.
Further, the step corresponding to the recording and storing in the step 3 is:
respectively logging data related to desensitization processing on the determined file attribute sensitive information into desensitization logs, and synchronously logging data related to desensitization processing on the determined image content sensitive information into desensitization logs; and the data are classified and stored according to the file attribute sensitive information and the image content sensitive information, so that the data collection is facilitated for subsequent utilization. For example, checking the validity and normalization of the modified image file, and saving the original file covering the image file containing the sensitive information. The data recording process comprises the following steps: 1. checking whether the file flow of the image file processed with the sensitive information is legal and standard, if not, prompting illegal and irregular attribute information, writing the information into a log file, skipping the processing of the current file, and processing the next file in the list; 2. covering an original file containing sensitive information by adopting an additional storage mode; 3. the additional storage is successful, the desensitization processing of the current image file is successful, and other files in the list are processed in sequence.
Another object of the present invention is to provide a system for desensitizing medical image data, as shown in fig. 2, comprising:
the medical image data reading module can read medical image data to be processed from a database;
the file attribute sensitive information searching module is connected with the medical image data reading module and can analyze and determine the file attribute sensitive information in the medical image data; further, the file attribute sensitive information analyzing and determining process comprises 1, loading a configuration file, reading a file attribute information name needing to be processed, and selecting file attribute information needing to be desensitized according to actual needs of a user, such as patient information (including patient relation information, patient identification information, patient statistical information, and patient medical information), treatment information (including treatment relation information, treatment identification information, treatment status information, treatment admission information, treatment discharge information, and treatment arrangement information). Some sensitive information is listed in tabular form below:
patient information:
the information of the treatment:
the image sensitive region identification model is an identification model which is trained to correspond to the set image sensitive region by using the historical medical image data as a training set and using a deep learning convolutional neural network; furthermore, the file attribute sensitive information and the image content sensitive information are set by a user according to the use requirement, for example, the file attribute sensitive information can be the attribute fields of the name and the unit of the patient carried by the DICOM file; the image content sensitive information can be sensitive information of certain position areas in the image data, such as the name and age of a patient, and the sensitive information needs to be found by the image recognition model aiming at the sensitive information in the images because the information is integrated with the images; for example, H3., when the information sensitive area is screened, due to different devices or different operations of a hospital technician, some sensitive information, such as legal name of a patient, birth date of the patient, name of a hospital, address of the hospital, etc., may be stored in the stored image information in some image files, and the image sensitive information search module of the present invention needs to search and screen multiple areas. If the sensitive information exists, the sensitive area is processed in the next step, namely the sensitive area result detected by the identification model is hidden or mosaic operation is carried out on the position needing to be processed, and the processed image information is reversely written into the file stream of the image file.
The desensitization processing module is connected with the file attribute sensitive information searching module and the image content sensitive information searching module and can perform desensitization processing on the determined file attribute sensitive information and the determined image content sensitive information;
and the recording storage module is used for recording and storing the desensitized data.
Further, the medical image data reading module comprises:
the historical data reading sub-module can acquire a plurality of historical DICOM file data samples and image file data corresponding to the historical DICOM file data samples from a database;
the image file data extraction submodule can select image file data containing the determined image sensitive area from the acquired image file data according to the determined image sensitive area;
the image preprocessing submodule can respectively carry out image preprocessing on the selected image file data so as to extract the image data in the image file data;
the image data marking submodule can mark the extracted image data and generate an extensible mark file from the marked image data;
and the model creating sub-module can use the marking file and the extracted image data as model input parameters and train an image sensitive area identification model corresponding to the set image sensitive area by using a deep learning convolutional neural network.
Further, the medical image data reading module further comprises:
and the model verification submodule can reselect a plurality of image file data containing the determined image sensitive areas from the database, and uses the image file data as test data to carry out reliability verification on the image sensitive area identification model.
Furthermore, the desensitization processing of the determined file attribute sensitive information in the desensitization processing module refers to performing an erasing operation or a deleting operation or an encrypting operation on the determined file attribute sensitive information; desensitizing the determined image content sensitive information refers to blurring an image in an image area where the determined image content sensitive information is located.
Preferably, the encryption operation is to perform hash encryption processing on the determined file attribute sensitive information.
Further, the step corresponding to the recording and storing module performing recording and storing on the data is:
respectively logging data related to desensitization processing on the determined file attribute sensitive information into desensitization logs, and synchronously logging data related to desensitization processing on the determined image content sensitive information into desensitization logs; and storing the data in a classified manner according to the file attribute sensitive information and the image content sensitive information.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (7)
1. A method of desensitizing medical image data, comprising the steps of:
step 1, training an image sensitive area identification model corresponding to a set image sensitive area by using historical medical image data as a training set and utilizing a deep learning convolutional neural network;
the step 1 comprises the following steps:
step 11, acquiring a plurality of historical DICOM file data samples and image file data corresponding to the historical DICOM file data samples from a database;
step 12, determining an image sensitive area and selecting image file data containing the determined image sensitive area from the acquired image file data;
step 13, respectively carrying out image preprocessing on the selected image file data to extract image data in the image file data;
step 14, marking the extracted image data and generating an extensible mark file from the marked image data;
step 15, training an image sensitive area identification model corresponding to the set image sensitive area by using the label file and the extracted image data as model input parameters and using a deep learning convolutional neural network;
step 16, selecting a plurality of image file data containing the determined image sensitive areas from the database again, taking the image file data as test data, and performing reliability verification on the image sensitive area identification model;
step 2, reading medical image data to be processed, analyzing and determining file attribute sensitive information in the medical image data, and determining image content sensitive information, namely an image sensitive area, in the medical image data through the image sensitive area identification model;
and 3, desensitizing the determined file attribute sensitive information and image content sensitive information, and recording and storing.
2. A method of desensitizing medical imaging data according to claim 1, wherein:
performing desensitization processing on the determined file attribute sensitive information in the step 3 refers to performing erasing operation or encryption operation on the determined file attribute sensitive information; desensitizing the determined image content sensitive information refers to blurring an image in an image area where the determined image content sensitive information is located.
3. A method of desensitizing medical imaging data according to claim 2, wherein:
the encryption operation refers to carrying out hash encryption processing on the determined file attribute sensitive information.
4. A method of desensitizing medical imaging data according to claim 1, wherein:
the step corresponding to the recording and storing in the step 3 is as follows:
respectively logging data related to desensitization processing on the determined file attribute sensitive information into desensitization logs, and synchronously logging data related to desensitization processing on the determined image content sensitive information into desensitization logs; and storing the data in a classified manner according to the file attribute sensitive information and the image content sensitive information.
5. A system for desensitizing medical imaging data, comprising:
the medical image data reading module can read medical image data to be processed from a database;
the file attribute sensitive information searching module is connected with the medical image data reading module and can analyze and determine the file attribute sensitive information in the medical image data;
the image sensitive region identification module is used for training an identification model corresponding to the set image sensitive region by using the historical medical image data as a training set and using a deep learning convolutional neural network;
the desensitization processing module is connected with the file attribute sensitive information searching module and the image content sensitive information searching module and can perform desensitization processing on the determined file attribute sensitive information and the determined image content sensitive information;
and carry on the record storage module of record storage to the data after desensitization treatment;
the medical image data reading module comprises:
the historical data reading sub-module can acquire a plurality of historical DICOM file data samples and image file data corresponding to the historical DICOM file data samples from a database;
the image file data extraction submodule can select image file data containing the determined image sensitive area from the acquired image file data according to the determined image sensitive area;
the image preprocessing submodule can respectively carry out image preprocessing on the selected image file data so as to extract the image data in the image file data;
the image data marking submodule can mark the extracted image data and generate an extensible mark file from the marked image data;
and the model creating sub-module can use the marking file and the extracted image data as model input parameters and train an image sensitive area identification model corresponding to the set image sensitive area by using a deep learning convolutional neural network.
6. A system for desensitizing medical imaging data according to claim 5, wherein:
the medical image data reading module further comprises:
and the model verification submodule can reselect a plurality of image file data containing the determined image sensitive areas from the database, and uses the image file data as test data to carry out reliability verification on the image sensitive area identification model.
7. A system for desensitizing medical imaging data according to claim 5, wherein:
the desensitization processing module desensitizes the determined file attribute sensitive information, namely performing erasing operation or encryption operation on the determined file attribute sensitive information; the desensitization processing of the determined image content sensitive information refers to the image blurring processing of an image area where the determined image content sensitive information is located, and the encryption operation refers to the hash encryption processing of the determined 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 CN107239666A (en) | 2017-10-10 |
CN107239666B true 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) |
Families Citing this family (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7009955B2 (en) * | 2017-11-24 | 2022-01-26 | トヨタ自動車株式会社 | Medical data communication equipment, servers, medical data communication methods and medical data communication programs |
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 |
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 |
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 |
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 |
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 |
CN109598730B (en) * | 2018-12-03 | 2019-12-20 | 鄂珑江 | Chest radiography segmentation and processing method and 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 |
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 |
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 |
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 |
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 |
US10762607B2 (en) | 2019-04-10 | 2020-09-01 | Alibaba Group Holding Limited | Method and device for sensitive data masking 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 |
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 |
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 |
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 |
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 |
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 |
CN114040223B (en) * | 2021-11-05 | 2023-11-24 | 亿咖通(湖北)技术有限公司 | Image processing method and system |
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 |
Citations (2)
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 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN105718952B (en) * | 2016-01-22 | 2018-10-30 | 武汉科恩斯医疗科技有限公司 | The system that lesion classification is carried out to tomography medical image using deep learning network |
CN106203432B (en) * | 2016-07-14 | 2020-01-17 | 杭州健培科技有限公司 | Positioning system of region of interest based on convolutional neural network significance map |
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 |
CN106682435B (en) * | 2016-12-31 | 2021-01-29 | 西安百利信息科技有限公司 | System and method for automatically detecting lesion in medical image through multi-model fusion |
-
2017
- 2017-06-09 CN CN201710433608.7A patent/CN107239666B/en active Active
Patent Citations (2)
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 |
Non-Patent Citations (1)
Title |
---|
ECARMI: An Ensemble Based Approach for Medical Images Based Disease Classification and ROIs Recognition;Hui Li等;《2015 7th International Conference on Information Technology in Medicine and Education (ITME)》;20160310;第89-93页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107239666A (en) | 2017-10-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107239666B (en) | Method and system for desensitizing medical image data | |
US9626555B2 (en) | Content-based document image classification | |
CN109034069B (en) | Method and apparatus for generating information | |
US20140212040A1 (en) | Document Alteration Based on Native Text Analysis and OCR | |
CN110705235B (en) | Information input method and device for business handling, storage medium and electronic equipment | |
JP2019079347A (en) | Character estimation system, character estimation method, and character estimation program | |
CN111415336A (en) | Image tampering identification method and device, server and storage medium | |
US20140173422A1 (en) | Document template auto discovery | |
US11783072B1 (en) | Filter for sensitive data | |
CN113568934B (en) | Data query method and device, electronic equipment and storage medium | |
CN109660621A (en) | A kind of content delivery method and service equipment | |
CN112241470A (en) | Video classification method and system | |
CN114842982B (en) | Knowledge expression method, device and system for medical information system | |
GB2546567A (en) | Method of associating a person with a digital object | |
CN113312486B (en) | Signal portrait construction method and device, electronic equipment and storage medium | |
CN114090650A (en) | Sample data identification method and device, electronic equipment and storage medium | |
WO2021018016A1 (en) | Patent information display method and apparatus, device, and storage medium | |
CN113887191A (en) | Method and device for detecting similarity of articles | |
CN113297617A (en) | Authority data acquisition method and device, computer equipment and storage medium | |
CN113705560A (en) | Data extraction method, device and equipment based on image recognition and storage medium | |
US20240135740A1 (en) | System to extract checkbox symbol and checkbox option pertaining to checkbox question from a document | |
US11354274B1 (en) | System and method for performing data minimization without reading data content | |
US11790110B2 (en) | System and method for preventing sensitive information from being recorded | |
CN116109990B (en) | Sensitive illegal content detection system for video | |
CN106961423A (en) | A kind of information issuing method |
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 |