WO2022124591A1 - 의료지표 측정방법 및 이를 위한 초음파 진단장치 - Google Patents
의료지표 측정방법 및 이를 위한 초음파 진단장치 Download PDFInfo
- Publication number
- WO2022124591A1 WO2022124591A1 PCT/KR2021/016173 KR2021016173W WO2022124591A1 WO 2022124591 A1 WO2022124591 A1 WO 2022124591A1 KR 2021016173 W KR2021016173 W KR 2021016173W WO 2022124591 A1 WO2022124591 A1 WO 2022124591A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- medical
- measuring
- image data
- points
- Prior art date
Links
- 238000002604 ultrasonography Methods 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 48
- 210000003484 anatomy Anatomy 0.000 claims abstract description 19
- 238000005259 measurement Methods 0.000 claims description 26
- 230000001605 fetal effect Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 19
- 210000003754 fetus Anatomy 0.000 claims description 18
- 239000000523 sample Substances 0.000 claims description 16
- 210000001015 abdomen Anatomy 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 210000000988 bone and bone Anatomy 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 7
- 210000000689 upper leg Anatomy 0.000 claims description 6
- 210000000784 arm bone Anatomy 0.000 claims description 5
- 210000002758 humerus Anatomy 0.000 claims description 4
- 230000035935 pregnancy Effects 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 230000001678 irradiating effect Effects 0.000 claims description 2
- 238000000691 measurement method Methods 0.000 claims 3
- 238000003745 diagnosis Methods 0.000 description 39
- 238000010586 diagram Methods 0.000 description 17
- 239000000284 extract Substances 0.000 description 13
- 238000001514 detection method Methods 0.000 description 12
- 238000000605 extraction Methods 0.000 description 12
- 230000009466 transformation Effects 0.000 description 5
- 210000001694 thigh bone Anatomy 0.000 description 4
- 230000003187 abdominal effect Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000001930 leg bone Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003821 menstrual periods Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 210000004197 pelvis Anatomy 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0833—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures
- A61B8/085—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0866—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby
-
- 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
- A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
-
- 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
- A61B8/5269—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving detection or reduction of artifacts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- 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; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30008—Bone
-
- 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
- G06T2207/30044—Fetus; Embryo
Definitions
- the present invention relates to a diagnostic technology using ultrasound, and more particularly, to a technology for measuring a medical indicator using ultrasound.
- the present invention was supported by the national R&D project, project specific number: 1425140041, project number: S2482471, department name: Ministry of SMEs and Startups, research management professional institution: Korea Industrial Technology Promotion Agency, research project name: WC300 R&D, research project name: Software Beamforming Ultrasound Diagnostics Line-up Development, Hosted by: Alpinion Medical Systems Co., Ltd.
- various medical imaging apparatuses are widely used for imaging and acquiring information on living tissues of the human body for the purpose of early diagnosis or surgery of various diseases.
- Representative examples of such a medical imaging apparatus include an ultrasound diagnosis apparatus, a CT apparatus, and an MRI apparatus.
- the ultrasound diagnosis apparatus irradiates an ultrasound signal generated from an ultrasound probe to an object, receives information on an echo signal reflected from the object, and obtains an image of an internal portion of the object.
- the ultrasound diagnosis apparatus is used for medical purposes, such as observation of the inside of an object, detection of a foreign substance, and measurement of an injury.
- These ultrasound diagnostic apparatuses are widely used together with other image diagnostic apparatuses because they have higher stability than diagnostic apparatuses using X-rays, display images in real time, and are safe because there is no radiation exposure.
- a method of irradiating an ultrasound signal to a subject through an ultrasound probe, measuring the size of a body part on an ultrasound image obtained by using an ultrasound echo signal reflected from the subject, and predicting a medical index is widely used.
- a method of measuring the size of a body part there is a semantic segmentation technique. The technique is to segment the objects in the image into meaningful units.
- a method for measuring a medical indicator capable of more accurately and easily automatically measuring a medical indicator, and an ultrasound diagnosis apparatus for the same are proposed.
- a method for measuring a medical indicator includes: acquiring, by an ultrasound diagnosis apparatus, ultrasound image data; extracting feature points from the acquired ultrasound image data; and generating figure information including the extracted feature points. and determining an anatomical structure from the generated figure information, and measuring a medical index based on the determined anatomical structure.
- a number of points greater than the minimum number of points required to construct the figure may be extracted.
- the step of extracting the feature points it is possible to extract the perimeter points constituting the ellipse, extract the perimeter points constituting the circle, extract both endpoints constituting the line segment, and extract each vertex constituting the polygon. .
- the extracting of the feature points includes: learning the original image data and the image data of interest extracted from the original image data; extracting the first feature points of the object of interest from the original image data; It may include the steps of generating the image data of interest by transforming the original image data using the method, extracting the final feature point from the generated image data of interest, and inversely transforming the coordinates of the final feature point to match the original image data.
- learning can be performed using a structure in which a convolution layer of a neural network and a nonlinear function are repeatedly stacked.
- the learning step it is possible to prevent information loss caused by reducing the output size by using padding of the neural network.
- the learning step it is possible to learn through a network structure that connects multiple resolution streams in parallel for repeated resolution information exchange between the first resolution frame and the second resolution frame.
- a 0-dimensional figure made of points, a one-dimensional figure made of straight lines or curves, or a two-dimensional figure made of an ellipse, a circle, or a polygon can be generated.
- candidate figure information that can replace the basic figure information may be generated together with the basic figure information.
- a score may be assigned to the extracted feature points, and figure information may be generated using upper feature points greater than or equal to a preset standard.
- a relationship between the feature points may be constructed using the geometric properties of the figure to be generated, and correction may be performed to remove an outlier through the relationship between the feature points.
- the figure information can be corrected by bringing at least one of the measurement result of the other parameter and the measurement result of the other side of the twin fetus from the pre-stored and accumulated fetal body measurement data. .
- the figure information may be corrected by selecting a feature point based on a user's manipulation signal input with respect to the generated figure information.
- the head In the step of determining the anatomical structure, the head may be determined from the oval, the abdomen may be determined from the circle, and the thigh bone (Femur) or upper arm bone (Humerus) may be determined from a line segment or a square.
- the head size is measured using the points of the circumference constituting the ellipse
- the circumference of the abdomen is measured using the points of the circumference constituting the circle
- both endpoints or rectangles constituting the line segment are measured.
- the length of the thigh bone or upper arm bone can be measured using the four corners that make up it.
- the medical indicator may be measured by considering the fetal body measurement data related to the patient's pregnancy information among the pre-stored and accumulated fetal body measurement data.
- the method for measuring a medical indicator includes at least one of dividing the generated figure information into identifiable visual information on the ultrasound image data and displaying the measured medical indicator as numerical information on the shape of the ultrasound image data. may include more.
- an ultrasound diagnosis apparatus includes an ultrasound probe that irradiates an ultrasound signal to a subject and receives a reflected wave signal signal from the subject, and an image processor that generates ultrasound image data using the reflected wave signal of the ultrasound probe;
- a point extracting unit for extracting feature points from the generated ultrasound image data, a figure generating unit generating figure information composed of the extracted feature points, a structure determining unit determining an anatomical structure from the generated figure information, and the determined It includes an indicator measuring unit for measuring a medical indicator based on the anatomical structure, and an output unit for outputting a medical indicator measurement result.
- a method for measuring a medical indicator and an ultrasound diagnosis apparatus therefor it is possible to automatically and more accurately and easily measure a medical indicator compared to a semantic segmentation technique.
- FIG. 1 is a diagram showing the configuration of an ultrasound diagnosis apparatus according to an embodiment of the present invention.
- FIG. 2 is a diagram illustrating a flow of a method for measuring a medical indicator using an ultrasound diagnosis apparatus according to an embodiment of the present invention
- FIG. 3 is a diagram illustrating an example of extracting feature points from ultrasound image data according to an embodiment of the present invention
- FIG. 4 is a diagram illustrating a screen for measuring the size of a fetal head using a key-point detection technique according to an embodiment of the present invention
- FIG. 5 is a diagram illustrating a screen for measuring the abdominal circumference of a fetus using a key-point detection technique according to an embodiment of the present invention
- FIG. 6 is a diagram illustrating a screen for measuring the length of a fetal bone using a key-point detection technique according to an embodiment of the present invention.
- Each block in the accompanying block diagram and combinations of steps in the flowchart may be executed by computer program instructions (execution engine), which are executed by the processor of a general-purpose computer, special-purpose computer, or other programmable data processing device. It may be mounted so that its instructions, which are executed by the processor of a computer or other programmable data processing device, create means for performing the functions described in each block of the block diagram or in each step of the flowchart.
- execution engine executed by computer program instructions (execution engine), which are executed by the processor of a general-purpose computer, special-purpose computer, or other programmable data processing device. It may be mounted so that its instructions, which are executed by the processor of a computer or other programmable data processing device, create means for performing the functions described in each block of the block diagram or in each step of the flowchart.
- These computer program instructions may also be stored in a computer usable or computer readable memory which may direct a computer or other programmable data processing device to implement a function in a particular manner, and thus the computer usable or computer readable memory. It is also possible to produce an article of manufacture containing instruction means for performing the functions described in each block of the block diagram or each step of the flowchart, the instructions stored in the block diagram.
- the computer program instructions may be mounted on a computer or other programmable data processing device, a series of operational steps is performed on the computer or other programmable data processing device to create a computer-executable process to create a computer or other programmable data processing device. It is also possible that instructions for performing the data processing apparatus provide steps for executing functions described in each block in the block diagram and in each step in the flowchart.
- each block or step may represent a module, segment, or portion of code comprising one or more executable instructions for executing specified logical functions, and in some alternative embodiments the blocks or steps referred to in the block or steps. It should be noted that it is also possible for functions to occur out of sequence. For example, it is possible that two blocks or steps shown one after another may be performed substantially simultaneously, and also the blocks or steps may be performed in the reverse order of the corresponding functions, if necessary.
- FIG. 1 is a diagram illustrating a configuration of an ultrasound diagnosis apparatus according to an embodiment of the present invention.
- the ultrasound diagnosis apparatus includes an ultrasound probe 102 , a main body 100 , an input unit 104 , an output unit 106 , and a learning unit 108 .
- the ultrasonic probe 102 , the input unit 104 , and the output unit 106 are communicatively connected to the main body 100 .
- the ultrasonic probe 102 has a plurality of piezoelectric vibrators, and the plurality of piezoelectric vibrators generate ultrasonic waves based on a driving signal supplied from the transceiver 110 of the main body 100 . Also, the ultrasonic probe 102 receives the reflected wave from the subject and converts it into an electrical signal. That is, the ultrasonic probe 102 performs ultrasonic scanning on the subject to receive a reflected wave from the subject. The ultrasonic probe 102 is detachably connected from the main body 100 .
- the subject may be a fetus of a pregnant woman, but is not limited thereto, and all patients may be the subject.
- the input unit 104 includes a track ball, a switch button, a mouse, a keyboard, and the like for setting a predetermined position (eg, a position of a tissue shape, a region of interest, a region other than the region of interest, etc.) This is realized by a touchpad that performs input operation by touching the operation surface, a screen in which the display screen and the touchpad are integrated, a non-contact input circuit using an optical sensor, an audio input circuit, and the like.
- the input unit 104 is connected to the control unit 130 to be described later, and converts the input operation signal received from the user into an electrical signal and outputs it to the control unit 130 .
- the output unit 106 displays a graphical user interface (GUI) for a user of the ultrasound diagnosis apparatus to input various setting requests using the input unit 104 or displays ultrasound image data generated by the main body 100 . .
- GUI graphical user interface
- the output unit 106 displays various messages and information in order to notify the user of the processing status and processing results of the main body 100 .
- the output unit 106 may have a speaker and output audio.
- the output unit 106 may display the measurement result of the medical indicator generated through the control unit 130 on the screen.
- the medical indicator may be, for example, a fetal indicator. Fetal indicators include the fetus's abdomen (Abdomen), head (Head), thigh bone (Femur), and upper arm bone (Humerus). However, medical indicators are not limited to fetal indicators, and all body organs of the subject can be the target. For example, it is applicable to the pelvis and the like.
- the output unit 106 may classify and display the figure information generated by the controller 130 into identifiable visual information (eg, color) on the ultrasound image data.
- the output unit 106 may display the measured medical indicator as numerical information on a figure of the ultrasound image data.
- the medical indicator measured through the controller 130 may be displayed as numerical information on the ultrasound image data.
- the learning unit 108 learns the ultrasound image data using a neural network.
- the learning data may be used by at least one of the point extracting unit 131 , the figure generating unit 132 , the structure determining unit 133 , and the index measuring unit 134 constituting the control unit 130 .
- the learning unit 108 may be in the form of a server connected to the main body 100 through a network, or may be located in the main body 100 .
- the learning unit 108 may learn the original image data and the image data of interest extracted from the original image data together.
- the main body 100 is a device that generates ultrasound image data based on a reflected wave signal received by the ultrasound probe 102 .
- the main body 100 according to an embodiment includes a transceiver 110 , an image processing unit 120 , a control unit 130 , a storage unit 140 , and a learning data receiving unit 150 .
- the transceiver 110 supplies a driving signal to the ultrasonic probe 102 and repeatedly generates a pulse for forming a transmitted ultrasonic wave at a predetermined frequency. Also, the ultrasound generated from the ultrasound probe 102 is converged by beamforming.
- the transceiver 110 includes a preamplifier, an analog/digital (A/D) converter, a reception delay unit, an adder, etc., and performs various processing on the echo signal received by the ultrasonic probe 102 to generate reflected wave data. have.
- Various types of output signals from the transceiver 110 are selectable, such as a signal including phase information called a radio frequency (RF) signal or amplitude information after envelope detection processing.
- RF radio frequency
- the image processing unit 120 receives the reflected wave data from the transceiver 110 and generates ultrasound image data of the fetus. In this case, the image processing unit 120 generates ultrasound image data by performing logarithmic amplification, envelope detection, and the like.
- the storage unit 140 stores image data generated by the image processing unit 120 or the control unit 130 .
- the controller 130 controls each component of the ultrasound diagnosis apparatus.
- the control unit 130 may include the transceiver 110, the image processing unit ( 120) to control the processing.
- the controller 130 displays the ultrasound image data stored in the storage 140 through the output unit 106 .
- the control unit 130 includes a point extraction unit 131 , a figure generation unit 132 , a structure determination unit 133 , and an indicator measurement unit 134 .
- the point extraction unit 131 extracts feature points from the ultrasound image data generated by the image processing unit 120 .
- the feature point may be a feature point representing a boundary, a feature point representing an overall shape, a difference in pixel brightness, and the like.
- perimeter points constituting an ellipse may be extracted
- perimeter points constituting a circle may be extracted
- both endpoints constituting a line segment may be extracted
- each vertex constituting a polygon may be extracted.
- Polygons include triangles, quadrilaterals, and pentagons.
- a focus may be additionally extracted
- a midpoint may be additionally extracted to increase the accuracy.
- the figure generating unit 132 generates figure information composed of the feature points extracted through the point extracting unit 131 .
- a 0-dimensional figure made of points a one-dimensional figure made of straight lines or curves, or a two-dimensional figure made of an ellipse, a circle, or a polygon can be generated.
- the structure determining unit 133 determines an anatomical structure from the figure information generated by the figure generating unit 132 .
- the anatomical structure includes a fetal abdomen (Abdomen), a head (Head), bones, and the like.
- bones include the thigh bone (Femur) and the upper arm bone (Humerus). Determination of anatomical structures
- the abdomen of the fetus is determined from a circle
- a head is determined from an ellipse
- a bone is determined from a line segment or a rectangle.
- the indicator measuring unit 134 measures a medical indicator based on the anatomical structure determined by the structure determining unit 133 . For example, measure Head Circumference from the circumference of an ellipse, measure Abdominal Circumference from the circumference of the circle, and measure the femur Length from the length of a line segment or rectangle .
- controller 130 extracts points constituting the figure, creates a figure using the extracted feature points, and measures the index of the fetus from the figure, it will be referred to as a key-point detection technique.
- a key-point detection technique A more detailed embodiment of the key-point detection technique will be described later with reference to FIG. 2 .
- the training data receiving unit 150 receives the training data from the learning unit 108 and transmits it to the control unit 130 .
- the original image data and the image data of interest learned through the learning unit 108 may be provided to the point extracting unit 131 of the control unit 130 .
- FIG. 2 is a diagram illustrating a flow of a method for measuring a medical indicator using an ultrasound diagnosis apparatus according to an embodiment of the present invention.
- the ultrasound diagnosis apparatus acquires ultrasound image data of a fetus ( S210 ).
- the ultrasound diagnosis apparatus extracts feature points from the acquired ultrasound image data ( S220 ).
- the feature point may be a feature point representing a boundary, a feature point representing an overall shape, a difference in pixel brightness, and the like.
- the keypoint extraction step 220 may include a learning step, a first keypoint extraction step, a transformation step, and a second keypoint extraction step.
- the ultrasound diagnosis apparatus learns both the original image data and the image data of interest extracted from the original image data through the learning step.
- the original image data is an original image captured by the device
- the image of interest data is an image obtained by extracting (eg, cropping) a region of interest that is determined to have an object of interest from the original image data.
- the ultrasound diagnosis apparatus generates original image data and image data of interest based on the label of the image data, and trains them both.
- an object position Prior to extracting key points, an object position may be retrieved from the original image data, and an image may be cropped based on the retrieved object position. If the position of the object is first searched and then the original image data cut based on the position of the object is input to extract the feature points, the accuracy is greatly improved. It is also possible to convert (Resize) the image size to the input size of the network (eg, 256x256).
- the ultrasound diagnosis apparatus extracts the first feature point of the object of interest from the original image data through the first feature point extraction step.
- the ultrasound diagnosis apparatus generates the image data of interest by converting the original image data using the extracted first feature points through the conversion step.
- the transformation may include rotation, warping, magnification, and the like.
- the ultrasound diagnosis apparatus extracts the final feature point from the generated image data of interest through the second feature point extraction step, and inversely transforms the coordinates of the final feature point to match the original image data.
- False positives may be corrected through learning, first feature point extraction, transformation, and second specific point extraction steps.
- a target data standardization effect can be achieved through transformation such as image warping. Transformations such as image enlargement can improve pixel accuracy.
- the ultrasound diagnosis apparatus may extract a greater number of points than the minimum number of points required to construct a figure.
- the object in the ultrasound image is incomplete, so even if a key point cannot be detected, this is to construct a figure to be made. Accordingly, more points than information constituting the figure are extracted. For example, in the case of an ellipse, 4 points are needed to construct an ellipse, but we want to increase the accuracy by extracting 16 points.
- the perimeter of the ellipse is defined as the outline of the object. 5 or more points (eg, 16 points) are extracted along the perimeter of the ellipse.
- points eg, 16 points
- the rectangle four points corresponding to corners are extracted from the rectangle boundary containing the object.
- the rectangle at both ends of the object is defined as a valid rectangle, not the entire rectangle, and the corresponding points are extracted.
- points corresponding to the lower end of the real object may be further extracted.
- the ultrasound diagnosis apparatus extracts points around the ellipse (focal points can be added) using a key-point detection technique, and points around the circles (focus points can be added) It is possible to extract, extract both endpoints constituting a line segment, and extract each vertex constituting a polygon.
- Polygons include triangles, quadrilaterals, and pentagons.
- the ultrasound diagnosis apparatus generates figure information composed of the extracted feature points ( 230 ).
- the ultrasound diagnosis apparatus may generate a 0-dimensional figure made of points, a one-dimensional figure made of straight lines or curves, or a two-dimensional figure made of an ellipse, a circle, or a polygon.
- the ultrasound diagnosis apparatus may generate candidate shape information that can replace the basic shape information together with the basic shape information. For example, a figure composed of both upper end points of a leg bone is set as basic figure information, and a figure composed of both lower end points of a leg bone that is similar in length is set as candidate figure information.
- the ultrasound diagnosis apparatus may allocate a score to the extracted feature points, and generate the figure information using points higher than or equal to a preset standard.
- a step of correcting based on the characteristics of the figure to be generated may be added. Since the extracted feature point is a component of a certain figure, a relationship between the feature points can be constructed using the geometric properties of the figure to be created, and an outlier can be removed in advance through the relationship between the feature points. For example, in the case of a circle, an outlier may be removed by using the distance relationship between the midpoint and each feature point. In the case of an ellipse, anomalies can be removed by using distance information of the focal point, the minor axis, and the major axis.
- the ultrasound diagnosis apparatus brings at least one of the measurement result of the other parameter and the measurement result of the other side of the twin fetus from the pre-stored and accumulated fetal body measurement data to obtain the shape information can be corrected.
- the figure information may be corrected by selecting a point based on the user's manipulation signal input for the generated figure information.
- the ultrasound diagnosis apparatus may classify the generated shape information into identifiable visual information (eg, color) on the ultrasound image data and display it.
- identifiable visual information eg, color
- the ultrasound diagnosis apparatus determines an anatomical structure from the generated graphic information (240), and measures a medical index based on the determined anatomical structure (250).
- the ultrasound diagnosis apparatus measures the size of the fetus' head by using the circumferential points (focus can be added) constituting the ellipse, and uses the circumferential points (additional focus is possible) constituting the circle.
- the circumference of the abdomen of the fetus is measured, and the length of the bones of the fetus can be measured using both endpoints constituting the line segment or the four corners constituting the rectangle.
- the ultrasound diagnosis apparatus may measure the medical indicator by considering the fetal body measurement data related to the patient's pregnancy information among the previously stored and accumulated fetal body measurement data.
- Pregnancy information includes information about the patient's last menstrual period (LMP) or date of conception (DOC).
- the ultrasound diagnosis apparatus may perform learning using a neural network on ultrasound image data.
- the learning data may be used in at least one of the feature point extraction step 220 , the figure information generation step 230 , the anatomical structure determination step 240 , and the medical indicator measurement step 250 .
- the ultrasound diagnosis apparatus may learn using a structure in which a convolution layer of a neural network (eg, CNN) and a nonlinear function (Relu, activation function) are repeatedly stacked.
- a convolution layer of a neural network eg, CNN
- a nonlinear function Relu, activation function
- the ultrasound diagnosis apparatus may reduce the output size by using padding of the neural network to prevent loss of information and maintain the resolution of the original layer.
- the ultrasound diagnosis apparatus may learn through a network structure that connects multiple resolution streams in parallel to exchange resolution information repeatedly between the first resolution frame and the second resolution frame.
- the first resolution frame may be a high resolution frame
- the second resolution frame may be a low resolution frame.
- resolution information may be repeatedly exchanged between the high-resolution frame and the low-resolution frame.
- the ultrasound diagnosis apparatus may display the measured medical index as numerical information on the shape of the ultrasound image data.
- FIG. 3 is a diagram illustrating an example of extracting feature points from ultrasound image data according to an embodiment of the present invention.
- the ultrasound diagnosis apparatus may extract points around the ellipse to measure the size of the fetus's head.
- 16 points constituting an ellipse are extracted.
- points on the circumference forming a circle may be extracted.
- 16 points forming a circle are extracted.
- both end points forming a line segment may be extracted to measure the length of the bone.
- FIG. 4 is a diagram illustrating a screen for measuring a fetal head size using a key-point detection technique according to an embodiment of the present invention.
- the perimeter points constituting the ellipse are extracted from the ultrasound image data, the head is determined from the ellipse, and the fetal head size is determined using the perimeter points (focus can be added) constituting the ellipse.
- the perimeter of the ellipse, the length of the horizontal axis and the length of the vertical axis within the ellipse may be displayed separately by identifiable visual information (eg, color).
- the measurement values of the fetal abdomen including the length of the horizontal axis and the length of the vertical axis may be displayed on the horizontal axis and the vertical axis.
- FIG. 5 is a diagram illustrating a screen for measuring the abdominal circumference of a fetus using a key-point detection technique according to an embodiment of the present invention.
- points around the circle are extracted from the ultrasound image data, the abdomen of the fetus is determined from the circle, and the circumference of the abdomen of the fetus is measured using the points and midpoints of the circumference constituting the circle. do.
- the circumference of the circle may be displayed by dividing it into identifiable visual information (eg, color).
- a measurement value of the fetal abdomen circumference may be displayed on a circle.
- FIG. 6 is a diagram illustrating a screen for measuring the length of a fetal bone using a key-point detection technique according to an embodiment of the present invention.
- both end points constituting a line segment are extracted from ultrasound image data, and the length of the fetal bone is measured using both end points constituting the line segment.
- both end points of the line segment and the line segment connecting the end points may be displayed by classifying them with identifiable visual information (eg, color).
- identifiable visual information eg, color
- the fetal bone length measurement value may be displayed on the bone.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physiology (AREA)
- Geometry (AREA)
- Gynecology & Obstetrics (AREA)
- Pregnancy & Childbirth (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Vascular Medicine (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
Abstract
Description
Claims (17)
- 초음파 진단장치를 이용한 의료지표 측정방법에 있어서, 초음파 진단장치가초음파 영상 데이터를 획득하는 단계;획득된 초음파 영상 데이터로부터 특징점들을 추출하는 단계;추출된 특징점들로 구성되는 도형정보를 생성하는 단계;생성된 도형정보로부터 해부학적 구조물을 판단하는 단계; 및판단된 해부학적 구조물에 기초하여 의료지표를 측정하는 단계;를 포함하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 특징점들을 추출하는 단계는도형을 구성하기 위해 필요한 최소한의 점의 수보다 더 많은 수의 점들을 추출하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 특징점들을 추출하는 단계는타원을 구성하는 둘레의 점을 추출하고, 원을 구성하는 둘레의 점을 추출하고, 선분을 구성하는 양 끝점을 추출하며, 다각형을 구성하는 각 꼭지점을 추출하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 특징점들을 추출하는 단계는원본 영상 데이터와, 원본 영상 데이터에서 추출된 관심 영상 데이터를 함께 학습시키는 단계;원본 영상 데이터에서 관심객체의 제1 특징점을 추출하는 단계;추출된 제1 특징점을 이용하여 원본 영상 데이터를 변환시켜 관심 영상 데이터를 생성하는 단계; 및생성된 관심 영상 데이터에서 최종 특징점을 추출하고 최종 특징점의 좌표를 원본 영상 데이터에 맞게 역변환 시키는 단계;를 포함하는 것을 특징으로 하는 의료지표 측정방법.
- 제 4 항에 있어서, 학습 시키는 단계는신경망의 컨볼루션 계층(Convolution layer)와 비선형 함수를 반복해서 쌓는 구조를 이용하여 학습시키는 것을 특징으로 하는 의료지표 측정방법.
- 제 4 항에 있어서, 학습시키는 단계는신경망의 패딩(Padding)을 이용하여 출력 사이즈를 줄이면서 생기는 정보의 손실을 방지하는 것을 특징으로 하는 의료지표 측정방법.
- 제 4 항에 있어서, 학습하는 단계는제1 해상도 프레임과 제2 해상도 프레임 간 반복적인 해상도 정보 교환을 위해 병렬로 다중 해상도 스트림을 연결하는 네트워크 구조를 통해 학습하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 도형정보를 생성하는 단계는점으로 이루어진 0차원 도형이나, 직선 또는 곡선으로 이루어진 1차원 도형이나, 타원, 원 또는 다각형으로 이루어진 2차원 도형을 생성하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 도형정보를 생성하는 단계는기본 도형정보와 함께 기본 도형정보를 대체할 수 있는 후보 도형정보를 생성하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 도형정보를 생성하는 단계는추출된 특징점들에 대해 점수를 할당하고, 미리 설정된 기준 이상의 상위 특징점들을 이용하여 도형정보를 생성하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 도형정보를 생성하는 단계는생성할 도형의 기하학적 성질을 이용하여 특징점들 간의 관계를 구성하고, 특징점들 간의 관계를 통해 이상점(outlier)을 제거하는 보정을 수행하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 도형정보를 생성하는 단계는미리 저장되어 누적된 태아의 신체 측정 데이터로부터 현재의 측정이 종료된 다른 파라미터 측정 값 및 쌍둥이 태아의 다른 한쪽의 측정 결과 중 적어도 하나를 가져와 도형정보를 보정하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 도형정보를 생성하는 단계는생성된 도형정보를 대상으로 사용자의 조작신호 입력에 의한 특징점 선택을 통해 도형정보를 보정하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 해부학적 구조물을 판단하는 단계는타원으로부터 머리(Head)를 판단하고, 원으로부터 복부(Abdomen)을 판단하며, 선분 또는 사각형으로부터 넓적다리 뼈(Femur) 또는 위팔뼈(Humerus)를 판별하며,의료지표를 측정하는 단계는타원을 구성하는 둘레의 점을 이용하여 머리 크기를 측정하고, 원을 구성하는 둘레의 점을 이용하여 복부 둘레를 측정하며, 선분을 구성하는 양 끝점 또는 사각형을 구성하는 네 모서리를 이용하여 넓적다리 뼈 또는 위팔뼈의 길이를 측정하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 의료지표를 측정하는 단계는미리 저장되어 누적된 태아의 신체 측정 데이터 중 환자의 임신정보와 관련된 태아의 신체 측정 데이터를 함께 고려하여 의료지표를 측정하는 것을 특징으로 하는 의료지표 측정방법.
- 제 1 항에 있어서, 의료지표 측정방법은생성된 도형정보를 초음파 영상 데이터 상에 식별 가능한 시각정보로 구분하여 표시하는 단계; 및측정된 의료지표를 초음파 영상 데이터의 도형 상에 수치정보로 표시하는 단계;중 적어도 하나를 더 포함하는 것을 특징으로 하는 의료지표 측정방법.
- 피검체에 초음파 신호를 조사하고, 피검체로부터 반사파 신호신호를 수신하는 초음파 프로브;초음파 프로브의 반사파 신호를 사용하여 초음파 영상 데이터를 생성하는 이미지 처리부;생성된 초음파 영상 데이터로부터 특징점들을 추출하는 점 추출부;추출된 특징점들로 구성되는 도형정보를 생성하는 도형 생성부;생성된 도형정보로부터 해부학적 구조물을 판단하는 구조물 판단부;판단된 해부학적 구조물에 기초하여 의료지표를 측정하는 지표 측정부; 및의료지표 측정결과를 출력하는 출력부;를 포함하는 것을 특징으로 하는 초음파 진단장치.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE112021006417.7T DE112021006417T5 (de) | 2020-12-11 | 2021-11-09 | Verfahren zum messen eines medizinischen indikators und ultraschalldiagnosevorrichtung dafür |
US18/039,383 US20230414202A1 (en) | 2020-12-11 | 2021-11-09 | Medical indicator measuring method and ultrasound diagnostic device therefor |
CN202180082080.8A CN116583912A (zh) | 2020-12-11 | 2021-11-09 | 医学指标测量方法及针对该方法的超声诊断设备 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020200173175A KR102617378B1 (ko) | 2020-12-11 | 2020-12-11 | 의료지표 측정방법 및 이를 위한 초음파 진단장치 |
KR10-2020-0173175 | 2020-12-11 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022124591A1 true WO2022124591A1 (ko) | 2022-06-16 |
Family
ID=81974626
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2021/016173 WO2022124591A1 (ko) | 2020-12-11 | 2021-11-09 | 의료지표 측정방법 및 이를 위한 초음파 진단장치 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20230414202A1 (ko) |
KR (2) | KR102617378B1 (ko) |
CN (1) | CN116583912A (ko) |
DE (1) | DE112021006417T5 (ko) |
WO (1) | WO2022124591A1 (ko) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007267979A (ja) * | 2006-03-31 | 2007-10-18 | Yoko Arimasa | 生物の臓器形態解析方法と生物の臓器形態解析システム |
KR20130082318A (ko) * | 2012-01-11 | 2013-07-19 | 삼성전자주식회사 | 태아 모델링 방법 및 그에 따른 영상 처리 장치 |
JP2015198907A (ja) * | 2014-04-01 | 2015-11-12 | セイコーエプソン株式会社 | 超音波測定装置 |
JP2016522708A (ja) * | 2013-05-03 | 2016-08-04 | インパック メディカル システムズ、 インク.Impac Medical Systems Inc. | 診療計画を導くための画像の構造形状を自動的に表示する方法及び装置 |
WO2019145147A1 (en) * | 2018-01-23 | 2019-08-01 | Koninklijke Philips N.V. | Device and method for obtaining anatomical measurements from an ultrasound image |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5243845B2 (ko) * | 1972-08-21 | 1977-11-02 | ||
JP5243845B2 (ja) | 2008-05-22 | 2013-07-24 | 日立アロカメディカル株式会社 | ボリュームデータ処理装置 |
KR101971622B1 (ko) * | 2012-01-04 | 2019-08-13 | 삼성전자주식회사 | 대상체의 생체 정보를 측정하는 방법 및 장치 |
JP5865463B1 (ja) * | 2014-10-01 | 2016-02-17 | 日立アロカメディカル株式会社 | 超音波画像処理装置 |
JP7075854B2 (ja) * | 2018-09-11 | 2022-05-26 | 富士フイルムヘルスケア株式会社 | 超音波診断装置及び表示方法 |
-
2020
- 2020-12-11 KR KR1020200173175A patent/KR102617378B1/ko active IP Right Grant
-
2021
- 2021-11-09 WO PCT/KR2021/016173 patent/WO2022124591A1/ko active Application Filing
- 2021-11-09 US US18/039,383 patent/US20230414202A1/en active Pending
- 2021-11-09 DE DE112021006417.7T patent/DE112021006417T5/de active Pending
- 2021-11-09 CN CN202180082080.8A patent/CN116583912A/zh active Pending
-
2023
- 2023-12-07 KR KR1020230176991A patent/KR20230169067A/ko not_active Application Discontinuation
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007267979A (ja) * | 2006-03-31 | 2007-10-18 | Yoko Arimasa | 生物の臓器形態解析方法と生物の臓器形態解析システム |
KR20130082318A (ko) * | 2012-01-11 | 2013-07-19 | 삼성전자주식회사 | 태아 모델링 방법 및 그에 따른 영상 처리 장치 |
JP2016522708A (ja) * | 2013-05-03 | 2016-08-04 | インパック メディカル システムズ、 インク.Impac Medical Systems Inc. | 診療計画を導くための画像の構造形状を自動的に表示する方法及び装置 |
JP2015198907A (ja) * | 2014-04-01 | 2015-11-12 | セイコーエプソン株式会社 | 超音波測定装置 |
WO2019145147A1 (en) * | 2018-01-23 | 2019-08-01 | Koninklijke Philips N.V. | Device and method for obtaining anatomical measurements from an ultrasound image |
Also Published As
Publication number | Publication date |
---|---|
KR20220083894A (ko) | 2022-06-21 |
US20230414202A1 (en) | 2023-12-28 |
DE112021006417T5 (de) | 2023-10-05 |
KR20230169067A (ko) | 2023-12-15 |
KR102617378B1 (ko) | 2023-12-27 |
CN116583912A (zh) | 2023-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10813625B2 (en) | Ultrasound image diagnostic apparatus | |
WO2015002256A1 (ja) | 医用情報処理システム、医用情報処理プログラム及び超音波診断装置 | |
CN111227864A (zh) | 使用超声图像利用计算机视觉进行病灶检测的方法与装置 | |
US10463316B2 (en) | Medical information processing system | |
CN111242921B (zh) | 一种医学超声图像辅助诊断系统自动更新的方法及系统 | |
KR102545008B1 (ko) | 초음파 영상 장치 및 그 제어 방법 | |
WO2013105815A1 (en) | Fetus modeling method and image processing apparatus therefor | |
JP2020039645A (ja) | 超音波診断装置及び表示方法 | |
JP2007167116A (ja) | 超音波診断装置 | |
US20180220994A1 (en) | Medical information processing system and medical image processing apparatus | |
JP6258084B2 (ja) | 医用画像表示装置、医用画像表示システムおよび医用画像表示プログラム | |
WO2022124591A1 (ko) | 의료지표 측정방법 및 이를 위한 초음파 진단장치 | |
JP2015112123A (ja) | 医用画像診断装置 | |
CN100475156C (zh) | 超声成像方法及妇科处置用实时超声监视装置 | |
WO2022145988A1 (ko) | 인공지능을 이용한 안면부 골절 판독 장치 및 방법 | |
WO2016006932A1 (ko) | 태아 조형물 프린팅 서비스 시스템 및 방법 | |
JP4691732B1 (ja) | 組織抽出システム | |
WO2020159008A1 (ko) | 초음파 영상 장치 및 초음파 영상 생성 방법 | |
JP6785557B2 (ja) | 内視鏡レポート作成支援システム | |
CN113643213A (zh) | B超诊断设备安全状态解析系统及存储介质 | |
JP6822806B2 (ja) | 超音波診断装置および医用画像処理装置 | |
JP2019107453A (ja) | 画像処理装置及び画像処理方法 | |
WO2023229415A1 (ko) | Ar 영상 제공 방법 및 ar 영상 제공 장치 | |
RU2766046C1 (ru) | Способ дистанционной регистрации процесса дыхания пациента и устройство для его осуществления | |
WO2023135816A1 (ja) | 医療支援システムおよび医療支援方法 |
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: 21903638 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18039383 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180082080.8 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 112021006417 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21903638 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27.11.2023) |