WO2023070284A1 - 匿名化处理方法和系统 - Google Patents

匿名化处理方法和系统 Download PDF

Info

Publication number
WO2023070284A1
WO2023070284A1 PCT/CN2021/126194 CN2021126194W WO2023070284A1 WO 2023070284 A1 WO2023070284 A1 WO 2023070284A1 CN 2021126194 W CN2021126194 W CN 2021126194W WO 2023070284 A1 WO2023070284 A1 WO 2023070284A1
Authority
WO
WIPO (PCT)
Prior art keywords
medical data
data set
candidate
target
data sets
Prior art date
Application number
PCT/CN2021/126194
Other languages
English (en)
French (fr)
Inventor
周玉钰
Original Assignee
武汉联影医疗科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 武汉联影医疗科技有限公司 filed Critical 武汉联影医疗科技有限公司
Priority to PCT/CN2021/126194 priority Critical patent/WO2023070284A1/zh
Priority to CN202180009630.3A priority patent/CN115004314A/zh
Publication of WO2023070284A1 publication Critical patent/WO2023070284A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00ICT specially adapted for the handling or processing of medical images
    • G16H30/20ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20092Interactive image processing based on input by user
    • G06T2207/20104Interactive definition of region of interest [ROI]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing

Definitions

  • the present application generally relates to the field of data processing, and in particular relates to an anonymization processing method and system.
  • DICOM Digital Imaging and Communications in Medicine
  • NEMA National Electric Manufacturers Association
  • AI artificial intelligence
  • a method for anonymization processing includes acquiring at least one candidate medical data set and determining one or more target medical data sets based on the at least one candidate medical data set according to the received instructions.
  • Each candidate medical data set in the at least one candidate medical data set corresponds to an object, and each candidate medical data set includes at least one candidate medical image of the object.
  • the method further includes anonymizing the one or more target medical data sets to obtain one or more anonymized medical data sets.
  • the determining one or more target medical data sets based on the at least one candidate medical data set according to the received instruction comprises: based on the instruction, selecting from the at least one candidate medical data set Selecting one or more medical images as a group of target medical images; and designating one or more candidate medical data sets corresponding to the group of target medical images as the one or more target medical data sets.
  • the instructions include information on body parts of interest, and according to the instructions, determining a set of target medical images based on the at least one candidate medical data set includes: based on the instructions, from In the at least one candidate medical data set, determining a medical image corresponding to the body part of interest; and specifying the medical image corresponding to the body part of interest as the set of targets medical images.
  • the determining the medical image corresponding to the body part of interest from the at least one candidate medical data set according to the instruction includes: based on the instruction, performing the at least One or more candidate medical images in a candidate medical data set are identified to determine a medical image corresponding to the body part of interest.
  • the method further includes grouping the one or more candidate medical images based on body parts corresponding to at least one candidate medical image in the at least one candidate medical data set.
  • each candidate medical data set of the at least one candidate medical data set includes one or more feature tags
  • the instructions include at least one of the one or more feature tags.
  • the selecting one or more target medical data sets from the at least one candidate medical data set based on the received instruction includes: determining the target medical data set from the at least one candidate medical data set based on the instruction A subset of medical data under at least one feature tag of interest; and designating the subset of medical data under at least one feature tag of interest as the one or more target medical data sets.
  • the one or more feature tags are selected from the following combinations: type of medical image, body part corresponding to the medical image, object identification number, examination time, examination type, examination parameters, subject name, subject gender, Subject's age, subject's weight, whether the subject is pregnant, and whether the subject has a particular disease.
  • the anonymizing the one or more target medical data sets includes: using an anonymization algorithm to clear, hide or replace one or more target medical data sets corresponding to one or more Privacy information text under a feature tag.
  • the anonymizing the one or more target medical data sets includes: for each medical image in the one or more medical images in the one or more target medical data sets , using an anonymization algorithm to clear, hide or replace the private information text displayed on the medical image.
  • the method further includes displaying an information list corresponding to the at least one medical data set to be selected through a terminal; causing the terminal to display an information list selected from the at least one medical data set to be selected. options; and acquiring said instruction input from said terminal about selecting said one or more target medical data sets.
  • the method further includes: after performing the anonymization process on the one or more target medical data sets, updating the information list, the updated information list includes the one or more Anonymized private information texts under one or more feature tags corresponding to target medical data sets; and displaying the updated information list through the terminal.
  • the option of causing the terminal to display a selection from the at least one medical data set to be selected includes: causing the terminal to display one or more medical data sets corresponding to the at least one medical data set to be selected. option to select from within each feature tab.
  • the anonymizing the one or more target medical data sets includes: automatically performing anonymization on the one or more target medical data sets in response to a one-key anonymous button displayed on the terminal being triggered. Batch-based anonymization.
  • the selecting one or more target medical data sets from the at least one medical data set to be selected based on the received instruction includes: responding to a one-key anonymous button displayed on the terminal being triggered, causing all The terminal displays options for selecting from all anonymous functions and partial anonymous functions; in response to the partial anonymous function being selected, causing the terminal to display options for selecting from the at least one medical data set to be selected; obtaining from The instruction input by the terminal regarding the selection of the one or more target medical data sets.
  • the method further comprises sending the one or more sets of anonymized medical data to a server.
  • a system for anonymization processing includes at least one storage medium storing at least one set of instructions; and at least one processor configured to communicating with the at least one storage medium.
  • the at least one processor when executing the at least one set of instructions, is instructed to cause the system to obtain at least one candidate medical data set and according to the received instructions, based on the at least one candidate medical data set, One or more target medical data sets are determined.
  • Each candidate medical data set in the at least one candidate medical data set corresponds to an object, and each candidate medical data set includes at least one candidate medical image of the object.
  • the at least one processor is further instructed to cause the system to anonymize the one or more target medical data sets to obtain one or more anonymized medical data sets.
  • a system for anonymization processing includes an acquisition module, a selection module, and an anonymization processing module.
  • the obtaining module is used to obtain at least one medical data set to be selected, each medical data set to be selected in the at least one medical data set to be selected corresponds to an object, and each medical data set to be selected includes all at least one candidate medical image of the subject.
  • the selection module is configured to determine one or more target medical data sets based on the at least one candidate medical data set according to the received instruction.
  • the anonymization processing module is used to anonymize the one or more target medical data sets to obtain one or more anonymized medical data sets.
  • a non-transitory computer-readable storage medium for anonymization processing includes at least one set of instructions. When executed by at least one processor of a computing device, the at least one set of instructions instructs the at least one processor to perform a set of methods.
  • the method includes acquiring at least one candidate medical data set and determining one or more target medical data sets based on the at least one candidate medical data set according to the received instructions. Each candidate medical data set in the at least one candidate medical data set corresponds to an object, and each candidate medical data set includes at least one candidate medical image of the object.
  • the method further includes anonymizing the one or more target medical data sets to obtain one or more anonymized medical data sets.
  • Fig. 1 is a schematic diagram of an application scenario of a medical data processing system according to some embodiments of this specification
  • FIG. 2 is a schematic diagram of exemplary hardware and/or software of a computing device according to some embodiments of the present specification
  • Fig. 3 is a schematic diagram of exemplary hardware and/or software of a terminal device according to some embodiments of this specification;
  • Fig. 4 is an exemplary block diagram of a processing device according to some embodiments of the present specification.
  • Fig. 5 is an exemplary flow chart of an anonymization processing method according to some embodiments of this specification.
  • Fig. 6 is a schematic diagram of a user interface for batch anonymization according to some embodiments of the present specification.
  • Fig. 7 is a schematic diagram of a user interface for batch anonymization according to some embodiments of the present specification.
  • Fig. 8 is a schematic diagram of a user interface for batch anonymization according to some embodiments of the present specification.
  • system used in this application are used to distinguish different components, elements, parts, parts or method of the component. However, these terms may also be replaced by other expressions if the same purpose can be achieved.
  • the flow chart is used in this specification to illustrate the operations performed by the system according to the embodiment of this specification, and the relevant description is to help better understand the medical imaging method and/or system. It should be understood that the preceding or following operations are not necessarily performed in the exact order. Instead, various steps may be processed in reverse order or simultaneously. At the same time, other operations can be added to these procedures, or a certain step or steps can be removed from these procedures.
  • This specification provides an anonymization processing method and system.
  • the method and system can be used to process private information contained in medical data, thereby realizing the anonymization of medical data and protecting patient privacy.
  • the traditional method of anonymizing medical data is usually to select a medical data set separately, perform anonymization, and then select the next medical data set in turn and complete the anonymization. This method is time-consuming and requires users to A lot of time and energy.
  • the processor may provide the user with an option to select from multiple medical data sets to be selected. For example, the user can select all, select part of, or select a certain category of medical data set to be selected as the target medical data set that needs to be anonymized according to the feature label.
  • the medical data set may include medical images, such as DICOM images, DICOM tags, information lists and other data.
  • the terminal device may receive instructions provided by the user regarding the selected target medical data set, and transmit the instructions to the processor.
  • the processor can perform batch anonymization processing on the target medical data sets to obtain one or more anonymized medical data sets.
  • the processor may then upload the one or more anonymized medical data sets to the server.
  • the anonymization method provided in this manual can quickly and efficiently anonymize a large amount of data, effectively protect the security of private information, save users' time and energy, and improve user experience.
  • Fig. 1 is a schematic diagram of an application scenario of a medical data processing system according to some embodiments of the present specification.
  • the medical data processing system 100 may include a processing device 110 , a network 120 , a terminal device 130 , a storage device 140 and a server 150 .
  • Various components in the system 100 may be connected to each other through a network 120 .
  • the processing device 110 and the terminal device 130 may be connected or communicate through the network 120 .
  • the processing device 110 and the server 150 may be connected or communicate through the network 120 .
  • the processing device 110 may process data and/or information obtained from at least one terminal device 130 , a storage device 140 or other components of the medical data processing system 100 .
  • processing device 110 may retrieve medical data from storage device 140 .
  • the processing device 110 may also acquire a medical image of the subject from a medical imaging device (not shown in FIG. 1 ), and perform anonymization processing on it. After completing the anonymization process, the processing device 110 may also send the anonymized medical data to the server 150 .
  • the medical imaging device can be used to scan the object in the detection area to obtain the scan data of the object.
  • the subject may include a patient.
  • a medical imaging device may scan a specific part of a patient's body (eg, head, chest, abdomen, etc.) or the entire body to obtain a medical image of the subject.
  • the medical images may include computed tomography (CT) images, magnetic resonance (MR) images, ultrasound images, positron emission tomography (PET) images, optical coherence tomography (OCT) images, etc., or any combination thereof .
  • CT computed tomography
  • MR magnetic resonance
  • PET positron emission tomography
  • OCT optical coherence tomography
  • processing device 110 may include one or more processors (eg, single-chip processors or multi-chip processors).
  • the processing device 110 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processing DSP, Field Programmable Gate Array (FPGA), Programmable Logic Device (PLD), Controller, Microcontroller Unit, Reduced Instruction Set Computer (RISC), Microprocessor, etc. or any combination thereof.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • ASIP application specific instruction set processor
  • GPU graphics processing unit
  • PPU physical processing unit
  • PLD Programmable Logic Device
  • Controller Microcontroller Unit
  • RISC Reduced Instruction Set Computer
  • Network 120 may include any suitable network capable of facilitating the exchange of information and/or data for medical data processing system 100 .
  • at least one component for example, terminal device 130, processing device 110, storage device 140
  • processing device 110 may retrieve medical data for one or more subjects from storage device 140 over network 120 .
  • Network 120 may include public networks (e.g., the Internet), private networks (e.g., local area networks (LANs)), wired networks, wireless networks (e.g., 802.11 networks, Wi-Fi networks), frame relay networks, virtual private networks (VPN), satellite network, telephone network, routers, hubs, switches, etc. or any combination thereof.
  • public networks e.g., the Internet
  • private networks e.g., local area networks (LANs)
  • wired networks e.g., wireless networks (e.g., 802.11 networks, Wi-Fi networks), frame relay networks, virtual private networks (VPN), satellite network, telephone network, routers, hubs, switches, etc. or any combination thereof.
  • VPN virtual private networks
  • network 120 may include a wired network, a wired network, a fiber optic network, a telecommunications network, an intranet, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth TM network, a ZigBee TM network, near field communication (NFC) network, etc. or any combination thereof.
  • network 120 may include at least one network access point.
  • network 120 may include wired and/or wireless network access points, such as base stations and/or Internet exchange points, through which at least one component of medical data processing system 100 may be connected to network 120 to exchange data and/or information .
  • the terminal device 130 may communicate with and/or be connected to the processing device 110 and/or the storage device 140 .
  • the user can interact with the processing device 110 through the terminal device 130 to send instructions.
  • the user may select a medical data set that needs to be anonymized from the medical data sets to be selected through the terminal device 130 .
  • the user may send an instruction to start performing batch anonymization processing through the terminal 130 .
  • the terminal device 130 may include a mobile device 131, a tablet computer 132, a notebook computer 133, etc. or any combination thereof.
  • mobile device 131 may include a mobile controller handle, personal digital assistant (PDA), smartphone, etc., or any combination thereof.
  • the terminal device 130 may include an input device, an output device, and the like.
  • Input means may include keyboard input, touch screen (eg, with tactile or tactile feedback) input, voice input, eye tracking input, gesture tracking input, brain monitoring system input, image input, video input, or any other similar input mechanism.
  • Input information received via the input device may be transmitted, eg, via a bus, to the processing device 110 for further processing.
  • Other types of input devices may include cursor control devices such as a mouse, a trackball, or cursor direction keys, among others.
  • Output devices may include displays, speakers, printers, etc., or any combination thereof. Output devices can be used to present information to users, provide functional options (such as the option to perform anonymization), etc.
  • the terminal device 130 may be integrated with the processing device 110 .
  • server 150 may be a single server or a group of servers. Server groups can be centralized or distributed. In some embodiments, server 150 may be local or remote. For example, server 150 may receive an anonymized medical data set from process 110 over network 120 . The server 150 can also send the received anonymized medical data set to other external devices, for example, share it with other storage devices or terminal devices. In some embodiments, the server 150 can be implemented on a cloud platform.
  • a cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof.
  • Storage device 140 may store data, instructions and/or any other information.
  • the storage device 140 may store medical image data of a subject acquired by a medical imaging device.
  • the storage device 140 may store data obtained from the processing device 110 , the terminal device 130 and/or the server 150 .
  • the storage device 140 may store the anonymized medical data set that has been anonymized by the processing device 110 .
  • storage device 140 may store data and/or instructions that processing device 110 executes or uses to perform the exemplary methods described in this specification.
  • the storage device 140 may include mass storage, removable storage, volatile read-write storage, read-only memory (ROM), etc., or any combination thereof.
  • storage device 140 may be implemented on a cloud platform.
  • storage device 140 may be integrated with processing device 110 or other devices.
  • the server 150 may also be a data storage device including cloud computing platforms (such as public cloud, private cloud, community and hybrid cloud, etc.). However, these changes and modifications do not depart from the scope of the present application.
  • FIG. 2 is a schematic diagram of exemplary hardware and/or software of a computing device according to some embodiments of the present application.
  • computing device 200 may include processor 210 , memory 220 , input/output (I/O) interface 230 , and communication port 240 .
  • processing device 110 of data processing system 100 may be implemented in computing device 200 .
  • the processor 210 can execute calculation instructions (program codes) and perform the functions of the medical data processing system 100 described in this application.
  • the computing instructions may include programs, objects, components, data structures, procedures, modules, and functions (the functions refer to specific functions described in this application).
  • the processor 210 may perform bulk anonymization of medical data obtained from any component of the medical data processing system 100 .
  • the processor 210 may include a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a central processing unit (CPU) , graphics processing unit (GPU), physical processing unit (PPU), microcontroller unit, digital signal processor (DSP), field programmable gate array (FPGA), advanced RISC machine (ARM), programmable logic device and capable Any circuit and processor, etc., or any combination thereof, that performs one or more functions.
  • RISC reduced instruction set computer
  • ASIC application specific integrated circuit
  • ASIP application specific instruction set processor
  • CPU central processing unit
  • GPU graphics processing unit
  • PPU physical processing unit
  • DSP digital signal processor
  • FPGA field programmable gate array
  • ARM advanced RISC machine
  • Memory 220 may store data/information obtained from any other component of medical data processing system 100 .
  • the memory 220 may include mass memory, removable memory, volatile read and write memory, read only memory (ROM), etc., or any combination thereof.
  • Exemplary mass storage may include magnetic disks, optical disks, and solid-state drives, among others.
  • Removable storage can include flash drives, floppy disks, compact disks, memory cards, compact disks, and tapes, among others.
  • Volatile read and write memory can include random access memory (RAM).
  • RAM can include dynamic RAM (DRAM), double rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), and zero capacitance (Z-RAM).
  • DRAM dynamic RAM
  • DDR SDRAM double rate synchronous dynamic RAM
  • SRAM static RAM
  • T-RAM thyristor RAM
  • Z-RAM zero capacitance
  • ROMs can include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (PEROM), electrically erasable programmable ROM (EEPROM), compact disc ROM (CD-ROM) and digital versatile disc ROM wait.
  • MROM mask ROM
  • PROM programmable ROM
  • PEROM erasable programmable ROM
  • EEPROM electrically erasable programmable ROM
  • CD-ROM compact disc ROM
  • digital versatile disc ROM wait digital versatile disc ROM wait.
  • Input/output interface (I/O) 230 may be used to input or output signals, data or information. In some embodiments, input/output interface 230 may enable a user to communicate with medical data processing system 100 . In some embodiments, input/output interface (I/O) 230 may include input devices and output devices. Exemplary input devices may include one or any combination of a keyboard, a mouse, a touch screen, and a microphone. Exemplary output devices may include display devices, speakers, printers, projectors, etc., or any combination thereof.
  • Exemplary display devices may include one or any combination of a liquid crystal display (LCD), a light emitting diode (LED) based display, a flat panel display, a curved display, a television set, a cathode ray tube (CRT), and the like.
  • Communication port 240 may be connected to a network for data communication.
  • the connection may be a wired connection, a wireless connection, or a combination of both.
  • a wired connection may include electrical cables, fiber optic cables, or telephone lines, etc., or any combination thereof.
  • the wireless connection may include one or any combination of Bluetooth, Wi-Fi, WiMax, WLAN, ZigBee, mobile network (for example, 3G, 4G or 5G, etc.) and the like.
  • the communication port 240 may be a standardized port, such as RS232, RS485, and the like. In some embodiments, communication port 240 may be a specially designed port. For example, communication port 240 may be designed according to the Digital Imaging and Medicine Communication Protocol (DICOM).
  • DICOM Digital Imaging and Medicine Communication Protocol
  • Fig. 3 is a schematic diagram of exemplary hardware and/or software components of a terminal device according to some embodiments of the present application.
  • the terminal device 130 in the medical data processing system 100 can be implemented on the terminal device 300 .
  • the terminal device 300 may include a communication platform 310 , a display 320 , a graphics processing unit (GPU) 330 , a central processing unit (CPU) 340 , an I/O 350 , a memory 360 and a storage 390 .
  • any other suitable components may also be included in the terminal device 300, including but not limited to a system bus or a controller (not shown).
  • an operating system 370 eg, iOS TM , Android TM , WindowsPhone TM
  • one or more applications 380 may be loaded from storage 390 into memory 360 for execution by CPU 340 .
  • Application 380 may include a browser or any other suitable mobile application for receiving and rendering image processing related or other information from processing device 110 .
  • User interaction with the stream of information may be accomplished through I/O 350 and provided to processing device 120 and/or other components of medical data processing system 100 through network 120 .
  • One aspect of this specification provides a method for anonymization processing, which can be implemented, for example, in the medical data processing system 100 shown in FIG. 1 .
  • Fig. 4 is an exemplary block diagram of a processing device according to some embodiments of the present specification.
  • the processing device 110 may include an acquisition module 410 , a selection module 420 , an anonymization processing module 430 and a sending module 440 .
  • the aforementioned modules may be all or part of the hardware circuits of the processing device 110 .
  • the above modules can also be implemented as applications or instructions read and executed by the processing device 110 .
  • the above-mentioned modules may be any combination of hardware circuits and application programs/instructions.
  • the aforementioned modules may be part of the processing device 110 when the processing device 110 is executing applications/instructions.
  • the obtaining module 410 may obtain data related to the anonymization processing system 100 from an external device and/or obtain data from other components in the anonymization processing system 100 .
  • the obtaining module 410 may obtain at least one medical data set to be selected from the storage device 140 .
  • a set of medical data may correspond to a medical examination of a subject, such as a medical imaging examination.
  • the medical data set may include various forms of medical data, such as text, image, audio, video and other forms of data.
  • a medical data set may include an information record of a subject, at least one medical image of the subject (eg, a patient), an image label of the at least one medical image, and the like.
  • the information record of the object may be a record in text form, which is convenient for users to consult.
  • the information record of an object can be an information list, and information related to the object and/or the medical image can be listed in the information list, such as the body part corresponding to the medical image, the object identification number, the examination time, the examination type, the examination parameters, and the subject’s name , subject’s ID number, subject’s social security number, subject’s gender, subject’s phone number, subject’s home address, subject’s age, subject’s weight, whether the subject is pregnant, and whether the subject suffers from a specific disease.
  • the medical image may be an ultrasound image, a CT image, an MR image, a PET image, or the like.
  • the medical image tag may be a DICOM Tag.
  • the selection module 420 may determine one or more target medical data sets based on the at least one candidate medical data set according to the received instruction.
  • the terminal device 130 may present at least part of the information in the at least one medical data set to be selected to the user, so that the user can select the one or more target medical data sets.
  • the terminal device 130 may send the instruction to the processing device 110 .
  • the selection module 420 may determine the one or more target sets of medical data based on the received instructions.
  • the selection module 420 can select the medical data under the at least one interested feature label specified by the user according to the feature label of each candidate medical data set in the at least one candidate medical data set A subset of is designated as the one or more target medical data sets. In some embodiments, the selection module 420 may determine the medical image corresponding to the body part of interest from the at least one medical data set to be selected based on the instruction; The medical images corresponding to the body parts of are designated as the set of target medical images.
  • the anonymization processing module 430 may perform anonymization processing on the one or more target medical data sets to obtain one or more anonymized medical data sets. For example, the anonymization processing module 430 may use an anonymization algorithm to clear, hide or replace the private information text under one or more feature tags corresponding to the one or more target medical data sets. For another example, the anonymization processing module 430 may use an anonymization algorithm to clear, hide or replace the private information text displayed on the medical image. In some embodiments, the anonymization processing module 430 may also generate a series of instructions to control the content displayed to the user on the terminal device 130 .
  • the anonymization processing module 430 may send an instruction to the terminal device 130, so that the information list corresponding to the at least one medical data set to be selected is displayed through the terminal device 130; an option to select from among the data sets; and acquiring the instruction input from the terminal device 130 on selecting the one or more target medical data sets.
  • the anonymization processing module 430 may update the information list after performing the anonymization processing on the one or more target medical data sets, and the updated information list includes the one or more target medical data sets. Anonymized private information text under one or more feature tags corresponding to the medical data set; and generating an instruction to display the updated information list through the terminal device 130 .
  • the anonymization processing module 430 may enable the terminal to display options for selecting from one or more feature tags corresponding to the at least one medical data set to be selected.
  • the anonymization processing module 430 may automatically perform batch anonymization processing on the one or more target medical data sets in response to the one-key anonymization button displayed on the terminal being triggered.
  • the anonymization processing module 430 in response to the one-key anonymous button displayed on the terminal being triggered, the anonymization processing module 430 may generate an instruction to make the terminal display options for selecting from all anonymous functions and partial anonymous functions; in response to the The partially anonymous function is selected, causing the terminal to display options for selecting from the at least one medical data set to be selected; obtaining the information about the selected one or more target medical data sets input from the terminal instruction.
  • the sending module 440 may send the one or more anonymized medical data sets to the server 150 .
  • the sending module 440 may automatically send the anonymized medical data set to the server 150 after the anonymization processing module 430 finishes anonymizing the target medical data set.
  • the sending module 440 may send the anonymized medical data set to the server 150 after the obtaining module 410 receives the user's instruction about uploading the anonymized medical data set.
  • the processor may upload at least a part of the data set selected by the user from one or more anonymized medical data sets to the server according to the user instruction.
  • the sending module 440 may also send various instructions (such as various instructions generated by the anonymization processing module 430 ) to the terminal device 130 to control the content displayed by the terminal device 130 to the user.
  • any of the modules mentioned above may be divided into two or more units.
  • the selection module 420 can be divided into two units, one of which can be configured to determine the target medical data set selected by the user from one or more medical data sets to be selected based on the received user instruction; the other can be It is configured to group the medical data sets to be selected according to the feature labels of the medical data sets to be selected.
  • processing device 110 may include one or more additional modules.
  • the processing device 110 may further include a storage module, which may be configured to store data acquired or generated by other modules, for example, the storage module may store an anonymized medical data set.
  • Fig. 5 is an exemplary flow chart of an anonymization processing method according to some embodiments of this specification.
  • the process 500 may be executed by a processor, such as the processing device 110 in the medical data processing system 100, the processor 210 of the computing device 200, or the CPU 340 of the terminal device 300.
  • the process 500 can be stored in a storage device (such as the storage device 140 or the memory 220) in the form of a program or an instruction.
  • a storage device such as the storage device 140 or the memory 220
  • the medical data processing system 100 such as the processing device 110
  • Process 500 may be performed by one or more modules in FIG. 4 .
  • the processing device 110 may acquire at least one candidate medical data set.
  • the processing device 110 may obtain the at least one candidate medical data set from the storage device 140 .
  • step 502 may be performed by the obtaining module 410 .
  • a medical data set may correspond to a medical examination of an object, such as a medical imaging examination.
  • the at least one candidate medical data set may include candidate medical data sets corresponding to multiple subjects.
  • a medical data set may also include relevant data corresponding to multiple medical examinations of a subject.
  • the medical data set may include various forms of medical data, such as text, image, audio, video and other forms of data.
  • a medical data set may include an information record of a subject, at least one medical image of the subject (eg, a patient), an image label of the at least one medical image, and the like.
  • the information record of the object may be a record in text form, which is convenient for users to consult.
  • the information record of an object can be an information list, and information related to the object and/or the medical image can be listed in the information list, such as the body part corresponding to the medical image, the object identification number, the examination time, the examination type, the examination parameters, and the subject’s name , subject’s ID number, subject’s social security number, subject’s gender, subject’s phone number, subject’s home address, subject’s age, subject’s weight, whether the subject is pregnant, and whether the subject suffers from a specific disease.
  • the medical imaging device can scan the whole body of the patient or a specific part of the body (such as the head, chest, abdomen, etc.) according to the imaging protocol to obtain a medical image of the object.
  • the medical image may be an ultrasound image, a CT image, an MR image, a PET image, or the like.
  • the medical image may be a two-dimensional image, a three-dimensional image or a four-dimensional image.
  • Image tags can be used to record medical images and/or subject-related information, such as the subject's name, date of examination, subject's identification number (ID), subject's age, examination type, important parameters in the imaging protocol, etc.
  • the medical image may be a DICOM image
  • the image tag may be a DICOM Tag.
  • the medical data set needs to be uploaded to a server (such as the server 150 in FIG.
  • the processing device 110 needs to anonymize the medical data to be uploaded, that is, delete, hide or replace the patient's private information, so as to protect data privacy.
  • Private information may include, but is not limited to, one or more of the following information: subject's name, subject identification number, subject's address, subject's phone number, subject's ID number, subject's social security number, subject's weight, etc.
  • subject's name e.g., a name
  • subject identification number e.g., subject identification number
  • subject's address e.g., subject's phone number
  • subject's ID number e.g., a part of the at least one candidate medical data set
  • subject's weight e.g., a part of the at least one candidate medical data set needs to be anonymized and uploaded to the server.
  • step 504 the processing device 110 may determine one or more target medical data sets based on the at least one candidate medical data set according to the received instruction. In some embodiments, step 504 may be performed by selection module 420 .
  • the terminal device 130 may present at least part of the information in the at least one medical data set to be selected to the user, so that the user can determine the one or more target medical data sets. After the terminal device 130 receives the user's instruction on the determined target medical data set, it may send the instruction to the processing device 110 . The processing device 110 may determine the one or more target sets of medical data based on the received instructions.
  • the user may select all of the at least one medical data set to be selected as the target medical set. In some embodiments, the user may select a part of the medical data set to be selected or a sub-set of the at least one medical data set to be selected as the target medical set. A subset of the medical data set to be selected may include the entire content of the medical data set to be selected, or may only include part of the content of the medical data set to be selected.
  • each candidate medical data set of the at least one candidate medical data set includes one or more feature labels. Feature labels can be used to identify the type of data in a medical dataset. In some embodiments, part of the feature tag exists in the information list and part of the image tag exists in the medical image.
  • feature tags may only exist in information lists or only in image tags of medical images.
  • feature tags may include one or more of the following: type of medical image, body part corresponding to the medical image, subject identification number, examination time, examination type, examination parameter, subject name, subject gender, subject age , the subject's weight, whether the subject is pregnant, whether the subject has a particular disease, etc.
  • the user may view the one or more feature tags from the terminal device 130, and select one or more interesting feature tags from the one or more feature tags.
  • the processing device 110 After the processing device 110 receives the user's instruction about the selected feature tag of interest, it may determine a subset of medical data under the at least one feature tag of interest from the at least one medical data set to be selected as a target Medicine collection.
  • the "subset" used here includes a part or all of the original medical data set to be selected.
  • the sub-collection may only include the information list of the subject; the sub-collection may only include the medical image and the image label of the subject; or, the sub-collection may include both the information list of the subject and the medical image of the subject.
  • the terminal may provide the user with content to be included in selecting the target medical collection through a user interface, such as whether to include medical images, image tags, information lists, and the like.
  • the processing device 110 may acquire only one candidate medical data set in step 502 . At least a part of medical data (ie, a subset) of the medical data set to be selected may be designated as a target medical data set in step 504 . In some embodiments, the processing device 110 may obtain at least two medical data sets to be selected in step 502, and the processing device 110 may combine at least a part of the medical data to be selected in the at least two medical data sets to be selected in step 502 A subset of the datasets is designated as the target medical dataset.
  • the user may issue an instruction to select a group of target medical images from the at least one medical data set to be selected through the terminal device 130 .
  • the instructions may include information on one or more body parts of interest.
  • the processing device 110 may determine, from the at least one candidate medical data set, medical images corresponding to the body part of interest as a set of target medical images (target medical data set) based on the instruction.
  • the processing device 110 may pre-process the at least one medical data set to be selected before the user selects the target medical data set, identify the body part corresponding to each medical image, and record it under the feature tag. In this way, after the user selects a body part of interest, the processing device 110 can respond quickly and determine the medical image corresponding to one or more body parts of interest as the target medical image.
  • the processing device 110 may group the at least two medical images in advance according to the body parts corresponding to the at least two medical images in the at least one medical data set to be selected. For example, the processing device 110 may identify a set of medical images corresponding to the head, a set of medical images corresponding to the abdomen, and so on.
  • the processing device 110 can directly determine the group corresponding to one or more body parts of interest according to the group information, and designate the medical image in the group as the target medical image .
  • the processing device 110 can perform multi-level grouping of medical images according to different feature labels. For example, the processing device 110 may first group the medical images according to the corresponding body parts, and then divide each group of medical images into one or more subgroups based on other feature labels such as examination type, subject gender, and subject age.
  • the processing device 110 can group the medical images simultaneously according to multiple feature labels. For example, the processing device 110 may first determine a group of ultrasound images corresponding to the liver according to the examination type and the corresponding body part category.
  • the processing device 110 may also divide the group of ultrasound images corresponding to the liver into a subgroup of ultrasound images corresponding to the upper part of the liver, a subgroup of ultrasound images corresponding to the lower part of the liver, and a subgroup of ultrasound images corresponding to the corresponding body part subclasses. A subset of ultrasound images corresponding to the left lobe of the liver, a subset of ultrasound images corresponding to the right lobe of the liver, etc.
  • the terminal device 130 may search for examination parameters (such as various parameters of an imaging protocol) from object information records in the medical data set to be selected, so as to determine the body part corresponding to the medical image in the medical data set to be selected.
  • examination parameters such as various parameters of an imaging protocol
  • the terminal device 130 may use image recognition algorithms, machine learning models, etc. to identify the body part corresponding to the medical image in advance from each medical image, and record it under the feature tag.
  • the terminal device 130 may also process the at least one medical data set to be selected in real time after the user issues an instruction corresponding to the body part of interest, and identify the medical image in a manner similar to the above method corresponding body parts, and according to the information of the one or more body parts of interest, determine the medical image corresponding to the one or more body parts of interest as the target medical image.
  • step 506 the processing device 110 may perform batch anonymization processing on the one or more target medical data sets to obtain one or more anonymized medical data sets.
  • step 506 may be completed by the anonymization processing module 430 .
  • the processing device 110 needs to anonymize data in the form of information lists, medical images and/or image tags in one or more target medical data sets.
  • information listings and image tags may contain private information text. Additionally or alternatively, private information text may be displayed on the medical image.
  • the processing device 110 may use an anonymization algorithm to clear, hide or replace the private information text under one or more feature tags corresponding to the one or more target medical data sets. For example, the processing device 110 may delete all private data that needs to be anonymized from the one or more target medical data sets. Alternatively, the processing device 110 may replace the private data in the one or more target medical data sets with other values, such as random values, random text, and the like.
  • the processing device 110 may use an anonymization algorithm to clear, hide or replace the private information text displayed on the medical images in one or more target medical data sets.
  • the processing device 110 can perform text recognition on the medical image to find the private information text on the medical image. For example, if the private information text on the medical image is editable, the processing device 110 may directly edit the private information text displayed on the medical image to clear, hide or replace the private information text with other content. If the private information text on the medical image is not editable, the processing device 110 may cover the identified private information text that needs to be removed with a layer, thereby hiding the private information text. In some embodiments, the processing device 110 may also insert text on the layer, so as to replace the originally displayed private information text with other content. By clearing, hiding or replacing the private information text, the privacy of patients can be effectively protected.
  • the processing device 110 may automatically and sequentially anonymize the one or more target medical data sets. Alternatively, the processing device 110 may simultaneously perform anonymization processing on at least two medical data sets among the one or more target medical data sets. In some embodiments, the processing device 110 may also process in batches the information that needs to be anonymized in each target medical data set. Such an automatic batch processing method can greatly improve the efficiency of anonymization processing and save the user's time and energy. In some embodiments, the user can customize the type of information that needs to be anonymized, and the processing device 110 can perform anonymization according to the type of information that needs to be anonymized as confirmed by the user.
  • the processing device 110 can adopt various feasible anonymization algorithms, such as algorithms based on rules and dictionaries, K-anonymity algorithm, L-diversity algorithm, T-proximity algorithm, differential privacy algorithm, machine learning-based The algorithm of the model, etc., are not limited in this description.
  • step 508 the processing device 110 may send the one or more sets of anonymized medical data to the server 150 .
  • step 508 may be performed by the sending module 440 .
  • the processing device 110 may automatically send the anonymized medical data set to the server 150 after step 506 is completed. Alternatively, the processing device 110 may send the anonymized medical data set to the server 150 after receiving the user's instruction on uploading the anonymized medical data set. In some embodiments, the processor may upload at least a part selected by the user from one or more anonymized medical data sets to the server according to the user instruction. Optionally, before uploading each medical data set, the processing device 110 needs to confirm whether the medical data set has been anonymized.
  • the processing device 110 can Upload to the server; if it is determined that the medical data set has not been anonymized, the processing device 110 will not upload the medical data set, and may further send a prompt message to the user through the terminal device 130, informing the user that the medical data set has not been anonymized deal with.
  • the server may be a local server or a remote server.
  • the server After the server receives the anonymized medical data set, it can archive and classify it, and can also send the anonymized medical data set to other servers or terminals according to user instructions to complete data sharing. Since the server receives the anonymized medical data set, the patient's private information is not easy to leak from the server, so the security of the private information is well protected.
  • one or more operations may be omitted and/or one or more additional operations may be added.
  • the processing device 110 may not group the medical images in all candidate medical data sets according to their corresponding body parts before performing anonymization processing on the target medical image, but may, after completing the anonymization processing, For all the medical images in the anonymized medical data set, they are grouped according to the corresponding body parts in the feature labels.
  • the processing device 110 may upload the medical images of each group to the server for archiving. Other users can directly select the medical images of each group for observation, which is convenient and trouble-free.
  • 6-8 are schematic diagrams of user interfaces for batch anonymization according to some embodiments of the present specification.
  • the processing device 110 or the anonymization processing module 430 may generate instructions to control what is presented to the user on the user interface.
  • the terminal device 130 may integrate the information lists corresponding to the at least two medical data sets to be selected and present them to the user. As shown in Figure 6, the patient identification number (Patient ID), patient name (Patient Name), examination type (Exam Type) and examination type are displayed in the patient list (Patient List) 610 (equivalent to the information list mentioned above). Date (Exam Date), which is convenient for users to check.
  • the user may first select the target medical data set that needs to be anonymized, and then click the “one-key anonymization” button 620 . After detecting that the “one-key anonymization” button 620 is triggered, the terminal device 130 may send an instruction to perform anonymization to the processing device 110 .
  • the processing device 110 may automatically perform batch anonymization processing on the one or more target medical data sets according to the instruction.
  • the terminal device 130 may display options for selecting from all anonymous functions and partial anonymous functions.
  • the terminal device 130 may display an option to select from the at least two medical data sets to be selected.
  • the terminal device 130 may provide the user with an option of "select all" on the user interface, and the user may click "select all” to issue an instruction to determine all medical data sets to be selected as the target medical data set.
  • the user may manually check one or more medical data sets to be selected to issue an instruction to determine the selected medical data set to be selected as the target medical data set.
  • the processing device 110 may update the information list, and the updated information list includes the one or more target medical data sets Anonymized private information text under one or more feature tags corresponding to the set.
  • the processing device 110 may send the updated information list to the terminal device 130 for display.
  • the patient list 630 is an exemplary information list obtained after the anonymization process is completed. It can be seen that the patient identification number, patient name and examination date in the patient list 630 have been replaced, and the specific information of the examination type that does not involve privacy is retained. In some embodiments, multiple information records corresponding to the same patient can also be found based on the anonymized patient identification number.
  • FIG. 7 is another exemplary user interface for anonymization.
  • the interface in Fig. 7 also shows the image before the anonymization process. For example, by clicking a row of data in the list, the user can view the medical image corresponding to the data.
  • the terminal device 130 may anonymize the medical image and the information in the patient list. After completing the anonymization process, the relevant private information displayed on the medical images was replaced.
  • FIG. 8 is another exemplary user interface for anonymization.
  • the user can select a specific text description, specific value or specific range of the feature label, thereby selecting a medical data set that needs to be anonymized.
  • the user can select the examination time range, examination type and tissue name (equivalent to the body part of interest mentioned above).
  • the patient list displayed on the terminal device 130 can be automatically updated to display records that match the user's selection.
  • the user can click the button 620 of “one-click anonymization”.
  • the processing device 110 may call out the medical images in the target medical data set selected by the user, and perform anonymization processing on these medical images and image tags.
  • the user can also select a specific feature tag type through the terminal device 130, and then select one or more contents (text or value, etc.) corresponding to the specific feature tag. For example, the user can select “body parts corresponding to medical images” as the feature label of interest, then select “liver”, and further select “information list, medical image and image label” as the data type to be included in the target medical data set; For another example, the user can select "type of medical image” and “body part corresponding to medical image” as the feature tags of interest, select “type of medical image” as “ultrasound image”, and select “body part corresponding to medical image "Select as "abdomen”, and further select “medical image and image label” as the data type to be included in the target medical data set.
  • the possible beneficial effects of the embodiments of this specification include but are not limited to: (1) Medical data collections can be anonymized in batches according to user instructions, which improves the efficiency of anonymization processing and saves users (2) uploading the medical data collection to the server after completing the anonymization process can improve the security of the patient's private information and prevent the patient's private information from being leaked from the server; (3) the user can according to One or more feature tags (such as body parts corresponding to medical images) are used to select medical data sets, which is convenient for quickly selecting medical data sets that need to be anonymized, and also facilitates the system to automatically perform follow-up archiving management on anonymized medical data sets and user groups for viewing. It should be noted that different embodiments may have different beneficial effects. In different embodiments, the possible beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.
  • numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of the embodiments use the modifiers "about”, “approximately” or “substantially” in some examples. grooming. Unless otherwise stated, “about”, “approximately” or “substantially” indicates that the stated figure allows for a variation of ⁇ 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that can vary depending upon the desired characteristics of individual embodiments. In some embodiments, numerical parameters should take into account the specified significant digits and adopt the general digit reservation method. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of the range are approximations, in specific embodiments, such numerical values are set as precisely as practicable.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Radiology & Medical Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

本说明书实施例之一提供了一种匿名化处理方法和系统。所述方法可以包括:获取至少一个待选医学数据集合,所述至少一个待选医学数据集合中的每个医学数据集合对应于一个对象,所述每个医学数据集合中包括所述对象的至少一个医学图像;根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合;对于所述一个或多个目标医学数据集合进行批量式匿名化处理,以得到一个或多个匿名化医学数据集合;以及将所述一个或多个匿名化医学数据集合发送至服务器。

Description

匿名化处理方法和系统 技术领域
本申请总体上涉及数据处理领域,特别涉及一种匿名化处理方法和系统。
背景技术
在医学图像领域,医学数字成像和通信(DICOM,Digital Imaging and Communications in Medicine)是一种广泛用于医学图像处理、存储、传输、打印的文件格式标准。该标准由美国电气制造协会(NEMA,National Electric Manufactures Association)创建,用来帮助传输和查看医学图像。DICOM图像在诸如远程会诊、学术会议、多中心临床试验、人工智能(AI)等领域有着广泛的应用。在将包括DICOM图像在内的医学数据共享给不同用户之前,通常需要对医学数据进行匿名化处理,即对患者的姓名、身份证号等隐私信息进行删除、隐藏或替换,以保护数据隐私安全。近年来随着云存储、云共享等技术的蓬勃发展,对于医学数据的共享需求也越来越大。因此,需要提供一种高效的隐私信息处理方法。
发明内容
根据本发明的一方面,提供了一种用于匿名化处理的方法。所述方法包括获取至少一个待选医学数据集合以及根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合。所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合中包括所述对象的至少一个待选医学图像。所述方 法还包括对于所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
在一些实施例中,所述根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合包括:基于所述指令,从所述至少一个待选医学数据集合中选定一个或多个医学图像作为一组目标医学图像;以及将所述一组目标医学图像对应的一个或多个待选医学数据集合指定为所述一个或多个目标医学数据集合。
在一些实施例中,所述指令包括感兴趣的身体部位的信息,所述根据所述指令,基于所述至少一个待选医学数据集合,确定一组目标医学图像包括:基于所述指令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位所对应的医学图像;以及将所述与所述感兴趣的身体部位所对应的医学图像指定为所述一组目标医学图像。
在一些实施例中,所述根据所述指令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位对应的医学图像,包括:基于所述指令,对所述至少一个待选医学数据集合中的一个或多个待选医学图像进行识别,以确定与所述感兴趣的身体部位对应的医学图像。
在一些实施例中,所述方法还包括基于所述至少一个待选医学数据集合中的至少一个待选医学图像对应的身体部位,对所述一个或多个待选医学图像进行分组。
在一些实施例中,所述至少一个待选医学数据集合中的每个待选医学数据集合包括一个或多个特征标签,所述指令包括所述一个或多个特征标签中的至少一个感兴趣的特征标签的信息。所述基于接收的指令,从所述至少一个待选医学数据集合中选定一个或多个目标医学数据集合包括:基于所述指令,从所述至少一个待选医学数据集合中,确定所述至少一个 感兴趣的特征标签下的医学数据的子集合;以及将所述至少一个感兴趣的特征标签下的医学数据的子集合指定为所述一个或多个目标医学数据集合。
在一些实施例中,所述一个或多个特征标签选自以下组合:医学图像的类型、医学图像对应的身体部位、对象识别号、检查时间、检查类型、检查参数、对象姓名、对象性别、对象年龄、对象体重、对象是否怀孕和对象是否患有特定疾病。
在一些实施例中,所述对于所述一个或多个目标医学数据集合进行匿名化处理包括:使用匿名化算法,清除、隐藏或替换所述一个或多个目标医学数据集合对应的一个或多个特征标签下的隐私信息文本。
在一些实施例中,所述对于所述一个或多个目标医学数据集合进行匿名化处理包括:对于所述一个或多个目标医学数据集合中的一个或多个医学图像中的每个医学图像,使用匿名化算法,清除、隐藏或替换所述医学图像上显示的隐私信息文本。
在一些实施例中,所述方法还包括使对应于所述至少一个待选医学数据集合的信息列表通过终端进行展示;使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项;以及获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令。
在一些实施例中,所述方法还包括:对于所述一个或多个目标医学数据集合进行所述匿名化处理后,更新所述信息列表,更新后的所述信息列表包含所述一个或多个目标医学数据集合对应的一个或多个特征标签下的匿名化的隐私信息文本;以及将更新后的所述信息列表通过终端进行展示。
在一些实施例中,所述使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项包括:使所述终端显示从所述至少一个待选医学数据集合对应的一个或多个特征标签中进行选择的选项。
在一些实施例中,所述对于所述一个或多个目标医学数据集合进行匿名化处理包括:响应于终端显示的一键匿名按钮被触发,自动对于所述一个或多个目标医学数据集合进行批量式匿名化处理。
在一些实施例中,所述基于接收的指令,从所述至少一个待选医学数据集合中选定一个或多个目标医学数据集合包括:响应于终端显示的一键匿名按钮被触发,使所述终端显示在全部匿名功能和部分匿名功能中进行选择的选项;响应于所述部分匿名功能被选中,使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项;获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令。
在一些实施例中,所述方法还包括将所述一个或多个匿名化医学数据集合发送至服务器。
根据本发明的另一方面,提供了一种用于匿名化处理的系统,其特征在于,所述系统包括至少一个存储介质,其存储有至少一组指令;以及至少一个处理器,被配置为与所述至少一个存储介质通信。其中,当执行所述至少一组指令时,所述至少一个处理器被指示为使所述系统获取至少一个待选医学数据集合以及根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合。所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合中包括所述对象的至少一个待选医学图像。所述至少一个处理器还被指示为使所述系统对于所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
根据本发明的又一方面,提供了一种用于匿名化处理的系统,其特征在于,所述系统包括获取模块、选择模块以及匿名化处理模块。所述获取模块用于获取至少一个待选医学数据集合,所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据 集合中包括所述对象的至少一个待选医学图像。所述选择模块用于根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合。所述匿名化处理模块用于对所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
根据本发明的又一方面,提供了一种用于匿名化处理的非暂时性计算机可读存储介质。所述非暂时性计算机可读存储介质包括至少一组指令。当由计算机设备的至少一个处理器执行时,所述至少一组指令指示所述至少一个处理器执行一套方法。所述方法包括获取至少一个待选医学数据集合以及根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合。所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合中包括所述对象的至少一个待选医学图像。所述方法还包括对于所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
附图说明
本说明书将以示例性实施例的方式进一步说明,这些示例性实施例将通过附图进行详细描述。这些实施例并非限制性的,在这些实施例中,相同的编号表示相同的结构,其中:
图1是根据本说明书一些实施例所示的医学数据处理系统的应用场景示意图;
图2是根据本说明书一些实施例所示的计算设备的示例性硬件和/或软件的示意图;
图3是根据本说明书一些实施例所示的一种终端设备的示例性硬件和/或软件示意图;
图4是根据本说明书一些实施例所示的处理设备的示例性模块图;
图5是根据本说明书一些实施例所示的匿名化处理方法的示例性流程图;
图6是根据本说明书一些实施例所示的批量匿名化处理的用户界面的示意图;
图7是根据本说明书一些实施例所示的批量匿名化处理的用户界面的示意图;
图8是根据本说明书一些实施例所示的批量匿名化处理的用户界面的示意图。
具体实施方式
为了更清楚地说明本申请实施例的技术方案,下面将对实施例描述中所需要使用的附图作简单的介绍。然而,本领域技术人员应该明白,可以在没有这些细节的情况下实施本申请。在其它情况下,为了避免不必要地使本申请的各方面变得晦涩难懂,已经在较高的层次上描述了众所周知的方法、过程、系统、组件和/或电路。对于本领域的普通技术人员来讲,显然可以对所披露的实施例做出各种改变,并且在不偏离本申请的原则和范围的情况下,本申请中所定义的普遍原则可以适用于其他实施例和应用场景。因此,本申请不限于所示的实施例,而是符合与申请专利范围一致的最广泛范围。
本申请中所使用的术语仅出于描述特定示例实施例的目的,而非限制性的。如本申请使用的单数形式“一”、“一个”及“该”同样可以包括复数形式,除非上下文明确提示例外情形。还应当理解,如在本申请说明书中使用的术语“包括”、“包含”仅提示存在所述特征、整数、步骤、操作、组件和/或部件,但并不排除存在或添加以上其它特征、整数、步骤、操作、组件、部件和/或其组合的情况。
可以理解的是,本申请使用的术语“系统”、“引擎”、“单元”、“模块”和/或“区块”是用于按升序区分不同级别的不同构件、元件、部件、部分或组件的方法。然而,如果可以达到相同的目的,这些术语也可以被其他表达替换。
可以理解的是,除非上下文另有明确说明,当单元、引擎、模块或块被称为在另一单元、引擎、模块或块“上”、“连接”或“耦合至”另一单元、引擎、模块或块时,其可以直接在其它单元、引擎、模块或块上,与其连接或耦合或与之通信,或者可能存在中间单元、引擎、模块或块。在本申请中,术语“和/或”可包括任何一个或以上相关所列条目或其组合。
本说明书中使用了流程图用来说明根据本说明书的实施例的系统所执行的操作,相关描述是为帮助更好地理解医学成像方法和/或系统。应当理解的是,前面或后面操作不一定按照顺序来精确地执行。相反,可以按照倒序或同时处理各个步骤。同时,也可以将其他操作添加到这些过程中,或从这些过程移除某一步或数步操作。
本说明书提供了一种匿名化处理方法和系统。该方法和系统可以用于处理医学数据中含有的隐私信息,从而实现医学数据的匿名化,以保护患者隐私。传统的对于医学数据进行匿名化处理的方法通常是单独选择一个医学数据集合,执行匿名化处理后,再依次选择下一个医学数据集合并完成匿名化,这种方式较为耗时,且需要耗费用户大量的时间和精力。本说明书提供的匿名化处理方法中,处理器可以为用户提供从多个待选医学数据集合中进行选择的选项。例如,用户可以全选,部分选择,或根据特征标签选择某个类别的待选医学数据集合作为需要匿名化处理的目标医学数据集合。医学数据集合中可以包括医学图像,如DICOM图像、DICOM标签、信息列表等数据。终端设备可以接收用户提供的关于选定的目标医学数据集合的指令,并将该指令传输给处理器。处理器可以对所述目标医学 数据集合进行批量匿名化处理,以得到一个或多个匿名化的医学数据集合。随后处理器可以将所述一个或多个匿名化的医学数据集合上传到服务器。与传统方式相比,本说明书提供的匿名化处理方法可以快速高效地匿名化处理大量数据,有效保护隐私信息安全,并节约用户的时间和精力,改善使用体验。
图1是根据本说明书一些实施例所示的医学数据处理系统的应用场景示意图。
如图1所示,医学数据处理系统100中可以包括处理设备110、网络120、终端设备130、存储设备140以及服务器150。该系统100中的各个组件之间可以通过网络120互相连接。例如,处理设备110和终端设备130可以通过网络120连接或通信。又例如,处理设备110和服务器150可以通过网络120连接或通信。
处理设备110可以处理从至少一个终端设备130、存储设备140或医学数据处理系统100的其他组件获得的数据和/或信息。例如,处理设备110可以从存储设备140获取医学数据。处理设备110还可以从医学成像装置(图1中未示出)获取对象的医学图像,并对其进行匿名化处理。在完成匿名化处理之后,处理设备110还可以将匿名化的医学数据发送至服务器150。
医学成像装置可以用于对检测区域内的对象进行扫描,得到该对象的扫描数据。在一些实施例中,所述对象可以包括患者。医学成像装置可以对患者的身体的特定部分(例如头部、胸部、腹部等)或整个身体进行扫描,以获取对象的医学图像。例如,所述医学图像可以包括计算机断层扫描(CT)图像、核磁共振(MR)图像、超声图像、正电子发射断层扫描(PET)图像、光学相干断层扫描(OCT)图像等,或其任意组合。
在一些实施例中,处理设备110可以包括一个或以上处理器(例如,单芯片处理器或多芯片处理器)。仅作为示例,处理设备110可以包括中央处理单元(CPU)、专用集成电路(ASIC)、专用指令集处理器(ASIP)、图像处理单元(GPU)、物理运算处理单元(PPU)、数字信号处理器(DSP)、现场可编程门阵列(FPGA)、可编程逻辑器件(PLD)、控制器、微控制器单元、精简指令集计算机(RISC)、微处理器等或其任意组合。
网络120可以包括能够促进医学数据处理系统100的信息和/或数据交换的任何合适的网络。在一些实施例中,医学数据处理系统100的至少一个组件(例如,终端设备130、处理设备110、存储设备140)可以通过网络120与医学数据处理系统100中至少一个其他组件交换信息和/或数据。例如,处理设备110可以通过网络120从存储设备140获取一个或多个对象的医学数据。网络120可以包括公共网络(例如,因特网)、专用网络(例如,局部区域网络(LAN))、有线网络、无线网络(例如,802.11网络、Wi-Fi网络)、帧中继网络、虚拟专用网络(VPN)、卫星网络、电话网络、路由器、集线器、交换机等或其任意组合。例如,网络120可以包括有线网络、有线网络、光纤网络、电信网络、内联网、无线局部区域网络(WLAN)、城域网(MAN)、公共电话交换网络(PSTN)、蓝牙 TM网络、ZigBee TM网络、近场通信(NFC)网络等或其任意组合。在一些实施例中,网络120可以包括至少一个网络接入点。例如,网络120可以包括有线和/或无线网络接入点,例如基站和/或互联网交换点,医学数据处理系统100的至少一个组件可以通过接入点连接到网络120以交换数据和/或信息。
终端设备130可以与处理设备110和/或存储设备140通信和/或连接。在一些实施例中,用户可以通过终端设备130与处理设备110进行交互,以发送指令。例如,用户可以通过终端设备130,从待选医学数据集合中选取需要匿名化处理的医学数据集合。又例如,用户可以通过终端130, 发送开始执行批量匿名化处理的指令。在一些实施例中,终端设备130可以包括移动设备131、平板计算机132、笔记本电脑133等或其任意组合。例如,移动设备131可以包括移动控制手柄、个人数字助理(PDA)、智能手机等或其任意组合。
在一些实施例中,终端设备130可以包括输入设备、输出设备等。输入方式可以包括键盘输入、触摸屏(例如,具有触觉或触觉反馈)输入、语音输入、眼睛跟踪输入、手势跟踪输入、大脑监测系统输入、图像输入、视频输入或任何其他类似的输入机制。通过输入设备接收的输入信息可以通过如总线传输到处理设备110,以进行进一步处理。其他类型的输入设备可以包括光标控制装置,例如,鼠标、轨迹球或光标方向键等。输出设备可以包括显示器、扬声器、打印机等或其任意组合。输出设备可以用于向用户展示信息,提供功能性选项(如执行匿名化处理的选项)等。在一些实施例中,终端设备130可以与处理设备110的集成在一起。
在一些实施例中,服务器150可以是单一服务器或服务器组。服务器组可以是集中式的或分布式的。在一些实施例中,服务器150可以是本地或远程的。例如,服务器150可以通过网络120从处理110接收匿名化的医学数据集合。服务器150还可以将接收到的匿名化医学数据集合发送给其他外部设备,例如共享到其他存储设备或终端设备。在一些实施例中,服务器150可以在云平台上实现。例如,云平台可以包括私有云、公共云、混合云、社区云、分布式云、云间云、多云等或其任意组合。
存储设备140可以存储数据、指令和/或任何其他信息。例如,存储设备140可以存储医学图像设备获取的对象的医学图像数据。在一些实施例中,存储设备140可以存储从处理设备110、终端设备130和/或服务器150获得的数据。例如,存储设备140可以存储由处理设备110匿名化处理后的匿名化医学数据集合。在一些实施例中,存储设备140可以存储处 理设备110用来执行或使用来完成本说明书中描述的示例性方法的数据和/或指令。在一些实施例中,存储设备140可以包括大容量存储器、可移动存储器、易失性读写存储器、只读存储器(ROM)等或其任意组合。在一些实施例中,存储设备140可以在云平台上实现。在一些实施例中,存储设备140可以与处理设备110或其他设备集成在一起。
应该注意的是,上述描述仅出于说明性目的而提供,并不旨在限制本申请的范围。对于本领域普通技术人员而言,在本申请内容的指导下,可做出多种变化和修改。可以以各种方式组合本申请描述的示例性实施例的特征、结构、方法和其他特征,以获得另外的和/或替代的示例性实施例。例如,服务器150还可以是包括云计算平台(例如公共云、私有云、社区和混合云等)的数据存储设备。然而,这些变化与修改不会背离本申请的范围。
图2是根据本申请的一些实施例所示的计算设备的示例性硬件和/或软件的示意图。如图2所示,计算设备200可以包括处理器210、存储器220、输入/输出(I/O)接口230和通信端口240。在一些实施例中,数据处理系统100的处理设备110可以在计算设备200中实现。
处理器210可以执行计算指令(程序代码)并执行本申请描述的医学数据处理系统100的功能。所述计算指令可以包括程序、对象、组件、数据结构、过程、模块和功能(所述功能指本申请中描述的特定功能)。例如,处理器210可以对从医学数据处理系统100的任何组件获得的医学数据进行批量匿名化处理。在一些实施例中,处理器210可以包括微控制器、微处理器、精简指令集计算机(RISC)、专用集成电路(ASIC)、应用特定指令集处理器(ASIP)、中央处理器(CPU)、图形处理单元(GPU)、物理处理单元(PPU)、微控制器单元、数字信号处理器(DSP)、现场可编程门阵列(FPGA)、高级RISC机(ARM)、可编程逻辑器件以及能够 执行一个或多个功能的任何电路和处理器等,或其任意组合。仅为了说明,图2中的计算设备200只描述了一个处理器,但需要注意的是本申请中的计算设备200还可以包括多个处理器。
存储器220可以存储从医学数据处理系统100的任何其他组件获得的数据/信息。在一些实施例中,存储器220可以包括大容量存储器、可移动存储器、易失性读取和写入存储器和只读存储器(ROM)等,或其任意组合。示例性大容量存储器可以包括磁盘、光盘和固态驱动器等。可移动存储器可以包括闪存驱动器、软盘、光盘、存储卡、压缩盘和磁带等。易失性读取和写入存储器可以包括随机存取存储器(RAM)。RAM可以包括动态RAM(DRAM)、双倍速率同步动态RAM(DDR SDRAM)、静态RAM(SRAM)、晶闸管RAM(T-RAM)和零电容(Z-RAM)等。ROM可以包括掩模ROM(MROM)、可编程ROM(PROM)、可擦除可编程ROM(PEROM)、电可擦除可编程ROM(EEPROM)、光盘ROM(CD-ROM)和数字通用盘ROM等。
输入/输出接口(I/O)230可以用于输入或输出信号、数据或信息。在一些实施例中,输入/输出接口230可以使用户与医学数据处理系统100进行联系。在一些实施例中,输入/输出接口(I/O)230可以包括输入装置和输出装置。示例性输入装置可以包括键盘、鼠标、触摸屏和麦克风等中的一种或以上任意组合。示例性输出设备可以包括显示设备、扬声器、打印机、投影仪等,或其任意组合。示例性显示装置可以包括液晶显示器(LCD)、基于发光二极管(LED)的显示器、平板显示器、曲面显示器、电视设备、阴极射线管(CRT)等中的一种或以上任意组合。通信端口240可以连接到网络以便数据通信。所述连接可以是有线连接、无线连接或两者的组合。有线连接可以包括电缆、光缆或电话线等,或其任意组合。无线连接可以包括蓝牙、Wi-Fi、WiMax、WLAN、ZigBee、移动网络(例如, 3G、4G或5G等)等中的一种或以上任意组合。在一些实施例中,通信端口240可以是标准化端口,如RS232、RS485等。在一些实施例中,通信端口240可以是专门设计的端口。例如,通信端口240可以根据数字成像和医学通信协议(DICOM)进行设计。
图3是根据本申请的一些实施例所示的终端设备的示例性硬件和/或软件组件的示意图。医学数据处理系统100中的终端设备130可以在终端设备300上实现。如图3所示,终端设备300可以包括通信平台310、显示器320、图像处理单元(GPU)330、中央处理单元(CPU)340、I/O350、内存360和存储器390。在一些实施例中,终端设备300中还可以包括任何其他适当的组件,包括但不限于系统总线或控制器(未示出)。在一些实施例中,可将操作系统370(例如,iOS TM,Android TM,WindowsPhone TM)和一个或多个应用380从存储器390加载到内存360中,以便由CPU 340执行。应用程序380可以包括浏览器或任何其他合适的移动应用程序,用于从处理设备110接收和渲染与图像处理有关的信息或其他信息。用户与信息流的交互可以通过I/O350实现,并通过网络120提供给处理设备120和/或医学数据处理系统100的其他组件。
本说明书的一个方面提供了一种匿名化处理的方法,该方法可以在例如图1所示的医学数据处理系统100中实现。
图4是根据本说明书一些实施例所示的处理设备的示例性模块图。如图4所示,处理设备110可以包括获取模块410,、选择模块420、匿名化处理模块430以及发送模块440。上述模块可以是处理设备110的全部或一部分的硬件电路。上述模块也可以被实现为由处理设备110读取和执行的应用或指令。此外,上述模块可以是硬件电路和应用程序/指令的任意组合。例如,当处理设备110正在执行应用程序/指令时,上述模块可以是处理设备110的一部分。
获取模块410可以从外部设备获取与匿名化处理系统100有关的数据和/或从匿名化处理系统100中的其他组件获取数据。例如,获取模块410可以从存储设备140中获取至少一个待选医学数据集合。在一些实施例中,一个医学数据集合可以对应于对象的一次医学检查,如医学影像检查。医学数据集合可以包括各种形式的医学数据,例如文字、图像、音频、视频等形式的数据。例如,医学数据集合可以包括对象的信息记录、对象(例如病人)的至少一张医学图像、所述至少一张医学图像的图像标签等。对象的信息记录可以是诸如文字形式的记录,便于用户查阅。例如,对象的信息记录可以是信息列表,信息列表中可以列出对象和/或医学图像的相关信息,如医学图像对应的身体部位、对象识别号、检查时间、检查类型、检查参数、对象姓名、对象身份证号、对象社保号、对象性别、对象联系电话、对象的家庭住址、对象年龄、对象体重、对象是否怀孕和对象是否患有特定疾病等信息中的一种或多种。仅作为示例,所述医学图像可以是超声图像、CT图像、MR图像、PET图像等。在一些实施例中,所述医学图像可以是DICOM图像,所述图像标签可以是DICOM Tag。
选择模块420可以根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合。在一些实施例中,终端设备130可以将所述至少一个待选医学数据集合中的至少部分信息展示给用户,以便用户选择所述一个或多个目标医学数据集合。终端设备130接收到用户关于选定的目标医学数据集合的指令后,可以将所述指令发送给处理设备110。选择模块420可以基于接收的指令,确定所述一个或多个目标医学数据集合。在一些实施例中,选择模块420可以根据所述至少一个待选医学数据集合中的每个待选医学数据集合的特征标签,将用户指定的所述至少一个感兴趣的特征标签下的医学数据的子集合指定为所述一个或多个目标医学数据集合。在一些实施例中,选择模块420可以基于所述指令,从 所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位对应的医学图像;以及将所述与所述感兴趣的身体部位对应的医学图像指定为所述一组目标医学图像。
匿名化处理模块430可以对所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。例如,匿名化处理模块430可以使用匿名化算法,清除、隐藏或替换所述一个或多个目标医学数据集合对应的一个或多个特征标签下的隐私信息文本。又例如,匿名化处理模块430可以使用匿名化算法,清除、隐藏或替换医学图像上显示的隐私信息文本。在一些实施例中,匿名化处理模块430还可以生成一系列指令,以控制终端设备130上展示给用户的内容。例如,匿名化处理模块430可以向终端设备130发送指令,使对应于所述至少一个待选医学数据集合的信息列表通过终端设备130进行展示;使终端设备130显示从所述至少一个待选医学数据集合中进行选择的选项;以及获取从终端设备130输入的关于选定所述一个或多个目标医学数据集合的所述指令。再例如,匿名化处理模块430可以在对于所述一个或多个目标医学数据集合进行所述匿名化处理后,更新所述信息列表,更新后的所述信息列表包含所述一个或多个目标医学数据集合对应的一个或多个特征标签下的匿名化的隐私信息文本;以及生成指令,使更新后的所述信息列表通过终端设备130进行展示。在一些实施例中,匿名化处理模块430可以使所述终端显示从所述至少一个待选医学数据集合对应的一个或多个特征标签中进行选择的选项。匿名化处理模块430可以响应于终端显示的一键匿名按钮被触发,自动对于所述一个或多个目标医学数据集合进行批量式匿名化处理。在一些实施例中,响应于终端显示的一键匿名按钮被触发,匿名化处理模块430可以生成指令,使所述终端显示在全部匿名功能和部分匿名功能中进行选择的选项;响应于所述部分匿名功能被选中,使所述终端显示从所述至少一 个待选医学数据集合中进行选择的选项;获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令。
发送模块440可以将所述一个或多个匿名化医学数据集合发送至服务器150。在一些实施例中,发送模块440可以在匿名化处理模块430完成对目标医学数据集合的匿名化处理之后,自动将匿名化医学数据集合发送至服务器150。或者,可以在获取模块410接收到用户关于上传匿名化医学数据集合的指令之后,再由发送模块440将匿名化医学数据集合发送至服务器150。在一些实施例中,处理器可以根据用户指令上传用户从一个或多个匿名化医学数据集合中选取的至少一部分数据集合上传到服务器。在一些实施例中,发送模块440还可以向终端设备130发送各种指令(例如由匿名化处理模块430生成的各种指令),以控制终端设备130所展示给用户的内容。
应当注意的是,以上描述仅出于说明的目的而提供,并不旨在限制本申请的范围。对于本领域的普通技术人员来说,可以根据本申请的描述,做出各种各样的变化和修改。然而,这些变化和修改不脱离本申请的范围。在一些实施例中,以上提到的任何模块可以被分成两个或更多个单元。例如,选择模块420可以被划分为两个单元,其中一个可以被配置为基于接收到的用户指令,从一个或多个待选医学数据集合中确定用户选定的目标医学数据集合;另一个可以被配置为根据待选医学数据集合的特征标签,对待选医学数据集合进行分组。在一些实施例中,处理设备110可以包括一个或多个附加模块。例如,处理设备110可以进一步包括存储模块,该存储模块可以被配置为存储其他模块获取或生成的数据,例如存储模块可以存储匿名化的医学数据集合。
图5是根据本说明书一些实施例所示的匿名化处理方法的示例性流程图。具体的,过程500可以由处理器执行,例如医学数据处理系统100中 的处理设备110、计算设备200的处理器210或终端设备300的CPU 340。在一些实施例中,过程500可以以程序或指令的形式存储在存储装置(如存储设备140或存储器220)中,当医学数据处理系统100(如处理设备110)执行该程序或指令时,可以实现过程500。在一些实施例中,过程500可以由图4中的一个或多个模块执行。
在步骤502中,处理设备110可以获取至少一个待选医学数据集合。例如,处理设备110可以从存储设备140中获取所述至少一个待选医学数据集合。在一些实施例中,步骤502可以由获取模块410执行。
在一些实施例中,一个医学数据集合可以对应于一个对象的一次医学检查,如医学影像检查。所述至少一个待选医学数据集合中可以包括对应于多个对象的待选医学数据集合。在一些实施例中,一个医学数据集合也可以包括对应于一个对象的多次医学检查的相关数据。医学数据集合可以包括各种形式的医学数据,例如文字、图像、音频、视频等形式的数据。例如,医学数据集合可以包括对象的信息记录、对象(例如病人)的至少一张医学图像、所述至少一张医学图像的图像标签等。对象的信息记录可以是诸如文字形式的记录,便于用户查阅。例如,对象的信息记录可以是信息列表,信息列表中可以列出对象和/或医学图像的相关信息,如医学图像对应的身体部位、对象识别号、检查时间、检查类型、检查参数、对象姓名、对象身份证号、对象社保号、对象性别、对象联系电话、对象的家庭住址、对象年龄、对象体重、对象是否怀孕和对象是否患有特定疾病等信息中的一种或多种。医学成像装置可以根据成像协议,对病人的整个身体或身体的特定部分(例如头部、胸部、腹部等)进行扫描,以获取对象的医学图像。仅作为示例,所述医学图像可以是超声图像、CT图像、MR图像、PET图像等。所述医学图像可以是二维图像、三维图像或者四维图像。图像标签可以用于记录医学图像和/或对象的相关信息,例如对象的姓名、检 查日期、对象的识别号(ID)、对象年龄、检查类型、成像协议中的重要参数等。在一些实施例中,所述医学图像可以是DICOM图像,所述图像标签可以是DICOM Tag。在一些实施例中,需要将医学数据集合上传到服务器(例如图1中的服务器150),以便进行远程会诊、学术会议、多中心临床试验、人工智能(AI)训练等应用。因此,在上传之前,处理设备110需要对待上传的医学数据进行匿名化处理,即对患者的隐私信息进行删除、隐藏或替换,以保护数据隐私安全。隐私信息可以包括但不限于以下信息中的一项或多项:对象姓名、对象识别号、对象住址、对象电话、对象身份证号、对象社保号、对象体重等。在一些实施例中,所述至少一个待选医学数据集合中只有一部分医学数据集合需要被匿名化并上传至服务器。
在步骤504中,处理设备110可以根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合。在一些实施例中,步骤504可以由选择模块420执行。
在一些实施例中,终端设备130可以将所述至少一个待选医学数据集合中的至少部分信息展示给用户,以便用户确定所述一个或多个目标医学数据集合。终端设备130接收到用户关于确定的目标医学数据集合的指令后,可以将所述指令发送给处理设备110。处理设备110可以基于接收的指令,确定所述一个或多个目标医学数据集合。
在一些实施例中,用户可以将所述至少一个待选医学数据集合全选为所述目标医学集合。在一些实施例中,用户可以选择所述至少一个待选医学数据集合中的一部分待选医学数据集合或其子集合作为目标医学集合。一个待选医学数据集合的子集合可以包括该待选医学数据集合的全部内容,也可以只包括该待选医学数据集合的部分内容。在一些实施例中,所述至少一个待选医学数据集合中的每个待选医学数据集合包括一个或多个特征标签。特征标签可以用来标识医学数据集合中数据的类型。在一些实施例 中,特征标签的一部分存在于信息列表中,一部分存在于医学图像的图像标签中。在一些实施例中,特征标签可以仅存在于信息列表中或仅存在于医学图像的图像标签中。仅作为示例,特征标签可以包括以下中的一种或多种:医学图像的类型、医学图像对应的身体部位、对象识别号、检查时间、检查类型、检查参数、对象姓名、对象性别、对象年龄、对象体重、对象是否怀孕和对象是否患有特定疾病等。用户可以从终端设备130上查看所述一个或多个特征标签,并从所述一个或多个特征标签中选择一个或多个感兴趣的特征标签。处理设备110接收到用户关于选定的感兴趣的特征标签的指令后,可以从所述至少一个待选医学数据集合中确定所述至少一个感兴趣的特征标签下的医学数据的子集合作为目标医学集合。此处所使用的“子集合”包括原始的待选医学数据集合的一部分或全部数据。例如,子集合可以只包括对象的信息列表;子集合可以只包括对象的医学图像和图像标签;或者,子集合可以既包括对象的信息列表也包括对象的医学图像。在一些实施例中,终端可以通过用户界面给用户提供选择目标医学集合所要包括的内容,例如是否包括医学图像、图像标签、信息列表等。
在一些实施例中,处理设备110在步骤502中可以仅获取一个待选医学数据集合。该待选医学数据集合中的至少一部分医学数据(即子集合)可以在步骤504中被指定为目标医学数据集合。在一些实施例中,处理设备110可以在步骤502中获取至少两个待选医学数据集合,处理设备110在步骤502中可以将所述至少两个待选医学数据集合中的至少一部分待选医学数据集合的子集合指定为目标医学数据集合。
在一些实施例中,用户可以通过终端设备130,发出从所述至少一个待选医学数据集合中选定一组目标医学图像的指令。例如,所述指令可以包括一个或多个感兴趣的身体部位的信息。处理设备110可以基于所述指 令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位对应的医学图像作为一组目标医学图像(目标医学数据集合)。
在一些实施例中,处理设备110可以在用户选择目标医学数据集合之前,预先对所述至少一个待选医学数据集合进行处理,识别每个医学图像对应的身体部位,并记录在特征标签下。这样,当用户选择了感兴趣的身体部位后,处理设备110可以快速响应,确定对应于一个或多个感兴趣的身体部位的医学图像为所述目标医学图像。或者,处理设备110可以预先根据所述至少一个待选医学数据集合中的至少两个医学图像对应的身体部位,对至少两个医学图像进行分组。例如处理设备110可以确认对应于头部的一组医学图像、对应于腹部的一组医学图像等。当接收到用户关于感兴趣的身体部位的指令之后,处理设备110可以直接根据分组信息,确定一个或多个感兴趣的身体部位对应的分组,并将该分组中的医学图像指定为目标医学图像。在一些实施例中,处理设备110可以根据不同特征标签对医学图像进行多级分组。例如,处理设备110可以先根据对应的身体部位,对医学图像进行分组,再对每组医学图像,基于检查类型、对象性别、对象年龄等其他特征标签分为一个或多个子组。在一些实施例中,处理设备110可以根据多个特征标签,对医学图像同时进行分组。例如,处理设备110可以先根据检查类型和对应的身体部位大类,确定一组对应于肝脏的超声图像。进一步地,处理设备110还可以根据对应的身体部位亚类,将对应于肝脏的这组超声图像分为对应于肝脏上部的一个子组超声图像、对应于肝脏下部的一个子组超声图像、对应于肝左叶的一个子组超声图像、对应于肝右叶的一个子组超声图像等。
仅作为示例,终端设备130可以从待选医学数据集合中的对象信息记录里查找检查参数(如成像协议的各种参数),从而确定该待选医学数据集合中的医学图像对应的身体部位。又例如,终端设备130可以采用图 像识别算法、机器学习模型等方式,预先从每个医学图像中识别出该医学图像对应的身体部位,并记录在特征标签下。
在一些实施例中,终端设备130也可以在用户发出关于感兴趣的身体部位对应的指令后,实时对所述至少一个待选医学数据集合进行处理,按照与上述方法类似的方式识别出医学图像对应的身体部位,并根据所述一个或多个感兴趣的身体部位的信息,确定对应于一个或多个感兴趣的身体部位的医学图像为所述目标医学图像。
在步骤506中,处理设备110可以对所述一个或多个目标医学数据集合进行批量式匿名化处理,以得到一个或多个匿名化医学数据集合。在一些实施例中,步骤506可以由匿名化处理模块430完成。
在一些实施例中,处理设备110需要对一个或多个目标医学数据集合中的信息列表、医学图像和/或图像标签等形式的数据进行匿名化处理。例如,信息列表和图像标签中可能含有隐私信息文本。附加地或可替代地,医学图像上可能显示有隐私信息文本。在一些实施例中,处理设备110可以使用匿名化算法,清除、隐藏或替换所述一个或多个目标医学数据集合对应的一个或多个特征标签下的隐私信息文本。例如,处理设备110可以从所述一个或多个目标医学数据集合中删除所有需要匿名化处理的隐私数据。或者,处理设备110可以将所述一个或多个目标医学数据集合中的隐私数据替换成其他值,例如随机值、随机文字等。在一些实施例中,处理设备110可以使用匿名化算法,清除、隐藏或替换一个或多个目标医学数据集合中的医学图像上显示的隐私信息文本。处理设备110可以对医学图像进行文字识别,找到医学图像上的隐私信息文本。例如,若医学图像上的隐私信息文本是可编辑的,处理设备110可以直接编辑医学图像上显示的隐私信息文本,将隐私信息文本清除、隐藏或替换成其他内容。若医学图像上的隐私信息文本是不可编辑的,处理设备110可以用图层覆盖识别出 来的需要清除的隐私信息文本,从而将所述隐私信息文本隐藏起来。在一些实施例中,处理设备110还可以再所述图层上再插入文字,从而将原来显示的隐私信息文本替换成其他内容。通过对隐私信息文本的清除、隐藏或替换,可以有效保护患者隐私。
在一些实施例中,为了进行批量式匿名化处理,处理设备110可以自动依次对所述一个或多个目标医学数据集合进行匿名化处理。或者,处理设备110可以对所述一个或多个目标医学数据集合中的至少两个医学数据集合同时进行匿名化处理。在一些实施例中,处理设备110也可以批量式处理每个目标医学数据集合中的各项需要匿名化处理的信息。这样自动批量式处理的方式可以大大提高匿名化处理的效率,并节约用户的时间和精力。在一些实施例中,用户可以自定义需要匿名化处理的信息种类,处理设备110可以根据用户确认的需要匿名化处理的信息种类来执行匿名化。在一些实施例中,处理设备110可以采取各种可行的匿名化算法,例如基于规则和词典的算法、K-匿名算法、L-多样性算法、T-接近算法、差分隐私算法、基于机器学习模型的算法等,本说明书对此不作限制。
在步骤508中,处理设备110可以将所述一个或多个匿名化医学数据集合发送至服务器150。在一些实施例中,步骤508可以由发送模块440执行。
在一些实施例中,处理设备110可以在完成步骤506之后,自动将匿名化医学数据集合发送至服务器150。或者,处理设备110可以在接收到用户关于上传匿名化医学数据集合的指令之后,再将匿名化医学数据集合发送至服务器150。在一些实施例中,处理器可以根据用户指令上传用户从一个或多个匿名化医学数据集合中选取的至少一部分上传到服务器。可选地,在上传每个医学数据集合之前,处理设备110需要确认该医学数据集合是否经过匿名化处理,若确定该医学数据集合确定经过匿名化处理,则 处理设备110可以将该医学数据集合上传至服务器;若确定该医学数据集合未经过匿名化处理,则处理设备110不上传该医学数据集合,还可以进一步通过终端设备130给用户发出提示信息,告知用户该医学数据集合未经过匿名化处理。
在一些实施例中,所述服务器可以是本地服务器,也可以是远程服务器。服务器接收到匿名化医学数据集合后,可以进行存档归类,还可以根据用户指令将匿名化医学数据集合发送给其他服务器或终端,完成数据共享。由于服务器接收到的是匿名化处理之后的医学数据集合,患者的隐私信息不容易从服务器端发生泄漏,因此隐私信息的安全性得到了很好的保护。
应当注意,关于流程500的以上描述仅是出于说明的目的而提供的,并且无意于限制本申请的范围。对于本领域的普通技术人员来说,可以根据本申请的描述,做出各种各样的变化和修改。然而,这些变化和修改不脱离本申请的范围。在一些实施例中,可以省略一个或多个操作和/或可以添加一个或多个附加操作。举例来说,处理设备110可以不用在对目标医学图像进行匿名化处理之前,对所有待选医学数据集合中的医学图像根据其对应的身体部位进行分组,而是可以在完成匿名化处理之后,对所有匿名化医学数据集合中的医学图像,根据特征标签中医学推向对应的身体部位,进行分组。步骤508中,处理设备110可以将各个分组的医学图像上传至服务器,便于归档。其他用户可以直接选择各个分组的医学图像进行观察,方便省事。
图6-8是根据本说明书一些实施例所示的批量匿名化处理的用户界面的示意图。在一些实施例中,处理设备110或匿名化处理模块430可以生成指令以控制用户界面上所展示给用户的内容。
在一些实施例中,终端设备130可以将对应于所述至少两个待选医学数据集合的信息列表整合在一起,并展示给用户。如图6所示,患者列表(Patient List)610(相当于前文中提到的信息列表)中显示了患者识别号(Patient ID)、患者姓名(Patient Name)、检查类型(Exam Type)和检查日期(Exam Date),便于用户查看。在一些实施例中,用户可以先选择需要执行匿名化处理的目标医学数据集合,再点击“一键匿名化”按钮620。终端设备130检测到“一键匿名化”按钮620被触发后,可以将执行匿名化的指令发送至处理设备110。处理设备110可以根据指令,自动对所述一个或多个目标医学数据集合进行批量式匿名化处理。在一些实施例中,当终端设备130检测到“一键匿名化”按钮620被触发后,可以显示在全部匿名功能和部分匿名功能中进行选择的选项。响应于所述部分匿名功能被选中,终端设备130可以显示从所述至少两个待选医学数据集合中进行选择的选项。例如,终端设备130可以在用户界面上为用户提供“全选”的选项,用户可以点击“全选”,以发出指令,将所有待选医学数据集合确定为目标医学数据集合。又例如,用户可以手动勾选一个或多个待选医学数据集合,以发出指令,将选中的待选医学数据集合确定为目标医学数据集合。
在一些实施例中,对于所述一个或多个目标医学数据集合进行匿名化处理后,处理设备110可以更新所述信息列表,更新后的所述信息列表包含所述一个或多个目标医学数据集合对应的一个或多个特征标签下的匿名化的隐私信息文本。处理设备110可以将更新后的所述信息列表发送给终端设备130进行展示。参见图6,患者列表630为匿名化处理完成后得到的示例性信息列表。可以看到,患者列表630中患者识别号、患者姓名和检查日期已经被做了替换处理,而不涉及隐私的检查类型的具体信息被 保留了下来。在一些实施例中,还可以根据匿名化后的患者识别号,找到对应于同一个患者的多条信息记录。
图7是匿名化处理的另一个示例性用户界面。和图6相比,图7中的界面还显示了匿名化处理之前的图像。例如,用户通过点击列表中的一行数据,就可以查看该数据对应的医学图像。类似地,终端设备130可以在检测到“一键匿名化”按钮620被触发后,对医学图像和患者列表中的信息一起进行匿名化处理。完成匿名化处理后,医学图像上显示的相关隐私信息被替换了。
图8是匿名化处理的另一个示例性用户界面。如图8所示,用户可以选择特征标签的具体文字描述、具体值或具体范围,从而选择需要匿名化处理的医学数据集合。例如,用户可以选择检查时间范围、检查类型和组织名称(相当于前文所述感兴趣的身体部位)。在一些实施例中,每当用户完成一项选择,终端设备130上展示的患者列表可以进行自动更新,显示出符合用户选择的记录。在完成所有选择后,用户可以点击“一键匿名化”按钮620。仅作为示例,处理设备110可以调出用户选定的目标医学数据集合中的医学图像,并对这些医学图像和图像标签进行匿名化处理。
在一些实施例中,用户还可以通过终端设备130选择一个特定的特征标签类型,再选择该特定的特征标签对应的一项或多项内容(文字或数值等)。例如,用户可以选择“医学图像对应的身体部位”作为感兴趣的特征标签,再选择“肝脏”,并进一步选择“信息列表、医学图像和图像标签”作为目标医学数据集合要包括的数据类型;又例如,用户可以选择“医学图像的类型”和“医学图像对应的身体部位”作为感兴趣的特征标签,将“医学图像的类型”选择为“超声图像”,将“医学图像对应的身体部位”选择为“腹部”,并进一步选择“医学图像和图像标签”作为目标医学数据集合要包括的数据类型。
总体上说来,本说明书实施例可能带来的有益效果包括但不限于:(1)能够根据用户指令,批量对医学数据集合进行匿名化处理,提高了匿名化处理的效率,也节约了用户的时间和精力;(2)在对医学数据集合完成匿名化处理之后再将其上传到服务器,可以提升患者隐私信息的安全性,防止患者隐私信息从服务器端被泄漏;(3)用户可以根据一个或多个特征标签(如医学图像对应的身体部位)来选择医学数据集合,便于快速选择需要匿名化处理的医学数据集合,也便于系统自动对匿名化处理过的医学数据集合进行后续存档管理和用户分组进行查看。需要说明的是,不同实施例可能产生的有益效果不同,在不同的实施例里,可能产生的有益效果可以是以上任意一种或几种的组合,也可以是其他任何可能获得的有益效果。
上文已对基本概念做了描述,显然,对于本领域技术人员来说,上述详细披露仅仅作为示例,而并不构成对本说明书的限定。虽然此处并没有明确说明,本领域技术人员可能会对本说明书进行各种修改、改进和修正。该类修改、改进和修正在本说明书中被建议,所以该类修改、改进、修正仍属于本说明书示范实施例的精神和范围。
同时,本说明书使用了特定词语来描述本说明书的实施例。如“一个实施例”、“一实施例”、和/或“一些实施例”意指与本说明书至少一个实施例相关的某一特征、结构或特点。因此,应强调并注意的是,本说明书中在不同位置两次或多次提及的“一实施例”或“一个实施例”或“一个替代性实施例”并不一定是指同一实施例。此外,本说明书的一个或多个实施例中的某些特征、结构或特点可以进行适当的组合。
此外,除非权利要求中明确说明,本说明书所述处理元素和序列的顺序、数字字母的使用、或其他名称的使用,并非用于限定本说明书流程和方法的顺序。尽管上述披露中通过各种示例讨论了一些目前认为有用的 发明实施例,但应当理解的是,该类细节仅起到说明的目的,附加的权利要求并不仅限于披露的实施例,相反,权利要求旨在覆盖所有符合本说明书实施例实质和范围的修正和等价组合。例如,虽然以上所描述的系统组件可以通过硬件设备实现,但是也可以只通过软件的解决方案得以实现,如在现有的服务器或移动设备上安装所描述的系统。
同理,应当注意的是,为了简化本说明书披露的表述,从而帮助对一个或多个发明实施例的理解,前文对本说明书实施例的描述中,有时会将多种特征归并至一个实施例、附图或对其的描述中。但是,这种披露方法并不意味着本说明书对象所需要的特征比权利要求中提及的特征多。实际上,实施例的特征要少于上述披露的单个实施例的全部特征。
一些实施例中使用了描述成分、属性数量的数字,应当理解的是,此类用于实施例描述的数字,在一些示例中使用了修饰词“大约”、“近似”或“大体上”来修饰。除非另外说明,“大约”、“近似”或“大体上”表明所述数字允许有±20%的变化。相应地,在一些实施例中,说明书和权利要求中使用的数值参数均为近似值,该近似值根据个别实施例所需特点可以发生改变。在一些实施例中,数值参数应考虑规定的有效数位并采用一般位数保留的方法。尽管本说明书一些实施例中用于确认其范围广度的数值域和参数为近似值,在具体实施例中,此类数值的设定在可行范围内尽可能精确。
针对本说明书引用的每个专利、专利申请、专利申请公开物和其他材料,如文章、书籍、说明书、出版物、文档等,特此将其全部内容并入本说明书作为参考。与本说明书内容不一致或产生冲突的申请历史文件除外,对本说明书权利要求最广范围有限制的文件(当前或之后附加于本说明书中的)也除外。需要说明的是,如果本说明书附属材料中的描述、定义、和/或术语的使用与本说明书所述内容有不一致或冲突的地方,以本说明书的描述、定义和/或术语的使用为准。
最后,应当理解的是,本说明书中所述实施例仅用以说明本说明书实施例的原则。其他的变形也可能属于本说明书的范围。因此,作为示例而非限制,本说明书实施例的替代配置可视为与本说明书的教导一致。相应地,本说明书的实施例不仅限于本说明书明确介绍和描述的实施例。

Claims (32)

  1. 一种匿名化处理方法,其特征在于,所述方法包括:
    获取至少一个待选医学数据集合,所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合包括所述对象的至少一个待选医学图像;
    根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合;以及
    对于所述一个或多个目标医学数据集合进行批量式匿名化处理,以得到一个或多个匿名化医学数据集合。
  2. 如权利要求1所述的方法,其特征在于,所述根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合包括:
    基于所述指令,从所述至少一个待选医学数据集合中选定一个或多个待选医学图像作为一组目标医学图像;以及
    将所述一组目标医学图像对应的一个或多个待选医学数据集合指定为所述一个或多个目标医学数据集合。
  3. 如权利要求2所述的方法,其特征在于,所述指令包括感兴趣的身体部位的信息,所述根据所述指令,基于所述至少一个待选医学数据集合,确定一组目标医学图像包括:
    基于所述指令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位所对应的医学图像;以及
    将所述与所述感兴趣的身体部位所对应的医学图像指定为所述一组目标医学图像。
  4. 如权利要求3所述的方法,其特征在于,所述根据所述指令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位对应的医学图像,包括:
    基于所述指令,对所述至少一个待选医学数据集合中的一个或多个待选医学图像进行识别,以确定与所述感兴趣的身体部位对应的医学图像。
  5. 如权利要求3所述的方法,其特征在于,所述方法还包括:
    基于所述至少一个待选医学数据集合中的一个或多个待选医学图像对应的身体部位,对所述一个或多个待选医学图像进行分组。
  6. 如权利要求1所述的方法,其特征在于:
    所述至少一个待选医学数据集合中的每个待选医学数据集合包括一个或多个特征标签,
    所述指令包括所述一个或多个特征标签中的至少一个感兴趣的特征标签的信息;
    所述基于接收的指令,从所述至少一个待选医学数据集合中选定一个或多个目标医学数据集合包括:
    基于所述指令,从所述至少一个待选医学数据集合中,确定所述至少一个感兴趣的特征标签下的医学数据的子集合;以及
    将所述至少一个感兴趣的特征标签下的医学数据的子集合指定为所述一个或多个目标医学数据集合。
  7. 如权利要求6所述的方法,其特征在于,所述一个或多个特征标签选自以下组合:医学图像的类型、医学图像对应的身体部位、对象识别号、 检查时间、检查类型、检查参数、对象姓名、对象性别、对象年龄、对象体重、对象是否怀孕和对象是否患有特定疾病。
  8. 如权利要求1所述的方法,其特征在于,所述对于所述一个或多个目标医学数据集合进行匿名化处理包括:
    使用匿名化算法,清除、隐藏或替换所述一个或多个目标医学数据集合对应的一个或多个特征标签下的隐私信息文本。
  9. 如权利要求1所述的方法,其特征在于,所述对于所述一个或多个目标医学数据集合进行匿名化处理包括:
    对于所述一个或多个目标医学数据集合中的一个或多个医学图像中的每个医学图像,
    使用匿名化算法,清除、隐藏或替换所述医学图像上显示的隐私信息文本。
  10. 如权利要求1所述的方法,其特征在于,所述方法还包括:
    使对应于所述至少一个待选医学数据集合的信息列表通过终端进行展示;
    使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项;以及
    获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令。
  11. 如权利要求10所述的方法,其特征在于,所述方法还包括:
    对于所述一个或多个目标医学数据集合进行所述匿名化处理后,更新所述信息列表,更新后的所述信息列表包含所述一个或多个目标医学数据集合对应的一个或多个特征标签下的匿名化的隐私信息文本;以及
    将更新后的所述信息列表通过终端进行展示。
  12. 如权利要求10所述的方法,其特征在于,所述使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项包括:
    使所述终端显示从所述至少一个待选医学数据集合对应的一个或多个特征标签中进行选择的选项。
  13. 如权利要求1所述的方法,其特征在于,所述对于所述一个或多个目标医学数据集合进行匿名化处理包括:
    响应于终端显示的一键匿名按钮被触发,自动对于所述一个或多个目标医学数据集合进行批量式匿名化处理。
  14. 如权利要求1所述的方法,其特征在于,所述基于接收的指令,从所述至少一个待选医学数据集合中选定一个或多个目标医学数据集合包括:
    响应于终端显示的一键匿名按钮被触发,使所述终端显示在全部匿名功能和部分匿名功能中进行选择的选项;
    响应于所述部分匿名功能被选中,使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项;
    获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令;
    基于所述指令,从所述至少一个待选医学数据集合中选定一个或多个目标医学数据集合。
  15. 如权利要求1所述的方法,其特征在于,还包括:
    将所述一个或多个匿名化医学数据集合发送至服务器。
  16. 一种用于匿名化处理的系统,其特征在于,所述系统包括:
    至少一个存储介质,其存储有至少一组指令;以及
    至少一个处理器,被配置为与所述至少一个存储介质通信,其中,当执行所述至少一组指令时,所述至少一个处理器被指示为使所述系统:
    获取至少一个待选医学数据集合,所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合中包括所述对象的至少一个待选医学图像;
    根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合;以及
    对于所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
  17. 如权利要求16所述的系统,其特征在于,为了根据所述接收的指令,基于所述至少一个待选医学数据集合,确定所述一个或多个目标医学数据集合,所述至少一个处理器被指示为使所述系统:
    基于所述指令,从所述至少一个待选医学数据集合中选定一个或多个医学图像作为一组目标医学图像;以及
    将所述一组目标医学图像对应的一个或多个待选医学数据集合指定为所述一个或多个目标医学数据集合。
  18. 如权利要求17所述的系统,其特征在于,所述指令包括感兴趣的身体部位的信息,为了根据所述指令,基于所述至少一个待选医学数据集合,确定所述一组目标医学图像,所述至少一个处理器被指示为使所述系统:
    基于所述指令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位所对应的医学图像;以及
    将所述与所述感兴趣的身体部位所对应的医学图像指定为所述一组目标医学图像。
  19. 如权利要求18所述的系统,其特征在于,为了根据所述指令,从所述至少一个待选医学数据集合中,确定与所述感兴趣的身体部位对应的医学图像,所述至少一个处理器被指示为使所述系统:
    基于所述指令,对所述至少一个待选医学数据集合中的一个或多个待选医学图像进行识别,以确定与所述感兴趣的身体部位对应的医学图像。
  20. 如权利要求18所述的系统,其特征在于,所述至少一个处理器还被指示为使所述系统:
    基于所述至少一个待选医学数据集合中的一个或多个待选医学图像对应的身体部位,对所述一个或多个待选医学图像进行分组。
  21. 如权利要求16所述的系统,其特征在于:
    所述至少一个待选医学数据集合中的每个待选医学数据集合包括一个或多个特征标签,
    所述指令包括所述一个或多个特征标签中的至少一个感兴趣的特征标签的信息;
    为了基于接收的指令,从所述至少一个待选医学数据集合中选定所述一个或多个目标医学数据集合,所述至少一个处理器被指示为使所述系统:
    基于所述指令,从所述至少一个待选医学数据集合中,确定所述至少一个感兴趣的特征标签下的医学数据的子集合;以及
    将所述至少一个感兴趣的特征标签下的医学数据的子集合指定为所述一个或多个目标医学数据集合。
  22. 如权利要求21所述的系统,其特征在于,所述一个或多个特征标签选自以下组合:医学图像的类型、医学图像对应的身体部位、对象识别号、检查时间、检查类型、检查参数、对象姓名、对象性别、对象年龄、对象体重、对象是否怀孕和对象是否患有特定疾病。
  23. 如权利要求16所述的系统,其特征在于,为了对于所述一个或多个目标医学数据集合进行匿名化处理,所述至少一个处理器被指示为使所述系统:
    使用匿名化算法,清除、隐藏或替换所述一个或多个目标医学数据集合对应的一个或多个特征标签下的隐私信息文本。
  24. 如权利要求16所述的系统,其特征在于,为了对于所述一个或多个目标医学数据集合进行匿名化处理,所述至少一个处理器被指示为使所述系统:
    对于所述一个或多个目标医学数据集合中的一个或多个医学图像中的每个医学图像,
    使用匿名化算法,清除、隐藏或替换所述医学图像上显示的隐私信息文本。
  25. 如权利要求16所述的系统,其特征在于,所述至少一个处理器还被指示为使所述系统:
    使对应于所述至少一个待选医学数据集合的信息列表通过终端进行展示;
    使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项;以及
    获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令。
  26. 如权利要求25所述的系统,其特征在于,所述至少一个处理器还被指示为使所述系统:
    对于所述一个或多个目标医学数据集合进行所述匿名化处理后,更新所述信息列表,更新后的所述信息列表包含所述一个或多个目标医学数据集合对应的一个或多个特征标签下的匿名化的隐私信息文本;以及
    将更新后的所述信息列表通过终端进行展示。
  27. 如权利要求25所述的系统,其特征在于,为了使所述终端显示从所述至少一个待选医学数据集合中进行选择,所述至少一个处理器被指示为使所述系统:
    使所述终端显示从所述至少一个待选医学数据集合对应的一个或多个特征标签中进行选择的选项。
  28. 如权利要求16所述的系统,其特征在于,为了对于所述一个或多个目标医学数据集合进行匿名化处理,所述至少一个处理器被指示为使所述系统:
    响应于终端显示的一键匿名按钮被触发,自动对于所述一个或多个目标医学数据集合进行批量式匿名化处理。
  29. 如权利要求16所述的系统,其特征在于,为了基于接收的指令,从所述至少一个待选医学数据集合中选定一个或多个目标医学数据集合,所述至少一个处理器被指示为使所述系统:
    响应于终端显示的一键匿名按钮被触发,使所述终端显示在全部匿名功能和部分匿名功能中进行选择的选项;
    响应于所述部分匿名功能被选中,使所述终端显示从所述至少一个待选医学数据集合中进行选择的选项;
    获取从所述终端输入的关于选定所述一个或多个目标医学数据集合的所述指令。
  30. 如权利要求29所述的系统,其特征在于,所述至少一个处理器还被指示为使所述系统:
    将所述一个或多个匿名化医学数据集合发送至服务器。
  31. 一种用于匿名化处理的系统,其特征在于,所述系统包括:
    获取模块,所述获取模块用于获取至少一个待选医学数据集合,所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合中包括所述对象的至少一个待选医学图像;
    选择模块,所述选择模块用于根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合;以及
    匿名化处理模块,所述匿名化处理模块用于对所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
  32. 一种非暂时性计算机可读存储介质,包括至少一组指令,其中,当由计算机设备的至少一个处理器执行时,所述至少一组指令指示所述至少一个处理器:
    获取至少一个待选医学数据集合,所述至少一个待选医学数据集合中的每个待选医学数据集合对应于一个对象,所述每个待选医学数据集合中包括所述对象的至少一个待选医学图像;
    根据接收的指令,基于所述至少一个待选医学数据集合,确定一个或多个目标医学数据集合;以及
    对于所述一个或多个目标医学数据集合进行匿名化处理,以得到一个或多个匿名化医学数据集合。
PCT/CN2021/126194 2021-10-25 2021-10-25 匿名化处理方法和系统 WO2023070284A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2021/126194 WO2023070284A1 (zh) 2021-10-25 2021-10-25 匿名化处理方法和系统
CN202180009630.3A CN115004314A (zh) 2021-10-25 2021-10-25 匿名化处理方法和系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/126194 WO2023070284A1 (zh) 2021-10-25 2021-10-25 匿名化处理方法和系统

Publications (1)

Publication Number Publication Date
WO2023070284A1 true WO2023070284A1 (zh) 2023-05-04

Family

ID=83017987

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/126194 WO2023070284A1 (zh) 2021-10-25 2021-10-25 匿名化处理方法和系统

Country Status (2)

Country Link
CN (1) CN115004314A (zh)
WO (1) WO2023070284A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017003494A1 (en) * 2015-06-29 2017-01-05 Bender Gregory T Method for communicating sensitive incident information and locations to receivers
CN106682429A (zh) * 2016-12-30 2017-05-17 上海联影医疗科技有限公司 医学数据处理方法及医学数据管理系统
CN108122605A (zh) * 2016-11-29 2018-06-05 锐珂(上海)医疗器材有限公司 医学图像选择方法及设备
CN108352196A (zh) * 2015-10-30 2018-07-31 皇家飞利浦有限公司 没有明显的准标识符的去标识的健康护理数据库的医院匹配
CN109716345A (zh) * 2016-04-29 2019-05-03 普威达有限公司 计算机实现的隐私工程系统和方法
CN110060312A (zh) * 2017-12-14 2019-07-26 西门子保健有限责任公司 用于匿名化的三维医学图像工作流程的可记忆图像生成的方法
US20200226282A1 (en) * 2018-12-19 2020-07-16 Canon Medical Systems Corporation Medical information anonymizing system and anonymizing method setting device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017003494A1 (en) * 2015-06-29 2017-01-05 Bender Gregory T Method for communicating sensitive incident information and locations to receivers
CN108352196A (zh) * 2015-10-30 2018-07-31 皇家飞利浦有限公司 没有明显的准标识符的去标识的健康护理数据库的医院匹配
CN109716345A (zh) * 2016-04-29 2019-05-03 普威达有限公司 计算机实现的隐私工程系统和方法
CN108122605A (zh) * 2016-11-29 2018-06-05 锐珂(上海)医疗器材有限公司 医学图像选择方法及设备
CN106682429A (zh) * 2016-12-30 2017-05-17 上海联影医疗科技有限公司 医学数据处理方法及医学数据管理系统
CN110060312A (zh) * 2017-12-14 2019-07-26 西门子保健有限责任公司 用于匿名化的三维医学图像工作流程的可记忆图像生成的方法
US20200226282A1 (en) * 2018-12-19 2020-07-16 Canon Medical Systems Corporation Medical information anonymizing system and anonymizing method setting device

Also Published As

Publication number Publication date
CN115004314A (zh) 2022-09-02

Similar Documents

Publication Publication Date Title
JP6850291B2 (ja) 顔認識アプリケーションにおけるフォールスポジティブの最小化のための方法および装置
US10515721B2 (en) Automated cloud image processing and routing
JP5843414B2 (ja) 医療記録ソフトウエアと高度画像処理の統合
US20160267222A1 (en) Medical imaging reference retrieval and report generation
US20190156937A1 (en) Priority alerts based on medical information
US10977796B2 (en) Platform for evaluating medical information and method for using the same
WO2013040693A1 (en) Computer system and method for atlas-based consensual and consistent contouring of medical images
US20210303935A1 (en) Medical image processing method and system and data processing method
US9202007B2 (en) Method, apparatus and computer program product for providing documentation and/or annotation capabilities for volumetric data
US20170300282A1 (en) Mobile device, system and method for medical image displaying using multiple mobile devices
US20240029865A1 (en) Imaging discovery utility for augmenting clinical image management
US20160267221A1 (en) Medical imaging reference retrieval
US20170132320A1 (en) System and Methods for Transmitting Health level 7 Data from One or More Sending Applications to a Dictation System
WO2023070284A1 (zh) 匿名化处理方法和系统
JP2004344314A (ja) 医療情報管理システム及び医療情報管理方法
US20130195331A1 (en) Apparatus for sharing and managing information in picture archiving communication system and method thereof
US20160217254A1 (en) Image insertion into an electronic health record
CA2906297C (en) Medical research retrieval engine
JP5930711B2 (ja) 医用画像表示装置、医用画像表示方法及びプログラム
US11495343B2 (en) Device, system, and method for determining a reading environment by synthesizing downstream needs
US20240087740A1 (en) Augmenting files such as dicom objects containing medical imaging information with additional medical information about the subject of the medical imaging information
US20200051676A1 (en) Device, system, and method for optimizing usage of prior studies
TWI801761B (zh) 醫學影像處理系統及其方法
WO2019095550A1 (zh) 区域医疗电子病历共享系统及方法
US11881298B2 (en) Systems and methods for universal artificial intelligence integration services

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21961668

Country of ref document: EP

Kind code of ref document: A1