[go: up one dir, main page]

WO2019058963A1 - Dispositif de traitement d'image médicale, procédé de traitement d'image médicale, et programme de traitement correspondant - Google Patents

Dispositif de traitement d'image médicale, procédé de traitement d'image médicale, et programme de traitement correspondant Download PDF

Info

Publication number
WO2019058963A1
WO2019058963A1 PCT/JP2018/032828 JP2018032828W WO2019058963A1 WO 2019058963 A1 WO2019058963 A1 WO 2019058963A1 JP 2018032828 W JP2018032828 W JP 2018032828W WO 2019058963 A1 WO2019058963 A1 WO 2019058963A1
Authority
WO
WIPO (PCT)
Prior art keywords
analysis
processing
protocol
image
medical image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2018/032828
Other languages
English (en)
Japanese (ja)
Inventor
拡樹 谷口
将之 金井
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
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 Hitachi Ltd filed Critical Hitachi Ltd
Publication of WO2019058963A1 publication Critical patent/WO2019058963A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
    • A61B6/03—Computed tomography [CT]

Definitions

  • the present invention relates to a medical image processing apparatus and processing method using a medical image obtained from a medical image diagnostic apparatus including an X-ray CT apparatus, an MRI apparatus, and an ultrasonic apparatus, and in particular to improve the work efficiency of medical image diagnosis. It relates to technology.
  • GUI graphical user interface
  • Patent Document 1 shows a program that executes a plurality of processes included in imaging or a plurality of processes included in post-processing on data collected by the imaging, and each process receives an input operation by an operator.
  • a storage unit that is classified into one process and a second process that does not receive the input operation, and stores a program associated with the imaging or the order performed in the post-processing, and starts the imaging or the post-processing
  • the program starts execution of the program
  • an execution control unit that controls the respective processes to be executed according to the order, and the program executes the first process
  • a medical image diagnostic apparatus is disclosed that displays information selected according to the purpose of the imaging or the post-processing as an operation screen for receiving an input operation on a display unit. Ru.
  • Patent Document 1 based on the definition of each process executed in each imaging, a plurality of types of imaging are ordered and executed on the subject. At that time, when each process executed in each imaging involves the input operation of the operator, the display timing of the further defined operation screen is received and each process is executed.
  • the order of imaging is defined by an imaging protocol that describes a plurality of imaging conditions necessary to execute each imaging, and the operator performs imaging according to a medical image diagnostic examination (hereinafter referred to as an examination). Desired imaging can be performed by selecting a protocol.
  • each process executed in each imaging is defined only in a special medical diagnostic imaging examination in which the operation step of each process is clear.
  • an object of the present invention is to provide a medical image processing apparatus, a medical image processing method, and a processing program used for the same, which can further improve the work efficiency of image processing.
  • the present invention is a medical image processing apparatus for processing a medical image obtained from a medical image diagnostic apparatus, as an example, in view of the above background art, and an image acquisition for acquiring a medical image from a medical image diagnostic apparatus Unit, an image processing unit that performs predetermined image processing on the acquired medical image, and an input unit of the operator, and based on the indication of the operator by the input unit on the medical image subjected to the image processing by the image processing unit
  • the image processing unit is configured to perform the image processing again.
  • a medical image processing apparatus it is possible to provide a medical image processing apparatus, a medical image processing method, and a processing program used for the same, which can further improve the working efficiency of image processing by performing image processing again based on the indication of the operator.
  • FIG. 6 is a diagram showing a hardware configuration of a medical image processing apparatus in Embodiment 2.
  • FIG. 14 is a diagram showing the flow of operations of a conventional medical diagnostic imaging examination in Embodiment 2.
  • FIG. 8 is a diagram showing the flow of operations of medical diagnostic imaging in the second embodiment.
  • FIG. 18 is a diagram showing inspection workflow protocol registration in the second embodiment.
  • FIG. 16 is a diagram showing a first form of a test workflow protocol configuration in Example 2;
  • FIG. 18 is a diagram showing a second form of the inspection workflow protocol configuration in the second embodiment.
  • FIG. 17 is a diagram showing inspection workflow protocol execution control in the second embodiment.
  • FIG. 16 is a diagram showing an inspection workflow protocol execution flowchart in the second embodiment.
  • FIG. 7 is a diagram showing an analysis protocol configuration in Example 2;
  • FIG. 7 is a diagram showing an analysis protocol configuration in Example 2;
  • FIG. 18 is a diagram showing an analysis protocol execution form in Example 2.
  • FIG. 16 is a diagram showing an analysis protocol execution control flowchart in the second embodiment.
  • FIG. 18 is a diagram showing a first analysis processing result image correction method in the second embodiment.
  • FIG. 16 is a flowchart of a first analysis processing result image correction method in the second embodiment.
  • FIG. 7 is a diagram showing an input operation in a second embodiment.
  • FIG. 18 is a diagram showing a second analysis processing result image correction method in the second embodiment.
  • FIG. 18 is a diagram showing analysis processing flow history display in the second embodiment.
  • FIG. 14 is a diagram showing an analysis processing correction method for multiple indications from the user in the second embodiment.
  • FIG. 18 is a functional configuration diagram of CAD processing in a third embodiment.
  • FIG. 18 is a functional block diagram of feature quantity extraction and update processing in the third embodiment;
  • FIG. 18 is an overall flowchart of CAD processing in a third embodiment.
  • FIG. 18 is a flowchart of feature amount extraction and update processing in the third embodiment.
  • FIG. 18 is a schematic diagram of feature amount extraction and update processing in the third embodiment.
  • FIG. 1 is a conceptual configuration diagram of a medical image processing apparatus in Embodiment 1.
  • FIG. 23 is a conceptual block diagram of the medical image processing apparatus in the present embodiment.
  • the medical image processing apparatus is a medical image processing apparatus for processing a medical image obtained from a medical image diagnostic apparatus, and an image acquisition unit 90 for acquiring a medical image from the medical image diagnostic apparatus;
  • the image processing unit 91 performs predetermined image processing on an image, and the operator input unit 92 receives an input operation of the operator. Then, the image processing unit 91 performs the image processing again on the medical image subjected to the image processing by the image processing unit 91 based on the indication of the operator by the operator input unit 92.
  • the final step of the examination workflow is focused on the transfer of medical images to a storage device or a medical image database (hereinafter, data transfer).
  • data transfer some analysis processing based on the imaging protocol is executed, and finally, when considering an inspection workflow that transfers some analysis processing result image, if analysis processing with complicated operation steps is black box, imaging Protocols and data transfers are uniquely associated and defined.
  • any analysis processing condition based on the imaging protocol is defined as an analysis protocol
  • a transfer condition for data transfer is defined as a data transfer protocol
  • the imaging protocol and the analysis protocol can be related to each other by sharing the analysis purpose held in common.
  • the analysis protocol and the data transfer protocol can be related to each other in common by keeping the data transfer purpose held in common.
  • analysis processing is interlocked, and complicated operation steps are omitted and executed automatically.
  • the operation step of the analysis processing of the analysis protocol is traced back to redo the processing, and the analysis processing is executed again. Are repeated to finally obtain a desired analysis processing result image.
  • the final analysis processing result image before data transfer is presented first, and the operator points out the processing of the analysis processing result image while presenting the corrected portion and performs the desired analysis. Provide a way to move closer to the processing result image.
  • FIG. 1 is a diagram showing a hardware configuration of the medical image processing apparatus 1 in the present embodiment.
  • the medical image processing apparatus 1 includes a central processing unit (CPU) 2, a main memory 3, a storage device 4, a display memory 5, a display device 6, a controller 7 connected to a mouse 8, a keyboard 9, and a network adapter 10. 11, it is connected so that signal transmission / reception is possible, and is comprised.
  • the medical image processing apparatus 1 is connected to the medical imaging apparatus 13 and the medical image database 14 via the network 12 so as to be able to transmit and receive signals.
  • “capable of signal transmission / reception” indicates a state in which signals can be transmitted / received to each other or from one to the other regardless of electrical or optical wired or wireless.
  • the CPU 2 is a device that controls the operation of each component.
  • the CPU 2 loads a program stored in the storage device 4 and data necessary for program execution into the main memory 3 and executes it.
  • the storage device 4 is a device for storing medical image information captured by the medical imaging device 13, and more specifically, is a hard disk or the like.
  • the storage device 4 may be a device that exchanges data with a portable recording medium such as a flexible disk, an optical (magnetic) disk, a ZIP memory, or a USB memory.
  • Medical image information is acquired from the medical imaging device 13 or the medical image database 14 via the network 12 such as a LAN (Local Area Network).
  • the storage device 4 stores programs executed by the CPU 2 and data necessary for program execution.
  • the main memory 3 stores programs executed by the CPU 2 and the progress of arithmetic processing.
  • the display memory 5 temporarily stores display data to be displayed on a display device 6 such as a liquid crystal display or a CRT (Cathode Ray Tube).
  • the mouse 8 and the keyboard 9 are operation devices that the operator instructs the medical image processing apparatus 1 to operate.
  • the mouse 8 may be another pointing device such as a track pad or a track ball.
  • the controller 7 detects the state of the mouse 8, acquires the position of the mouse pointer on the display device 6, and outputs the acquired position information and the like to the CPU 2.
  • the network adapter 10 is for connecting the medical image processing apparatus 1 to a network 12 such as a LAN, a telephone line, and the Internet.
  • the medical imaging apparatus 13 is an apparatus for acquiring medical image information such as a tomographic image of a subject.
  • the medical imaging apparatus 13 is, for example, an MRI apparatus, an X-ray CT apparatus, an ultrasonic diagnostic apparatus, a scintillation camera apparatus, a PET apparatus, a SPECT apparatus, or the like.
  • the medical image database 14 is a database system that stores medical image information captured by the medical imaging device 13.
  • a medical image is created, and the created medical image is displayed on the display device 6.
  • the term "medical image” as used herein refers to an examination image to be described later and an analysis processing result image. That is, the image processing described in the present embodiment is specifically software processing which is realized by the CPU executing a processing program.
  • FIG. 2 is a diagram showing the flow of operation of medical image diagnostic examination in the conventional method.
  • a plurality of types of imaging are ordered and executed on the subject.
  • the display timing of the further defined operation screen is received and each process is executed.
  • the inspection workflow is an analysis performed after imaging processing and imaging processing It can be divided into processing and data transfer processing.
  • An imaging protocol that describes in advance a plurality of imaging conditions necessary to execute each imaging, an analysis processing flow for performing analysis processing with an inspection image captured according to the imaging conditions as an input, and an analysis protocol that describes setting values, imaging conditions A data transfer protocol that describes the data transfer conditions of the inspection image captured by the camera, and an aggregation of them is defined as an inspection workflow protocol, and the inspection workflow protocol and the operation screen for accepting input operations in the inspection workflow are displayed There is an operation screen display timing.
  • an operation screen for receiving an input operation is displayed at the operation screen display timing between inspection workflows, a parameter for executing the next process is set, and the next process is reflected. If the condition for not accepting the input operation is set, the processing is automatically executed until the next input operation is accepted. According to this, in the example of FIG. 2, the operation screen is displayed at three timings (analysis process 1, analysis process 4, and data transfer process) of displaying the operation screen, and the operator is prompted to confirm.
  • FIG. 3 is a diagram showing the flow of operation of medical image diagnostic examination in the present embodiment.
  • a plurality of types of imaging processes are sequentially ordered and executed on the subject, and analysis processing according to the analysis protocol is automatically executed at the completion timing of creation of the inspection image.
  • the analysis processing result image is displayed at the timing of creating the analysis processing result image of the analysis processing executed last, the operator confirms it, and if there is no problem in the analysis processing result image, the data transfer processing is executed.
  • the analysis processing is repeated until the analysis processing having the problem, the analysis processing is automatically executed from that point, and the analysis processing result image is presented to the operator again. By repeating the inspection flow, it is a method of approaching the analysis processing result image desired by the operator.
  • an operation screen for receiving an input operation is displayed in the middle of processing, and while the parameters are adjusted, the final analysis processing result image is reached.
  • correction is necessary when an image desired by the operator is not finally obtained, it is not possible to define in advance which analysis processing should be traced back, and it is necessary to execute according to the inspection workflow protocol. Absent.
  • the operator repeats the processing while repeating the process while intuitively grasping the problem from the analysis processing result image presented first, and the final adjustment processing result image is created. That is, since there is no useless confirmation work to correct the problem by pinpointing, it can reach an optimal analysis processing result image by the shortest route.
  • FIG. 4 is a diagram showing inspection workflow protocol registration in the present embodiment.
  • the inspection workflow protocol includes an imaging protocol, an analysis protocol, and a data transfer protocol.
  • the imaging protocol that describes a plurality of imaging conditions necessary to execute each imaging is stored in the imaging protocol storage unit 101, and the data transfer protocol that describes the data transfer conditions of the inspection image captured according to the imaging conditions is data
  • An analysis processing flow which is stored in the transfer protocol storage unit 103 and which performs analysis processing with the inspection image captured under the imaging condition as an input is described in the analysis protocol storage unit 102.
  • the imaging protocol and the data transfer protocol are uniquely associated.
  • the imaging protocol when performing analysis processing of an inspection image captured under a certain imaging condition and transferring the analysis result image, the imaging protocol includes FOV: Field Of View, reconstruction filter, contrast agent Analysis processing depending on existence, etc., analysis processing depending on the number of imaging times (single study / multiple studies, single series / multiple series), analysis process from examination (site, disease, type of examination etc.), etc. . It consists of combination patterns of these analysis processes, and defines an analysis purpose that specifies what kind of post-processing is expected to be taken.
  • the inspection image and analysis processing result image are backed up to the data server (data backup of various environments from small to large scale), analysis processing results are continuously received in response to analysis processing results
  • a medical image management system PES: Picture Archiving and Communication System
  • This transfer destination combination pattern is defined as the data transfer purpose.
  • Analysis protocol also defines analysis purpose and data transfer purpose.
  • the combination of the imaging protocol and the data transfer protocol is, so to speak, a combination of an analysis purpose and a data transfer purpose, and an analysis protocol matching the combination can be adapted to the imaging protocol and the data transfer protocol. If it is an analysis protocol that matches the analysis purpose to be input and the data transfer purpose to be output, an inspection workflow protocol that associates a series of processes from imaging to analysis and further analysis to data transfer without knowing the configuration of the analysis protocol And stored in the inspection workflow protocol storage unit 105. In the purpose determination unit 104, whether or not the analysis purpose of the imaging protocol and the analysis purpose of the analysis protocol match, and whether the data transfer purpose of the analysis protocol and the data transfer purpose of the data transfer protocol match. It can be determined.
  • analysis protocol in which the analysis purpose and the data transfer purpose coincide with each other can be presented to the operator and the analysis protocol can be selected or edited, the operation will not be complicated.
  • analysis processing can be interlocked, and complicated operation steps can be omitted and executed automatically.
  • FIG. 5 is a diagram showing a first form of the inspection workflow protocol configuration in the present embodiment.
  • the inspection workflow protocol includes an imaging protocol 201, an analysis protocol 202, and a data transfer protocol 203.
  • a certain imaging protocol A and data transfer protocol A are uniquely associated.
  • (a) the case where the analysis protocol is one is shown, the photographing process by the photographing protocol A is executed, the inspection image is inputted, and the analysis process by the analysis protocol a-1 is executed, and finally the analysis result image
  • the data transfer process by the data transfer protocol A is sequentially executed with the (B) shows a case where a plurality of analysis protocols are connected in parallel, and the imaging process is performed by the imaging protocol A, and the inspection image is used as an input, and the analysis process and the analysis protocol by the analysis protocol a-1
  • the analysis process according to a-2 is executed, and finally the data transfer process according to the data transfer protocol A is sequentially executed with the analysis process result image of each analysis process as an input.
  • (c) a case where a plurality of analysis protocols are connected in series is shown, and the imaging process by the imaging protocol A is executed, and the inspection image is input to execute the analysis process by the analysis protocol a-1.
  • the analysis processing result image according to the analysis protocol a-1 is subjected to the analysis processing according to the analysis protocol a-2.
  • the analysis processing result image according to the analysis protocol a-2 is input to the data according to the data transfer protocol A. The transfer process is sequentially performed.
  • FIG. 6 is a diagram showing a second form of the inspection workflow protocol configuration in the present embodiment.
  • the configuration of the inspection workflow protocol is the same as that shown in FIG.
  • Certain imaging protocol A and data transfer protocol A (A-1, A-2) are uniquely associated.
  • A-1, A-2 the case where the analysis protocol is one is shown, the photographing process by the photographing protocol A is executed, and the inspection image is inputted, the analysis process by the analysis protocol a-1 is executed, and finally the analysis process result With an image as input, data transfer processing by data transfer protocol A-1 and data transfer processing by data transfer protocol A-2 are sequentially executed.
  • (B) shows a case where a plurality of analysis protocols are connected in parallel, and the imaging process is performed by the imaging protocol A, and the inspection image is used as an input, and the analysis process and the analysis protocol by the analysis protocol a-1 The analysis process of a-2 is executed, and finally the analysis result image of each analysis process is input, and the data transfer process of data transfer protocol A-1 and data transfer protocol A-2 is sequentially executed.
  • (c) a case where a plurality of analysis protocols are connected in series is shown, and the imaging process by the imaging protocol A is executed, and the inspection image is input to execute the analysis process by the analysis protocol a-1.
  • the analysis processing result image by the analysis protocol a-1 is subjected to the analysis processing by the analysis protocol a-2, and finally the analysis processing result image of each analysis processing is input, the data transfer protocol A-1, the data transfer Data transfer processing according to protocol A-2 is sequentially performed.
  • FIG. 7 is a diagram showing inspection workflow protocol execution control in the present embodiment. Further, FIG. 8 is a diagram showing an inspection workflow protocol execution control flowchart in the present embodiment. Hereinafter, the implementation method will be described with reference to FIGS. 7 and 8.
  • the inspection workflow protocol is acquired from the inspection workflow protocol storage unit 105.
  • the inspection workflow protocol execution control unit 301 controls the execution order of imaging, analysis, and data transfer.
  • the inspection workflow protocol execution control unit 301 transmits the imaging protocol of the inspection workflow protocol to the imaging protocol execution control unit 302, and urges the execution of the imaging protocol.
  • the imaging protocol execution control unit 302 sequentially executes the imaging process according to the imaging protocol, and transmits the generated inspection image creation completion timing to the inspection workflow protocol execution control unit 301.
  • Step S104 Upon receiving the inspection image creation completion timing, the inspection workflow protocol execution control unit 301 transmits the analysis protocol of the inspection workflow protocol to the analysis protocol execution control unit 303, and urges the execution of the analysis protocol.
  • the analysis protocol execution control unit 303 acquires an inspection image.
  • Steps S105, S106, and S107 The analysis protocol execution control unit 303 automatically executes the analysis processing sequentially according to the analysis protocol, and displays the generation completion timing of the analysis processing result image generated at the end as the analysis processing result image It transmits to the part 305. As shown in FIGS. 5 and 6, in the case of a plurality of analysis protocols, the analysis process is performed a plurality of times.
  • Step S108 In response to the generation completion timing of the analysis processing result image, the analysis processing result image display unit 305 displays the analysis processing result image, and if the operator confirms that the analysis processing result image is a desired image, The inspection end timing is transmitted to the analysis protocol execution control unit 303.
  • the analysis protocol execution control unit 303 transmits the inspection end timing to the inspection workflow protocol execution control unit 301.
  • Step S109, Step S110, Step S111 In response to the inspection end timing, the inspection workflow protocol execution control unit 301 transmits the inspection end timing to the data transfer protocol execution control unit 304, thereby data according to the data transfer protocol. Execute transfer processing. As shown in FIGS.
  • Step S112 data transfer processing is executed on an analysis processing result image obtained from analysis processing of each analysis protocol.
  • the imaging process defined in the imaging protocol is repeatedly executed, and all analysis result images desired by the operator are transferred.
  • FIG. 9 is a diagram showing an analysis protocol configuration in the present embodiment.
  • FIG. 10 is a diagram showing an analysis protocol execution form in the present embodiment.
  • the analysis protocol can be executed by the analysis protocol execution control unit 303 using the analysis parameter set 404 consisting of a combination of a plurality of analysis parameters 405 and sequencing the analysis processing engine 403 by combining analysis processing in series 505 or parallel 506. Defined so that the analysis function 402 can be combined in series 503 or parallel 504 and executed in order using a plurality of analysis processing engines 403, and the analysis application 401 is serially connected 501 using a plurality of analysis functions 402.
  • the analysis parameter set can combine a plurality of analysis parameters ⁇ 1, 2,..., M ⁇ , and other analysis parameter sets and analysis parameters may overlap.
  • the analysis processing engine can combine a plurality of analysis parameter sets ⁇ 1, 2,..., N ⁇ , and other analysis processing engines and analysis parameter sets may overlap.
  • the analysis function can combine a plurality of analysis processing engines ⁇ 1, 2, ..., k ⁇ , and other analysis functions and analysis processing engines may overlap.
  • the analysis application can combine a plurality of analysis functions ⁇ 1, 2,..., J ⁇ , and other analysis applications and analysis functions may overlap.
  • the analysis protocol can combine a plurality of analysis applications ⁇ 1, 2,..., I ⁇ , and other analysis protocols and analysis applications may overlap.
  • FIG. 11 is a diagram showing an analysis protocol execution control flowchart in the present embodiment.
  • the analysis protocol is configured such that analysis applications, analysis functions, and analysis processing engines are combined in series or in parallel and executed in order. Further, the analysis processing engine is set to be able to input an analysis parameter set (a plurality of analysis parameters). Furthermore, the inspection image obtained in the imaging process of the imaging protocol is set to be able to be input to the first application, and the analysis process result image of the analysis processing engine of the analysis protocol that is the input of the data transfer process of the data transfer protocol can be output It is set to.
  • an analysis parameter set a plurality of analysis parameters
  • steps S101 to S112 are the same as in FIG. 8, and the detailed processing in the circle 1 of step S106 is the processing of steps S201 to S207 on the right side of the figure.
  • steps S201 to S207 will be described.
  • Step S201 The analysis protocol execution control unit acquires an analysis protocol from the inspection workflow protocol storage unit, and activates an analysis application configured in order of the analysis protocol. At the time of analysis processing execution by the analysis protocol, first, the analysis application at the top of the analysis protocol is activated, and an inspection image obtained by the photographing processing of the photographing protocol is input. (Step S202) The analysis function is called. (Step S203) The analysis processing engine is called, and an inspection image and an analysis parameter set (analysis parameter) are input. (Step S204) The analysis processing engine is executed. (Step S205) If one step of the analysis protocol is composed of a plurality of analysis processing engines, each analysis processing engine is called and S203 to S205 are repeated.
  • Step S206 If one step of the analysis protocol is composed of a plurality of analysis functions, each analysis function is called and S202 to S206 are repeated.
  • Step S207 If one step of the analysis protocol is composed of a plurality of analysis applications, each analysis application is activated and S201 to S207 are repeated. The analysis application configured in order of the analysis protocol is activated as needed, and an analysis processing result image required for data transfer processing is output.
  • FIG. 12 is a diagram showing a first analysis processing result image correction method in the present embodiment.
  • FIG. 13 is a flowchart of a first analysis processing result image correction method in the present embodiment. The implementation method will be described with reference to FIGS. 12 and 13.
  • steps S101 to S112 are the same as in FIG. 8, and the detailed process in the circle 2 in step S106 is the process in the circle 1 on the right side in the figure and the processes in steps S301 to S305.
  • the process in the circle 1 is the process of steps S201 to S207 which is the process on the right side of FIG.
  • steps S301 to S305 will be described.
  • Step S301 After automatically executing the analysis processing by the analysis protocol, the analysis processing flow history storage unit 601 stores the history of the processing flow of the analysis processing along the time axis executed by the analysis protocol execution control unit 303.
  • Step S302 The analysis processing result image of the analysis processing finally executed by the analysis protocol execution control unit 303 is displayed on the analysis processing result image display unit.
  • the analysis process executed last is the last analysis process viewed from the data transfer process, and there are a plurality of analysis processes depending on the data transfer protocol.
  • Step S303 If the analysis processing result image is an image desired by the operator, the analysis processing by the analysis protocol is ended.
  • Step S304 and S305 When the input operation reception unit receives an input operation of the operator, the analysis processing check unit 603 collates the input operation and the analysis protocol of the analysis processing flow acquired from the analysis processing flow history storage unit 601. , Identify the analysis process. When the analysis process is specified, S201 to S207 shown in FIG. 11 are repeated to repeat the process.
  • the analysis processing comparison unit 603 can determine which analysis application has created the analysis processing result image that the operator confirms in the analysis processing result image display unit 305. Further, when an input operation from the operator is received on the analysis processing result image, it is possible to specify which analysis processing result image obtained by which analysis processing engine of which analysis function. Further, if the operator inputs the change amount of the analysis parameter set of which analysis processing engine, the analysis protocol execution control unit 303 performs the analysis processing collated by the analysis processing collating unit 603 to the analysis processing to be finally executed. It can run automatically.
  • FIG. 14 is a diagram showing an input operation according to the present embodiment.
  • the inspection image 702 is acquired, and the inspection image is input, and the analysis processing by the analysis protocol is executed.
  • the analysis processing result image (703, 704, 705) is acquired. If it is displayed on the analysis processing result image display unit 305, the analysis processing result image can be corrected by operating the mouse on the analysis processing result images 703 to 705.
  • An analysis processing result image 703 shows an example 1 in which density conversion, three-dimensional rotation, scaling, and parallel movement are performed.
  • an example 2 of changing the part extraction region extracted by the image processing is shown.
  • an example 3 of setting the position of multi-section reconstruction before executing the MPR on the reference image is shown.
  • the process is repeated by going back to the analysis processing of the analysis protocol executed on the time axis, and the analysis processing result image is corrected. For example, in the case of the time axis, correction is added to the analysis processing result image of the analysis processing executed at a time close to the current time.
  • Example 2 is a modification of the analysis processing result image of the analysis processing executed at the oldest time, in terms of the time axis.
  • the analysis processing result image of the analysis processing performed in the middle of the time is corrected.
  • Examples 2 and 3 are modifications that also affect the subsequent analysis processing.
  • the analysis result of the region extraction region of Example 2 is commonly used in the analysis processing of the latter stage, and the setting of the position of multi-section reconstruction in Example 3 is limited to the analysis processing for performing MPR, Used in the analysis process of Also in Example 1, the density conversion, three-dimensional rotation, scaling, and parallel movement with respect to the reference image of Example 3 affect the analysis processing of the latter stage.
  • analysis processing can be executed automatically up to the last analysis processing, if analysis processing is performed retroactively to analysis processing collated based on the history information acquired from the analysis processing flow history storage unit 601, the analysis that is retroactive It is also possible to execute manually from the process.
  • FIG. 15 is a diagram showing a second analysis processing result image correction method in the present embodiment.
  • the analysis flow can be acquired from the analysis processing flow history storage unit 601 and displayed on the analysis processing flow history display unit 604.
  • FIG. 16 is shown as a display example using the analysis processing flow history display unit 604.
  • FIG. 16 is a diagram showing analysis workflow history display according to the present embodiment.
  • the analysis processing flow history display 802 is displayed on the analysis processing result image 801 of the last analysis processing, in which the time axis operation bar 803 which can operate the time axis of the analysis processing flow, the analysis processing collating unit 603
  • the analysis processing result images 804 to 806 created by executing the analysis processing at the traced point are displayed by repeating the retroactive processing up to the collated analysis processing.
  • the analysis processing result images 804 to 806 can be reference images in the case of manually executing from the analysis processing result traced back by operating the time axis operation bar 803 as described in FIG. Further, the analysis processing result images 804 to 806 reflect the latest analysis processing flow in which the analysis processing which has been traced back is performed because the analysis processing result image which has been traced back to the analysis processing which has been rechecked is re-created.
  • FIG. 17 is a diagram showing an analysis processing correction method for multiple indications from the user according to the present embodiment.
  • the analysis processing result image (904, 905) for the user's indication portion (902, 903) is displayed in the user indication list 901 in combination with the analysis workflow history display of FIG. be able to.
  • the corrected portion is also reflected on the analysis processing result image newer than that on the time axis of the analysis processing flow.
  • 904 is older than 905 on the time axis of the analysis processing flow. Therefore, the correction result of 904 is reflected in 905. Since the user does not want to be aware of the time axis of the analysis process flow, it is possible to sort the analysis process result image in the time axis of the analysis process flow in the user indication list.
  • the analysis processing set of the analysis processing engine finally corrected is stored in the inspection workflow protocol storage unit 105, so that imaging is currently performed.
  • the analysis parameter set read out from the inspection workflow protocol storage unit 105 can be presented and reflected on the same analysis protocol as the currently executed analysis protocol.
  • the analysis parameter set can be used even for other inspections, and the number of times of using the analysis parameter set is totaled by the inspection workflow
  • the analysis parameter set stored in the protocol storage unit 105 and achieving a certain usage rate can be reflected in an unexecuted analysis protocol not used for the current imaging in the analysis protocol storage unit 102.
  • each process executed in each imaging can be automatically executed based on the imaging protocol, analysis protocol, and data transfer protocol registered in advance, the operator's confirmation step can be omitted. . Since the processing content of the inspection workflow does not change whether it is manual operation or automatic processing, the inspection can be completed in a short time without degrading the quality of the inspection. Even when the analysis protocol needs to be edited, only the compatible analysis protocol can be edited, and the operation procedure is not complicated. If the image is not a desired analysis processing result image, it is possible to repeat the processing from the analysis processing result image before data transfer according to the instruction of the operator and trace back the analysis processing, and the analysis processing is performed again with fine adjustment. You can create a result image. That is, by checking the analysis processing result image first, useless confirmation work is eliminated, and the optimum analysis processing result image can be reached with the shortest route.
  • a medical image processing apparatus a medical image processing method, and a processing program used for the same, which can further improve the work efficiency of image processing by performing image processing again based on the indication of the operator.
  • a processing program used for the same which can further improve the work efficiency of image processing by performing image processing again based on the indication of the operator.
  • this embodiment uses a program for detecting a specific abnormality (hereinafter referred to as a nodule) on an image such as an X-ray CT image or an MRI that can confirm the internal structure.
  • a program for detecting a specific abnormality hereinafter referred to as a nodule
  • an image such as an X-ray CT image or an MRI that can confirm the internal structure.
  • CAD Computed Aided Diagnosis
  • the CAD program is generally a process for an image that can confirm the internal structure such as a CT image, and detects a nodule by an implemented algorithm.
  • the target image may be used as it is, but in order to improve detection performance, detection processing is often performed after parameter adjustment of the detection processing or image preprocessing is performed on the image.
  • the present embodiment aims to enhance the detection accuracy by making the feature effective for detection stand out by image preprocessing, and describes a system for highlighting the feature effective for detection.
  • various pretreatments are evaluated and sorted on the basis of the operator's indication to the result of CAD, and the sorted pretreatment is applied to the image, and then CAD is performed again. Redo the processing to be applied.
  • the hardware configuration of the medical image processing apparatus in the present embodiment is the same as that of FIG. 1 of the first embodiment, and the description thereof will be omitted.
  • the image processing to be described below is specifically software processing that is realized by the CPU executing a processing program.
  • FIG. 18 is a functional block diagram of CAD processing in the present embodiment.
  • preprocessing 20 for performing feature amount extraction processing is performed on the image A, which is the detection processing target, stored in the medical image database 14, and abnormal shadow detection processing is performed on the image obtained by the preprocessing.
  • 21 applied evaluation processing 22 evaluated by the operator on the applied detection result, and evaluation and selection of the feature amount extraction processing of various pre-processings based on the operator's evaluation and indication
  • a feature quantity extraction update process 23 for updating the extraction process is performed, and the preprocess 20 for applying the updated feature quantity extraction process to the image is repeated again.
  • the numbers in parentheses indicate the processing order, and by performing the feature value extraction update processing 23, the detection accuracy in the evaluation processing 22 is, for example, from 50% / 50% to 85% / 80% of sensitivity / specificity. It can be improved.
  • FIG. 19 is a functional block diagram of the feature quantity extraction and update process 23.
  • a plurality of filter processes which are feature quantity extraction processes, are applied to a target image.
  • FIG. 19 shows an example in which three processes are applied.
  • abnormal shadow detection processing is applied to each of the three images a1, a2, and a3 to which the filter processing has been applied.
  • White arrows in the figure indicate abnormal shadow detection processing.
  • the detection results obtained as a result are compared with the evaluation results obtained by the operator evaluating the detection results obtained by applying the abnormal shadow detection processing to the image to be detected and processed. It divides into detection groups and uses them to update the filtering process which is the feature value extraction process.
  • FIG. 20 shows an overall flow chart of CAD processing in the present embodiment.
  • step S401 a detection result is obtained in which the abnormal shadow detection process is applied to the image A which is the detection process target.
  • the operator confirms the first detection result, and if the result is satisfied at this time, the CAD processing ends. If the result is not satisfactory, the operator is true positive (TP: True Positive), false positive (FP: False Positive)), true negative (TN: True Negative) for the image A and the detection result in step S 403. ), False negative (FN: False Negative) :).
  • steps S404 to S407 are performed as the feature amount extraction and update process.
  • step S404 a plurality of filter processes are applied to the image A. If you have previously created preprocessing, you may use this. It is desirable that the types of filters be diverse, but not limited. The number of filters is preferably 30 or more in order to obtain the effect of t-test described later. Although a small number of filters can be implemented, there is a high possibility that a significant difference will not occur, but a small number may be employed if a significant difference occurs.
  • step S405 abnormal shadow detection processing is applied to all filtered images.
  • step S406 the abnormal shadow detection processing result is compared with the indication result by the operator performed in S403. Among them, the results matching TP and FN are classified into a correct answer preliminary group, and results matching the FP and TN are classified into a false detection group.
  • step S407 the feature amount extraction process is updated for both image groups. Details of the feature amount extraction and update process will be described later. Then, the feature extraction processing updated in step S407 is applied to the image A, and the abnormal shadow detection processing is applied anew. Although the process may end at this point, it is also possible to return to S402 and update the feature amount extraction process again.
  • FIG. 21 is a flowchart of the feature quantity extraction and update process described in S407.
  • step S410 at least one feature amount (feature image) from an image by frequency analysis, CNN (Convolutional Neural Network), or anatomical viewpoint for each of the correct answer preliminary group and the false detection group get.
  • CNN Convolutional Neural Network
  • anatomical viewpoint for each of the correct answer preliminary group and the false detection group.
  • a two-dimensional discrete Fourier transform shown in the following equation (1) is used for an image.
  • f (x, y) is an expression representing the image A
  • F (u, v) is a signal value when discrete Fourier transform is performed on f (x, y)
  • u and v are x and y, respectively.
  • CNN is generally composed of three layers, in this embodiment, a convolution layer is used when acquiring the feature amount.
  • the role of the convolution layer is to filter the original image with an image filter, and treat the image after filtering as a feature amount.
  • the image filter may be randomly generated, but the CNN may be learned by machine learning to generate a filter pattern.
  • the features are analyzed with the elements constituting the human body. For example, using the relationship between CT value and human body composition (air is -1000, water is 0, etc.), a histogram is created with CT value bin, and this one bin is used as a feature value It is possible to acquire.
  • step S411 an arbitrary one of the feature quantities extracted in step S410 is selected, and Welch's t-test is performed between the correct answer preliminary group and the false detection group.
  • the feature quantity is an image format, it is inconvenient to handle with the t-test as it is (because it has a two-dimensional spread), so it is transformed into a one-dimensional number by any of the following methods. Hereinafter, this is called an evaluation value.
  • Method 1 Calculate the barycentric position of the feature image, and use this as the evaluation value.
  • Method 2 Contour extraction is performed, and the degree of coincidence is calculated by a normalized cross correlation method or the like, and this is used as an evaluation value.
  • Method 3 Using the above combination, the following equation (2) is given.
  • step S410 the feature quantity extraction method described in the description of step S410 is because the feature image size increases when finding more specific features in the extraction process, and the shape and distribution of feature quantities often become important. Do.
  • the degree of coincidence of the contour is an example, and may be replaced with pixel value distribution information such as a standard deviation of pixel values.
  • step S412 the statistic t is applied to the Welch's t test equation defined by the following equation (3) with respect to the evaluation value obtained in step S411.
  • the degree of freedom v is defined by the following equation (4).
  • Xi is the average of the feature value evaluation values
  • si is the variance
  • Ni is the number of evaluation values. That is, assuming the t distribution with degree of freedom v, determine the upper p value of the statistical value t, compare with the significance level ⁇ , and define that there is a significant difference between the two evaluation values if p ⁇ Do.
  • ⁇ represents a confidence interval, which is an index that can be defined by the user and can reject the hypothesis that the mean value of the correctness reserve group and the false detection group is the same group.
  • step S413 as a result of testing the evaluation value obtained in step S411 with respect to the evaluation value obtained in step S411, if there is a significant difference, in step S414, the method selected in step S411 from which this feature quantity is derived It is defined as a new feature quantity extraction process and the process ends. If there is no significant difference, steps S411 and S412 are performed again to obtain a significant difference as long as the extracted feature quantity is exhausted.
  • FIG. 22 is a diagram schematically showing the flow of FIG. 21.
  • Feature extraction 40 is performed for the correct answer preliminary group and the false detection group which are the separated detection result group 30 corresponding to the indication result by the operator.
  • evaluation value calculation (50) is performed for the feature amount group 41 that is the feature amount E1.
  • the calculated evaluation value is subjected to t-test processing (60), and significant difference determination (61) is made as to whether there is a significant difference in the average of each group of the correct answer preliminary group 31 and the false detection group 32.
  • a feature amount extraction process update (62) is performed which defines the extraction process of the selected feature amount E1 as filtering process of pre-processing which is a new feature amount extraction process.
  • the present invention is not limited to the allowable range of parameter adjustment of pre-processing, and various feature quantity extractions are performed.
  • the present invention is effective even when the result is largely different from the previous result, and it is possible to make it a robust method.
  • the characteristic of Welch's t-test is that there is no correlation (correspondence) between the two data (estimated value), and two more data are both unequally distributed (the distribution of each group is different) It can be used for
  • the feature quantities to be dealt with in this case are often unrelated to each other, and can be coped with by setting the variances of the false detection group and the correct answer reserve group to be unequally distributed.
  • the equation shown can be said to be a method based on Welch's t-test.
  • the two groups are classified according to the significant difference, and the classification accuracy of the correct answer preliminary group and the false detection group is secured by the confidence interval. Even if a new image comes in and the preprocessing is updated, the preprocessing can be updated without degrading the accuracy unless the confidence interval is changed.
  • the difference between the feature amounts can be set as a confidence interval (significant difference) instead of a value such as the Euclidean distance, which needs to change the threshold depending on the object, and there is no need to change the threshold. That is, it is more versatile than the conventional one because there is no concept of distance.
  • the parameter since the parameter is not extracted from the similar findings, the user's input is directly handled and the parameter is updated, so that the method is less in the risk of lowering the accuracy.
  • a medical image processing apparatus a medical image processing method, and a processing program used for the same, which can further improve the work efficiency of image processing by performing image processing again based on the indication of the operator.
  • a processing program used for the same which can further improve the work efficiency of image processing by performing image processing again based on the indication of the operator.
  • the present invention is not limited to the above-described embodiments, and includes various modifications.
  • part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment.
  • Medical image processing apparatus 2 CPU 3: Main memory 4: 4: Storage device 5: Display memory 6: 6: Display device 7: 7: Controller 8: Mouse 9: Keyboard 10: Network adapter 11: 11 System bus, 12: network, 13: medical imaging apparatus, 14: medical image database, 20: preprocessing, 21: abnormal shadow detection processing, 22: evaluation processing, 23: feature value extraction update processing, 30: detection result group , 31: correct answer preliminary group, 32: false detection group, 40: feature quantity extraction, 41: feature quantity group, 50: evaluation value calculation, 60: t test process, 61: significant difference judgment, 62: feature quantity extraction process update , 90: image acquisition unit, 91: image processing unit, 92 operator input unit, 101: imaging protocol storage unit, 102: analysis protocol storage unit, 103: data transfer protocol storage unit, 104: purpose Fixed part, 105: inspection workflow protocol storage part, 201: imaging protocol, 202: analysis protocol, 203: data transfer protocol, 301: inspection workflow protocol execution control part, 302: imaging protocol execution control part, 303

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Optics & Photonics (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

La présente invention vise à obtenir un dispositif de traitement d'image médicale, un procédé de traitement et un programme de traitement qui permettent un traitement d'image avec une efficacité de fonctionnement améliorée. L'invention concerne donc un dispositif de traitement d'image médicale qui traite une image médicale obtenue d'un dispositif de diagnostic d'image médicale. Le dispositif de traitement d'image médicale comprend : une unité d'acquisition d'image qui acquiert l'image médicale à partir du dispositif de diagnostic d'image médicale ; une unité de traitement d'image qui effectue un traitement d'image prédéfini sur l'image médicale acquise ; et une unité d'entrée pour un opérateur. Le traitement d'image dans l'unité de traitement d'image est de nouveau effectué sur la base d'une instruction provenant de l'opérateur par l'intermédiaire de l'unité d'entrée relativement à l'image médicale qui a été traitée par l'unité de traitement d'image.
PCT/JP2018/032828 2017-09-20 2018-09-05 Dispositif de traitement d'image médicale, procédé de traitement d'image médicale, et programme de traitement correspondant Ceased WO2019058963A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017179672A JP2019054896A (ja) 2017-09-20 2017-09-20 医用画像処理装置及び医用画像処理方法及びそれに用いる処理プログラム
JP2017-179672 2017-09-20

Publications (1)

Publication Number Publication Date
WO2019058963A1 true WO2019058963A1 (fr) 2019-03-28

Family

ID=65810208

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/032828 Ceased WO2019058963A1 (fr) 2017-09-20 2018-09-05 Dispositif de traitement d'image médicale, procédé de traitement d'image médicale, et programme de traitement correspondant

Country Status (2)

Country Link
JP (1) JP2019054896A (fr)
WO (1) WO2019058963A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021124861A (ja) * 2020-02-04 2021-08-30 ソニーグループ株式会社 解析装置、解析方法、解析プログラム及び診断支援システム
WO2022018809A1 (fr) 2020-07-20 2022-01-27 日本電気株式会社 Dispositif d'analyse d'images, système d'analyse d'images, procédé d'analyse d'images, et programme
JP7532139B2 (ja) 2020-08-04 2024-08-13 キヤノンメディカルシステムズ株式会社 医用情報処理装置及び医用情報生成装置
JP7736486B2 (ja) 2021-08-30 2025-09-09 キヤノンメディカルシステムズ株式会社 解析支援装置、解析支援システム及びプログラム

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003033342A (ja) * 2001-07-24 2003-02-04 Canon Inc 撮影装置、撮影システム、撮影制御方法、記憶媒体、及びプログラム
JP2005270318A (ja) * 2004-03-24 2005-10-06 Konica Minolta Medical & Graphic Inc 画像処理システム
US20080194946A1 (en) * 2007-02-12 2008-08-14 The Government Of The U.S.A. As Represented By The Secretary Of The Dept. Of Health & Human Services Virtual colonoscopy via wavelets
US20090169073A1 (en) * 2008-01-02 2009-07-02 General Electric Company Computer implemented method and system for processing images
JP2013192624A (ja) * 2012-03-16 2013-09-30 Hitachi Ltd 医用画像診断支援装置、医用画像診断支援方法ならびにコンピュータプログラム
US20160361025A1 (en) * 2015-06-12 2016-12-15 Merge Healthcare Incorporated Methods and Systems for Automatically Scoring Diagnoses associated with Clinical Images
JP2017501459A (ja) * 2013-09-25 2017-01-12 テラリコン インコーポレイテッド 高度医用画像処理ウィザード

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003033342A (ja) * 2001-07-24 2003-02-04 Canon Inc 撮影装置、撮影システム、撮影制御方法、記憶媒体、及びプログラム
JP2005270318A (ja) * 2004-03-24 2005-10-06 Konica Minolta Medical & Graphic Inc 画像処理システム
US20080194946A1 (en) * 2007-02-12 2008-08-14 The Government Of The U.S.A. As Represented By The Secretary Of The Dept. Of Health & Human Services Virtual colonoscopy via wavelets
US20090169073A1 (en) * 2008-01-02 2009-07-02 General Electric Company Computer implemented method and system for processing images
JP2013192624A (ja) * 2012-03-16 2013-09-30 Hitachi Ltd 医用画像診断支援装置、医用画像診断支援方法ならびにコンピュータプログラム
JP2017501459A (ja) * 2013-09-25 2017-01-12 テラリコン インコーポレイテッド 高度医用画像処理ウィザード
US20160361025A1 (en) * 2015-06-12 2016-12-15 Merge Healthcare Incorporated Methods and Systems for Automatically Scoring Diagnoses associated with Clinical Images

Also Published As

Publication number Publication date
JP2019054896A (ja) 2019-04-11

Similar Documents

Publication Publication Date Title
CN111696083B (zh) 一种图像处理方法、装置、电子设备及存储介质
US11797846B2 (en) Learning assistance device, method of operating learning assistance device, learning assistance program, learning assistance system, and terminal device
US11996198B2 (en) Determination of a growth rate of an object in 3D data sets using deep learning
WO2019058963A1 (fr) Dispositif de traitement d'image médicale, procédé de traitement d'image médicale, et programme de traitement correspondant
US11756199B2 (en) Image analysis in pathology
US11471096B2 (en) Automatic computerized joint segmentation and inflammation quantification in MRI
CN110717905A (zh) 脑部图像检测方法、计算机设备和存储介质
CN1655193A (zh) 用于对断层图像数据分段的方法和图像处理系统
CN110942447A (zh) Oct图像分割方法、装置、设备及存储介质
CN116363104B (zh) 一种具有影像医学用自动诊断设备及系统
CN108665963A (zh) 一种影像数据分析方法及相关设备
CN112236832A (zh) 诊断辅助系统、诊断辅助方法以及诊断辅助程序
WO2020110774A1 (fr) Dispositif de traitement d'image, procédé de traitement d'image et programme
CN110211200A (zh) 一种基于神经网络技术的牙弓线生成方法及其系统
JP6915969B2 (ja) 医用画像処理装置、医用画像処理方法および超音波診断装置
JP2007172604A (ja) 取得システムのプロトコル及び／又はパラメータに基づいてコンピュータ利用アルゴリズムを選択するための方法及び装置
CN113269733B (zh) 一种断层扫描图像中放射粒子的伪影检测方法
CN109214451A (zh) 一种脑部异常的分类方法及设备
CN117530708B (zh) 手术配准方法和手术配准设备
CN111192679A (zh) 一种影像数据异常的处理方法、装置及存储介质
KR102400568B1 (ko) 인코더를 이용한 이미지의 특이 영역 분석 방법 및 장치
CN117476185B (zh) 医学影像展示方法、装置、电子设备和存储介质
KR20210073047A (ko) 최대강도투사를 통한 인공지능 노듈 세그먼테이션 방법 및 그 장치
JP2019191792A (ja) オブジェクト認識装置、オブジェクト認識方法及びプログラム
CN114255852A (zh) 自动生成后处理任务列表的方法及系统

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: 18858946

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18858946

Country of ref document: EP

Kind code of ref document: A1