WO2022054439A1 - 医用画像処理システム、医用画像処理方法、情報処理装置およびプログラム - Google Patents

医用画像処理システム、医用画像処理方法、情報処理装置およびプログラム Download PDF

Info

Publication number
WO2022054439A1
WO2022054439A1 PCT/JP2021/027899 JP2021027899W WO2022054439A1 WO 2022054439 A1 WO2022054439 A1 WO 2022054439A1 JP 2021027899 W JP2021027899 W JP 2021027899W WO 2022054439 A1 WO2022054439 A1 WO 2022054439A1
Authority
WO
WIPO (PCT)
Prior art keywords
image processing
image
processing
priority
medical
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/JP2021/027899
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
大暉 上原
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.)
Fujifilm Corp
Original Assignee
Fujifilm Corp
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 Fujifilm Corp filed Critical Fujifilm Corp
Priority to DE112021004715.9T priority Critical patent/DE112021004715T5/de
Priority to JP2022547432A priority patent/JP7551230B2/ja
Publication of WO2022054439A1 publication Critical patent/WO2022054439A1/ja
Priority to US18/168,571 priority patent/US20230197252A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • 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
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/60—Memory management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • 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]
    • A61B6/032—Transmission computed tomography [CT]
    • 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
    • A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/504—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of blood vessels, e.g. by angiography
    • 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
    • A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/505—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of bone
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30016—Brain
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30056—Liver; Hepatic
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30061—Lung
    • G06T2207/30064—Lung nodule
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • the present invention relates to a medical image processing system, a medical image processing method, an information processing apparatus, and a program, and in particular, an image processing server receives an image to be processed and a processing request, executes processing according to the processing request, and obtains a processing result.
  • the present invention relates to a medical image processing technique suitable for providing a medical image processing service returned to a requester.
  • CAD computer-aided diagnosis
  • Patent Document 1 describes a mechanism for optimizing the allocation of computational resources such as a CPU (Central Processing Unit) and memory for various analysis processes within the allocated computational resources in an image processing program that performs various medical image analysis. Has been proposed.
  • CPU Central Processing Unit
  • Patent Document 2 describes a method of optimizing a process of storing and / or communicating a medical image taken by using an image diagnostic apparatus in a medical image storage communication system (Picture Archiving and Communication System: PACS). Has been proposed.
  • PACS Picture Archiving and Communication System
  • a medical image processing service that receives medical images and processing requests stored in each medical institution from a plurality of medical institutions and returns the processing results to the request source is provided.
  • various medical image processing functions such as lung CAD are provided from an image processing API server.
  • the lung CAD includes, for example, an AI processing module using a trained AI model that uses a CT image of a lung as input data and outputs a detection result of a lung disease region and / or a recognition result of a disease name (disease name).
  • the image In order to respond to such a request, as soon as an image is taken by modality, the image is automatically acquired from a DICOM (Digital Imaging and Communication in Medicine) server, etc., and possible processing for the image is automatically performed. You need the ability to do it. At this time, if the automatically acquired image is such that a processing request is made for all the images that meet the automatic execution conditions of image processing, the following problems occur.
  • DICOM Digital Imaging and Communication in Medicine
  • a processing request is thrown from a terminal on the medical institution side to a destination (processing request destination) to which a processing request is thrown, such as an image processing API deployed on-premises or on the cloud.
  • a destination processing request destination
  • the computational resources (resources) of are tight, if all the processing requests that meet the automatic execution conditions are thrown, the resource of the processing request destination will be used for the calculation to obtain the low priority processing result. It may be oppressed and high priority processing may not be executed easily.
  • the low-priority processing result here means, for example, an image processing result that is rarely used in an actual diagnostic workflow.
  • the operation on the server side becomes unstable or the minimum required processing result on the client terminal side. There may be a long waiting time for the acquisition.
  • the present disclosure has been made in view of such circumstances, and is a medical image processing system and a medical image processing method capable of solving at least one of the above-mentioned plurality of problems and ensuring the stability and usability of the system.
  • Information processing equipment and programs are provided.
  • the present disclosure is a processing request by dynamically determining the priority of the requested processing when the processing request is thrown on the client terminal side that automatically requests the processing for a new image taken by the modality.
  • the medical image processing system is a medical image processing system including an image processing server that performs image processing of medical images and an information processing device connected to the image processing server via a network.
  • the image processing server includes one or more first processors, in which the first processor executes a plurality of processing modules for performing a plurality of image processes, and the information processing apparatus determines the image to be processed and the processing request. Is received, image processing corresponding to the processing request is performed, and the processing result is returned to the request source.
  • the information processing apparatus includes one or more second processors, and the second processor is connected to the information processing apparatus.
  • Image processing can be performed for the acquired new image, which image processing can be executed among multiple image processes, the load status of the image processing server can be grasped, and the determined image processing can be performed. Based on the priority of each one or more image processing and the grasped load status of the image processing server, the processing request of one or more image processing that can be executed according to the priority standard to the image processing server. To send.
  • the medical image processing system of this embodiment when the information processing apparatus on the side issuing the processing request sends a processing request for image processing to the acquired image, the load status of the image processing server is grasped and the target image is displayed.
  • the processing request to be sent to the image processing server can be determined. Control the number (number of processing requests sent).
  • processing requests for high-priority processing are prioritized according to the load status, and when the resources of the image processing server are tight, processing requests for low-priority processing are suppressed.
  • the priority of each image processing is calculated based on the operation log when the user refers to the processing result using the image viewer, the processing result that is highly necessary for the user or the processing result with high priority is calculated. Can be determined appropriately. According to this aspect, even in a situation where the resources of the image processing server are tight, the processing result with high priority can be acquired relatively early, and the stability and / or responsiveness of the entire system can be obtained. Can be secured.
  • the image processing server may be configured to be installed on a network accessible from each information processing device of a plurality of medical institutions.
  • a plurality of information processing devices connected to an image processing server via a network are included, and each of the plurality of information processing devices is within a medical institution of a different medical institution.
  • the configuration may include terminals connected to the network.
  • an image storage server for storing images taken by one or more modality may be installed on a network in a medical institution.
  • the information processing apparatus acquires information on the reference count and the reference order of the image processing processing result from the operation log, and uses the reference count and reference order information to be used for each. It may be configured to calculate the priority of image processing.
  • the information processing device may be configured to also serve as an image viewer.
  • a plurality of image viewers are connected to the network in the medical institution, and the information processing apparatus collects and collects operation logs of the plurality of image viewers.
  • the priority may be calculated by statistically processing the information recorded in the operation log of.
  • the information processing apparatus performs an organ extraction process for extracting the organs shown in the acquired new image, and based on the information of the extracted organs, a plurality of organs are extracted. It may be configured to discriminate the image processing related to the organ from the image processing as the feasible image processing.
  • the information processing apparatus determines an image processing that can be performed from a plurality of image processings based on the tag information attached to the acquired new image. It may be a configuration.
  • the image processing server includes an endpoint that receives an inquiry about the load status from the information processing device and responds to the current load status, and the information processing device is an end. It may be configured to use points and acquire information indicating the load status of the image processing server from the endpoint.
  • the information processing apparatus records the response time from the transmission of the processing request to the image processing server until the processing result is obtained for each processing request, and responds. By calculating the rate of increase in time, the load status of the image processing server may be grasped.
  • the information processing apparatus compares the grasped numerical value indicating the load status of the image processing server with the threshold value, and makes an image of the processing request for the processing of the priority according to the threshold value. It may be configured to send to the processing server.
  • the priority may be divided into 50 or more levels from the lowest priority level to the highest priority level.
  • the plurality of image processing is at least one of computer detection support (Computer Aided Detection: CADe) processing and computer diagnosis support (Computer Aided Diagnosis: CADx) processing. It may be a configuration including processing.
  • the plurality of processing modules may be configured to include a CADe module that processes CADe and a CADx module that processes CADx.
  • the CADe processing priority may be set to a higher priority than the CADx processing priority.
  • the plurality of processing modules may be configured to include a processing module that performs a report creation support process including a process of generating a candidate for a finding sentence.
  • the priority of the report creation support process is set to be lower than the priority of the CADe process and the priority of the CADx process. It may be a configuration.
  • the plurality of image processing includes a fracture detection process for detecting the position of a fracture, a bone labeling process for labeling a bone number, and a lung for detecting the position of a lung nodule. It may be configured to include at least one of a nodule detection process, a property discrimination process for differentiating the properties of lung nodules, and a lung area labeling process for lung area labeling.
  • an image processing server that processes an image to be processed and a processing request from an information processing apparatus connected to an image processing server capable of performing a plurality of image processing via a network.
  • This is a medical image processing method in which the image processing server performs image processing corresponding to the processing request and returns the processing result to the request source. Obtained by collecting the operation log of the image viewer used when viewing the processing result of image processing, calculating the priority of each of multiple image processing based on the collected operation log, and calculating. It records the priority information, updates and manages the priority information of each of multiple image processes, and acquires new images taken by one or more modalities connected to the network in the medical institution.
  • the image processing server is subject to the priority criteria of one or more image processing that can be performed. Including making a processing request.
  • the information processing apparatus is an information processing apparatus connected to an image processing server capable of performing a plurality of image processing via a network, and includes one or more processors. , Collect the operation log of the image viewer used when the user browses the processing result of image processing on the network in the medical institution to which the information processing device is connected, and based on the collected operation log, multiple image processing Calculate each priority of, record the priority information obtained by the calculation, update and manage each priority information of multiple image processing, and one or more connected to the network in the medical institution. Acquires a new image taken by the modality of, determines what image processing can be executed among multiple image processes for the acquired new image, and grasps the load status of the image processing server. , One that can be executed according to the priority criteria for the image processing server based on the priority of each of the determined one or more image processing that can be executed and the load status of the grasped image processing server. The processing request for the above image processing is transmitted.
  • the program according to another aspect of the present disclosure is a program for making a computer function as an information processing apparatus connected to an image processing server capable of performing a plurality of image processing via a network, and the computer is informed of information.
  • Multiple image processing based on the function to collect the operation log of the image viewer used when the user browses the processing result of the image processing on the network in the medical institution to which the processing device is connected, and the collected operation log.
  • a function to acquire a new image taken by one or more modalities a function to determine which image processing among a plurality of image processes can be executed for the acquired new image, and an image.
  • Priority is given to the image processing server based on the function of grasping the load status of the processing server, the priority of each of the determined and executable image processing, and the grasped load status of the image processing server. It is a program for realizing a function of transmitting a processing request for one or more image processing that can be executed according to a standard of degree.
  • the number of processing requests sent to the image processing server is effective based on the load status of the image processing server and the priority of each image processing. Can be narrowed down to. According to the present invention, it is possible to ensure the stability of the operation of the image processing server that provides the processing result of the image processing according to the processing request. In addition, the information processing apparatus according to the present invention can quickly acquire processing results that are highly necessary for the user, and usability is ensured.
  • FIG. 1 is a block diagram schematically showing the configuration and operation of the medical image processing system according to the embodiment of the present invention.
  • FIG. 2 is a flowchart showing the operation flow of the medical image processing system shown in FIG.
  • FIG. 3 is a flowchart showing an example of the operation related to the priority calculation.
  • FIG. 4 is a diagram schematically showing a system configuration example of a medical image processing system.
  • FIG. 5 is a block diagram showing a configuration example of an image processing API server.
  • FIG. 6 is a block diagram showing a configuration example of an image processing management terminal on a network in a medical institution.
  • FIG. 7 is a block diagram showing a configuration example of a viewer terminal.
  • FIG. 8 is a block diagram showing an example of a computer hardware configuration.
  • FIG. 1 is a block diagram schematically showing the configuration and operation of the medical image processing system 10 according to the embodiment of the present invention.
  • the medical image processing system 10 comprises a terminal 20 installed on a network in each medical institution of a plurality of medical institutions and an image processing API server 30 installed on a network accessible from the terminal 20 of each medical institution. include.
  • the terminal 20 refers to a computational resource existing in a network that can safely access data in a medical institution, and the terminal 20 does not have to physically exist in the medical institution.
  • the terminal 20 of each medical institution may be a physical machine or a virtual machine, and the specific form is not limited.
  • a typical example of a medical institution is a "hospital”.
  • the indications of "hospital 1", “hospital 2" ... "hospital N" shown in FIG. 1 indicate that N medical institutions exist.
  • At least one terminal 20 for one medical institution is provided on the medical institution network.
  • the terminal 20 is an example of the "information processing device" in the present disclosure.
  • the image processing API server 30 is a central image processing server that receives an image processing request from each terminal 20 of N medical institutions, executes the requested image processing, and returns the processing result to the request source.
  • Modality 40 is a device for taking an inspection image.
  • the modality 40 includes a device that generates an inspection image representing the inspection target portion of the subject by photographing the inspection target portion, adds incidental information defined by the DICOM standard to the image, and outputs the inspection image.
  • Specific examples of the modality 40 include a CT device (Computed Tomography), an MRI device (magnetic resonance imaging), an angiography X-ray diagnostic device, and a PET device (Positron Emission Tomography). Examples thereof include a tomography apparatus), an ultrasonic apparatus, a CR apparatus (Computed Radiography: computer X-ray imaging apparatus) using a flat X-ray detector (FPD), a mammography apparatus, and an endoscopic apparatus.
  • the DICOM server 50 is a server that operates according to the DICOM specifications.
  • the DICOM server 50 is a computer that stores and manages various data including images taken by using the modality 40, and includes a large-capacity external storage device and a database management program.
  • the DICOM server 50 is an example of the "image storage server" in the present disclosure.
  • a viewer 202 In each medical institution, a viewer 202, an operation log collection unit 204, a priority information update management unit 206, and an image processing automatic request unit 208 are constructed on one or more terminals 20.
  • Viewer 202 includes an image interpretation viewer program that assists the diagnostic workflow of diagnostic imaging by a physician.
  • the viewer 202 causes the display device to display the inspection image, the image processing result, and the like.
  • the viewer 202 may be dedicated browsing software, a Web browser, or the like.
  • the viewer 202 is an example of the "image viewer" in the present disclosure.
  • the operation log collection unit 204 is a program that collects operation logs when the user 60 uses the viewer 202.
  • the operation log collection unit 204 automatically collects operation logs at appropriate timings without making the user 60 aware of the operation log collection work.
  • the collected operation log data is stored in the operation log database (DataBase: DB) 205.
  • the user 60 is mainly a doctor or the like, and is a person who refers to the image processing result by using the viewer 202.
  • the priority information update management unit 206 is a program that calculates the priority of various medical image processing based on the operation log collected by the operation log collection unit 204.
  • the priority information update management unit 206 may calculate the priority for each individual based on the operation log acquired for each individual of the user 60, or statistically process the operation log of the plurality of users 60 for medical treatment. You may calculate the priority of the average usage assumption in the institution.
  • the image processing automatic request unit 208 acquires an image stored in the DICOM server 50, selects an image process to be applied to the acquired image, and performs an image processing API according to the priority information determined by the priority information update management unit 206. This is a program that requests image processing from the server 30.
  • the image processing API server 30 may exist on a network that can be safely accessed from the image processing automatic request unit 208 on the respective medical institution networks of a plurality of medical institutions, and may be in any form such as a physical machine or a virtual machine. ..
  • the image processing API server 30 may be a cloud server or an on-premises server.
  • the image processing API server 30 is an example of the "image processing server" in the present disclosure.
  • FIG. 1 shows an example in which the viewer 202, the operation log collection unit 204, the priority information update management unit 206, and the image processing automatic request unit 208 are constructed on one terminal 20.
  • the program may be distributed and constructed in two or more terminals existing on the network in the medical institution.
  • the viewer 202 is built on the first terminal, and the operation log collection unit 204, the priority information update management unit 206, and the image processing automatic request unit 208 are built on a second terminal different from the first terminal. May be done.
  • the viewer 202, the operation log collection unit 204, the priority information update management unit 206, and the image processing automatic request unit 208 may be constructed on separate terminals.
  • the flow of the procedures [a] to [d] in FIG. 1 shows the flow from the inspection image being taken by the modality 40 to the processing request being made to the image processing API server 30.
  • the flow of procedures [0] to [4] in FIG. 1 shows a flow in which the user 60 calculates the priority of various image processing from the operation log using the viewer 202.
  • the flow of steps [a] to [d] and the flow of steps [0] to [4] may be performed in parallel.
  • FIG. 2 is a flowchart showing the operation flow of the medical image processing system 10.
  • the inspection image is taken by the modality 40 (step S11).
  • the inspection image taken by the modality 40 is stored in the DICOM server 50 (step S12, procedure [a] in FIG. 1).
  • the image processing automatic request unit 208 automatically acquires the image newly saved in the DICOM server 50 (step S13, procedure [b] in FIG. 1), and the image processing automatic request unit 208 obtains the image.
  • the processing content is determined as to what kind of processing should be performed (step S14, procedure [c] in FIG. 1).
  • “automatically” means that the user does not need to input an instruction by each operation from the user 60, and the image taken by the modality 40 is saved in the DICOM server 50. It means that it is automatically performed in the background in conjunction with the operation.
  • the image processing automatic request unit 208 performs organ extraction processing on the acquired image.
  • Information on which organ is shown may be extracted, and for example, if the lung is shown, lung nodule detection may be performed.
  • One or more image processes that can be executed are associated with each organ, and one or more image processes that can be executed are determined according to the extracted organ. There may be a plurality of image processes that can be executed for one image.
  • the image processing automatic request unit 208 may use the information obtained from the DICOM tag attached to the image as the processing applicability determination criterion.
  • the information obtained from the DICOM tag for example, conditions such as CT slice thickness may be used. If the CT slice thickness is thick, there may be some processing that cannot be performed. Therefore, it may be determined whether or not the treatment can be applied based on the information on the CT slice thickness, provided that the treatment can be performed when the CT slice thickness is equal to or less than a predetermined reference value.
  • the applicability of the treatment may be determined by the combination of the result of organ extraction and the condition of CT slice thickness.
  • DICOM tag information is an example of "tag information" in the present disclosure.
  • the image processing automatic request unit 208 grasps the load status of the image processing API server 30 before transmitting the processing request determined to be applicable to the acquired image to the image processing API server 30. (Step S15).
  • the method of grasping the load status responds to the load status on the image processing API server 30 side, such as an API endpoint (Endpoint) that returns the number of processes waiting in the current image processing API server 30.
  • the API endpoint to be used may be provided on the image processing API server 30 side, the API endpoint may be used by the image processing automatic request unit 208, and the load status of the image processing API server 30 may be acquired from the response content.
  • the API endpoint is an example of an "endpoint" in the present disclosure.
  • the image processing automatic request unit 208 processes the response time from sending the processing request to the image processing API server 30 until the processing result is obtained. It may be possible to grasp the load status by recording each request in the image processing automatic request unit 208 and calculating the increasing tendency of the time until the response is returned.
  • the image processing automatic request unit 208 acquires the latest priority information of each process from the priority information update management unit 206 as necessary (step S16, procedure [4] in FIG. 1).
  • the image processing automatic request unit 208 compares the numerical value indicating the load status grasped in step S15 with the threshold value, and requests the image processing API server 30 to process the priority according to the threshold value (step S17, FIG. 1). Procedure [d]).
  • the priority is divided into 100 levels from “1" indicating the lowest level to "100" indicating the highest level, and the priority is determined for each process by the priority information update management unit 206.
  • the image processing automatic request unit 208 transmits, for example, a processing request having a priority of 30 to 100 when the increase rate of the response time of the image processing API server 30 is 30% in the last 10 requests. And so on.
  • priority 1 to 100 is shown here as an example of the particle size of priority, the definition of priority is not limited to this example. In order to flexibly set priorities for multiple image processes, it is desirable to make the priority particles finer.
  • the priority is preferably divided into 50 or more levels from the lowest priority level to the highest priority level, and more preferably 100 or more levels.
  • the priority level may be defined in 256 levels or 1024 levels.
  • the image processing API server 30 that received the processing request from the image processing automatic request unit 208 executes the requested processing (step S18).
  • the image processing automatic request unit 208 acquires the processing result from the image processing API server 30 at an appropriate timing (step S20).
  • the image processing API server 30 may notify the image processing automatic request unit 208 that the processing result has been created, or the image processing automatic request unit 208 periodically performs image processing.
  • the flow may be such that the API server 30 is inquired about the existence of the processing result and the processing result is acquired when the processing result is obtained.
  • the image processing automatic request unit 208 that has acquired the processing result from the image processing API server 30 saves the processing result in a format that can be referred to by the viewer 202 (step S21).
  • the processing result information may be associated with the image and stored in the DICOM server 50.
  • the user 60 can refer to the processing result through the viewer 202 (step S22).
  • step S13 when the calculation resource of the image processing API server 30 is abundant in response to the processing request from the image processing automatic request unit 208, when the user 60 refers to the processing result in the above procedure, step S13. It is assumed that all the processing results determined to be applicable to the image acquired from the DICOM server 50 by the image processing automatic request unit 208 in step S14 can be referred to in the viewer 202. As a result of considering the load status of the image processing API server 30, when the processing requests to be transmitted from the image processing automatic request unit 208 are narrowed down, some results cannot be prepared when the user 60 refers to the processing results. Is assumed. Specific examples of such cases will be described below.
  • fracture CAD for detecting a fracture from an image
  • bone labeling for labeling a bone number. Since fracture CAD is often performed at the beginning of the diagnostic workflow to find a fracture, the results are often referred to in the viewer 202, and the fracture CAD processing results can be referenced by the user 60 at an early stage. Is desirable.
  • bone labeling is, for example, a process of automatically recognizing the number of the spine, and the labeling of the bone number obtained as a result of bone labeling is a fracture in the report when the fracture is detected by the fracture CAD. While it plays an important role in identifying the location, if no fracture is detected, there is no need to write the bone number in the report, and bone labeling does not have to be done. Further, even if a fracture is detected but there is no result of bone labeling, it is a little inconvenient for the user 60 side, but the report itself can be created by specifying the bone number by oneself. For this reason, in this example, it is possible to make a determination such as "fracture CAD> bone labeling" as the priority of image processing.
  • Such a relative magnitude relationship of priorities may be determined in the default priority setting (factory setting) or may be determined from the analysis result of the operation log of the viewer 202. For example, there is a default priority setting, and then the preference of the user 60 in each medical institution may be reflected in the priority from the analysis of the operation log.
  • each processing request it is also conceivable to initially send each processing request to the image processing API server 30 without giving any priority.
  • the user 60 such as a doctor may feel inconvenience because it takes time until the processing result can be referred to at first, but the processing waiting until the processing is completed is a high-priority processing and does not wait. If the process is canceled, the priority can be set for each process as a process with a low priority, and thereafter, the process that reflects the priority becomes possible.
  • the image processing automatic request unit 208 prioritizes the processing request of the fracture CAD over the processing of the bone labeling.
  • ⁇ Specific example 2> there are three processes of lung nodule detection, lung area labeling, and report candidate sentence generation processing using these two processing results.
  • Lung nodules may indicate some disease, and the results of lung nodule detection to detect the location of the lung nodules are often referred to early in the diagnostic workflow.
  • lung segment labeling is a function that divides the lung region so that it can be easily distinguished, and is often referred to after the result of lung nodule detection, and if there are no abnormal findings in the lung field image. , It may not be necessary to include the name of the lung region in detail in the report, and the results of lung segment labeling may not be referenced.
  • the report candidate sentence generation process is a process of generating a candidate of the finding sentence to be described in the report.
  • the report candidate sentence generation function generates candidates for findings by inputting the results of lung nodule detection and lung segment labeling, but even if there are no findings candidates, the results of lung nodule detection and lung segment labeling can be obtained.
  • the relationship between the priorities of each of the three processes can be determined as "lung nodule detection> lung area labeling> report candidate sentence generation”.
  • the image processing automatic request unit 208 can perform processing such as giving priority to a processing request for detecting a lung nodule.
  • the report candidate sentence generation process is an example of the "report creation support process" in the present disclosure.
  • the image processing automatic request unit 208 periodically grasps the load status of the image processing API server 30 performed in step S15.
  • the image processing automatic request unit 208 must internally send a processing request, but internally holds a processing request (for example, a bone labeling processing request) that cannot be sent due to its low priority. is doing.
  • the pending image processing request is transmitted after a certain period of time has elapsed.
  • the value of this timeout time may be given as a fixed value as a setting file or the like.
  • the image processing automatic request unit 208 is an average of the operation logs collected by the operation log collection unit 204 for the interpretation workflow.
  • the time-out time may be dynamically set based on the calculated time.
  • a dynamic setting may be made to set 60 minutes as the timeout period.
  • FIG. 3 is a flowchart showing an example of the operation related to the priority calculation.
  • the user 60 refers to various image processing results using the viewer 202 and performs a diagnostic workflow (step S51 of FIG. 3).
  • the operation log collection unit 204 collects the operation log of the operation of the viewer 202 by the user 60 (step S52).
  • the priority information update management unit 206 acquires the information necessary for the priority calculation of the processing request from the operation log (step S53).
  • the priority information update management unit 206 provides, for example, a log regarding the number of times the processing result is referenced and information on the reference order such as which processing result is referenced and then which processing result is referenced. get.
  • the priority information update management unit 206 that has acquired the necessary information calculates the priority of each process using the information in the procedure [3] (step S54).
  • the process here is a process of requesting the image processing API server 30 from the image processing automatic request unit 208 in each medical institution, for example, lung nodule detection. In the calculation of priority, for example, the following priority criteria are applied.
  • the subsequent priority calculation method may be passed as a setting file to the information processing device in which the priority information update management unit 206 is constructed, or may be directly implemented as a source code. ..
  • the above "priority standard" raises the priority of processing in which the result is frequently referred to, but it is also preferable to consider the following criteria as priority criteria other than the number of references. That is, it is considered necessary to raise the priority of the processing required as the pre-stage of other processing, such as the CADe-based processing, which is the pre-stage processing of the CADx-based processing.
  • the CADx-based process is a process for performing property analysis, and corresponds to, for example, a process for discriminating (differentiating) whether it is cancer or pneumonia.
  • the CADe system processing is a detection system processing that detects a specific area or target from the image, for example, a processing that detects whether an abnormal area is on the image and extracts an abnormal area. Corresponds to. When an abnormal region is detected by the CADe system processing, a stepwise processing mode in which the property analysis is performed by the CADx system processing can be considered.
  • the default priority value is given as an attribute to the priority value of various processes, and the result reference.
  • the number of times may be given as an addition value to the default value.
  • priority 200 is given as a default priority value for CADe-based processing
  • priority 100 is given as an attribute for CADx-based processing
  • the number of references to the result specified from the operation log is the default.
  • the process A may be, for example, an abnormal region extraction process in the lung
  • the process B may be, for example, a lung cancer AI determination process
  • the process C may be, for example, a pneumonia AI determination process
  • the process D may be, for example, a bronchitis AI determination process. ..
  • the abnormal region extraction process in the lung is an example of "CADe treatment” in the present disclosure
  • each of the lung cancer AI judgment process, the pneumonia AI judgment process, and the bronchitis AI judgment process is an example of "CADx treatment” in the present disclosure. Is.
  • the priority information calculated in step S54 (procedure [3] in FIG. 1) is stored in the priority information update management unit 206 (step S55).
  • the image processing automatic request unit 208 acquires the latest priority information of each process before sending the image processing process request at the timings such as step S16 and step S17 described with reference to FIG.
  • FIG. 4 is a diagram schematically showing a system configuration example of the medical image processing system 10.
  • a medical institution network 100 having the same system configuration is constructed in each of a plurality of medical institutions for the sake of simplicity, but the medical institution network having a different system configuration for each medical institution is shown. May be constructed.
  • the medical institution network 100 is a computer network including a modality 40, a DICOM server 50, an image processing management terminal 20A, a viewer terminal 22, an electronic medical record system 24, and a premises communication line 26.
  • the network 100 in the medical institution may include a plurality of types of modality 40. There may be various combinations of modality 40 types connected to the medical institution network 100 for each medical institution.
  • the DICOM server 50 communicates with other devices via the premises communication line 26, and transmits / receives various data including image data.
  • the DICOM server 50 receives image data and other various data generated by the modality 40 via the premises communication line 26, and stores and manages the data in a recording medium such as a large-capacity external storage device.
  • the storage format of the image data and the communication between the devices via the premises communication line 26 are based on the DICOM protocol.
  • the image processing management terminal 20A is an information processing device corresponding to the terminal 20 described with reference to FIG.
  • the form of the image processing management terminal 20A is not particularly limited, and may be a personal computer, a workstation, a tablet terminal, or the like.
  • the image processing management terminal 20A has a communication function for communicating with the image processing API server 30, and is connected to the image processing API server 30 via the wide area communication line 120.
  • the image processing management terminal 20A can acquire data from the DICOM server 50 or the like via the premises communication line 26. Further, the image processing management terminal 20A can send the processing result acquired from the image processing API server 30 to the DICOM server 50 and the viewer terminal 22.
  • the image processing management terminal 20A may also be used as the viewer terminal 22.
  • Various data stored in the database of the DICOM server 50 and various information including the processing result acquired by the image processing management terminal 20A can be displayed on the viewer terminal 22.
  • the viewer terminal 22 is a terminal for viewing images called a PACS viewer or a DICOM viewer.
  • a plurality of viewer terminals 22 may be connected to the medical institution network 100.
  • the form of the viewer terminal 22 is not particularly limited, and may be a personal computer, a workstation, a tablet terminal, or the like.
  • a network within a medical institution having a similar system configuration is constructed in each of a plurality of medical institutions.
  • the image processing API server 30 communicates with the image processing management terminal 20A of each medical institution via the wide area communication line 120.
  • the wide area communication line 120 is an example of the "network" in the present disclosure.
  • the image processing API server 30 can perform a plurality of image processing, and provides various image processing services in response to a processing request from the image processing management terminal 20A.
  • Image processing The image processing provided by the API server 30 includes, for example, a fracture detection process for detecting the position of a fracture, a bone labeling process for labeling bone numbers, a lung nodule detection process for detecting the position of a lung nodule, and a lung nodule.
  • the lung nodule property differentiation process for differentiating the properties of the lung nodule, and the labeling of the lung area may include at least one process of the lung area labeling process.
  • Image processing The image processing provided by the API server 30 also includes organ segmentation processing, blood vessel region extraction processing, brain CAD processing, breast CAD processing, liver CAD processing, large intestine CAD processing, and report creation support processing. sell.
  • FIG. 5 is a block diagram showing a configuration example of the image processing API server 30.
  • the image processing API server 30 can be realized by a computer system configured by using one or a plurality of computers. By installing a program on the computer, various functions of the image processing API server 30 are realized.
  • the image processing API server 30 includes a processor 302, a non-temporary tangible computer-readable medium 304, a communication interface 306, an input / output interface 308, a bus 310, an input device 314, and a display device 316.
  • the processor 302 is an example of the "first processor” in the present disclosure.
  • the computer-readable medium 304 is an example of the "first storage device” in the present disclosure.
  • the processor 302 includes a CPU (Central Processing Unit).
  • the processor 302 may include a GPU (Graphics Processing Unit).
  • the processor 302 is connected to the computer-readable medium 304, the communication interface 306, and the input / output interface 308 via the bus 310.
  • the input device 314 and the display device 316 are connected to the bus 310 via the input / output interface 308.
  • the computer-readable medium 304 includes a memory as a main storage device and a storage as an auxiliary storage device.
  • the computer-readable medium 304 may be, for example, a semiconductor memory, a hard disk (HDD: Hard Disk Drive) device, a solid state drive (SSD: Solid State Drive) device, or a combination thereof.
  • HDD Hard Disk Drive
  • SSD Solid State Drive
  • the image processing API server 30 is connected to the wide area communication line 120 (see FIG. 4) via the communication interface 306.
  • the computer-readable medium 304 stores a plurality of programs, data, and the like for performing various processes including a plurality of image processes.
  • the computer-readable medium 304 includes, for example, an organ segmentation program 320, a vascular region extraction program 322, a fracture CAD program 324, a bone labeling program 326, a lung nodule detection program 330, a lung nodule property analysis program 332, a pneumonia CAD program 334, and a lung area.
  • One or more of the labeling program 336, the breast CAD program 340, the liver CAD program 342, the brain CAD program 344, the colon CAD program 346, the report creation support program 348, and the like may be stored.
  • the report creation support program 348 includes a finding sentence candidate generation program 349.
  • These various processing programs may be AI processing modules including trained models trained to apply machine learning such as deep learning to obtain the output of the desired task.
  • the AI model for CAD can be configured by using, for example, various convolutional neural networks (CNN: Convolutional Neural Network) having a convolutional layer.
  • the input data for the AI model includes, for example, a medical image such as a two-dimensional image, a three-dimensional image or a moving image, and the output from the AI model is, for example, information indicating the position of a diseased area (lesion site) in the image, or It may be information indicating a classification such as a disease name, or a combination thereof.
  • An AI model that handles time-series data, document data, etc. can be configured using, for example, various recurrent neural networks (RNNs).
  • the time series data includes, for example, ECG waveform data.
  • Document data includes, for example, findings created by a doctor.
  • Each of the processing programs illustrated in FIG. 5 is an example of the "processing module” in the present disclosure.
  • Each of the fracture CAD program 324 and the lung nodule detection program 330 is an example of the "CADe module” in the present disclosure.
  • Each of the lung nodule property analysis program 332 and the pneumonia CAD program 334 is an example of the "CADx module” in the present disclosure.
  • the types and combinations of processing programs implemented in the image processing API server 30 can have various forms.
  • a server program including various processing programs stored in the computer-readable medium 304 is an example of the "first program" in the present disclosure.
  • the computer of the image processing API server 30 functions as a processing unit corresponding to the processing program.
  • the computer of the image processing API server 30 functions as an organ segmentation processing unit that performs organ segmentation processing. The same applies to other programs.
  • the processor 302 receives the image to be processed and the processing request from the image processing management terminal 20A of each medical institution by executing the instruction of the program stored in the computer-readable medium 304, and performs image processing corresponding to the processing request. Is executed and the processing result is returned to the request source.
  • the operation executed by the image processing API server 30 is an example of the "first operation" in the present disclosure.
  • the display control program 350 is stored in the computer-readable medium 304.
  • the display control program 350 generates a display signal necessary for display output to the display device 316, and controls the display of the display device 316.
  • the display device 316 is composed of, for example, a liquid crystal display, an organic EL (organic electro-luminescence: OEL) display, a projector, or an appropriate combination thereof.
  • the input device 314 is composed of, for example, a keyboard, a mouse, a touch panel, or other pointing device, a voice input device, or an appropriate combination thereof.
  • the input device 314 accepts various inputs by the operator.
  • the display device 316 and the input device 314 may be integrally configured by using the touch panel.
  • FIG. 6 is a block diagram showing a configuration example of the image processing management terminal 20A on the network 100 in the medical institution.
  • the image processing management terminal 20A can be realized by a computer system configured by using one or a plurality of computers.
  • the image processing management terminal 20A includes a processor 212, a non-temporary tangible computer readable medium 214, a communication interface 216, an input / output interface 218, a bus 220, an input device 224, and a display device 226.
  • the hardware configuration of the image processing management terminal 20A may be the same as the hardware configuration of the image processing API server 30 described with reference to FIG. That is, the hardware configurations of the processor 212, the computer readable medium 214, the communication interface 216, the input / output interface 218, the bus 220, the input device 224, and the display device 226 shown in FIG. 6 are the same as the corresponding elements shown in FIG. It may be.
  • the processor 212 is an example of the “second processor” and the “processor” in the present disclosure.
  • the computer-readable medium 214 is an example of the “second storage device” and the “storage device” in the present disclosure.
  • the image processing management terminal 20A is connected to the viewer terminal 22, the DICOM server 50, and the image processing API server 30 via the communication interface 216.
  • the computer-readable medium 214 stores various programs and data including the medical image processing request optimization program 200 and the display control program 260.
  • the medical image processing request optimization program 200 includes an operation log collection unit 204, a priority information update management unit 206, and an image processing automatic request unit 208.
  • the computer-readable medium 214 has an operation log database 205 that stores and manages operation log data collected by the operation log collection unit 204, and an image processing result acquired by the image processing automatic request unit 208 from the image processing API server 30. Includes a processing result storage unit 264 for storing the data.
  • the display control program 260 generates a display signal necessary for display output to the display device 226, and controls the display of the display device 226.
  • the processor 212 collects the operation log of the viewer terminal 22 by executing the instruction of the medical image processing request optimization program 200 stored in the computer readable medium 214, and based on the collected operation log, each Calculate the priority of image processing, record the priority information obtained by the calculation, update and manage the priority information of each image processing, and create a new image taken by modality 40. To acquire, to determine what image processing can be executed for the acquired new image, to grasp the load status of the image processing API server 30, and to determine the determined executable image processing. Based on each priority of the above and the load status of the image processing API server 30, an operation including sending a processing request to the image processing API server 30 according to the priority standard is performed.
  • the operation executed by the image processing management terminal 20A is an example of the "second operation" in the present disclosure.
  • the medical image processing request optimization program 200 is an example of the "second program" and the "program" in the present disclosure. Although an example of constructing an operation log collection unit 204, a priority information update management unit 206, and an image processing automatic request unit 208 in one image processing management terminal 20A is shown here, medical image processing request optimization is shown.
  • the processing function of the program 200 may be realized by sharing the processing function among two or more computers.
  • FIG. 7 is a block diagram showing a configuration example of the viewer terminal 22.
  • the hardware configuration of the viewer terminal 22 may be the same as the hardware configuration of the image processing management terminal 20A described with reference to FIG.
  • the viewer terminal 22 includes a processor 232, a computer-readable medium 234, a communication interface 236, an input / output interface 238, a bus 240, an input device 244, and a display device 246.
  • Each hardware configuration may be similar to the corresponding element of the configuration shown in FIG.
  • the computer-readable medium 234 includes a viewer 202, which is a medical image viewing program, an operation log storage unit 203 for storing the operation log of the viewer 202, and a display control program 262.
  • the viewer 202 causes the display device 246 to display various information including the image read from the DICOM server 50 connected via the communication interface 236 and the processing result of the image processing. Further, the viewer 202 saves the history (operation log) in which the user 60 operates the input device 244 in the operation log storage unit 203.
  • the operation log data saved in the operation log storage unit 203 is sent to the operation log collection unit 204 of the image processing management terminal 20A.
  • the display control program 262 generates a display signal necessary for display output to the display device 246, and controls the display of the display device 246.
  • FIG. 8 is a block diagram showing an example of a computer hardware configuration.
  • the computer 800 may be a personal computer, a workstation, or a server computer.
  • the computer 800 has a part or all of the terminal 20, the image processing API server 30, the DICOM server 50, the electronic medical record system 24, the image processing management terminal 20A, and the viewer terminal 22 described above, or a plurality of functions thereof. It can be used as a equipped device.
  • the computer 800 includes a CPU 802, a RAM (RandomAccessMemory) 804, a ROM (ReadOnlyMemory) 806, a GPU 808, a storage 810, a communication unit 812, an input device 814, a display device 816, and a bus 818.
  • the GPU 808 may be provided as needed.
  • the CPU 802 reads various programs stored in the ROM 806, the storage 810, or the like, and executes various processes.
  • the RAM 804 is used as a work area of the CPU 802. Further, the RAM 804 is used as a storage unit for temporarily storing the read program and various data.
  • the storage 810 includes, for example, a hard disk device, an optical disk, a magneto-optical disk, or a semiconductor memory, or a storage device configured by using an appropriate combination thereof.
  • Various programs, data, and the like are stored in the storage 810.
  • the program stored in the storage 810 is loaded into the RAM 804, and the CPU 802 executes the program, so that the computer 800 functions as a means for performing various processes specified by the program.
  • the communication unit 812 is an interface that performs communication processing with an external device by wire or wirelessly and exchanges information with the external device.
  • the communication unit 812 can play the role of an information acquisition unit that accepts input such as an image.
  • the input device 814 is an input interface that accepts various operation inputs to the computer 800.
  • the input device 814 may be, for example, a keyboard, mouse, touch panel, or other pointing device, or voice input device, or any combination thereof.
  • the display device 816 is an output interface for displaying various information.
  • the display device 816 may be, for example, a liquid crystal display, an organic electro-luminescence (OEL) display, a projector, or an appropriate combination thereof.
  • OEL organic electro-luminescence
  • a program that enables a computer to realize a part or all of at least one of the processing functions of the above is recorded on a computer-readable medium such as an optical disk, a magnetic disk, or a semiconductor memory or other tangible non-temporary information storage medium.
  • a computer-readable medium such as an optical disk, a magnetic disk, or a semiconductor memory or other tangible non-temporary information storage medium.
  • program signal as a download service using a telecommunication line such as the Internet, instead of storing and providing the program in such a tangible non-temporary computer-readable medium.
  • each processing unit executes various processes such as the operation log collection unit 204, the priority information update management unit 206, and the image processing automatic request unit 208 in the terminal 20 and the image processing management terminal 20A is For example, various processors as shown below.
  • CPU which is a general-purpose processor that executes programs and functions as various processing units
  • GPU which is a processor specialized in image processing
  • FPGA Field Programmable Gate Array
  • a dedicated electric circuit that is a processor with a circuit configuration specially designed to execute a specific process such as a programmable logic device (PLD) or ASIC (Application Specific Integrated Circuit), which is a processor that can change the CPU. Etc. are included.
  • PLD programmable logic device
  • ASIC Application Specific Integrated Circuit
  • One processing unit may be composed of one of these various processors, or may be composed of two or more processors of the same type or different types.
  • one processing unit may be configured by a plurality of FPGAs, a combination of a CPU and an FPGA, or a combination of a CPU and a GPU.
  • a plurality of processing units may be configured by one processor.
  • one processor is configured by a combination of one or more CPUs and software, as represented by a computer such as a client or a server. There is a form in which the processor functions as a plurality of processing units.
  • SoC System On Chip
  • the various processing units are configured by using one or more of the above-mentioned various processors as a hardware-like structure.
  • the hardware-like structure of these various processors is, more specifically, an electric circuit (circuitry) in which circuit elements such as semiconductor elements are combined.
  • the image processing system 10 According to the medical image processing system 10 according to the present embodiment, after the image is taken by the modality 40, the image processing result highly necessary for the user 60 can be viewed in a short time, so that the efficiency of the diagnostic work is high. Can be achieved.
  • Medical image processing system 20 Terminal 20A Image processing management terminal 22 Viewer terminal 24 Electronic chart system 26 On-site communication line 30 Image processing API server 40 Modality 50 DICOM server 60 User 100 Medical institution network 120 Wide area communication line 200 Medical image processing request Optimization program 202 Viewer 203 Operation log storage unit 204 Operation log collection unit 205 Operation log database 206 Priority information update management unit 208 Image processing automatic request unit 212 Processor 214 Computer readable medium 216 Communication interface 218 Communication interface 218 Input / output interface 220 Bus 224 Input device 226 Display device 232 Processor 234 Computer-readable medium 236 Communication interface 238 Input / output interface 240 Bus 244 Input device 246 Display device 260 Display control program 262 Display control program 264 Processing result storage unit 302 Processor 304 Computer-readable medium 306 Communication interface 308 Input / output interface 310 Bus 314 Input device 316 Display device 320 Organ segmentation program 322 Vascular region extraction program 324 Fracture CAD program 326 Bone labeling program 330 Pulmonary nodule detection

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Physics & Mathematics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Quality & Reliability (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Physiology (AREA)
  • Optics & Photonics (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
PCT/JP2021/027899 2020-09-08 2021-07-28 医用画像処理システム、医用画像処理方法、情報処理装置およびプログラム Ceased WO2022054439A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
DE112021004715.9T DE112021004715T5 (de) 2020-09-08 2021-07-28 Verarbeitungssystem für medizinische bilder, verarbeitungsverfahren für medizinische bilder, informationsverarbeitungsvorrichtung und programm
JP2022547432A JP7551230B2 (ja) 2020-09-08 2021-07-28 医用画像処理システム、医用画像処理方法、情報処理装置およびプログラム
US18/168,571 US20230197252A1 (en) 2020-09-08 2023-02-14 Medical image processing system, medical image processing method, information processing apparatus, and program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020-150287 2020-09-08
JP2020150287 2020-09-08

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/168,571 Continuation US20230197252A1 (en) 2020-09-08 2023-02-14 Medical image processing system, medical image processing method, information processing apparatus, and program

Publications (1)

Publication Number Publication Date
WO2022054439A1 true WO2022054439A1 (ja) 2022-03-17

Family

ID=80632501

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/027899 Ceased WO2022054439A1 (ja) 2020-09-08 2021-07-28 医用画像処理システム、医用画像処理方法、情報処理装置およびプログラム

Country Status (4)

Country Link
US (1) US20230197252A1 (https=)
JP (1) JP7551230B2 (https=)
DE (1) DE112021004715T5 (https=)
WO (1) WO2022054439A1 (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11432982B2 (en) * 2018-03-26 2022-09-06 Augustine Biomedical + Design, LLC Relocation module and methods for surgical equipment
JP2025011865A (ja) * 2023-07-12 2025-01-24 富士フイルム株式会社 超音波診断装置及びモデル動作検証方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009176173A (ja) * 2008-01-28 2009-08-06 Fujifilm Corp 検査データ管理装置及び方法、並びに医用ネットワークシステム
JP2013214295A (ja) * 2012-03-05 2013-10-17 Toshiba Corp 医用画像処理システム
WO2020066132A1 (ja) * 2018-09-27 2020-04-02 富士フイルム株式会社 医用画像診断支援装置、方法及びプログラム
JP2020121049A (ja) * 2019-01-31 2020-08-13 合同会社ｍｏｄｏｒａｄｏ 医療画像診断支援装置、医療画像撮影装置、画像管理サーバ及び医療画像診断支援方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4733953B2 (ja) 2003-09-30 2011-07-27 株式会社東芝 医用画像通信システム、医用画像通信装置、及び医用画像通信方法
JP7105927B2 (ja) 2019-01-30 2022-07-25 富士フイルム株式会社 医用画像解析装置、方法およびプログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009176173A (ja) * 2008-01-28 2009-08-06 Fujifilm Corp 検査データ管理装置及び方法、並びに医用ネットワークシステム
JP2013214295A (ja) * 2012-03-05 2013-10-17 Toshiba Corp 医用画像処理システム
WO2020066132A1 (ja) * 2018-09-27 2020-04-02 富士フイルム株式会社 医用画像診断支援装置、方法及びプログラム
JP2020121049A (ja) * 2019-01-31 2020-08-13 合同会社ｍｏｄｏｒａｄｏ 医療画像診断支援装置、医療画像撮影装置、画像管理サーバ及び医療画像診断支援方法

Also Published As

Publication number Publication date
JP7551230B2 (ja) 2024-09-17
US20230197252A1 (en) 2023-06-22
DE112021004715T5 (de) 2023-07-06
JPWO2022054439A1 (https=) 2022-03-17

Similar Documents

Publication Publication Date Title
JP7653361B2 (ja) 臨床ワークフローの判断を自動化し、優先読み取りインジケータを生成するためのシステムおよび方法
JP5843414B2 (ja) 医療記録ソフトウエアと高度画像処理の統合
JP7552845B2 (ja) 情報処理装置、医用画像表示装置及びプログラム
JP6275876B2 (ja) 医療データ処理のための進化型文脈的臨床データエンジン
US8526693B2 (en) Systems and methods for machine learning based hanging protocols
JP4979334B2 (ja) 医用画像読影支援システム及びプログラム
US20190156947A1 (en) Automated information collection and evaluation of clinical data
JP2022528095A (ja) 医療情報を評価するためのプラットフォームおよびその使用方法
CN111226287B (zh) 用于分析医学成像数据集的方法、系统、程序产品和介质
JP6727176B2 (ja) 学習支援装置、学習支援装置の作動方法、学習支援プログラム、学習支援システム、および端末装置
CN114077679B (zh) 加速医学图像检索的方法以及图片存档和通信系统
JP6362061B2 (ja) 診断支援システム、その作動方法、およびプログラム
US20220181005A1 (en) Utilizing multi-layer caching systems for storing and delivering images
EP4133503A1 (en) Clinically meaningful and personalized disease progression monitoring incorporating established disease staging definitions
US20230197252A1 (en) Medical image processing system, medical image processing method, information processing apparatus, and program
US20240078089A1 (en) System and method with medical data computing
JP7299314B2 (ja) 医療文書作成装置、方法およびプログラム、学習装置、方法およびプログラム、並びに学習済みモデル
JPWO2019102903A1 (ja) 検査情報表示装置、方法およびプログラム
JP7415787B2 (ja) 医用画像システム
JP7209738B2 (ja) 画像解析装置、解析機能決定方法、及び解析機能決定プログラム
WO2021180551A1 (en) Radiologist fingerprinting
JP2018114070A (ja) 医用画像保管装置および医用画像保管システム
JP7706098B2 (ja) 過去映像と現在映像とを比較する方法およびシステム
JP7640887B2 (ja) 情報処理装置、情報処理装置の制御方法、及びプログラム
EP4261832A1 (en) Patient monitoring device

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: 21866399

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022547432

Country of ref document: JP

Kind code of ref document: A

122 Ep: pct application non-entry in european phase

Ref document number: 21866399

Country of ref document: EP

Kind code of ref document: A1