WO2022215529A1 - 医用画像解析装置、医用画像解析方法、及び医用画像解析プログラム - Google Patents

医用画像解析装置、医用画像解析方法、及び医用画像解析プログラム Download PDF

Info

Publication number
WO2022215529A1
WO2022215529A1 PCT/JP2022/013692 JP2022013692W WO2022215529A1 WO 2022215529 A1 WO2022215529 A1 WO 2022215529A1 JP 2022013692 W JP2022013692 W JP 2022013692W WO 2022215529 A1 WO2022215529 A1 WO 2022215529A1
Authority
WO
WIPO (PCT)
Prior art keywords
analysis
interest
medical image
region
result
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/JP2022/013692
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
晶路 一ノ瀬
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 JP2023512927A priority Critical patent/JPWO2022215529A1/ja
Publication of WO2022215529A1 publication Critical patent/WO2022215529A1/ja
Priority to US18/479,118 priority patent/US12536659B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • 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]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • 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
    • 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
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • 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
    • G06T2207/10104—Positron emission tomography [PET]
    • 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
    • G06T2207/10116—X-ray image
    • 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
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20104—Interactive definition of region of interest [ROI]
    • 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
    • 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
    • G06T2207/30096—Tumor; Lesion

Definitions

  • the present disclosure relates to a medical image analysis device, a medical image analysis method, and a medical image analysis program.
  • the present disclosure has been made in view of the circumstances described above, and aims to provide a medical image analysis apparatus, a medical image analysis method, and a medical image analysis program capable of improving the accuracy of analysis results of a region of interest.
  • a medical image analysis apparatus of the present disclosure is a medical image analysis apparatus including at least one processor, wherein the processor performs first analysis processing on a plurality of regions of interest included in a medical image, , receives an input about a first region of interest, performs a second analysis process on a second region of interest related to the first region of interest based on the input, and outputs analysis results of the second region of interest. .
  • the processor accepts, as an input, selection of one analysis result from among a plurality of analysis results of the first analysis process regarding the first region of interest, and one analysis result is A second analysis process may be performed on a second region of interest for which associated analysis results have been obtained.
  • the processor receives, as an input, a statement of findings regarding the first region of interest, and based on the statement of findings, a plurality of analysis results of the first analysis process regarding the first region of interest. Among them, one analysis result may be selected, and the second analysis processing may be performed on the second region of interest for which the analysis result related to the one analysis result is obtained.
  • the processor as the second analysis process, relates to one analysis result among the plurality of analysis results obtained by the first analysis process regarding the second region of interest A process of correcting the certainty factor of the analysis result may be performed.
  • the processor performs the second analysis processing, a partial image including the second region of interest of the medical image, one analysis result, a learning partial image, and a learning Analysis processing for the second region of interest may be performed based on a trained model trained in advance using learning data including analysis results of the region of interest included in the partial image.
  • the processor when there are a plurality of analysis results related to one analysis result, the processor is configured to Based on the probability, one analysis result out of a plurality of analysis results related to one analysis result may be selected.
  • the processor may perform the first analysis process by changing the analysis parameter for the analysis result related to the analysis result of the first region of interest as the second analysis process. good.
  • the analysis result may be the name of the region of interest, the finding, the finding sentence, or the diagnosis name.
  • the result of the second analysis process for the second region of interest differs from the result of the first analysis process
  • the result of the second analysis process is the first You may notify that it is different from the result of the analysis processing.
  • the processor determines a second region of interest related to the first region of interest based on the input, and performs second analysis processing regarding the determined second region of interest. may be performed.
  • the processor determines a second region of interest associated with each of the plurality of regions of interest before receiving the input, and determines each of the plurality of regions of interest based on the input.
  • a second region of interest related to the first region of interest may be selected from among the second regions of interest, and a second analysis process may be performed on the selected second region of interest.
  • the medical image analysis method of the present disclosure performs a first analysis process on a plurality of regions of interest included in a medical image, receives an input for the first region of interest among the plurality of regions of interest, and based on the input Then, a processor included in the medical image analysis apparatus performs a second analysis process on a second region of interest related to the first region of interest, and outputs the analysis result of the second region of interest. .
  • the medical image analysis program of the present disclosure performs a first analysis process on a plurality of regions of interest included in a medical image, receives input regarding the first region of interest among the plurality of regions of interest, and based on the input a second region of interest related to the first region of interest, and outputting the analysis result of the second region of interest to a processor included in the medical image analysis apparatus. is.
  • the medical image analysis apparatus of the present disclosure is a medical image analysis apparatus including at least one processor, the processor performs analysis processing on a region of interest included in a medical image, and inputs corrections to analysis results of the region of interest. is received, and based on the input, analysis processing is performed by changing the analysis parameters for the analysis results related to the corrected analysis results.
  • the medical image analysis method of the present disclosure performs analysis processing on a region of interest included in a medical image, receives an input for correction of the analysis result of the region of interest, and performs analysis related to the corrected analysis result based on the input.
  • a processor provided in the medical image analysis apparatus executes the processing of changing the analysis parameters for the result and performing the analysis processing.
  • the medical image analysis program of the present disclosure performs analysis processing on a region of interest included in a medical image, receives an input for correction of the analysis result of the region of interest, and performs analysis related to the corrected analysis result based on the input. This is for causing the processor provided in the medical image analysis apparatus to execute the process of changing the analysis parameters for the result and performing the analysis process.
  • FIG. 1 is a block diagram showing a schematic configuration of a medical information system
  • FIG. 1 is a block diagram showing an example of the hardware configuration of a medical image analysis apparatus
  • FIG. 10 is a diagram showing an example of a related diagnosis name table
  • FIG. 1 is a block diagram showing an example of a functional configuration of a medical image analysis apparatus according to a first embodiment
  • FIG. 10 is a diagram for explaining a first analysis process using a trained model according to the first to third embodiments
  • FIG. It is a figure which shows an example of the 1st analysis result display screen which concerns on 1st and 2nd embodiment. It is a figure which shows an example of the 2nd analysis result display screen which concerns on 1st and 2nd embodiment.
  • FIG. 4 is a flowchart showing an example of medical image analysis processing according to the first embodiment
  • FIG. 11 is a diagram for explaining a second analysis process using a trained model
  • FIG. FIG. 11 is a diagram showing an example of a related diagnosis name table according to a modified example
  • It is a figure which shows an example of the 1st analysis result display screen which concerns on a modification.
  • It is a figure which shows an example of the 2nd analysis result display screen which concerns on a modification.
  • FIG. 11 is a block diagram showing an example of a functional configuration of a medical image analysis apparatus according to a second embodiment
  • FIG. FIG. 10 is a diagram for explaining input of an observation sentence by a user
  • 9 is a flowchart showing an example of medical image analysis processing according to the second embodiment
  • FIG. 11 is a block diagram showing an example of a functional configuration of a medical image analysis apparatus according to a third embodiment; FIG. It is a figure which shows an example of the 1st analysis result display screen which concerns on 3rd Embodiment. It is a figure which shows an example of the 2nd analysis result display screen which concerns on 3rd Embodiment.
  • FIG. 11 is a flowchart showing an example of medical image analysis processing according to the third embodiment; FIG. It is a figure which shows an example of a related finding table.
  • FIG. 12 is a block diagram showing an example of a functional configuration of a medical image analysis apparatus according to a fourth embodiment; FIG. FIG. 14 is a diagram for explaining analysis processing using a trained model according to the fourth embodiment; FIG. FIG.
  • FIG. 10 is a diagram for explaining that findings are corrected;
  • FIG. 14 is a flowchart showing an example of medical image analysis processing according to the fourth embodiment;
  • FIG. It is a figure which shows an example of the 2nd analysis result display screen which concerns on a modification.
  • 10 is a flowchart showing an example of medical image analysis processing according to a modification;
  • the medical information system 1 is a system for taking images of a diagnostic target region of a subject and storing the medical images acquired by the taking, based on an examination order from a doctor of a clinical department using a known ordering system. .
  • the medical information system 1 is a system for interpretation of medical images and creation of interpretation reports by interpretation doctors, and for viewing interpretation reports and detailed observations of medical images to be interpreted by doctors of the department that requested the diagnosis. be.
  • a medical information system 1 includes a plurality of imaging devices 2, a plurality of image interpretation workstations (WorkStation: WS) 3 which are image interpretation terminals, a clinical department WS 4, an image server 5, and an image database.
  • the imaging device 2, the interpretation WS3, the clinical department WS4, the image server 5, and the interpretation report server 7 are connected to each other via a wired or wireless network 9 so as to be able to communicate with each other.
  • the image DB 6 is connected to the image server 5 and the interpretation report DB 8 is connected to the interpretation report server 7 .
  • the imaging device 2 is a device that generates a medical image representing the diagnostic target region by imaging the diagnostic target region of the subject.
  • the imaging device 2 may be, for example, a simple X-ray imaging device, an endoscope device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, a PET (Positron Emission Tomography) device, or the like.
  • a medical image generated by the imaging device 2 is transmitted to the image server 5 and stored.
  • the clinical department WS4 is a computer used by doctors in the clinical department for detailed observation of medical images, viewing interpretation reports, and creating electronic medical charts.
  • each process of creating a patient's electronic medical record, requesting image browsing to the image server 5, and displaying the medical image received from the image server 5 is executed by executing a software program for each process.
  • each process such as automatic detection or highlighting of a region suspected of a disease in a medical image, request for viewing an interpretation report to the interpretation report server 7, and display of an interpretation report received from the interpretation report server 7 is performed. , by executing a software program for each process.
  • the image server 5 incorporates a software program that provides a general-purpose computer with the functions of a database management system (DBMS).
  • DBMS database management system
  • the incidental information includes, for example, an image ID (identification) for identifying individual medical images, a patient ID for identifying a patient who is a subject, an examination ID for identifying examination content, and an ID assigned to each medical image. It includes information such as a unique ID (UID: unique identification) that is assigned to the user.
  • the additional information includes the examination date when the medical image was generated, the examination time, the type of imaging device used in the examination for obtaining the medical image, patient information (for example, the patient's name, age, gender, etc.).
  • examination site i.e., imaging site
  • imaging information e.g., imaging protocol, imaging sequence, imaging technique, imaging conditions, use of contrast agent, etc.
  • multiple medical images acquired in one examination Information such as the series number or the collection number at the time is included.
  • the interpretation report server 7 incorporates a software program that provides DBMS functions to a general-purpose computer.
  • the interpretation report server 7 receives an interpretation report registration request from the interpretation WS 3 , the interpretation report is formatted for a database and registered in the interpretation report database 8 . Also, upon receiving a search request for an interpretation report, the interpretation report is searched from the interpretation report DB 8 .
  • the interpretation report DB 8 stores, for example, an image ID for identifying a medical image to be interpreted, an interpreting doctor ID for identifying an image diagnostician who performed the interpretation, a lesion name, lesion position information, findings, and confidence levels of findings. An interpretation report in which information such as is recorded is registered.
  • Network 9 is a wired or wireless local area network that connects various devices in the hospital. If the interpretation WS 3 is installed in another hospital or clinic, the network 9 may be configured to connect the local area networks of each hospital with the Internet or a dedicated line. In any case, the network 9 preferably has a configuration such as an optical network that enables high-speed transfer of medical images.
  • the interpretation WS 3 requests the image server 5 to view medical images, performs various image processing on the medical images received from the image server 5, displays the medical images, analyzes the medical images, emphasizes display of the medical images based on the analysis results, and analyzes the images. Create an interpretation report based on the results.
  • the interpretation WS 3 also supports the creation of interpretation reports, requests registration and viewing of interpretation reports to the interpretation report server 7 , displays interpretation reports received from the interpretation report server 7 , and the like.
  • the interpretation WS3 performs each of the above processes by executing a software program for each process.
  • the interpretation WS 3 includes a medical image analysis apparatus 10, which will be described later. Among the above processes, the processes other than those performed by the medical image analysis apparatus 10 are performed by well-known software programs. Description is omitted.
  • the interpretation WS3 does not perform processing other than the processing performed by the medical image analysis apparatus 10, and a computer that performs the processing is separately connected to the network 9, and in response to a processing request from the interpretation WS3, the computer You may make it perform the process which was carried out.
  • the medical image analysis apparatus 10 included in the interpretation WS3 will be described in detail below.
  • the medical image analysis apparatus 10 includes a CPU (Central Processing Unit) 20 , a memory 21 as a temporary storage area, and a nonvolatile storage section 22 .
  • the medical image analysis apparatus 10 also includes a display 23 such as a liquid crystal display, an input device 24 such as a keyboard and mouse, and a network I/F (InterFace) 25 connected to the network 9 .
  • CPU 20 , memory 21 , storage unit 22 , display 23 , input device 24 and network I/F 25 are connected to bus 27 .
  • the storage unit 22 is implemented by a HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, or the like.
  • a medical image analysis program 30 is stored in the storage unit 22 as a storage medium.
  • the CPU 20 reads out the medical image analysis program 30 from the storage unit 22 , expands it in the memory 21 , and executes the expanded medical image analysis program 30 .
  • a related diagnosis name table 32 is stored in the storage unit 22 .
  • FIG. 3 shows an example of the related diagnosis name table 32.
  • the related diagnosis name table 32 associates a diagnosis name with a diagnosis name related to the diagnosis name.
  • diagnosis name For example, primary lung cancer of the lung field is associated with hilar lymphoma. This is because lung field primary lung cancer and hilar lymphoma are associated, and one may develop when the other develops.
  • the medical image analysis apparatus 10 includes an acquisition section 40 , a first analysis section 42 , a first output section 44 , a reception section 46 , a second analysis section 48 and a second output section 50 .
  • the CPU 20 functions as an acquisition unit 40 , a first analysis unit 42 , a first output unit 44 , a reception unit 46 , a second analysis unit 48 and a second output unit 50 .
  • the acquisition unit 40 acquires a medical image to be diagnosed (hereinafter referred to as a "diagnosis target image") from the image server 5 via the network I/F 25.
  • a medical image to be diagnosed hereinafter referred to as a "diagnosis target image”
  • the image to be diagnosed is a chest CT image
  • the first analysis unit 42 performs a first analysis process on multiple regions of interest included in the diagnosis target image acquired by the acquisition unit 40 . Specifically, as the first analysis process, the first analysis unit 42 uses a learned model M1 for detecting an abnormal shadow as an example of a region of interest from a diagnosis target image, and detects an abnormal shadow. I do.
  • the trained model M1 is configured by, for example, a CNN (Convolutional Neural Network) that receives medical images and outputs information about abnormal shadows contained in the medical images.
  • the trained model M1 uses, as learning data, a large number of combinations of, for example, a medical image containing an abnormal shadow, information identifying an area in the medical image in which the abnormal shadow exists, and the diagnosis name of the abnormal shadow. It is a model learned by machine learning using
  • the first analysis unit 42 inputs the diagnosis target image to the learned model M1.
  • the learned model M1 outputs information representing an area in which an abnormal shadow is present in the input diagnosis target image, the diagnosis name of the abnormal shadow, and the degree of certainty of the diagnosis name.
  • the learned model M1 outputs information representing an area in which an abnormal shadow having a certainty degree of the diagnosis name equal to or higher than a predetermined threshold TH1 (for example, 0.5) exists.
  • a predetermined threshold TH1 for example, 0.5
  • the dashed rectangle indicates the area where the abnormal shadow exists, and the diagnosis name and confidence are indicated in the balloon.
  • the first analysis unit 42 obtains, as the analysis result of the first analysis process, information representing an area in which an abnormal shadow exists in the diagnosis target image, the diagnosis name of the abnormal shadow, and the certainty of the diagnosis name.
  • the first output unit 44 controls display on the display 23 by outputting the analysis result by the first analysis unit 42 to the display 23 . At this time, the first output unit 44 performs control to display the diagnostic names of abnormal shadows on the display 23 in descending order of certainty.
  • FIG. 6 shows an example of the first analysis result display screen displayed on the display 23 under the control of the first output section 44. As shown in FIG. As shown in FIG. 6, on the first analysis result display screen, information representing an area where an abnormal shadow exists and the diagnosis name of the abnormal shadow are displayed. In the example of FIG. 6, the area where the abnormal shadow exists is indicated by a dashed rectangle. FIG. 6 also shows an example where the confidence in benign tumors is higher than the confidence in primary lung cancer, and the confidence in cystic lesions is higher than the confidence in lymphoma.
  • a user such as a doctor selects one of a plurality of diagnosis names, which are a plurality of analysis results of a first analysis process relating to a first abnormal shadow among a plurality of abnormal shadows displayed on the first analysis result display screen. Select a diagnosis name.
  • the receiving unit 46 is selected by the user from among a plurality of diagnosis names, which are a plurality of analysis results of the first analysis processing regarding the first abnormal shadow, as an input for the first abnormal shadow among the plurality of abnormal shadows. accepts a single diagnostic name.
  • the second analysis unit 48 performs second analysis processing regarding a second abnormal shadow related to the first abnormal shadow. Specifically, first, the second analysis unit 48 refers to the related diagnosis name table 32 and acquires a diagnosis name related to one diagnosis name accepted by the acceptance unit 46 . Then, the second analysis unit 48 performs a second analysis process on the second abnormal shadow whose acquired diagnosis name is obtained as the analysis result of the first analysis unit 42 . In the present embodiment, as the second analysis process, the second analysis unit 48 performs a diagnosis name matching the acquired diagnosis name among the plurality of diagnosis names obtained by the first analysis process regarding the second abnormal shadow. Perform processing to correct the confidence of At this time, the second analysis unit 48 corrects the certainty to be higher by a predetermined percentage (for example, 20%).
  • a predetermined percentage for example, 20%
  • the second output unit 50 controls display on the display 23 by outputting the analysis result of the second abnormal shadow by the second analysis unit 48 to the display 23 . At this time, the second output unit 50 performs control to display the diagnosis name of the second abnormal shadow on the display 23 in descending order of certainty.
  • FIG. 7 shows an example of the second analysis result display screen displayed on the display 23 under the control of the second output unit 50. As shown in FIG. FIG. 7 shows an example in which the user selects primary lung cancer from a plurality of diagnoses of the first abnormal shadow on the left side in the example of FIG. Further, in FIG. 7, the second abnormal shadow on the right side related to primary lung cancer is corrected to be lymphoma by the second analysis unit 48 so that the confidence is higher than that of the cystic lesion. is shown. In this manner, the display order of the diagnosis name of the second abnormal shadow is changed according to the user's selection of the diagnosis name of the first abnormal shadow. The user creates a medical document such as an interpretation report by referring to the second display screen.
  • the second output unit 50 outputs the result of the second analysis process to the result of the first analysis process. You may notify that it is different.
  • FIG. 25 shows an example in which the display order of candidates for the diagnosis of the second abnormal shadow is changed as a result of the user selecting primary lung cancer as the diagnosis of the first abnormal shadow.
  • the function of notifying may be switchable between on and off by the user.
  • the medical image analysis process shown in FIG. 8 is executed by the CPU 20 executing the medical image analysis program 30 .
  • the medical image analysis processing shown in FIG. 8 is executed, for example, when the user inputs an instruction to start execution.
  • the acquisition unit 40 acquires the diagnosis target image from the image server 5 via the network I/F 25.
  • the first analysis unit 42 performs the first analysis processing on the plurality of regions of interest included in the diagnosis target image acquired in step S10.
  • the first output unit 44 outputs the analysis result obtained in step S ⁇ b>12 to the display 23 as described above, thereby controlling the display on the display 23 .
  • step S16 the receiving unit 46 receives one diagnostic name selected by the user from among the multiple diagnostic names of the first abnormal shadow among the multiple abnormal shadows displayed in step S14.
  • step S18 the second analysis unit 48 refers to the related diagnosis name table 32 as described above, and obtains the diagnosis name related to the one diagnosis name accepted in step S16. Then, as described above, the second analysis unit 48 performs the second analysis process on the second abnormal shadow obtained as the result of the analysis in step S12 with the acquired diagnosis name.
  • step S20 the second output unit 50 controls display on the display 23 by outputting the analysis result of the second abnormal shadow in step S18 to the display 23, as described above.
  • the medical image analysis process ends.
  • the second analysis unit 48 performs a partial image including the second abnormal shadow of the diagnosis target image, one diagnosis name received by the reception unit 46, a partial image for learning
  • the second abnormal shadow analysis process may be performed based on the trained model M2 that has been trained in advance using learning data that includes the diagnosis name of the abnormal shadow included in the learning partial image.
  • the second analysis unit 48 converts the partial image including the diagnosis name received by the reception unit 46 and the second abnormal shadow of the image to be diagnosed into the learned model M1. to enter.
  • the trained model M2 outputs the diagnosis name of the second abnormal shadow included in the input partial image and the degree of certainty of the diagnosis name.
  • the second analysis unit 48 obtains the diagnosis name of the second abnormal shadow and the degree of certainty of the diagnosis name as the analysis result of the second analysis process.
  • the second analysis unit 48 associates one diagnosis name with one diagnosis name.
  • One diagnosis may be selected from multiple diagnoses related to one diagnosis based on the co-occurrence probability with each of the multiple diagnoses. In this case, for example, the second analysis unit 48 selects the diagnosis with the highest co-occurrence probability among multiple diagnoses related to one diagnosis.
  • the co-occurrence probabilities may be stored in the related diagnosis name table 32 .
  • FIG. 10 shows an example of the related diagnosis name table 32 in this case.
  • the diagnosis name and findings are displayed on the first analysis result display screen.
  • the certainty of the diagnosis name corresponding to the combination of the diagnosis name and findings selected by the user is corrected on the second analysis result display screen, and then the diagnosis is corrected. Names are displayed according to confidence.
  • the second analysis unit 48 may determine the second abnormal shadow associated with each of the plurality of abnormal shadows before the receiving unit 46 receives the user's input regarding the first abnormal shadow. In this case, based on the input received by the receiving unit 46, the second analysis unit 48 selects a second abnormal shadow related to the first abnormal shadow from among the second abnormal shadows determined for each of the plurality of abnormal shadows. Choose a shade. Then, the second analysis unit 48 performs a second analysis process on the selected second abnormal shadow.
  • the second analysis unit 48 refers to the related diagnosis name table 32 and acquires the diagnosis name related to the diagnosis name obtained as the analysis result by the first analysis unit 42 for each of the plurality of abnormal shadows.
  • the second analysis unit 48 determines an abnormal shadow whose diagnosis name is included in the analysis result of the first analysis unit 42 as a related second abnormal shadow.
  • the second analysis unit 48 selects the second abnormal shadow determined for each of the plurality of abnormal shadows.
  • a second abnormal shadow whose diagnosis name is included in the analysis result of the first analysis unit 42 is selected.
  • the second analysis unit 48 performs a second analysis process on the selected second abnormal shadow.
  • FIG. Steps in FIG. 26 that execute the same processing as in FIG. 8 are given the same step numbers and descriptions thereof are omitted.
  • step S15 of FIG. 26 the second analysis unit 48 refers to the related diagnosis name table 32 and obtains diagnosis names related to the diagnosis name obtained as the analysis result of the first analysis unit 42 for each of the plurality of abnormal shadows. do.
  • the second analysis unit 48 determines an abnormal shadow whose diagnosis name is included in the analysis result of the first analysis unit 42 as a related second abnormal shadow.
  • the process of step S15 may be performed after step S12 and before step S14.
  • the process of step S15 may be performed in parallel with the process of step S14.
  • step S18D the second analysis unit 48 determines that one diagnosis name accepted in step S16 from among the second abnormal shadows determined in step S15 for each of the plurality of abnormal shadows is included in the analysis result of step S12. Select the second anomalous shadow that is Then, the second analysis unit 48 performs a second analysis process on the selected second abnormal shadow.
  • the medical image analysis apparatus 10 includes an acquisition unit 40, a first analysis unit 42, a first output unit 44, a reception unit 46A, a second analysis unit 48A, a second output unit 50A, and an extraction unit 52. including.
  • the CPU 20 executes the medical image analysis program 30, the acquisition unit 40, the first analysis unit 42, the first output unit 44, the reception unit 46A, the second analysis unit 48A, the second output unit 50A, and the extraction unit 52 Function.
  • the user designates a first abnormal shadow from among a plurality of abnormal shadows on the first analysis result display screen shown in FIG. Enter the statement of findings regarding the abnormal opacity of the patient.
  • the accepting unit 46A accepts a finding statement regarding the first abnormal shadow input by the user as an input regarding the first abnormal shadow.
  • the extraction unit 52 extracts the diagnosis name of the first abnormal shadow from the finding text received by the reception unit 46A.
  • a known technique such as natural language processing using a recurrent neural network or matching processing with a pre-prepared word dictionary of diagnosis names can be used.
  • the second analysis unit 48A matches the diagnosis name extracted by the extraction unit 52 from among a plurality of diagnosis names that are a plurality of analysis results of the first analysis processing by the first analysis unit 42 regarding the first abnormal shadow. Select the name of the diagnosis to be performed. Next, the second analysis unit 48A refers to the related diagnosis name table 32 and acquires the diagnosis name related to the selected one diagnosis name. Then, the second analysis unit 48 performs a second analysis process on the second abnormal shadow whose acquired diagnosis name is obtained as the analysis result of the first analysis unit 42 . The second analysis process is the same as that of the first embodiment, so the description is omitted.
  • the second output unit 50A controls the display on the display 23 by outputting the analysis result of the second abnormal shadow by the second analysis unit 48A to the display 23. I do. That is, in the present embodiment, when the user inputs the finding sentence shown in FIG. 14 for the first abnormal shadow on the left side in the example of FIG. The display order of the diagnosis names of abnormal shadows is changed.
  • the medical image analysis processing shown in FIG. 15 is executed by the CPU 20 executing the medical image analysis program 30 .
  • the medical image analysis processing shown in FIG. 15 is executed, for example, when the user inputs an execution start instruction. Steps in FIG. 15 that execute the same processing as in FIG. 8 are given the same step numbers and descriptions thereof are omitted.
  • the reception unit 46A receives a finding text input by the user for the first abnormal shadow among the plurality of abnormal shadows displayed at step S14.
  • the extraction unit 52 extracts the diagnosis name of the first abnormal shadow from the finding text received in step S16A.
  • step S18A the second analysis unit 48A matches the diagnosis name extracted in step S17 from among a plurality of diagnosis names, which are a plurality of analysis results of the first analysis processing in step S12 regarding the first abnormal shadow. Select the name of the diagnosis to be performed.
  • the second analysis unit 48A refers to the related diagnosis name table 32 and acquires the diagnosis name related to the selected one diagnosis name. Then, the second analysis unit 48 performs a second analysis process on the second abnormal shadow whose acquired diagnosis name is obtained as the analysis result in step S12.
  • the second output unit 50A controls the display on the display 23 by outputting the analysis result of the second abnormal shadow at step S18A to the display 23.
  • the medical image analysis process ends.
  • the medical image analysis apparatus 10 includes an acquisition unit 40, a first analysis unit 42, a first output unit 44B, a reception unit 46B, a second analysis unit 48B, a second output unit 50B, and an extraction unit 52B. including.
  • the CPU 20 executes the medical image analysis program 30, the acquisition unit 40, the first analysis unit 42, the first output unit 44B, the reception unit 46B, the second analysis unit 48B, the second output unit 50B, and the extraction unit 52B Function.
  • the first output unit 44B controls display on the display 23 by outputting the analysis result by the first analysis unit 42 to the display 23 .
  • the first output unit 44B controls the display 23 to display information representing the abnormal shadow.
  • FIG. 17 shows an example of the first analysis result display screen displayed on the display 23 under the control of the first output section 44B. As shown in FIG. 17, the diagnosis name of the abnormal shadow is not displayed on the display 23 on the first analysis result display screen according to the present embodiment.
  • the first output unit 44B may perform control to display the diagnosis name of the abnormal shadow on the display 23 as well as the first output unit 44B.
  • the user designates the first abnormal shadow on the first analysis result display screen shown in FIG. 17, and inputs an observation statement regarding the designated first abnormal shadow.
  • the receiving unit 46B receives, as an input regarding the first abnormal shadow, a remark regarding the first abnormal shadow input by the user, similarly to the receiving unit 46A according to the second embodiment.
  • the extracting unit 52B like the extracting unit 52 according to the second embodiment, extracts the diagnosis name of the first abnormal shadow from the finding text received by the receiving unit 46B.
  • the second analysis unit 48B changes the analysis parameters for the diagnosis name related to the diagnosis name extracted by the extraction unit 52B and performs the first analysis process.
  • the second analysis unit 48B refers to the related diagnosis name table 32 and acquires a diagnosis name related to the diagnosis name extracted by the extraction unit 52B. Then, the second analysis unit 48B changes the analysis parameter for the acquired diagnosis name and performs the first analysis process.
  • the second analysis unit 48B changes the threshold TH1, which is used as an analysis parameter for comparison with the certainty factor of the acquired diagnosis name, to a value smaller than that in the analysis by the first analysis unit 42. A first analysis process is performed.
  • the second analysis unit 48B changes the threshold TH1, which is used for comparison with the certainty factor of the acquired diagnosis name, to a value smaller than that used in the analysis processing by the first analysis unit 42, and then converts the image to be diagnosed.
  • the learned model M1 outputs information representing an area in which an abnormal shadow is present in the input diagnosis target image, the diagnosis name of the abnormal shadow, and the degree of certainty of the diagnosis name.
  • the learned model M1 outputs information representing an area in which an abnormal shadow having a certainty degree of the diagnosis name equal to or higher than the threshold TH1 exists. Therefore, compared with the analysis processing by the first analysis unit 42, the detection sensitivity for the diagnosis name related to the diagnosis name extracted by the extraction unit 52B is higher.
  • the threshold TH1 may be changed to a value larger than that in the analysis processing by the first analysis unit 42. good.
  • the second output unit 50B controls display on the display 23 by outputting the analysis result by the second analysis unit 48B to the display 23 in the same manner as the first output unit 44B.
  • FIG. 18 shows an example of the second analysis result display screen displayed on the display 23 under the control of the second output section 50B.
  • FIG. 18 shows an example in which an abnormal shadow surrounded by a right broken-line rectangle, which was not detected in the example of FIG. 17, is newly detected by the analysis processing by the second analysis unit 48B.
  • the medical image analysis processing shown in FIG. 19 is executed by the CPU 20 executing the medical image analysis program 30 .
  • the medical image analysis processing shown in FIG. 19 is executed, for example, when the user inputs an instruction to start execution. Steps in FIG. 19 that execute the same processing as in FIG. 8 are given the same step numbers and descriptions thereof are omitted.
  • step S14B of FIG. 19 the first output unit 44B outputs the analysis result of step S12 to the display 23, thereby controlling the display on the display 23. At this time, the first output unit 44B controls the display 23 to display information representing the abnormal shadow.
  • the reception unit 46B receives the finding text input by the user for the first abnormal shadow displayed in step S14B.
  • the extraction unit 52B extracts the diagnosis name of the first abnormal shadow from the finding text received in step S16B.
  • step S18B the second analysis unit 48B changes the analysis parameters for the diagnosis name related to the diagnosis name extracted in step S17B and performs the first analysis process as the second analysis process.
  • step S20B the second output unit 50B controls display on the display 23 by outputting the analysis result obtained in step S18B to the display 23. FIG. When the process of step S20B ends, the medical image analysis process ends.
  • a related finding table 34 is stored in the storage unit 22 instead of the related diagnosis name table 32 .
  • FIG. 20 shows an example of the related finding table 34.
  • the related findings table 34 associates findings with findings related to the findings. For example, spicule + is associated with lobed +. This is because spicule + and lobe + have relatively high co-occurrence probabilities.
  • the medical image analysis apparatus 10 includes an acquisition section 40, a first analysis section 42C, a first output section 44C, a reception section 46C, a second analysis section 48C, and a second output section 50C.
  • the CPU 20 functions as an acquisition unit 40, a first analysis unit 42C, a first output unit 44C, a reception unit 46C, a second analysis unit 48C, and a second output unit 50C.
  • the first analysis unit 42C performs analysis processing regarding the region of interest included in the diagnosis target image acquired by the acquisition unit 40. Specifically, first, similarly to the first analysis unit 42 according to the first embodiment, the first analysis unit 42C uses the learned model M1 to determine the abnormality as an example of the region of interest included in the diagnosis target image. Detect shadows.
  • the first analysis unit 42C performs processing for deriving findings using the learned model M3 for deriving findings from images containing abnormal shadows.
  • the trained model M3 is configured by, for example, a CNN that receives an image including an abnormal shadow as input and outputs findings regarding the abnormal shadow included in the image.
  • the learned model M3 is, for example, a model learned by machine learning using, as learning data, many combinations of images containing abnormal shadows and findings of abnormal shadows in the images.
  • the first analysis unit 42C inputs a partial image of an area including an abnormal shadow in the diagnosis target image to the learned model M3.
  • the learned model M3 outputs findings of abnormal shadows included in the input partial image.
  • the learned model M3 outputs findings having a certainty factor of the findings equal to or greater than a predetermined threshold TH2 (for example, 0.5).
  • FIG. 22 shows an example in which five findings are output from the trained model M3.
  • the first output unit 44C controls display on the display 23 by outputting the finding derived by the first analysis unit 42C to the display 23 as the analysis result by the first analysis unit 42C.
  • the user corrects the finding displayed on the display 23 as necessary.
  • 46 C of reception parts receive the input of correction with respect to the finding by a user.
  • the second analysis unit 48C performs analysis processing by changing analysis parameters for findings related to the corrected findings based on the input accepted by the acceptance unit 46C. Specifically, the second analysis unit 48C refers to the related findings table 34 and acquires findings related to the corrected findings. Then, the second analysis unit 48C changes the analysis parameters for the acquired findings and performs analysis processing. In the present embodiment, the second analysis unit 48C changes the threshold TH2, which is used for comparison with the certainty factor of the acquired findings, to a value smaller than that in the analysis by the first analysis unit 42C as an analysis parameter. process.
  • the second analysis unit 48C changes the threshold TH2 used for comparison with the certainty of the acquired finding to a value smaller than that in the analysis processing by the first analysis unit 42C,
  • a partial image of an area containing shadows is input to the trained model M3.
  • the learned model M3 outputs findings of abnormal shadows included in the input partial image.
  • the trained model M3 outputs information representing findings having a certainty factor of the findings equal to or higher than the threshold TH2. Therefore, compared to the analysis processing by the first analysis unit 42C, detection sensitivity for findings related to the corrected findings is increased.
  • the second output unit 50C outputs the finding derived by the second analysis unit 48C to the display 23 as the analysis result by the second analysis unit 48C, thereby controlling the display on the display 23. I do.
  • FIG. 23 shows an example in which "unclear edge" is corrected to "spicula+".
  • the second analysis unit 48C performs the finding derivation process by increasing the detection sensitivity of the finding "lobed +", which is the finding related to the corrected finding "spicula +".
  • FIG. 23 shows an example in which "leaf-shaped +", which was not derived by the analysis processing by the first analysis unit 42C, was derived by the analysis processing by the second analysis unit 48C.
  • the medical image analysis processing shown in FIG. 24 is executed by the CPU 20 executing the medical image analysis program 30 .
  • the medical image analysis processing shown in FIG. 24 is executed, for example, when the user inputs an instruction to start execution. Steps in FIG. 24 that execute the same processing as in FIG. 8 are given the same step numbers, and descriptions thereof are omitted.
  • the first analysis unit 42C uses the learned model M1 to detect abnormal shadows included in the diagnosis target image acquired at step S10, as described above. Then, as described above, the first analysis unit 42C uses the learned model M3 for deriving findings from the image including the detected abnormal shadow as the analysis process to perform the process of deriving findings.
  • the first output unit 44C performs control to display on the display 23 by outputting the finding derived at step S12C to the display 23 as the analysis result at step S12C.
  • the reception unit 46C receives input of correction by the user for the findings displayed in step S14C.
  • the second analysis unit 48C performs analysis processing by changing the analysis parameters for the findings related to the corrected findings based on the input accepted at step S16C, as described above.
  • the second output unit 50C performs control to display on the display 23 by outputting the finding derived at step S18C to the display 23 as the analysis result at step S18C.
  • the diagnosis name of the abnormal shadow is obtained as the analysis result by the first analysis unit 42
  • the present invention is not limited to this.
  • the name of the abnormal shadow, the findings of the abnormal shadow, or the findings of the abnormal shadow may be applied as the analysis result by the first analysis unit 42 .
  • findings in this case include the location, size, permeability (e.g., solidity or frosted glass), presence or absence of spicules, presence or absence of calcification, presence or absence of marginal irregularity, presence or absence of pleural invagination, Or the presence or absence of contact with the chest wall.
  • examples of observation sentences include sentences obtained by inputting a plurality of observations into a recurrent neural network.
  • an abnormal shadow region is applied as a region of interest
  • the present invention is not limited to this.
  • an organ region or an anatomical structure region may be applied.
  • the hardware structure of a processing unit that executes various processes includes the following various processors ( processor) can be used.
  • the various processors include, in addition to the CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, circuits such as FPGAs (Field Programmable Gate Arrays), etc.
  • Programmable Logic Device PLD which is a processor whose configuration can be changed, ASIC (Application Specific Integrated Circuit) etc. Circuits, etc. are included.
  • One processing unit may be composed of one of these various processors, or a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs, a combination of a CPU and an FPGA). combination). Also, a plurality of processing units may be configured by one processor.
  • a single processor is configured by combining one or more CPUs and software.
  • a processor functions as multiple processing units.
  • SoC System on Chip
  • the various processing units are configured using one or more of the above various processors as a hardware structure.
  • an electric circuit combining circuit elements such as semiconductor elements can be used.
  • the medical image analysis program 30 is pre-stored (installed) in the storage unit 22, but the present invention is not limited to this.
  • the medical image analysis program 30 is provided in a form recorded in a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), and a USB (Universal Serial Bus) memory.
  • a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), and a USB (Universal Serial Bus) memory.
  • the medical image analysis program 30 may be downloaded from an external device via a network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Primary Health Care (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Optics & Photonics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
PCT/JP2022/013692 2021-04-05 2022-03-23 医用画像解析装置、医用画像解析方法、及び医用画像解析プログラム Ceased WO2022215529A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2023512927A JPWO2022215529A1 (https=) 2021-04-05 2022-03-23
US18/479,118 US12536659B2 (en) 2021-04-05 2023-10-02 Medical image analysis apparatus, medical image analysis method, and medical image analysis program

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
JP2021-064397 2021-04-05
JP2021064397 2021-04-05
JP2021208524 2021-12-22
JP2021-208524 2021-12-22

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/479,118 Continuation US12536659B2 (en) 2021-04-05 2023-10-02 Medical image analysis apparatus, medical image analysis method, and medical image analysis program

Publications (1)

Publication Number Publication Date
WO2022215529A1 true WO2022215529A1 (ja) 2022-10-13

Family

ID=83545379

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/013692 Ceased WO2022215529A1 (ja) 2021-04-05 2022-03-23 医用画像解析装置、医用画像解析方法、及び医用画像解析プログラム

Country Status (3)

Country Link
US (1) US12536659B2 (https=)
JP (1) JPWO2022215529A1 (https=)
WO (1) WO2022215529A1 (https=)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2024164447A (ja) * 2023-05-15 2024-11-27 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013172940A (ja) * 2011-03-28 2013-09-05 Canon Inc 医療診断支援装置及び医療診断支援方法
JP2017033257A (ja) * 2015-07-31 2017-02-09 キヤノン株式会社 読影レポート作成支援システム、読影レポート作成支援方法、及び読影レポート作成支援プログラム
WO2017221537A1 (ja) * 2016-06-21 2017-12-28 株式会社日立製作所 画像処理装置、及び方法
WO2019008942A1 (ja) * 2017-07-03 2019-01-10 富士フイルム株式会社 医療画像処理装置、内視鏡装置、診断支援装置、医療業務支援装置、及び、レポート作成支援装置
US20200124691A1 (en) * 2018-10-22 2020-04-23 David Douglas Method to modify imaging protocols in real time through implementation of artificial intelligence
US20200211692A1 (en) * 2018-12-31 2020-07-02 GE Precision Healthcare, LLC Facilitating artificial intelligence integration into systems using a distributed learning platform

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112822973B (zh) * 2018-10-10 2025-05-06 佳能株式会社 医学图像处理装置、医学图像处理方法和程序
EP3941333A1 (en) * 2019-03-20 2022-01-26 Carl Zeiss Meditec, Inc. A patient tuned ophthalmic imaging system with single exposure multi-type imaging, improved focusing, and improved angiography image sequence display
JPWO2020209382A1 (https=) 2019-04-11 2020-10-15
JP7346285B2 (ja) * 2019-12-24 2023-09-19 富士フイルム株式会社 医療画像処理装置、内視鏡システム、医療画像処理装置の作動方法及びプログラム
EP4272636A4 (en) * 2020-12-30 2024-09-04 Neurophet Inc. MEDICAL IMAGE ANALYSIS METHOD, MEDICAL IMAGE ANALYSIS DEVICE AND MEDICAL IMAGE ANALYSIS SYSTEM

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013172940A (ja) * 2011-03-28 2013-09-05 Canon Inc 医療診断支援装置及び医療診断支援方法
JP2017033257A (ja) * 2015-07-31 2017-02-09 キヤノン株式会社 読影レポート作成支援システム、読影レポート作成支援方法、及び読影レポート作成支援プログラム
WO2017221537A1 (ja) * 2016-06-21 2017-12-28 株式会社日立製作所 画像処理装置、及び方法
WO2019008942A1 (ja) * 2017-07-03 2019-01-10 富士フイルム株式会社 医療画像処理装置、内視鏡装置、診断支援装置、医療業務支援装置、及び、レポート作成支援装置
US20200124691A1 (en) * 2018-10-22 2020-04-23 David Douglas Method to modify imaging protocols in real time through implementation of artificial intelligence
US20200211692A1 (en) * 2018-12-31 2020-07-02 GE Precision Healthcare, LLC Facilitating artificial intelligence integration into systems using a distributed learning platform

Also Published As

Publication number Publication date
US12536659B2 (en) 2026-01-27
US20240029251A1 (en) 2024-01-25
JPWO2022215529A1 (https=) 2022-10-13

Similar Documents

Publication Publication Date Title
JP2019153250A (ja) 医療文書作成支援装置、方法およびプログラム
EP4321100A1 (en) Medical image device, medical image method, and medical image program
JP6719421B2 (ja) 学習データ生成支援装置および学習データ生成支援方法並びに学習データ生成支援プログラム
US11978274B2 (en) Document creation support apparatus, document creation support method, and document creation support program
US12374443B2 (en) Document creation support apparatus, document creation support method, and program
JP7504987B2 (ja) 情報処理装置、情報処理方法及び情報処理プログラム
US20230005580A1 (en) Document creation support apparatus, method, and program
US20230281810A1 (en) Image display apparatus, method, and program
JP7102509B2 (ja) 医療文書作成支援装置、医療文書作成支援方法、及び医療文書作成支援プログラム
US20220028510A1 (en) Medical document creation apparatus, method, and program
US20230360213A1 (en) Information processing apparatus, method, and program
US12211600B2 (en) Information processing apparatus, information processing method, and information processing program
US20240046028A1 (en) Document creation support apparatus, document creation support method, and document creation support program
US20220076796A1 (en) Medical document creation apparatus, method and program, learning device, method and program, and trained model
WO2020202822A1 (ja) 医療文書作成支援装置、方法およびプログラム
JPWO2019208130A1 (ja) 医療文書作成支援装置、方法およびプログラム、学習済みモデル、並びに学習装置、方法およびプログラム
US12387825B2 (en) Information processing apparatus, information processing method, and information processing program
US20220375562A1 (en) Document creation support apparatus, document creation support method, and program
US12536659B2 (en) Medical image analysis apparatus, medical image analysis method, and medical image analysis program
JP7840933B2 (ja) 文書作成支援装置、文書作成支援方法、及び文書作成支援プログラム
JP7748454B2 (ja) 文書作成支援装置、文書作成支援方法、及び文書作成支援プログラム
WO2022220158A1 (ja) 作業支援装置、作業支援方法、及び作業支援プログラム
WO2022220081A1 (ja) 文書作成支援装置、文書作成支援方法、及び文書作成支援プログラム
WO2023054646A1 (ja) 情報処理装置、情報処理方法及び情報処理プログラム
WO2021172477A1 (ja) 文書作成支援装置、方法およびプログラム

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: 22784514

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023512927

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22784514

Country of ref document: EP

Kind code of ref document: A1