WO2022113801A1 - 医療用画像の異常検出システム及び異常検出方法 - Google Patents
医療用画像の異常検出システム及び異常検出方法 Download PDFInfo
- Publication number
- WO2022113801A1 WO2022113801A1 PCT/JP2021/041902 JP2021041902W WO2022113801A1 WO 2022113801 A1 WO2022113801 A1 WO 2022113801A1 JP 2021041902 W JP2021041902 W JP 2021041902W WO 2022113801 A1 WO2022113801 A1 WO 2022113801A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- medical image
- block
- anatomical structure
- block information
- abnormality detection
- Prior art date
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 87
- 238000001514 detection method Methods 0.000 title claims abstract description 62
- 230000002159 abnormal effect Effects 0.000 claims abstract description 69
- 210000003484 anatomy Anatomy 0.000 claims description 114
- 238000012545 processing Methods 0.000 description 21
- 238000000034 method Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 16
- 210000002376 aorta thoracic Anatomy 0.000 description 11
- 238000011976 chest X-ray Methods 0.000 description 11
- 238000003384 imaging method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 6
- 210000000056 organ Anatomy 0.000 description 6
- 230000002861 ventricular Effects 0.000 description 5
- 206010028980 Neoplasm Diseases 0.000 description 4
- 210000004072 lung Anatomy 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 238000002601 radiography Methods 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 210000005240 left ventricle Anatomy 0.000 description 2
- 210000005245 right atrium Anatomy 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000001746 atrial effect Effects 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012831 peritoneal equilibrium test Methods 0.000 description 1
- 238000012636 positron electron tomography Methods 0.000 description 1
- 238000012877 positron emission topography Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000002603 single-photon emission computed tomography Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- A61B6/46—Arrangements for interfacing with the operator or the patient
- A61B6/461—Displaying means of special interest
- A61B6/463—Displaying means of special interest characterised by displaying multiple images or images and diagnostic data on one display
-
- 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
- A61B6/46—Arrangements for interfacing with the operator or the patient
- A61B6/467—Arrangements for interfacing with the operator or the patient characterised by special input means
- A61B6/468—Arrangements for interfacing with the operator or the patient characterised by special input means allowing annotation or message recording
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
- A61B8/461—Displaying means of special interest
- A61B8/463—Displaying means of special interest characterised by displaying multiple images or images and diagnostic data on one display
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
- A61B8/467—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient characterised by special input means
- A61B8/468—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient characterised by special input means allowing annotation or message recording
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- 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
- 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
-
- 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
- G16H40/60—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 operation of medical equipment or devices
- G16H40/67—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 operation of medical equipment or devices for remote operation
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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]
-
- 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
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/037—Emission tomography
-
- 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; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
- G06V2201/031—Recognition of patterns in medical or anatomical images of internal organs
Definitions
- the present disclosure relates to an abnormality detection system and an abnormality detection method for medical images, and more particularly to a system for detecting the presence or absence of abnormalities in anatomical structures contained in medical images.
- Patent Document 1 a technique for detecting the presence or absence of an abnormality in an anatomical structure such as an organ based on a medical image has been proposed (see, for example, Patent Document 1).
- the region of interest is separated from the medical image by performing image segmentation on the medical image, and the presence or absence of abnormality is determined by the position of the center of gravity, volume, shape, intensity, density, transparency, etc. of the separated region of interest. Judging.
- "abnormal” / "normal” means “abnormal” / "normal” from a medical point of view (that is, diagnostically).
- an object of the present disclosure is to provide an abnormality detection system and an abnormality detection method for medical images capable of detecting the presence or absence of an abnormality in an anatomical structure with higher accuracy.
- the medical image anomaly detection system is anomalous with respect to one pre-specified anatomical structure contained in the medical image based on the medical image.
- An abnormality detection system that detects the presence or absence of a block information indicating a block that is a region in which pixels indicating the anatomical structure are connected in the medical image, and an acquisition unit acquired by the acquisition unit.
- the determination unit includes a determination unit that determines and outputs whether or not the anatomical structure is abnormal based on the number of blocks indicated by the block information, and the determination unit includes the number of blocks indicated by the block information. When it is determined that the anatomical structure is not abnormal, and the number of blocks indicated by the block information is 2 or more, when the blocks indicated by the block information satisfy a predetermined condition. It is determined that the anatomical structure is abnormal.
- the method for detecting an abnormality in a medical image is a pre-specified anatomical structure included in the medical image based on the medical image. It is an abnormality detection method by an abnormality detection system that detects the presence or absence of an abnormality, and is a step of acquiring block information indicating a block that is a region in which pixels indicating the anatomical structure are connected in the medical image, and an acquisition step.
- the determination step includes the determination step of determining whether or not the anatomical structure is abnormal based on the number of blocks indicated by the block information acquired in the acquisition step, and the determination step includes the block information.
- the number of blocks indicated by is 1, it is determined that the anatomical structure is not abnormal, and when the number of blocks indicated by the block information is 2 or more, the block indicated by the block information is predetermined. When the conditions are met, it is determined that the anatomical structure is abnormal.
- the present disclosure provides an abnormality detection system for medical images and an abnormality detection method capable of detecting the presence or absence of an abnormality in an anatomical structure with higher accuracy.
- FIG. 1 is a block diagram showing a configuration of a diagnostic support system according to an embodiment.
- FIG. 2A is a diagram showing an example of an anatomical structure in a medical image.
- FIG. 2B is a diagram showing another example of an anatomical structure in a medical image.
- FIG. 2C is a diagram showing another example of an anatomical structure in a medical image.
- FIG. 2D is a diagram showing another example of an anatomical structure in a medical image.
- FIG. 3 is a flowchart showing the main operation of the abnormality detection system in FIG.
- FIG. 4 is a flowchart showing a specific example of step S23 in FIG. FIG.
- FIG. 5 is a schematic diagram showing an example of an anatomical structure in a medical image for explaining an example of the result of the determination shown in FIGS. 3 and 4.
- FIG. 6 is a diagram showing the results of an experiment using a case for evaluating the determination shown in FIG.
- FIG. 7 is a flowchart showing another specific example of step S23 in FIG.
- FIG. 8A is a schematic diagram showing an example of an anatomical structure in a medical image for explaining an example of the result of the determination shown in FIGS. 3 and 7.
- FIG. 8B is a diagram showing an example of imaging an an anatomical structure in a medical image for explaining an example of the result of the determination shown in FIG. 7.
- FIG. 9 is a flowchart showing still another specific example of step S23 in FIG.
- FIG. 10A is a flowchart showing a method of determining a first threshold value used for determination using the area shown in FIG.
- FIG. 10B is a flowchart showing a method of determining the second threshold value
- FIG. 1 is a block diagram showing a configuration of the diagnostic support system 10 according to the embodiment.
- the diagnosis support system 10 is a system that assists doctors in efficiently diagnosing anatomical structures based on medical images, and is an imaging device 20, an image server 30, and an image server 30 connected by a communication path such as the Internet. It includes a viewer device 40 and an abnormality detection system 50.
- the imaging device 20 is an apparatus that generates a medical image 31a by photographing a human anatomical structure, and in the present embodiment, a chest X-ray image is generated as a medical image on the image server 30. It is an X-ray imaging device to be stored.
- the medical image is not limited to the chest X-ray image, but may be an X-ray image of another part, CT scan, PET / CT scan, SPECT scan, MRI, ultrasound, X-ray, breast. It may be an image provided by radiography, radiography, radiography, or a combination thereof.
- the image server 30 holds the medical image 31a generated by the imaging device 20 and the detected medical image 32a generated by the abnormality detection system 50, and the viewer device holds the medical image 32b. It is a data server provided to 40, and is, for example, a computer device provided with storage such as a hard disk.
- the data exchanged with the other device by the image server 30 may include not only the medical image but also various information (shooting date / time, information about the patient, detection result, etc.) associated with the medical image.
- the viewer device 40 displays the medical image 32b held in the image server 30 and various information associated with the medical image in various modes according to instructions from the user obtained via the GUI (Graphical User Interface). It is a device, for example, a computer device including a display, an input device such as a mouse, and a peripheral device such as a storage device such as a hard disk.
- the abnormality detection system 50 detects the presence or absence of a medical abnormality in one pre-specified anatomical structure included in the medical image based on the medical image 31b to be detected acquired from the image server 30. It is a system and includes a block information generation unit 51, an acquisition unit 52, a determination unit 53, and an image processing unit 54.
- the block information generation unit 51 generates block information indicating a block, which is a region in which pixels indicating an anatomical structure included in the medical image 31b are connected, from the medical image 31b to be detected acquired from the image server 30. That is, the medical image 31b is subjected to a labeling process and separated into a mass of images.
- the block information is not limited to a specific format as long as it is information that identifies individual blocks in the medical image 31b.
- the block information is information that distinguishes pixels belonging to individual blocks in the medical image 31b from other pixels (for example, the pixels constituting the block are "1" and the other pixels are "0". It may be (binary image) or information indicating the characteristics of individual blocks (for example, the area of each block obtained by analyzing the binary image, contour information, etc.).
- the acquisition unit 52 acquires the block information generated by the block information generation unit 51.
- the determination unit 53 determines and outputs whether or not the anatomical structure included in the medical image 31b is abnormal based on the number of blocks indicated by the block information acquired by the acquisition unit 52. At this time, the determination unit 53 recognizes that when the number of blocks indicated by the block information is 1, the anatomical structure that should be originally detected as one block is detected as one block, and the medical treatment is performed. It is determined that the anatomical structure contained in the image 31b is not abnormal. On the other hand, when the number of blocks indicated by the block information is 2 or more and the block indicated by the block information satisfies a predetermined condition, the determination unit 53 is originally one block instead of noise on the image or image processing. It is recognized that the anatomical structure to be detected is separated into two or more, and it is determined that the anatomical structure included in the medical image 31b is abnormal.
- the predetermined condition is, for example, a condition relating to the block having the second largest area in the medical image 31b among the two or more blocks indicated by the block information. More specifically, the predetermined condition is that, of the two or more blocks indicated by the block information, the block having the second largest area in the medical image 31b has an area of the first threshold value or more.
- the predetermined condition is, for example, that the minimum value of the distance in the medical image 31b between the block having the largest area in the medical image 31b and each of the other blocks among the two or more blocks indicated by the block information is set. It is below the second threshold. At this time, the predetermined condition may further include that, of the two or more blocks indicated by the block information, the block having the second largest area in the medical image 31b has an area of the first threshold value or more.
- the image processing unit 54 generates the detected medical image 32a by reflecting the determination result by the determination unit 53 on the medical image 31b to be detected, and stores it in the image server 30.
- the block information generation unit 51, acquisition unit 52, determination unit 53, and image processing unit 54 constituting the abnormality detection system 50 are specifically a non-volatile memory for holding a program and volatile as a temporary work area. It is realized by at least one computer including a memory, a processor for executing a program, an input / output circuit including a communication interface and a communication port, and the like.
- the block information generation unit 51, the acquisition unit 52, the determination unit 53, and the image processing unit 54 constituting the abnormality detection system 50 may be realized by one computer or an image processing device, or may be connected by a communication path. It may be realized in a distributed manner by a plurality of computers or image processing devices.
- diagnosis support system 10 is composed of an imaging device 20, an image server 30, a viewer device 40, and an abnormality detection system 50 connected by a communication path, but all or a part of these components is one. It may be assembled as a device.
- the abnormality detection system 50 does not necessarily have to include the block information generation unit 51 and the image processing unit 54, but may include at least the acquisition unit 52 and the determination unit 53. Even with such a configuration, it is possible to detect the presence or absence of an abnormality in the anatomical structure contained in the medical image. On the contrary, the abnormality detection system 50 may have at least one function of the photographing device 20, the image server 30, and the viewer device 40.
- FIGS. 2A to 2D are diagrams showing examples of anatomical structures (that is, examples of seven types of anatomical structures in total) in medical images (that is, included in medical images). More specifically, FIGS. 2A-2D show, as examples of anatomical structures, the right atrioventricular and left ventricular shadows, the descending aorta shadow, the right diaphragm dome shadow and the left diaphragm dome shadow, the right lateral lung shadow and the left, respectively. Shows lateral lung shadow. In each table of FIGS.
- a chest X-ray image in order from the left, a chest X-ray image, an anatomical structure name, an area of an anatomical structure, and an example of superimposition of a chest X-ray image and an anatomical structure. It is shown.
- the anatomical structures on the chest X-ray image are, as shown in FIGS. 2A to 2C, a right atrial shadow, a left ventricular shadow, a descending aorta shadow, a diaphragm dome shadow, and the like.
- the right atrium shadow is a boundary line drawn at the boundary between the right atrium and its surroundings on the chest X-ray image.
- the left ventricle shadow is a boundary line drawn at the boundary between the left ventricle and its surroundings on a chest X-ray image.
- the descending aorta shadow is a borderline drawn on the chest X-ray image at the boundary between the descending aorta and its surroundings.
- the diaphragm dome shadow is a boundary line drawn at the boundary between the diaphragm and its surroundings on a chest X-ray image.
- the anatomical structures on the chest X-ray image are not limited to these.
- the anatomical structure may be, for example, a shadow on the outer edge of the lung, which is the boundary drawn at the boundary between the outer part of the lung and its periphery on the chest radiograph, as shown in FIG. 2D. , Other structures or shadows of organs, etc.
- the anatomical structure is not limited to the structure included in the chest X-ray image, but the structure included in the medical image taken by other imaging devices such as CT image and MRI image. May be.
- diagnosis support system 10 configured as described above will be described focusing on the operation of the characteristic abnormality detection system 50 constituting the diagnosis support system 10.
- FIG. 3 is a flowchart showing the main operation (that is, the abnormality detection method) of the abnormality detection system 50 in FIG.
- FIG. 3A shows the main operation flow of the abnormality detection system 50
- FIG. 3B shows the details of step S2 in FIG. 3A.
- the acquisition unit 52 acquires the block information generated by the block information generation unit 51 (acquisition step S1).
- the determination unit 53 determines and outputs whether or not the anatomical structure included in the medical image is abnormal based on the number of blocks indicated by the block information acquired by the acquisition unit 52 ( Judgment step S2). More specifically, the determination unit 53 determines the number of blocks indicated by the block information (S21), and when the number of blocks is 1 (Yes in S21), the anatomical unit should be detected as one block. It is recognized that the structure is detected as one block, and it is determined that the anatomical structure included in the medical image is not abnormal (S22).
- the determination unit 53 determines whether or not the block indicated by the block information satisfies a predetermined condition when the number of blocks indicated by the block information is 2 or more (S23), and when the predetermined condition is satisfied. (Yes in S23), the anatomy included in the medical image, recognizing that the anatomical structure that should be detected as one block, not the noise on the image or image processing, is separated into two or more. An anatomical structure that should be detected as one block by noise on the image or image processing when it is determined that the structural structure is abnormal (S24) and the predetermined conditions are not satisfied (No in S23). It is recognized that the object is separated into two or more, and it is determined that the anatomical structure included in the medical image is not abnormal (S22).
- FIG. 4 is a flowchart showing a specific example of step S23 (determination of whether or not a predetermined condition is satisfied) in FIG.
- the determination unit 53 determines whether or not a predetermined condition is satisfied, and the block having the second largest area in the medical image is the second block among the two or more blocks indicated by the block information. It is determined whether or not the area has one threshold value or more (S23a).
- the determination unit 53 is essentially one rather than noise on the image or image processing. It is recognized that the anatomical structure to be detected as a block is separated into two or more, and it is determined that the anatomical structure included in the medical image is abnormal (to S24 in FIG. 3).
- the determination unit 53 originally has one due to noise on the image or image processing. It is recognized that the anatomical structure to be detected as a block is separated into two or more, and it is determined that the anatomical structure included in the medical image is not abnormal (to S22 in FIG. 3).
- FIG. 5 is a schematic diagram showing an example of an anatomical structure (here, a descending aorta shadow) in a medical image for explaining an example of the result of the determination shown in FIGS. 3 and 4. More specifically, FIG. 5A shows an example of a descending aortic shadow that is determined to be “not abnormal” because it was detected as one block 60 (Yes in step S21 of FIG. 3). (B) of FIG. 5 is detected as two blocks 60a and 60b (No in step S21 of FIG. 3), and the second largest block 60a has an area equal to or larger than the first threshold value (FIG. 4). Yes) in step S23a, an example of a descending aortic shadow determined to be "abnormal" is shown. FIG.
- step S23a of 4 an example of a descending aortic shadow determined to be “not abnormal” is shown.
- FIG. 6 is a diagram showing the results of an experiment using a case for evaluating the determination shown in FIG. More specifically, FIG. 6A shows the ROC curve (receiver operating characteristic curve) when the presence or absence of abnormality is determined by using the right tuft shadow as an anatomical structure, and FIG. 6B shows the left. The ROC curve when the presence or absence of abnormality is determined by using the chamber shadow as an anatomical structure is shown, and FIG. 6 (c) shows the ROC curve when determining the presence or absence of abnormality by using the descending aortic shadow as an anatomical structure. 6 (d) is a diagram showing the threshold selection result and AUC (Area Under the Curve) of the ROC curve shown in FIGS. 6 (a) to 6 (c).
- AUC Average Under the Curve
- the horizontal axis indicates the false positive rate (that is, the probability that the abnormality detection system 50 determines that a case known to be normal is abnormal (1-specificity). )), And the vertical axis shows the positive rate (that is, the probability (sensitivity) that the abnormality detection system 50 determines that the case known to be abnormal is abnormal).
- These ROC curves are plots of the determination results by the abnormality detection system 50 obtained by changing the first threshold value used for the determination shown in FIG. 4 for a plurality of cases in which normality and abnormality are known. be.
- the ROC curve is a curve that passes through a position closer to the upper left corner, indicating that the correct judgment can be made for the case.
- the judgment accuracy for the cases related to the left ventricular shadow and the descending aorta shadow shown in FIGS. 6 (b) and 6 (c) is improved as compared with the judgment accuracy based on the conventional image processing. It turns out that.
- This is conventionally determined by a method of determining anomaly / normal for one anatomical structure based on the number of blocks extracted from the medical image and the size of the block with the second largest area.
- the correct judgment can be made even in the case where it is difficult (for example, in the medical image, a part of the normal structure of the organ is overlapped with other abnormal substances such as tumor and water). ..
- the first threshold value corresponding to the point closest to the upper left corner black point in (a) to (c) of FIG. 6) can be said to be the most suitable as the threshold value used for the determination shown in FIG.
- the threshold value used for judgment in the ROC curve There are several methods for selecting the threshold value used for judgment in the ROC curve. For example, it is a method of selecting the point on the ROC curve where the value of the positive rate + (1-false positive rate) is the largest (the black point in (a) to (c) of FIG. 6). Positive rate + (1-false positive rate) is called Youden Index, and it is a method of selecting the point where it becomes the maximum. Another method is to select a point where the positive rate is the target value (for example, 0.9), or a point where the false positive rate is the target value (for example, 0.1). ..
- FIG. 7 is a flowchart showing another specific example of step S23 (determination of whether or not a predetermined condition is satisfied) in FIG.
- the determination unit 53 determines whether or not a predetermined condition is satisfied, the block having the largest area in the medical image and the other block among the two or more blocks indicated by the block information. It is determined whether or not the minimum value of the distance in the medical image with each of the above is equal to or less than the second threshold value (S23b).
- the determination unit 53 determines that the minimum value of the distance between the block having the largest area in the medical image and each of the other blocks in the medical image is equal to or less than the second threshold value (Yes in S23b). , Recognizes that the anatomical structure that should be detected as one block, not the noise on the image or image processing, is separated into two or more, and the anatomical structure contained in the medical image is abnormal. (To S24 in FIG. 3).
- the determination unit 53 determines the image (No in S23b). Recognizes that the anatomical structure that should be detected as one block is separated into two or more due to noise on the top or image processing, and determines that the anatomical structure contained in the medical image is not abnormal. (To S22 in FIG. 3).
- FIG. 8A is a schematic diagram showing an example of an anatomical structure (here, a descending aorta shadow) in a medical image for explaining an example of the result of the determination shown in FIGS. 3 and 7. More specifically, (a) of FIG. 8A shows an example of a descending aortic shadow that is determined to be "not abnormal" because it was detected as one block 60 (Yes in step S21 of FIG. 3). (B) of FIG. 8A is detected as two blocks 60c and 60d (No in step S21 of FIG. 3), and each of the block 60d and the other block having the largest area in the medical image (here, the block).
- an anatomical structure here, a descending aorta shadow
- FIG. 8B is a diagram showing an actual imaging example of an anatomical structure (here, a descending aorta shadow) in a medical image for explaining an example of the result of the determination shown in FIG. 7.
- FIG. 8B shows an image of the descending aorta shadow actually extracted as a block.
- 8B (a) to 8B show medical treatment with the block having the largest area in the medical image (here, 70b, 70d, 70f) and each of the other blocks (here, 70a, 70c, 70e).
- FIG. 8B (d). Is that the minimum value of the distance in the medical image between the block having the largest area in the medical image (here, 70h) and the other blocks (here, 70g), 70i) is equal to or less than the second threshold value. (No in step S23b of FIG. 7), an example of a descending aorta shadow that is correctly determined to be "abnormal" is shown.
- the blocks 70a and 70b shown in FIG. 8B (a) are the detection results of the descending aortic shadow, and show an example in which a break occurs but it is determined to be “not abnormal”.
- Blocks 70c and 70d shown in FIG. 8B (b) are the detection results of the diaphragm dome shadow on the right side, and show an example in which a break is generated but it is determined to be “not abnormal”.
- Blocks 70e and 70f shown in FIG. 8B (c) are the detection results of the left ventricular shadow, and show an example in which a break occurs but it is determined to be “not abnormal”.
- the block 70g, the block 70h, and the block 70i shown in FIG. 8B (d) are different detection results of the left ventricular shadow, and show an example of being determined to be "abnormal" because a small break is generated. ..
- step S23 determination of whether or not a predetermined condition is satisfied
- the determination is limited to the determination using the area shown in FIG. 4 and the determination using the distance shown in FIG. I can't.
- the determination may be made using both the determination using the area and the determination using the distance.
- FIG. 9 is a flowchart showing an example of a determination using both the determination using the area and the determination using the distance. That is, FIG. 9 is a flowchart showing still another specific example of step S23 (determination of whether or not a predetermined condition is satisfied) in FIG.
- the determination unit 53 first determines whether or not a predetermined condition is satisfied, and the block having the second largest area in the medical image among the two or more blocks indicated by the block information. Determines whether or not has an area equal to or greater than the first threshold value (S23a).
- the determination unit 53 is originally one due to noise on the image or image processing. It is recognized that the anatomical structure to be detected as one block is separated into two or more, and it is determined that the anatomical structure included in the medical image is not abnormal (to S22 in FIG. 3).
- the determination unit 53 subsequently performs among the two or more blocks indicated by the block information. It is determined whether or not the minimum value of the distance in the medical image between the block having the largest area in the medical image and each of the other blocks is equal to or less than the second threshold value (S23b).
- the determination unit 53 determines that the minimum value of the distance between the block having the largest area in the medical image and each of the other blocks in the medical image is equal to or less than the second threshold value (Yes in S23b). , Recognizes that the anatomical structure that should be detected as one block, not the noise on the image or image processing, is separated into two or more, and the anatomical structure contained in the medical image is abnormal. (To S24 in FIG. 3).
- the determination unit 53 determines the image (No in S23b). Recognizes that the anatomical structure that should be detected as one block is separated into two or more due to noise on the top or image processing, and determines that the anatomical structure contained in the medical image is not abnormal. (To S22 in FIG. 3).
- the anatomical structure included in the medical image is found when the condition for the area is satisfied (Yes in S23a) and the condition for the distance is satisfied (Yes in S23b). It was determined to be abnormal, and in other cases, the anatomical structure contained in the medical image was determined not to be abnormal, but instead, the condition for area (S23a) and the distance When at least one of the conditions (S23b) is satisfied, the anatomical structure contained in the medical image is determined to be abnormal, and in other cases, the anatomical structure contained in the medical image is determined to be abnormal. It may be determined that it is not abnormal.
- step S23 determination of whether or not a predetermined condition is satisfied
- FIG. 3 which of the determination examples shown in FIGS. 4, 7, 9, and the like is adopted is the target of determination.
- the judgment method with the highest accuracy of abnormal / normal judgment is determined. You may.
- FIG. 10A is a flowchart showing a method of determining a first threshold value used for determination using the area shown in FIG.
- the determination unit 53 determines whether or not the predetermined condition is satisfied, and the area in the medical image is the second largest among the two or more blocks indicated by the block information. Whether or not the block has an area equal to or larger than the first threshold value is determined, and the method for determining the first threshold value used at that time is as follows.
- the abnormality detection system 50 is made to make a judgment by changing the first threshold value used for the judgment shown in FIG. ) Is calculated (S30).
- the first threshold value corresponding to the point closest to the upper left corner is determined as the threshold value used for the determination shown in FIG. 4 (S31).
- FIG. 10B is a flowchart showing a method of determining a second threshold value used for determination using the distance shown in FIG. 7.
- the determination unit 53 determines whether or not the predetermined condition is satisfied with the block having the largest area in the medical image among the two or more blocks indicated by the block information. It is determined whether or not the minimum value of the distance in the medical image with each of the other blocks is equal to or less than the second threshold value, and the method for determining the second threshold value used at that time is as follows. ..
- the abnormality detection system 50 is made to make a judgment by changing the second threshold value used for the judgment shown in FIG. 7, thereby (a) to (c) of FIG. ) Is calculated (S40).
- the second threshold value corresponding to the point closest to the upper left corner is determined as the threshold value used for the determination shown in FIG. 7 (S41).
- the method for determining the first threshold value shown in FIG. 10A and the method for determining the second threshold value shown in FIG. 10B obtain ROC curves for distinguishing between abnormal and normal anatomical structures. It can be said that this is an example of a determination step for determining a predetermined condition (here, a first threshold value and a second threshold value) based on the acquired ROC curve.
- the abnormality detection system 50 constituting the diagnosis support system 10 has an abnormality in one pre-specified anatomical structure included in the medical image based on the medical image.
- the acquisition unit 52 that acquires block information indicating a block that is a region in which pixels indicating an anatomical structure are connected in a medical image, which is a system for detecting the presence or absence, and the block information acquired by the acquisition unit 52 indicate.
- the determination unit 53 includes a determination unit 53 that determines whether or not the anatomical structure is abnormal based on the number of blocks and outputs the determination unit 53 when the number of blocks indicated by the block information is 1. When it is determined that the anatomical structure is not abnormal and the number of blocks indicated by the block information is 2 or more, and the blocks indicated by the block information satisfy a predetermined condition, the anatomical structure is abnormal. Is determined.
- the presence or absence of an abnormality is determined based on whether or not the anatomical structure that should originally be detected as one block is detected as one block, so that it is difficult to determine in the past (for example, for medical use). Even in the case where a part of the normal structure of an organ is overlapped with other abnormal things such as tumor and water in the image), correct judgment is possible. Therefore, the presence or absence of abnormalities in the anatomical structure can be detected with higher accuracy than before.
- the predetermined condition is a condition relating to the block having the second largest area in the medical image among the two or more blocks indicated by the block information. More specifically, the predetermined condition is that, of the two or more blocks indicated by the block information, the block having the second largest area in the medical image has an area equal to or larger than the first threshold value.
- the determination accuracy of the determination unit 53 is improved as compared with the determination accuracy based on the conventional image processing.
- the predetermined condition among the two or more blocks indicated by the block information, the minimum value of the distance in the medical image between the block having the largest area in the medical image and each of the other blocks is equal to or less than the second threshold value. It may be.
- the predetermined condition may be that, of the two or more blocks indicated by the block information, the block having the second largest area in the medical image has an area of the first threshold value or more.
- the abnormality / normality of the anatomical structure is determined based on the information on what kind of multiple blocks the anatomical structure that should originally be detected as one block is detected. Even in difficult cases, it may be possible to make a correct judgment.
- the first threshold value may be a value obtained in advance for various areas and determined depending on the ROC curve for distinguishing between abnormal and normal anatomical structures.
- the second threshold may be a value preliminarily obtained for various distances that is determined depending on the ROC curve for distinguishing between abnormal and normal anatomical structures.
- the first threshold value and the second threshold value are determined from the ROC curve obtained for the case in which the abnormality / normality is known in advance, so that the presence or absence of the abnormality in the anatomical structure is detected with high accuracy.
- the abnormality detection method is an abnormality detection by an abnormality detection system 50 that detects the presence or absence of an abnormality in one pre-specified anatomical structure included in the medical image based on the medical image. It is a method, and the number of blocks indicated by the block information acquired in the acquisition step S1 and the acquisition step S1 for acquiring the block information indicating the block which is the area where the pixels indicating the anatomical structure are connected in the medical image. Including the determination step S2 for determining whether or not the anatomical structure is abnormal based on the determination step S2, in the determination step S2, when the number of blocks indicated by the block information is 1, the anatomical structure is included. It is determined that the object is not abnormal, and when the number of blocks indicated by the block information is 2 or more and the blocks indicated by the block information satisfy a predetermined condition, it is determined that the anatomical structure is abnormal.
- the presence or absence of an abnormality is determined based on whether or not the anatomical structure that should originally be detected as one block is detected as one block, so that it is difficult to determine in the past (for example, for medical use). Even in the case where a part of the normal structure of an organ is overlapped with other abnormal things such as tumor and water in the image), correct judgment is possible. Therefore, the presence or absence of abnormalities in the anatomical structure can be detected with higher accuracy than before.
- a determination step in which an ROC curve for distinguishing between an abnormality and a normality of an anatomical structure is acquired and a predetermined condition is determined based on the acquired ROC curve. May include.
- predetermined conditions including the first threshold value and the second threshold value are determined from the ROC curve obtained for the case in which the abnormality / normality is known in advance, so that the anatomical structure is abnormal with high accuracy. The presence or absence of is detected.
- the diagnostic support system, the abnormality detection system for medical images, and the abnormality detection method of the present disclosure have been described above based on the embodiment, but the present disclosure is not limited to this embodiment. As long as it does not deviate from the gist of the present disclosure, various modifications that can be conceived by those skilled in the art are applied to the present embodiment, and other forms constructed by combining some components in the embodiment are also within the scope of the present disclosure. Included in.
- the present disclosure may be realized as a program for executing the steps included in the abnormality detection method in the above embodiment, or as a computer-readable non-temporary recording medium such as a DVD on which the program is recorded. You may.
- the program may be stored in one storage device, or may be distributed and stored in a plurality of storage devices. Further, the program may be executed by one computer or may be executed in a distributed manner by a plurality of computers connected by a communication path.
- the abnormality detection method in the above embodiment includes steps by the acquisition unit 52 and the determination unit 53, but the steps are not limited to these steps, and the block information generation unit 51, the image processing unit 54, and the photographing device 20 are not limited to these steps. And at least one of the processes by the viewer device 40 may be included.
- a plurality of determination examples are shown as predetermined conditions, but these plurality of determination examples may be determined by the abnormality detection system 50 based on instructions from the user, or may be used for medical purposes.
- the abnormality detection system 50 may automatically determine and update the determination example having the highest hit rate in the past according to the type of image or anatomical structure.
- the first threshold value and the second threshold value used under the predetermined conditions are determined to be values corresponding to the points closest to the upper left corner in the ROC curve, but to another point close to that point. It may be determined or may be selected by the user from multiple points near the upper left corner.
- the abnormality detection system and abnormality detection method for medical images are systems for detecting the presence or absence of abnormalities in anatomical structures contained in medical images, for example, a doctor efficiently diagnoses a disease. It can be used as a system to support.
- Diagnosis support system 20 Imaging device 30 Image server 31a, 31b, 32a, 32b Medical image 40 Viewer device 50 Abnormality detection system 51 Block information generation unit 52 Acquisition unit 53 Judgment unit 54 Image processing unit 60, 60a to 60f, 70a to 70f block
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- Optics & Photonics (AREA)
- High Energy & Nuclear Physics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Physiology (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
Description
20 撮影装置
30 画像サーバ
31a、31b、32a、32b 医療用画像
40 ビューワ装置
50 異常検出システム
51 ブロック情報生成部
52 取得部
53 判定部
54 画像処理部
60、60a~60f、70a~70f ブロック
Claims (9)
- 医療用画像に基づいて前記医療用画像に含まれる予め特定された一の解剖学的構造物について異常の有無を検出する異常検出システムであって、
前記医療用画像において前記解剖学的構造物を示す画素が繋がった領域であるブロックを示すブロック情報を取得する取得部と、
前記取得部が取得した前記ブロック情報が示すブロックの数に基づいて前記解剖学的構造物が異常であるか否かを判定して出力する判定部とを備え、
前記判定部は、前記ブロック情報が示すブロックの数が1である場合に、前記解剖学的構造物が異常でないと判定し、前記ブロック情報が示すブロックの数が2以上である場合に、前記ブロック情報が示すブロックが所定の条件を満たすときに、前記解剖学的構造物が異常であると判定する、
異常検出システム。 - 前記所定の条件は、前記ブロック情報が示す2以上のブロックのうち、前記医療用画像における面積が2番目に大きいブロックに関する条件である、
請求項1記載の異常検出システム。 - 前記所定の条件は、前記ブロック情報が示す2以上のブロックのうち、前記医療用画像における面積が2番目に大きいブロックが第1閾値以上の面積を有することである、
請求項2記載の異常検出システム。 - 前記所定の条件は、前記ブロック情報が示す2以上のブロックのうち、前記医療用画像における面積が最も大きいブロックと他のブロックのそれぞれとの前記医療用画像における距離のうちの最小値が第2閾値以下であることである、
請求項1記載の異常検出システム。 - 前記所定の条件は、さらに、前記ブロック情報が示す2以上のブロックのうち、前記医療用画像における面積が2番目に大きいブロックが第1閾値以上の面積を有することである、
請求項4記載の異常検出システム。 - 前記第1閾値は、様々な前記面積について予め得られる、前記解剖学的構造物の異常と正常とを区別するためのROC曲線(receiver operating characteristic curve)に依存して定まる値である、
請求項3又は5記載の異常検出システム。 - 前記第2閾値は、様々な前記距離について予め得られる、前記解剖学的構造物の異常と正常とを区別するためのROC曲線に依存して定まる値である、
請求項4記載の異常検出システム。 - 医療用画像に基づいて前記医療用画像に含まれる予め特定された一の解剖学的構造物について異常の有無を検出する異常検出システムによる異常検出方法であって、
前記医療用画像において前記解剖学的構造物を示す画素が繋がった領域であるブロックを示すブロック情報を取得する取得ステップと、
前記取得ステップで取得した前記ブロック情報が示すブロックの数に基づいて前記解剖学的構造物が異常であるか否かを判定して出力する判定ステップとを含み、
前記判定ステップでは、前記ブロック情報が示すブロックの数が1である場合に、前記解剖学的構造物が異常でないと判定し、前記ブロック情報が示すブロックの数が2以上である場合に、前記ブロック情報が示すブロックが所定の条件を満たすときに、前記解剖学的構造物が異常であると判定する、
異常検出方法。 - さらに、前記解剖学的構造物の異常と正常とを区別するためのROC曲線を取得し、取得した前記ROC曲線に基づいて、前記所定の条件を決定する決定ステップを含む、
請求項8記載の異常検出方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180077325.8A CN116490130A (zh) | 2020-11-25 | 2021-11-15 | 医学图像的异常检测系统以及异常检测方法 |
JP2022565238A JPWO2022113801A1 (ja) | 2020-11-25 | 2021-11-15 | |
EP21897775.9A EP4252657A4 (en) | 2020-11-25 | 2021-11-15 | SYSTEM FOR DETECTING ANOMALIES IN A MEDICAL IMAGE AND METHOD FOR DETECTING ANOMALIES |
US18/200,693 US20230289965A1 (en) | 2020-11-25 | 2023-05-23 | Medical image abnormality detection system and abnormality detection method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020-195390 | 2020-11-25 | ||
JP2020195390 | 2020-11-25 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/200,693 Continuation US20230289965A1 (en) | 2020-11-25 | 2023-05-23 | Medical image abnormality detection system and abnormality detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022113801A1 true WO2022113801A1 (ja) | 2022-06-02 |
Family
ID=81755996
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/041902 WO2022113801A1 (ja) | 2020-11-25 | 2021-11-15 | 医療用画像の異常検出システム及び異常検出方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20230289965A1 (ja) |
EP (1) | EP4252657A4 (ja) |
JP (1) | JPWO2022113801A1 (ja) |
CN (1) | CN116490130A (ja) |
WO (1) | WO2022113801A1 (ja) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20230305551A1 (en) * | 2022-03-25 | 2023-09-28 | Yokogawa Electric Corporation | Method and system for automated fault detection |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010087112A1 (ja) * | 2009-01-27 | 2010-08-05 | 国立大学法人大阪大学 | 画像解析装置、画像解析方法、画像解析プログラムおよび記録媒体 |
WO2018088055A1 (ja) * | 2016-11-09 | 2018-05-17 | キヤノン株式会社 | 画像処理装置、画像処理方法、画像処理システム及びプログラム |
WO2019102829A1 (ja) * | 2017-11-24 | 2019-05-31 | 国立大学法人大阪大学 | 画像解析方法、画像解析装置、画像解析システム、画像解析プログラム、記録媒体 |
CN110555850A (zh) * | 2018-06-04 | 2019-12-10 | 青岛海信医疗设备股份有限公司 | 识别图像中肋骨区域的方法、装置、电子设备和存储介质 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5615243A (en) * | 1996-03-12 | 1997-03-25 | University Of Pittsburgh | Identification of suspicious mass regions in mammograms |
US20100168665A1 (en) * | 2008-12-30 | 2010-07-01 | Wilson-Cook Medical Inc. | Segmented balloon for catheter tip deflection |
-
2021
- 2021-11-15 WO PCT/JP2021/041902 patent/WO2022113801A1/ja active Application Filing
- 2021-11-15 CN CN202180077325.8A patent/CN116490130A/zh active Pending
- 2021-11-15 JP JP2022565238A patent/JPWO2022113801A1/ja active Pending
- 2021-11-15 EP EP21897775.9A patent/EP4252657A4/en active Pending
-
2023
- 2023-05-23 US US18/200,693 patent/US20230289965A1/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010087112A1 (ja) * | 2009-01-27 | 2010-08-05 | 国立大学法人大阪大学 | 画像解析装置、画像解析方法、画像解析プログラムおよび記録媒体 |
WO2018088055A1 (ja) * | 2016-11-09 | 2018-05-17 | キヤノン株式会社 | 画像処理装置、画像処理方法、画像処理システム及びプログラム |
WO2019102829A1 (ja) * | 2017-11-24 | 2019-05-31 | 国立大学法人大阪大学 | 画像解析方法、画像解析装置、画像解析システム、画像解析プログラム、記録媒体 |
CN110555850A (zh) * | 2018-06-04 | 2019-12-10 | 青岛海信医疗设备股份有限公司 | 识别图像中肋骨区域的方法、装置、电子设备和存储介质 |
Non-Patent Citations (2)
Title |
---|
HIDEO SHIMIZU: "Three-dimensional Structure of Sinusoids of Normal Human Liver and Hepatocellular Carcinoma", MEDICAL IMAGING TECHNOLOGY, vol. 15, no. 5, 1 September 1997 (1997-09-01), JP , pages 597 - 602, XP008169037, ISSN: 0288-450X * |
See also references of EP4252657A4 |
Also Published As
Publication number | Publication date |
---|---|
EP4252657A4 (en) | 2024-01-24 |
JPWO2022113801A1 (ja) | 2022-06-02 |
EP4252657A1 (en) | 2023-10-04 |
US20230289965A1 (en) | 2023-09-14 |
CN116490130A (zh) | 2023-07-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10846853B2 (en) | Medical image processing apparatus, medical image processing method, and medical image processing program | |
KR101887194B1 (ko) | 피검체의 의료 영상의 판독을 지원하는 방법 및 이를 이용한 장치 | |
US9536316B2 (en) | Apparatus and method for lesion segmentation and detection in medical images | |
US10997475B2 (en) | COPD classification with machine-trained abnormality detection | |
KR101874348B1 (ko) | 피검체의 흉부 pa 영상의 판독을 지원하는 방법 및 이를 이용한 장치 | |
CN101231678B (zh) | 医用图像处理装置及医用图像处理方法 | |
US20150173705A1 (en) | Apparatus and method for adapting diagnostic model for computer-aided diagnosis | |
JP2020511190A (ja) | 超音波分析のためのシステムおよび方法 | |
US20220366562A1 (en) | Medical image analysis apparatus and method, and medical image visualization apparatus and method | |
JP2019033966A (ja) | 画像処理装置、画像処理方法、及び画像処理プログラム | |
US20120166211A1 (en) | Method and apparatus for aiding imaging diagnosis using medical image, and image diagnosis aiding system for performing the method | |
US10290101B1 (en) | Heat map based medical image diagnostic mechanism | |
US20150003702A1 (en) | Processing and displaying a breast image | |
KR102245219B1 (ko) | 의료 영상에서 악성의심 병변을 구별하는 방법, 이를 이용한 의료 영상 판독 방법 및 컴퓨팅 장치 | |
WO2004049948A1 (ja) | コンピュータ支援診断装置 | |
JP7525248B2 (ja) | 医用情報処理装置及び医用情報処理プログラム | |
EP3939003B1 (en) | Systems and methods for assessing a likelihood of cteph and identifying characteristics indicative thereof | |
WO2022113801A1 (ja) | 医療用画像の異常検出システム及び異常検出方法 | |
WO2020235461A1 (ja) | 異常検出方法、異常検出プログラム、異常検出装置、サーバ装置及び情報処理方法 | |
JP2022117177A (ja) | 情報処理装置、情報処理方法及び情報処理プログラム | |
CN116580819B (zh) | 用于自动化地确定图像序列中的检查结果的方法和系统 | |
US8478007B2 (en) | Method for detecting ground glass opacity using chest computed tomography | |
WO2021197176A1 (en) | Systems and methods for tumor characterization | |
JP2007330419A (ja) | 画像表示装置および方法並びにプログラム | |
JP7114003B1 (ja) | 医療用画像表示システム、医療用画像表示方法及びプログラム |
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: 21897775 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022565238 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180077325.8 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021897775 Country of ref document: EP Effective date: 20230626 |