WO2023200043A1 - 엑스선 촬영 장치 및 이를 이용하는 엑스선 촬영 방법 - Google Patents
엑스선 촬영 장치 및 이를 이용하는 엑스선 촬영 방법 Download PDFInfo
- Publication number
- WO2023200043A1 WO2023200043A1 PCT/KR2022/009029 KR2022009029W WO2023200043A1 WO 2023200043 A1 WO2023200043 A1 WO 2023200043A1 KR 2022009029 W KR2022009029 W KR 2022009029W WO 2023200043 A1 WO2023200043 A1 WO 2023200043A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- energy
- low
- frequency component
- bone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- 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
- A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
- A61B6/5235—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image combining images from the same or different ionising radiation imaging techniques, e.g. PET and CT
- A61B6/5241—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image combining images from the same or different ionising radiation imaging techniques, e.g. PET and CT combining overlapping images of the same imaging modality, e.g. by stitching
-
- 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
- A61B6/40—Arrangements for generating radiation specially adapted for radiation diagnosis
- A61B6/4007—Arrangements for generating radiation specially adapted for radiation diagnosis characterised by using a plurality of source units
-
- 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
- A61B6/48—Diagnostic techniques
- A61B6/482—Diagnostic techniques involving multiple energy imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/505—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of bone
-
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—Two-dimensional [2D] image generation
- G06T11/10—Texturing; Colouring; Generation of textures or colours
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Definitions
- the present invention relates to an X-ray imaging device that acquires images using X-rays and an X-ray imaging method using the same.
- An X-ray imaging device is an imaging device that irradiates X-rays to a affected area of the body of a human or animal and receives the transmitted X-rays to obtain an image of the affected area.
- This X-ray imaging device is a device that continuously or continuously provides X-ray images of the affected area and is widely used for diagnosis, interpretation, and various medical procedures of the affected area.
- DES Dual Energy Subtraction
- DES Digital Energy Subtraction
- body parts for example, the chest.
- DES is especially widely used to improve the diagnostic accuracy of the chest.
- DES technology is based on the difference in attenuation of low-energy and high-energy By erasing the affected areas, soft tissue images and bone images are created respectively. Typically, removing a specific part from an X-ray image is called subtraction.
- Soft tissue images and bone images obtained by DES enable accurate diagnosis of lesions with improved visibility compared to existing general chest X-ray images.
- the two-shot shooting of the dual-energy X-ray image used in this DES processing is performed by irradiating high-energy and low-energy As the position of is misaligned, motion artifact occurs in the subtracted image. For this reason, when shooting 2 shots, the subject is fixed to reduce motion noise, but significant changes occur in the heart, pulmonary blood vessels, etc., and motion noise is bound to appear, which has a negative impact on image quality and reduces video quality. It may interfere with diagnosis.
- the problem to be solved by the present invention is to provide a method for reducing motion noise in images generated by subtraction image processing in order to improve the accuracy of image diagnosis.
- Another problem that the present invention aims to solve is to provide a method to improve the image quality of standard images, soft tissue images, and bone images obtained by irradiating dual energy X-rays.
- An X-ray imaging device includes an X-ray irradiation module configured to irradiate X-rays, and a X-ray irradiated from the It includes an X-ray detection module, and an image processor configured to generate an X-ray image using an output signal of the X-ray detection module.
- the image processor includes obtaining high-energy images and low-energy images respectively obtained by X-rays of relatively high energy and relatively low energy, decomposing the high-energy images to generate high-energy frequency component images for a plurality of frequency bands.
- the high-energy frequency component image for each of the plurality of frequency bands may include a high-energy Laplacian pyramid image of a plurality of levels and a high-energy Gaussian pyramid image of a plurality of levels, and the plurality of frequency bands
- the star low-energy frequency component image may include a low-energy Laplacian pyramid image of multiple levels and a low-energy Gaussian pyramid image of multiple levels.
- the merged frequency component image may be generated by merging the high-energy Laplacian pyramid image and the low-energy Laplacian pyramid image for each level.
- the high-energy Laplacian pyramid image and the low-energy Laplacian pyramid image may be merged into a patch unit including a plurality of pixels for each level, and the high-energy Laplacian pyramid image and the low-energy Laplacian pyramid image may be merged into the patch unit for each level.
- the patch corresponding to the higher contrast value among the corresponding patches of the high-energy Gaussian pyramid image and the low-energy Gaussian pyramid image of the corresponding level may be selected and merged.
- the high-energy Laplacian pyramid image and the low-energy Laplacian pyramid image may be merged with each other on a pixel basis for each level or on a patch basis including a plurality of pixels, and the high-energy Laplacian pyramid image and the low-energy Laplacian pyramid image may be merged with each other at the level.
- the pixel or patch corresponding to the statistical value representing the greater contrast among the corresponding patches of the high-energy Gaussian pyramid image and the low-energy Gaussian pyramid image of the corresponding level is selected and merged, or the high-energy Laplacian of the corresponding level is selected.
- the pixel or patch corresponding to the one with a statistical value indicating higher contrast may be selected and merged.
- the statistical value representing the contrast is the brightness value of a plurality of pixels constituting the corresponding patch. It may be the standard deviation or the average of the absolute deviations.
- the statistical value representing the contrast is the value of the plurality of pixels constituting the corresponding patch. It may be the average value or median of the brightness value.
- the high-energy frequency component images for each of the plurality of frequency bands may include high-energy frequency component images for each of the plurality of frequency bands decomposed by Fourier transform or wavelet transform.
- the low-energy frequency component image for each frequency band may include a plurality of low-energy frequency component images for each frequency band decomposed by Fourier transform or wavelet transform, and the merged frequency component image may include the high-energy frequency component image and the low-energy frequency component image.
- Frequency component images can be merged for each frequency band and generated using inverse Fourier transform or inverse wavelet transform.
- the high-energy frequency component image and the low-energy frequency component image may be merged with each other on a pixel basis for each frequency band or on a patch basis including a plurality of pixels, and the high-energy frequency component image and the low-energy frequency component image may be merged with each other.
- the pixel or patch corresponding to the statistical value indicating greater contrast among the corresponding patches of the high-energy frequency component image and the low-energy frequency component image of the corresponding frequency band may be selected and merged.
- the statistical value representing the contrast is the absolute value of the plurality of pixel values constituting the corresponding patch. It can be the average or median.
- the standard image may be generated by merging frequency component images for each frequency band that constitute the merged frequency component image.
- the image processor may be configured to further perform the step of registering one or more of the high-energy image and the low-energy image, and the registration may include bone masking information and soft tissue to reflect differences in motion between bone and soft tissue. It may include multiple image registrations each performed using masking information.
- the matching step includes generating a bone image and a soft tissue image through a subtraction operation of the high-energy image and the low-energy image, respectively, and bone including the bone masking information from the generated bone image and the generated soft tissue image.
- the bone masking image may include edge position information of a bone included in the bone image
- the soft tissue masking image may include edge position information of a soft tissue included in the soft tissue image.
- Primary registration using the bone masking image may use an image registration algorithm based on global optimization.
- the image registration algorithm may be an image registration algorithm that focuses on bone motion using a Free-Form Deformation (FD) method.
- FFD Free-Form Deformation
- Additional registration using the soft tissue masking image can be performed by a technique of locally registering the high-energy image and the low-energy image by measuring the similarity in patch units containing a predetermined number of pixels.
- the similarity may be measured through calculation of pixel values or information entropy between the high-energy image and the low-energy image.
- NCC Normalized Cross Correlation
- MI Magnetic Information
- An X-ray imaging device includes an X-ray irradiation module configured to irradiate X-rays, and a device configured to detect X-rays irradiated from the It includes an X-ray detection module, and an image processor configured to generate an X-ray image using an output signal of the X-ray detection module.
- the image processor may include obtaining a high-energy image and a low-energy image respectively obtained by X-rays of relatively high energy and relatively low energy, matching one or more of the high-energy image and the low-energy image, and performing the matching.
- the registration includes multiple image registrations performed using bone masking information and soft tissue masking information, respectively, to reflect differences in motion between bone and soft tissue.
- the X-ray imaging method includes the steps of irradiating X-rays toward an inspection object, detecting the X-rays that have passed through the inspection object and generating a corresponding digital signal, and Includes creation steps.
- the step of generating the X-ray image includes obtaining a high-energy image and a low-energy image obtained by Generating a frequency component image, decomposing the low energy image to generate a low energy frequency component image for each of a plurality of frequency bands, at least a portion of the high energy frequency component image for each of the plurality of frequency bands and low energy for each of the plurality of frequency bands. It includes generating a merged frequency component image by merging at least part of the frequency component image, and generating a standard image using the merged frequency component image.
- An X-ray imaging method includes the steps of irradiating X-rays toward an inspection object, detecting X-rays that have passed through the inspection object and generating a corresponding digital signal, and using the digital signal to create an It includes the step of generating.
- the step of generating the X-ray image includes acquiring a high-energy image and a low-energy image obtained by and generating one or more of a standard image, a bone image, and a soft tissue image through an operation using the high-energy image and the low-energy image that have undergone the matching step.
- the registration includes multiple image registrations performed using bone masking information and soft tissue masking information respectively to reflect differences in motion between bone and soft tissue.
- motion noise of an image generated by subtraction image processing can be reduced. Additionally, the image quality of standard images, soft tissue images, and bone images obtained by irradiating dual energy X-rays can be improved.
- FIG. 1 is a diagram schematically showing an X-ray imaging device according to an embodiment of the present invention.
- Figure 2 is a schematic block diagram of an X-ray imaging device according to an embodiment of the present invention.
- Figure 3 is a flowchart schematically showing a dual energy subtraction image processing method according to an embodiment of the present invention.
- Figure 4 is a graph showing the change in mass attenuation coefficient according to the energy of X-rays.
- Figure 5 shows examples of low-energy images and high-energy images obtained by low-energy X-rays and high-energy X-rays, respectively.
- Figure 6 shows a bone image without noise reduction technology using artificial intelligence and a bone image with noise reduction technology using artificial intelligence applied, respectively.
- Figure 7 is a flowchart showing the image registration process according to an embodiment of the present invention.
- Figure 8 shows an example of a masking image extracted by distinguishing the location and motion occurrence information of bone and soft tissue generated for image registration according to an embodiment of the present invention.
- Figure 9 is a diagram for explaining image registration using a bone masking image during the image registration process according to an embodiment of the present invention.
- Figure 10 shows an example of an image obtained by application of an image registration process according to an embodiment of the present invention.
- Figure 11 shows a schematic flowchart of a method for generating a standard image according to an embodiment of the present invention.
- FIG. 12 is a diagram illustrating the creation of a Laplacian pyramid image and a Gaussian pyramid image for generating a standard image according to an embodiment of the present invention, and the creation of a merged Laplacian pyramid image by merging them.
- Figure 13 is a diagram for explaining the process of generating a Gaussian pyramid image and a Laplacian pyramid image according to an embodiment of the present invention.
- Figure 14 is a diagram for explaining the process of merging a high-energy Laplacian pyramid image and a low-energy Laplacian pyramid image according to an embodiment of the present invention.
- FIG. 15 is a diagram illustrating a pixel or patch-wise merging method when merging a high-energy Laplacian pyramid image and a low-energy Laplacian pyramid image according to an embodiment of the present invention.
- Figure 16 is a diagram for explaining a method of generating a merged frequency component image according to an embodiment of the present invention.
- Figure 17 is a diagram showing the filtering process of discrete wavelet transform according to an embodiment of the present invention.
- Figure 18 is a diagram for explaining the process of generating a subband component image by discrete wavelet transform according to an embodiment of the present invention.
- the X-ray imaging device 10 includes an X-ray irradiation module 11 that generates and irradiates X-rays, and It includes X-ray detection modules 12 and 13 that detect.
- the X-ray detection modules 12 and 13 include a first X-ray detection module 12 for implementing a bed type imaging structure and a second X-ray detection module for implementing a stand type imaging structure ( 13) may be included.
- the X-ray irradiation module 11 is configured to be capable of linear movement and rotational movement so as to face any one of the first and second X-ray detection modules 12 and 13.
- the X-ray irradiation module 11 may include an X-ray source that generates X-rays, and receives power from the power module 15 to generate X-rays.
- the connection frame 17 extends upward on the power module 15 and may be provided with a guide groove 19 for guiding the upward and downward movement of the X-ray irradiation module 11.
- the X-ray irradiation module 11 is fastened to the connection frame 17 in a manner that allows movement in the vertical direction through the guide groove 19.
- the connection block 21 is fastened to the connection frame 17 so as to be movable in the vertical direction, and the X-ray irradiation module 11 is supported on the connection block 21 so as to move in the up and down direction together with the connection block 21.
- the X-ray irradiation module 11 may be supported on the connection block 21 so as to be rotatable about a horizontal axis.
- the power module 15 may be configured to be movable in the horizontal direction on the movable frame 23 extending in the horizontal direction.
- the moving frame 23 may be provided with a guide rail 25 extending in the horizontal direction, and the power module 15 may be moved in the horizontal direction through the guide rail 25. It is placed on top.
- the first X-ray detection module 12 may be installed on the connection frame 17 to face the X-ray irradiation module 11 in the vertical direction. X-ray imaging may be performed using the X-ray irradiation module 11 and the first X-ray detection module 12.
- a support table configured to allow an object, for example, a patient, to be placed on it may be placed, and the X-ray irradiation module 11 and the first X-ray detection module 12 are aligned to be positioned above and below the support table, respectively. After this, X-ray imaging can be done.
- the second X-ray detection module 13 may be supported on a separate stand 24 to be movable in the vertical direction.
- X-ray imaging may be performed using the X-ray irradiation module 11 and the second X-ray detection module 13.
- the X-ray irradiation module 11 rotates with respect to the connection block 21 and is aligned to face the second X-ray detection module 13.
- X-rays are irradiated through the irradiation module 11 and the second X-ray detection module 13 receives the X-rays that have passed through the patient, thereby performing X-ray imaging.
- the first and second X-ray detection modules 12 and 13 may each include an X-ray detector for detecting X-rays, and the X-ray detector may have a retractable or stationary structure. Additionally, the X-ray detector may be a cassette-type X-ray detector and, when necessary, can be stored in a storage unit such as a bucky and used. The cassette-type digital X-ray detector can convert incident X-rays into electrical signals capable of image signal processing.
- the X-ray detector may include a pixel circuit board including a thin film transistor, and may include a plurality of switching cell elements and photoelectric conversion elements arranged in a matrix.
- the X-ray detector may be a direct detector that includes a pixel circuit board and an optical conductor with optical conductivity, or it may be an indirect detector that includes a pixel circuit board and a light emitting layer such as a scintillator. .
- FIG. 2 shows a schematic block diagram of an X-ray imaging device according to an embodiment of the present invention.
- the X-ray irradiation module 11 is configured to irradiate X-rays 27 toward the patient S lying on a table 28 capable of transmitting ultrasonic waves.
- the system controller 31 controls the entire system, receives shooting commands input through a user interface 32 such as a keyboard, mouse, or touch screen input device, and controls the process to be performed accordingly.
- a user interface 32 such as a keyboard, mouse, or touch screen input device
- the system controller 31 controls the exposure controller 33, which controls the operation of the power module 25, and the exposure controller 33 controls the power module 25 accordingly to expose X-rays. Let this happen.
- the system controller 31 outputs a signal to control the detector controller 34 for controlling the X-ray detection module 12.
- the system controller 31 outputs a corresponding signal to the image processor 35.
- the system controller 31 can transmit and receive necessary data from the exposure controller 33, the detector controller 34, and the image processor 35.
- the image processor 35 may receive necessary information from the detector controller 34 and transmit the data necessary for image capture to the exposure controller 33.
- the X-ray detection module 12 detects X-rays irradiated from the X-ray irradiation module 11 and passed through the patient S and generates a digital signal corresponding to the detected X-rays.
- the image processor 35 generates an image using the digital image signal received from the X-ray detection module 12. Image processing performed by the image processor 35 and images obtained accordingly will be described later.
- the display 36 displays an image acquired by the image processor 35 and may be any display capable of displaying an image, such as a liquid crystal display device or an OLED display device.
- the image storage device 37 may be a memory capable of storing acquired images, and may be any type of memory such as memory, database, or cloud storage device.
- Figure 3 is a flow chart schematically showing a dual energy subtraction image processing method according to an embodiment of the present invention, and the image processor 35 described above may be configured to perform dual energy subtraction image processing.
- the image processor 35 is configured to perform the image processing process described below and may include a microprocessor, memory, and related hardware and software.
- a high-energy image (I H ) and a low-energy image (I L ) are acquired using dual energy, that is, high-energy and low-energy X-rays, respectively (101, 102).
- a high-energy image can be obtained by irradiating X-rays with relatively high energy (120 kVp)
- a low-energy image can be obtained by irradiating X-rays with relatively low energy (60 kVp).
- Different images are obtained depending on the difference in X-ray mass attenuation coefficient for soft tissue and bone under high-energy and low-energy conditions.
- Figure 4 is a graph showing the change in mass attenuation coefficient according to the energy of X-rays
- Figure 5 shows examples of low-energy images (a) and high-energy images (b) obtained by low-energy X-rays and high-energy X-rays, respectively.
- High-energy images and low-energy images can be obtained by irradiating high-energy, X-rays, and low-energy X-rays through control of the X-ray irradiation unit 11 and acquiring images through the image acquisition unit 13, respectively.
- FIG. 3 exemplarily shows a case in which noise reduction is performed on both a high-energy image and a low-energy image.
- noise reduction may be performed on only one of the high-energy image and the low-energy image.
- noise reduction can be achieved through learning through artificial intelligence (AI).
- AI artificial intelligence
- artificial intelligence technology using the CycleGAN architecture can learn random noise and reduce noise while minimizing anatomical loss in images.
- Figure 6 shows a bone image without noise reduction technology using artificial intelligence (a) and a bone image with noise reduction technology using artificial intelligence (b), respectively. It can be seen that the image quality of the finally obtained subtraction image is improved by applying noise reduction technology using artificial intelligence.
- Figure 3 exemplarily shows a case in which image registration is performed on both a high-energy image and a low-energy image, but image registration may be performed on only one of the high-energy image and the low-energy image.
- Figure 7 shows a schematic flowchart of the image registration process according to an embodiment of the present invention.
- Image registration is an image processing method that corrects for distortions caused by breathing, heartbeat, etc. that inevitably occur when imaging the same patient in order to compare them across time or viewpoints.
- imaging is performed by irradiating X-rays of different energies twice, a time interval of approximately 100 to 200 ms inevitably occurs between the two imaging, resulting in motion noise due to movement of the heart, pulmonary blood vessels, etc., resulting in image registration.
- the process becomes difficult and motion noise negatively affects material separation performance and imaging diagnostic accuracy.
- motion noise is reduced by applying an image registration algorithm that performs precise correction calculations while preventing the image from being artificially distorted.
- medical image registration uses a non-rigid registration method to prevent the image from being artificially distorted by considering the characteristics of the medical image. It is known to use multi-resolution image processing techniques such as Gaussian or Laplacian pyramids to take into account differences in the size and direction of motion depending on human tissue, but the existing patch unit The method of predicting motion and performing correction had limitations in accurately calculating motion for each human tissue. To overcome this limitation, in an embodiment of the present invention, the accuracy and calculation speed of the image registration algorithm are improved by distinguishing the motion of soft tissue and bone and applying each algorithm. The motion of the shoulders, spine, ribs, etc.
- the embodiment of the present invention applies an image registration algorithm that processes soft tissue and bone separately.
- the high-energy image (I H ) and the low-energy image (I L ) are subtracted to obtain the bone image (I BONE ) and Soft tissue images (I SOFT ) are respectively generated (201).
- I H and I L are used for the high-energy image and low-energy image, respectively.
- a bone masking image (I BONE_MASK ) and a soft tissue masking image (I SOFT_MASK ) are generated from the generated bone image (I BONE) and soft tissue image (I SOFT ) , respectively.
- the bone masking image (I BONE_MASK ) can be derived from the bone image (I BONE ) and includes location information of bones included in the image, specifically edge location information
- the soft tissue masking image (I SOFT_MASK ) is a soft tissue image.
- I SOFT and may include location information of the soft tissue included in the image, specifically location information of the edge of the soft tissue.
- a masking image is generated by extracting each position information.
- the principle of subtracting images obtained by high-energy X-rays and low-energy It is extracted from temporarily acquired soft tissue images and bone images.
- Soft tissue images and bone images contain only soft tissue or bone information, and since they are not registered, they also include information on the occurrence of motion noise. Therefore, by extracting edge information from these images, it is possible to obtain a masking image of the location of each bone and soft tissue and the location of motion occurrence in each tissue.
- Figure 8 shows masking images extracted by distinguishing the location and motion occurrence information of bones and soft tissues, where (a) is a masking image for bones and (b) is a masking image for soft tissues.
- the high-energy (I H ) and/or low-energy image (I L ) are firstly registered (203) using the generated bone masking image (I BONE_MASK ), and then the generated soft tissue masking is performed.
- the image (I SOFT_MASK ) is used to secondly register the firstly registered high-energy ( IH ) and/or low-energy image ( IL ) (204).
- Image registration using the bone masking image (I BONE_MASK ) is image registration for global optimization
- image registration using the soft tissue masking image (I SOFT_MASK ) is image registration for local optimization.
- the first image registration using a bone masking image is a global optimization to prevent motion registration across the image from being registered in conflicting directions and to produce optimized results by focusing on bone motion.
- Adopt a technique.
- the first image registration can be done with a focus on bone motion using the Free-Form Deformation (FFD) method, an image registration algorithm based on global optimization, to naturally register the global movements of the human body.
- FFD Free-Form Deformation
- Figure 9 shows an example of registration by image deformation by FFD.
- Figure 9 (a) shows the image before transformation, and (b) shows the control points of the control grid selected in the image (a).
- the control point shown in (b) of FIG. 9 can be transformed as in (c), and the image in (a) can be transformed as in (d) accordingly.
- This FFD method is a representative image transformation technique that allows objects to be naturally transformed so as not to violate physical laws by manipulating the control points of the control grid.
- the secondary image registration using the soft tissue masking image takes into account the fact that the motion of soft tissues such as the heart and surrounding pulmonary blood vessels occurs relatively locally, A local technique is additionally performed to match the motion of soft tissue to the image obtained by first-order registration.
- the motion of pulmonary blood vessels can individually show various directions and sizes regardless of the surrounding area, so it is difficult to obtain accurate results when applying the FFD technique, in which the surrounding area is uniformly transformed according to changes in the control point.
- additional registration is a technique of locally matching high-energy and low-energy images by calculating the similarity between high-energy and low-energy images in small-sized patches containing a fixed number of pixels for the required soft tissue area. It is done by.
- methods such as NCC (Normalized Cross Correlation) or MI (Mutual Information) can be used to measure similarity, and NCC and MI calculate the pixel value correlation between two images or information entropy, respectively. This is a method of measuring similarity.
- Figure 10 shows an image obtained by applying an image matching algorithm to the image of the extracted region of interest.
- Figure 10 (a) shows an image obtained by applying image registration on a patch basis according to the existing method
- Figure 10 (b) shows an image of bone and soft tissue with different characteristics according to an embodiment of the present invention. It shows images obtained by separating motions and applying an image matching algorithm to each.
- the present invention by distinguishing the motions of bone and soft tissue and registering them respectively, even if the motions generated by each tissue conflict with each other, it is possible to distinguish them and register them precisely.
- the target image that is, the standard image 111, and the soft tissue image are obtained through operation 107 of the image-registered high-energy image (I H ) and the low-energy image (I L ).
- image) (112) and bone image (113) are generated.
- the standard image 111 can be calculated by adding the high-energy image (I H ) and the low-energy image (I L ), and the soft tissue image 1122 and bone image 113 can be calculated by combining the high-energy image (I H) and the low-energy image (I L ). It can be calculated by a subtraction operation of the image (I L ).
- a high-energy image and a low-energy image are each decomposed to generate a plurality of frequency component images, that is, images for each frequency band, and the generated plurality of high-energy frequency component images and a plurality of low-energy frequency images are respectively generated.
- a merged frequency component image is generated by merging the components for each corresponding frequency band, and a standard image is created using the merged frequency component image for each frequency band.
- a multi-resolution pyramid image is generated using a high-energy image and a low-energy image, thereby generating high-energy and low-energy frequency component images for each frequency band.
- high-energy and low-energy frequency component images for each frequency band are generated through Discrete Wavelet Transform (DWT), and in another embodiment, frequency component images are generated through Discrete Fourier Transform (DFT). Generate high-energy and low-energy frequency component images for each band.
- DWT Discrete Wavelet Transform
- DFT Discrete Fourier Transform
- FIG. 11 shows a schematic flowchart of a method for generating a standard image 111 according to an embodiment of the present invention
- FIG. 12 shows a schematic flowchart of a method for generating a standard image 111 according to an embodiment of the present invention.
- the image processing process is schematically shown.
- a standard image 111 of excellent quality with improved global and local contrast is generated by merging a high-energy image (I H ) and a low-energy image ( IL ) to which image registration is applied.
- the high-energy image (I H ) and the low-energy image (I L ) are converted to log scale as shown in Equation 1 below (302). This process is performed to create a linear relationship between the intensity of the tissue in the high-energy image (I H ) and the low-energy image (I L ).
- the high-energy image (I H ) and the low-energy image (I L ) are normalized (303).
- image standardization as shown in Equation 2 below may be selected as a method for normalization.
- a multi-resolution pyramid image that is, a high-energy and low-energy frequency component image for each frequency band, is generated using the normalized low-energy image and the high-energy image (304).
- the generated pyramid images of different resolutions represent frequency components for each band.
- the generated pyramid images of different resolutions represent frequency component images for each frequency band.
- the highest level Gaussian parimid component that is, the image in the low frequency band, shows global contrast, and as it moves to the higher frequency band, it shows detailed edge information such as thick edge information of bones and heart and pulmonary blood.
- a high-energy Laplacian image pyramid (L H ) and a high-energy Gaussian image pyramid (G H ) are generated from the normalized high-energy image
- a low-energy Laplacian image pyramid (L L ) and a low-energy image pyramid are generated from the normalized low-energy image.
- a Gaussian image pyramid (G L ) is created.
- the resolution of the image decreases. For example, if a pyramid image consists of four levels, the pyramid image at the lowest level has a resolution of 1000*1000, the pyramid image at the next level has a resolution of 500*500, and the pyramid image at the next level has a resolution of 250*250. resolution, and the highest level pyramid image can have a resolution of 125*125. In this way, multiple images of a pyramid structure with multi-resolution can be implemented.
- Gaussian and Laplacian pyramid images can be generated as shown in Equation 3 below.
- G L k , G H k , L L k , L H k are the k-level Gaussian and Laplacian pyramid images of the normalized low-energy image and the high-energy image
- D and U are down-sampling and up-sampling operators.
- * is a convolution operator
- g is a Gaussian kernel.
- the high-energy Laplacian pyramid image (L H ) and the low-energy Laplacian pyramid image (L L ) are merged at each level of the pyramid (305).
- components at each level are selected and merged to increase global and local contrast.
- a high-energy Laplacian pyramid image (L H ) and a low-energy Laplacian pyramid image (L L ) are merged at each level to generate a merged Laplacian pyramid image (L R ) including images of multiple levels.
- FIG. 14 and 15 schematically show an image processing process for merging a high-energy Laplacian pyramid image (L H ) and a low-energy Laplacian pyramid image (L L ).
- Each component (L R 1 , L R 2 , L R 3 , L R 4 ) of the merged Laplacian pyramid image (L R ) is merged by merging each component (L L 1 , L L 2 , L L 3 , L L 4 ). creates .
- the high-energy Laplacian pyramid image ( One pixel or patch of L H ) and the low-energy Laplacian pyramid image (L L ) may be selected and merged.
- whether to select the corresponding pixel or patch of the low-energy Laplacian pyramid image (L H ) and the high-energy Laplacian pyramid image (L L ) at the same level depends on the high-energy Gaussian pyramid image (G H ) and a statistical value representing the contrast of the corresponding patch of the low-energy Gaussian pyramid image (G L ).
- it may mean a patch containing a plurality of pixels surrounding a pixel of the Laplacian pyramid image of the corresponding patch of the Gaussian pyramid image, or a patch identical to the patch of the Laplacian pyramid image.
- the high-energy Gaussian pyramid image (G H ) and the low-energy Gaussian pyramid image (G L) at the level with the same resolution. ) of the corresponding patches the patch of the Laplacian pyramid image that has a statistical value indicating greater contrast (standard deviation of the contrast of pixels belonging to the patch, or average of the absolute deviation) is selected.
- Figure 15 shows the lowest-level high-energy Laplacian pyramid image (L H 1 ) and the low-energy Laplacian pyramid according to the comparison results between the lowest-level high-energy Gaussian pyramid image (G H 0 ) and the low-energy Gaussian pyramid image (G L 0 ).
- An example of merging images (L L 1 ) is shown.
- the Gaussian pyramid image (G H 0 , G L 0 ) and the Laplacian pyramid image (L H 1 , L L 1 ) are pyramid images of the same level, that is, images with the same resolution.
- the high-energy Gaussian pyramid image A statistical value representing the contrast of the same patch of (G H 0 ) and the low-energy Gaussian pyramid image (G L 0 ), for example, the standard deviation (STD H_11 , STD L_11 ) of the brightness of the pixels belonging to the patch is larger, i.e.
- the brightness value (I H_11 ) of the corresponding patch of the high-energy Laplacian pyramid image (L H 1 ) is equal to that of the lowest level image (L R 1 ) of the merged Laplacian pyramid image (L R ). It is selected based on the brightness value of the corresponding patch.
- Figure 15(b) shows an example of selecting the brightness value of the second patch of the lowest level image (L R 1 ) of the merged Laplacian pyramid image (L R ).
- the standard deviation (STD H_12 , STD L_12 ) of the brightness of the pixels belonging to the corresponding patches of the high-energy Gaussian pyramid image (G H 0 ) and the low-energy Gaussian pyramid image (G L 0 ) is larger, that is, The lower energy side is selected, and accordingly, the brightness value (I L_12 ) of the corresponding patch of the low-energy Laplacian image (L L 1 ) is selected as the brightness value of the corresponding patch of the merged Laplacian pyramid image (L R ).
- Pixel contrast values at higher levels of the pyramid represent global contrast and pixel contrast values at lower levels of the pyramid represent local contrast. In this way, the Laplacian components at each pyramid level can be determined.
- the merging of the high-energy Laplacian pyramid image (L H ) and the low-energy Laplacian pyramid image (L L ) represents the contrast of the corresponding patch of the high-energy Gaussian pyramid image and the low-energy Gaussian pyramid image. It is not based on a comparison of statistical values, but rather a statistical value representing the contrast of the corresponding patch of the high-energy Laplacian pyramid image and the low-energy Laplacian pyramid image, for example, the average value or median of the brightness of the pixels constituting the patch, whichever is larger. You can select .
- a merged image is generated from the Laplacian components of the merged Laplacian pyramid obtained by merging the high-energy Laplacian image and the low-energy Laplacian image (306).
- a merged image can be created by sequentially merging the Laplacian components starting from the highest level.
- the merged Laplacian pyramid images are sequentially merged from the highest level to the lowest level of the pyramid (sequentially from the bottom to the top in FIG. 16). Because high-level pyramid images represent global image components well, and low-level pyramid images represent local image components well, sequential merging from the highest level of the pyramid to the lowest levels focuses on the global image components first. This means gradually focusing on local image components.
- scale conversion is performed to return the log scale of the merged image to the original intensity scale (307). This creates a standard video.
- the normalized low-energy image and the high-energy image can be decomposed using discrete wavelet transform (DWT) to generate frequency component images for multiple frequency bands.
- DWT discrete wavelet transform
- Discrete wavelet transform is a method of improving transformation efficiency by decomposing an image into different frequency components according to human visual characteristics using a localized basis and examining and processing each component associated with the resolution corresponding to each frequency band. .
- Discrete wavelet transform can be expressed as Equation 4 below.
- x(t) is the original image signal
- ⁇ is a wavelet function
- 2 j is a compression coefficient that determines the size
- k2 j is a transition coefficient related to movement on the time axis and a parent function whose size changes depending on the scale. (mother wavelet) is used.
- the original discrete signal is decomposed into several subband signals with different frequencies through down-sampling of multi-resolution analysis and synthesized into an original discrete signal through up-sampling.
- the original image signal is decomposed into a low-pass component (L) and a high-pass component (H) using a low-pass filter (LPF, h(n)) and a high-pass filter (HPF, g(n)).
- LPF, h(n) low-pass filter
- HPF, g(n) high-pass filter
- wavelet transform can interpret spatial information and frequency information in each subband, it enables adaptive image processing such as reducing specific high-frequency components corresponding to noise or preserving specific edge information.
- the transformed image obtained by performing discrete wavelet transform on the original image may include four subband component images (LL, LH, HL, HH).
- the LL subband component image can be made up of coefficients excluded from the high-frequency component in the image by applying a horizontal low-pass filter (LPF_y) and a vertical low-pass filter (LPF_x) to the original image (x), and the HH subband component
- the image is obtained by applying a horizontal high-pass filter (HPF_y) and a vertical high-pass filter (HPF_x) to the original image (x), and shows only high-frequency components, as opposed to the LL subband component image.
- the LH subband component image is obtained by applying a horizontal high-pass filter (HPF_y) to the original image (x) and includes error components of horizontal frequencies.
- the HL subband component image is obtained by applying a vertical high-frequency filter (HPF_x) to the original image (x) and includes a vertical frequency error component.
- first down sampling and second down sampling may be performed after applying a high-frequency or low-frequency pass filter, respectively.
- the high-energy component and the low-energy component are selected for each pixel of the image or each patch of pixels of the image. Any one pixel or patch may be selected and merged.
- the statistical value representing the contrast is the average value or median of the absolute value of a plurality of pixel values constituting the corresponding patch. You can.
- high-frequency frequency component images and low-frequency frequency component images for each frequency band can be generated by applying discrete Fourier transform (DFT).
- DFT discrete Fourier transform
- Equation 7 Equation 7 below.
- x is the original image signal
- k is 0, 1, 2, ... It is N-1.
- Equation 8 Equation 8
- x is the original image signal
- n is 0, 1, 2, ... It is N-1.
- a soft tissue image 112 and a bone image are generated through operation 107 of the image-registered high-energy image (I H ) and low-energy image (I L ).
- the soft tissue image 112 and the bone image 113 can be obtained through a subtraction operation that applies a subtraction factor to the low-energy image from the high-energy image. Obtaining soft tissue images and bone images through subtraction of such high-energy images and low-energy images can be performed using known methods.
- the present invention relates to an X-ray imaging device and method, and can be applied to X-ray imaging equipment, so it has industrial applicability.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Optics & Photonics (AREA)
- High Energy & Nuclear Physics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
Description
Claims (35)
- 엑스선을 조사할 수 있도록 구성되는 엑스선 조사 모듈,상기 엑스선 조사 모듈에서 조사되어 검사대상체를 통과한 엑스선을 검출하여 해당하는 디지털 신호를 출력할 수 있도록 구성되는 엑스선 검출 모듈, 그리고상기 엑스선 검출 모듈의 출력 신호를 이용하여 엑스선 영상을 생성할 수 있도록 구성되는 이미지 프로세서를 포함하고,상기 이미지 프로세서는상대적으로 큰 에너지와 상대적으로 작은 에너지의 엑스선에 의해 각각 얻어진 고에너지 영상과 저에너지 영상을 획득하는 단계,상기 고에너지 영상을 분해하여 복수의 주파수 대역별 고에너지 주파수 성분 영상을 생성하는 단계,상기 저에너지 영상을 분해하여 복수의 주파수 대역별 저에너지 주파수 성분 영상을 생성하는 단계,상기 복수의 주파수 대역별 고에너지 주파수 성분 영상의 적어도 일부와 상기 복수의 주파수 대역별 저에너지 주파수 성분 영상의 적어도 일부를 병합하여 병합된 주파수 성분 영상을 생성하는 단계, 그리고 상기 병합된 주파수 성분 영상을 이용하여 스탠다드 영상을 생성하는 단계를 수행하도록 구성되는 엑스선 촬영 장치.
- 제1항에 있어서,상기 복수의 주파수 대역별 고에너지 주파수 성분 영상은 복수의 레벨의 고에너지 라플라시안 피라미드 영상과 복수의 레벨의 고에너지 가우시안 피라미드 영상을 포함하고,상기 복수의 주파수 대역별 저에너지 주파수 성분 영상은 복수의 레벨의 저에너지 라플라시안 피라미드 영상과 복수의 레벨의 저에너지 가우시안 피라미드 영상을 포함하고,상기 병합된 주파수 성분 영상은 상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상이 각 레벨 별로 병합되어 생성되는 엑스선 촬영 장치.
- 제2항에 있어서,상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상은 각 레벨 별로 픽셀 단위로 또는 복수의 픽셀을 포함하는 패치 단위로 서로 병합되고,상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상을 상기 레벨 별로 병합할 때 해당 레벨의 고에너지 가우시안 피라미드 영상과 저에너지 가우시안 피라미드 영상의 해당하는 패치 중 더 큰 콘트라스트를 나타내는 통계값을 갖는 쪽에 해당하는 픽셀 또는 패치가 선택되어 병합이 이루어지거나 해당 레벨의 고에너지 라플라시안 피라미드 영상과 저에너지 라플라시안 피라미드 영상의 해당하는 패치 중 더 콘트라스트를 나타내는 통계값을 갖는 쪽에 해당하는 픽셀 또는 패치가 선택되어 병합이 이루어지는 엑스선 촬영 장치.
- 제3항에 있어서,상기 고에너지 가우시안 피라미드 영상과 상기 저에너지 가우시안 피라미드 영상의 해당하는 패치의 통계값의 비교를 기초로 상기 병합이 이루어지는 경우 상기 콘트라스트를 나타내는 통계값은 상기 해당하는 패치를 구성하는 복수의 픽셀의 밝기값의 표준편차 또는 절대편차의 평균이고,상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상의 해당하는 패치의 통계값의 비교를 기초로 상기 병합이 이루어지는 경우 상기 콘트라스트를 나타내는 통계값은 상기 해당하는 패치를 구성하는 복수의 픽셀의 밝기값의 평균값 또는 메디안인 엑스선 촬영 장치.
- 제1항에 있어서,상기 복수의 주파수 대역별 고에너지 주파수 성분 영상은 푸리에 변환 또는 웨이블릿 변환으로 분해된 복수의 주파수 대역별 고에너지 주파수 성분 영상을 포함하고,상기 복수의 주파수 대역별 저에너지 주파수 성분 영상은 푸리에 변환 또는 웨이블릿 변환으로 분해된 복수의 주파수 대역별 저에너지 주파수 성분 영상을 포함하고,상기 병합된 주파수 성분 영상은 상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상이 각 주파수 대역별로 병합되어 푸리에 역변환 또는 웨이블릿 역변환으로 생성되는 엑스선 촬영 장치.
- 제5항에 있어서,상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상은 각 주파수 대역별로 픽셀 단위로 또는 복수의 픽셀을 포함하는 패치 단위로 서로 병합되고,상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상을 상기 주파수 대역별로 병합할 때 해당 주파수 대역의 고에너지 주파수 성분 영상과 저에너지 주파수 성분 영상의 대응하는 패치 중 더 큰 콘트라스트를 나타내는 통계값을 갖는 쪽에 해당하는 픽셀 또는 패치가 선택되어 병합이 이루어지는 엑스선 촬영 장치.
- 제6항에 있어서,상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상의 대응하는 패치의 통계값의 비교를 기초로 상기 병합이 이루어지는 경우 상기 콘트라스트를 나타내는 통계값은 상기 해당하는 패치를 구성하는 복수의 픽셀값의 절대치의 평균값 또는 메디안인 엑스선 촬영 장치.
- 제1항에 있어서,상기 스탠다드 영상은 상기 병합된 주파수 성분 영상을 구성하는 복수의 주파수 대역별 주파수 성분 영상을 병합하여 생성되는 엑스선 촬영 장치.
- 제1항에 있어서,상기 이미지 프로세서는 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 정합하는 단계를 더 수행하도록 구성되고,상기 정합은 뼈와 연부조직의 모션의 차이를 반영할 수 있도록 뼈 마스킹 정보와 연부조직 마스킹 정보를 각각 이용하여 수행되는 복수의 영상 정합을 포함하는 엑스선 촬영 장치.
- 제9항에 있어서,상기 정합 단계는상기 고에너지 영상과 상기 저에너지 영상의 차감 연산을 통해 뼈 영상과 연부조직 영상을 각각 생성하는 단계,상기 생성된 뼈 영상과 상기 생성된 연부조직 영상으로부터 상기 뼈 마스킹 정보를 포함하는 뼈 마스킹 영상과 연부조직 마스킹 영상을 각각 생성하는 단계,상기 뼈 마스킹 영상을 이용하여 정합 대상인 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 일차적으로 정합하는 단계, 그리고상기 연부조직 마스킹 영상을 이용하여 상기 일차적으로 정합된 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 추가로 정합하는 단계를 포함하는 엑스선 촬영 장치.
- 제10항에 있어서,상기 뼈 마스킹 영상은 상기 뼈 영상에 포함된 뼈의 에지 위치 정보를 포함하고,상기 연부조직 마스킹 영상은 상기 연부조직 영상에 포함된 연부조직의 에지 위치 정보를 포함하는 엑스선 촬영 장치.
- 제10항에 있어서,상기 뼈 마스킹 영상을 이용하는 일차 정합은 전역적 최적화(global optimization) 기반의 영상 정합 알고리즘을 이용하는 엑스선 촬영 장치.
- 제12항에 있어서,상기 영상 정합 알고리즘은 FFD(Free-Form Deformation) 방법으로 뼈의 모션에 중점을 두는 영상 정합 알고리즘인 엑스선 촬영 장치.
- 제10항에 있어서,상기 연부조직 마스킹 영상을 이용하는 추가 정합은 미리 정해진 개수의 복수의 픽셀을 포함하는 패치 단위로 고에너지 영상과 저에너지 영상의 유사도를 측정하여 국소적으로 정합하는 기법에 의해 이루어지는 엑스선 촬영 장치.
- 제14항에 있어서,상기 유사도는 상기 고에너지 영상과 상기 저에너지 영상 간의 화소값 또는 정보 엔트로피의 계산을 통해 측정되는 엑스선 촬영 장치.
- 제15항에 있어서,상기 유사도는 NCC(Normalized Cross Correlation) 및 MI(Mutual Information) 중 하나 이상을 이용하여 측정되는 엑스선 촬영 장치.
- 엑스선을 조사할 수 있도록 구성되는 엑스선 조사 모듈,상기 엑스선 조사 모듈에서 조사되어 검사대상체를 통과한 엑스선을 검출하여 해당하는 디지털 신호를 출력할 수 있도록 구성되는 엑스선 검출 모듈, 그리고상기 엑스선 검출 모듈의 출력 신호를 이용하여 엑스선 영상을 생성할 수 있도록 구성되는 이미지 프로세서를 포함하고,상기 이미지 프로세서는상대적으로 큰 에너지와 상대적으로 작은 에너지의 엑스선에 의해 각각 얻어진 고에너지 영상과 저에너지 영상을 획득하는 단계,상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 정합하는 단계, 그리고상기 정합하는 단계를 거친 상기 고에너지 영상과 상기 저에너지 영상을 이용하는 연산을 통해 스탠다드 영상, 뼈 영상 그리고 연부조직 영상 중 하나 이상을 생성하는 단계를 수행하도록 구성되고,상기 정합은 뼈와 연부조직의 모션의 차이를 반영할 수 있도록 뼈 마스킹 정보와 연부조직 마스킹 정보를 각각 이용하여 수행되는 복수의 영상 정합을 포함하는 엑스선 촬영 장치.
- 제17항에 있어서,상기 정합 단계는상기 고에너지 영상과 상기 저에너지 영상의 차감 연산을 통해 뼈 영상과 연부조직 영상을 각각 생성하는 단계,상기 생성된 뼈 영상과 상기 생성된 연부조직 영상으로부터 상기 뼈 마스킹 정보를 포함하는 뼈 마스킹 영상과 연부조직 마스킹 영상을 각각 생성하는 단계,상기 뼈 마스킹 영상을 이용하여 정합 대상인 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 일차적으로 정합하는 단계, 그리고상기 연부조직 마스킹 영상을 이용하여 상기 일차적으로 정합된 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 추가로 정합하는 단계를 포함하는 엑스선 촬영 장치.
- 제18항에 있어서,상기 뼈 마스킹 영상은 상기 뼈 영상에 포함된 뼈의 에지 위치 정보를 포함하고,상기 연부조직 마스킹 영상은 상기 연부조직 영상에 포함된 연부조직의 에지 위치 정보를 포함하는 엑스선 촬영 장치.
- 검사대상체를 향해 엑스선을 조사하는 단계,상기 검사대상체를 통과한 엑스선을 검출하여 해당하는 디지털 신호를 생성하는 단계, 그리고상기 디지털 신호를 이용하여 엑스선 영상을 생성하는 단계를 포함하고,상기 엑스선 영상을 생성하는 단계는상대적으로 큰 에너지와 상대적으로 작은 에너지의 엑스선에 의해 각각 얻어진 고에너지 영상과 저에너지 영상을 획득하는 단계,상기 고에너지 영상을 분해하여 복수의 주파수 대역별 고에너지 주파수 성분 영상을 생성하는 단계,상기 저에너지 영상을 분해하여 복수의 주파수 대역별 저에너지 주파수 성분 영상을 생성하는 단계,상기 복수의 주파수 대역별 고에너지 주파수 성분 영상의 적어도 일부와 상기 복수의 주파수 대역별 저에너지 주파수 성분 영상의 적어도 일부를 병합하여 병합된 주파수 성분 영상을 생성하는 단계, 그리고상기 병합된 주파수 성분 영상을 이용하여 스탠다드 영상을 생성하는 단계를 포함하는 엑스선 촬영 방법.
- 제20항에 있어서,상기 복수의 주파수 대역별 고에너지 주파수 성분 영상은 복수의 레벨의 고에너지 라플라시안 피라미드 영상과 복수의 레벨의 고에너지 가우시안 피라미드 영상을 포함하고,상기 복수의 주파수 대역별 저에너지 주파수 성분 영상은 복수의 레벨의 저에너지 라플라시안 피라미드 영상과 복수의 레벨의 저에너지 가우시안 피라미드 영상을 포함하고,상기 병합된 주파수 성분 영상은 상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상이 각 레벨 별로 병합되어 생성되는 엑스선 촬영 방법.
- 제21항에 있어서,상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상은 각 레벨 별로 픽셀 단위로 또는 복수의 픽셀을 포함하는 패치 단위로 서로 병합되고,상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상을 상기 레벨 별로 병합할 때 해당 레벨의 고에너지 가우시안 피라미드 영상과 저에너지 가우시안 피라미드 영상의 해당하는 패치 중 더 큰 콘트라스트를 나타내는 통계값을 갖는 쪽에 해당하는 픽셀 또는 패치가 선택되어 병합이 이루어지거나 해당 레벨의 고에너지 라플라시안 피라미드 영상과 저에너지 라플라시안 피라미드 영상의 해당하는 패치 중 더 콘트라스트를 나타내는 통계값을 갖는 쪽에 해당하는 픽셀 또는 패치가 선택되어 병합이 이루어지는 엑스선 촬영 방법.
- 제22항에 있어서,상기 고에너지 가우시안 피라미드 영상과 상기 저에너지 가우시안 피라미드 영상의 해당하는 패치의 통계값의 비교를 기초로 상기 병합이 이루어지는 경우 상기 콘트라스트를 나타내는 통계값은 상기 해당하는 패치를 구성하는 복수의 픽셀의 밝기값의 표준편차 또는 절대편차의 평균이고,상기 고에너지 라플라시안 피라미드 영상과 상기 저에너지 라플라시안 피라미드 영상의 해당하는 패치의 통계값의 비교를 기초로 상기 병합이 이루어지는 경우 상기 콘트라스트를 나타내는 통계값은 상기 해당하는 패치를 구성하는 복수의 픽셀의 밝기값의 평균값 또는 메디안인 엑스선 촬영 방법.
- 제20항에 있어서,상기 복수의 주파수 대역별 고에너지 주파수 성분 영상은 푸리에 변환 또는 웨이블릿 변환으로 분해된 복수의 주파수 대역별 고에너지 주파수 성분 영상을 포함하고,상기 복수의 주파수 대역별 저에너지 주파수 성분 영상은 푸리에 변환 또는 웨이블릿 변환으로 분해된 복수의 주파수 대역별 저에너지 주파수 성분 영상을 포함하고,상기 병합된 주파수 성분 영상은 상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상이 각 주파수 대역별로 병합되어 푸리에 역변환 또는 웨이블릿 역변환으로 생성되는 엑스선 촬영 방법.
- 제24항에 있어서,상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상은 각 주파수 대역별로 픽셀 단위로 또는 복수의 픽셀을 포함하는 패치 단위로 서로 병합되고,상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상을 상기 주파수 대역별로 병합할 때 해당 주파수 대역의 고에너지 주파수 성분 영상과 저에너지 주파수 성분 영상의 대응하는 패치 중 더 큰 콘트라스트를 나타내는 통계값을 갖는 쪽에 해당하는 픽셀 또는 패치가 선택되어 병합이 이루어지는 엑스선 촬영 방법.
- 제25항에 있어서,상기 고에너지 주파수 성분 영상과 상기 저에너지 주파수 성분 영상의 대응하는 패치의 통계값의 비교를 기초로 상기 병합이 이루어지는 경우 상기 콘트라스트를 나타내는 통계값은 상기 해당하는 패치를 구성하는 복수의 픽셀값의 절대치의 평균값 또는 메디안인 엑스선 촬영 방법.
- 제20항에 있어서,상기 스탠다드 영상은 상기 병합된 주파수 성분 영상을 구성하는 복수의 주파수 대역별 주파수 성분 영상을 병합하여 생성되는 엑스선 촬영 방법.
- 제20항에 있어서,상기 엑스선 영상을 생성하는 단계는 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 정합하는 단계를 더 포함하고,상기 정합은 뼈와 연부조직의 모션의 차이를 반영할 수 있도록 뼈 마스킹 정보와 연부조직 마스킹 정보를 각각 이용하여 수행되는 복수의 영상 정합을 포함하는 엑스선 촬영 방법.
- 제28항에 있어서,상기 정합 단계는상기 고에너지 영상과 상기 저에너지 영상의 차감 연산을 통해 뼈 영상과 연부조직 영상을 각각 생성하는 단계,상기 생성된 뼈 영상과 상기 생성된 연부조직 영상으로부터 상기 뼈 마스킹 정보를 포함하는 뼈 마스킹 영상과 연부조직 마스킹 영상을 각각 생성하는 단계,상기 뼈 마스킹 영상을 이용하여 정합 대상인 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 일차적으로 정합하는 단계, 그리고상기 연부조직 마스킹 영상을 이용하여 상기 일차적으로 정합된 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 추가로 정합하는 단계를 포함하는 엑스선 촬영 방법.
- 제29항에 있어서,상기 뼈 마스킹 영상은 상기 뼈 영상에 포함된 뼈의 에지 위치 정보를 포함하고,상기 연부조직 마스킹 영상은 상기 연부조직 영상에 포함된 연부조직의 에지 위치 정보를 포함하는 엑스선 촬영 방법.
- 제29항에 있어서,상기 뼈 마스킹 영상을 이용하는 일차 정합은 전역적 최적화(global optimization) 기반의 영상 정합 알고리즘을 이용하는 엑스선 촬영 방법.
- 제29항에 있어서,상기 연부조직 마스킹 영상을 이용하는 추가 정합은 미리 정해진 개수의 복수의 픽셀을 포함하는 패치 단위로 고에너지 영상과 저에너지 영상의 유사도를 측정하여 국소적으로 정합하는 기법에 의해 이루어지는 엑스선 촬영 방법.
- 검사대상체를 향해 엑스선을 조사하는 단계,상기 검사대상체를 통과한 엑스선을 검출하여 해당하는 디지털 신호를 생성하는 단계, 그리고상기 디지털 신호를 이용하여 엑스선 영상을 생성하는 단계를 포함하고,상기 엑스선 영상을 생성하는 단계는상대적으로 큰 에너지와 상대적으로 작은 에너지의 엑스선에 의해 각각 얻어진 고에너지 영상과 저에너지 영상을 획득하는 단계,상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 정합하는 단계, 그리고상기 정합하는 단계를 거친 상기 고에너지 영상과 상기 저에너지 영상을 이용하는 연산을 통해 스탠다드 영상, 뼈 영상 그리고 연부조직 영상 중 하나 이상을 생성하는 단계를 포함하고,상기 정합은 뼈와 연부조직의 모션의 차이를 반영할 수 있도록 뼈 마스킹 정보와 연부조직 마스킹 정보를 각각 이용하여 수행되는 복수의 영상 정합을 포함하는 엑스선 촬영 방법.
- 제33항에 있어서,상기 정합 단계는상기 고에너지 영상과 상기 저에너지 영상의 차감 연산을 통해 뼈 영상과 연부조직 영상을 각각 생성하는 단계,상기 생성된 뼈 영상과 상기 생성된 연부조직 영상으로부터 상기 뼈 마스킹 정보를 포함하는 뼈 마스킹 영상과 연부조직 마스킹 영상을 각각 생성하는 단계,상기 뼈 마스킹 영상을 이용하여 정합 대상인 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 일차적으로 정합하는 단계, 그리고상기 연부조직 마스킹 영상을 이용하여 상기 일차적으로 정합된 상기 고에너지 영상과 상기 저에너지 영상 중 하나 이상을 추가로 정합하는 단계를 포함하는 엑스선 촬영 방법.
- 제34항에 있어서,상기 뼈 마스킹 영상은 상기 뼈 영상에 포함된 뼈의 에지 위치 정보를 포함하고,상기 연부조직 마스킹 영상은 상기 연부조직 영상에 포함된 연부조직의 에지 위치 정보를 포함하는 엑스선 촬영 방법.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2024540674A JP7804772B2 (ja) | 2022-04-11 | 2022-06-24 | X線撮影装置およびこれを利用するx線撮影方法 |
| CN202280089828.1A CN118591346A (zh) | 2022-04-11 | 2022-06-24 | X射线成像设备及使用该设备的x射线成像方法 |
| EP22937556.3A EP4445845A4 (en) | 2022-04-11 | 2022-06-24 | X-RAY IMAGING DEVICE AND X-RAY IMAGING METHOD USING IT |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2022-0044502 | 2022-04-11 | ||
| KR1020220044502A KR102760999B1 (ko) | 2022-04-11 | 2022-04-11 | 엑스선 촬영 장치 및 이를 이용하는 엑스선 촬영 방법 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023200043A1 true WO2023200043A1 (ko) | 2023-10-19 |
Family
ID=88239583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2022/009029 Ceased WO2023200043A1 (ko) | 2022-04-11 | 2022-06-24 | 엑스선 촬영 장치 및 이를 이용하는 엑스선 촬영 방법 |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US12272029B2 (ko) |
| EP (1) | EP4445845A4 (ko) |
| JP (1) | JP7804772B2 (ko) |
| KR (1) | KR102760999B1 (ko) |
| CN (1) | CN118591346A (ko) |
| WO (1) | WO2023200043A1 (ko) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW202435234A (zh) * | 2023-02-20 | 2024-09-01 | 睿生光電股份有限公司 | 影像分析方法以及影像分析系統 |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100046822A1 (en) * | 2006-11-14 | 2010-02-25 | Li Yunxiang | Virtual, grid imaging method and system for eliminating scattered radiation effect |
| KR20110111955A (ko) * | 2010-04-06 | 2011-10-12 | 삼성전자주식회사 | 멀티-에너지 X-ray 시스템의 영상 처리 장치 및 그 방법 |
| US8315355B2 (en) | 2009-10-28 | 2012-11-20 | Siemens Aktiengesellschaft | Method for operating C-arm systems during repeated angiographic medical procedures |
| KR20130142654A (ko) * | 2012-06-20 | 2013-12-30 | 삼성전자주식회사 | 엑스선 영상 장치 및 엑스선 영상 시스템 |
| KR101501086B1 (ko) | 2013-03-20 | 2015-03-10 | (주)제노레이 | X선 투시촬영장치의 구동방법 |
| JP2016537099A (ja) * | 2013-11-20 | 2016-12-01 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | デュアルエネルギスペクトルマンモグラフィー画像処理 |
| JP6549561B2 (ja) | 2013-05-13 | 2019-07-24 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | X線ビーム成形 |
| JP6681864B2 (ja) * | 2012-09-05 | 2020-04-15 | 三星電子株式会社Samsung Electronics Co.,Ltd. | エックス線画像装置 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3569566B2 (ja) * | 1995-06-12 | 2004-09-22 | コニカミノルタホールディングス株式会社 | 画像処理装置 |
| JPH0944659A (ja) * | 1995-07-27 | 1997-02-14 | Fuji Photo Film Co Ltd | エネルギーサブトラクション処理方法および装置 |
| JP2000342558A (ja) * | 1999-06-04 | 2000-12-12 | Konica Corp | 画像の位置合わせ処理装置及び画像間演算処理装置 |
| JP2002324238A (ja) * | 2001-04-26 | 2002-11-08 | Fuji Photo Film Co Ltd | 画像の位置合わせ方法および装置 |
| AU2003223072A1 (en) * | 2002-04-03 | 2003-10-13 | Segami S.A.R.L. | Image registration process |
| KR20130064483A (ko) * | 2011-12-08 | 2013-06-18 | 삼성전자주식회사 | 의료 영상 처리 방법 및 장치 |
| US20140243579A1 (en) * | 2013-02-27 | 2014-08-28 | Loyola University Chicago | Dual-energy image suppression method |
| JP2017536870A (ja) * | 2014-10-20 | 2017-12-14 | ボディ・ビジョン・メディカル・リミテッドBody Vision Medical Ltd. | 外科的デバイスおよび外科的デバイスの使用方法 |
| KR20160139163A (ko) * | 2015-05-27 | 2016-12-07 | 삼성전자주식회사 | 엑스선 장치 및 그 제어방법 |
| EP3806747B1 (en) * | 2018-06-15 | 2024-07-03 | Dalhousie University | Methods and apparatus for dual energy x-ray imaging |
| JP7433971B2 (ja) * | 2020-02-19 | 2024-02-20 | キヤノン株式会社 | 画像処理装置、画像処理装置の作動方法及びプログラム |
-
2022
- 2022-04-11 KR KR1020220044502A patent/KR102760999B1/ko active Active
- 2022-06-24 WO PCT/KR2022/009029 patent/WO2023200043A1/ko not_active Ceased
- 2022-06-24 JP JP2024540674A patent/JP7804772B2/ja active Active
- 2022-06-24 CN CN202280089828.1A patent/CN118591346A/zh active Pending
- 2022-06-24 EP EP22937556.3A patent/EP4445845A4/en active Pending
- 2022-09-01 US US17/900,944 patent/US12272029B2/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100046822A1 (en) * | 2006-11-14 | 2010-02-25 | Li Yunxiang | Virtual, grid imaging method and system for eliminating scattered radiation effect |
| US8315355B2 (en) | 2009-10-28 | 2012-11-20 | Siemens Aktiengesellschaft | Method for operating C-arm systems during repeated angiographic medical procedures |
| KR20110111955A (ko) * | 2010-04-06 | 2011-10-12 | 삼성전자주식회사 | 멀티-에너지 X-ray 시스템의 영상 처리 장치 및 그 방법 |
| KR20130142654A (ko) * | 2012-06-20 | 2013-12-30 | 삼성전자주식회사 | 엑스선 영상 장치 및 엑스선 영상 시스템 |
| JP6681864B2 (ja) * | 2012-09-05 | 2020-04-15 | 三星電子株式会社Samsung Electronics Co.,Ltd. | エックス線画像装置 |
| KR101501086B1 (ko) | 2013-03-20 | 2015-03-10 | (주)제노레이 | X선 투시촬영장치의 구동방법 |
| JP6549561B2 (ja) | 2013-05-13 | 2019-07-24 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | X線ビーム成形 |
| JP2016537099A (ja) * | 2013-11-20 | 2016-12-01 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | デュアルエネルギスペクトルマンモグラフィー画像処理 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP4445845A4 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2025500595A (ja) | 2025-01-09 |
| KR102760999B1 (ko) | 2025-02-03 |
| US20230325993A1 (en) | 2023-10-12 |
| EP4445845A4 (en) | 2025-12-10 |
| JP7804772B2 (ja) | 2026-01-22 |
| KR20230145748A (ko) | 2023-10-18 |
| US12272029B2 (en) | 2025-04-08 |
| CN118591346A (zh) | 2024-09-03 |
| EP4445845A1 (en) | 2024-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5963676A (en) | Multiscale adaptive system for enhancement of an image in X-ray angiography | |
| US7627084B2 (en) | Image acquisition and processing chain for dual-energy radiography using a portable flat panel detector | |
| US6101238A (en) | System for generating a compound x-ray image for diagnosis | |
| Chan et al. | Digitization requirements in mammography: Effects on computer‐aided detection of microcalcifications | |
| JP5556413B2 (ja) | 動態画像処理装置及びプログラム | |
| WO2023229415A1 (ko) | Ar 영상 제공 방법 및 ar 영상 제공 장치 | |
| JP3569566B2 (ja) | 画像処理装置 | |
| US20050135707A1 (en) | Method and apparatus for registration of lung image data | |
| EP2598032A2 (en) | Method and apparatus for processing image and medical image system employing the apparatus | |
| WO2015178745A1 (ko) | 깊이 카메라를 이용한 의료영상 촬영장치 및 의료영상 보정방법 | |
| JP2023120851A (ja) | 画像処理装置、画像処理方法、及びプログラム | |
| JP2000316837A (ja) | 画像診断支援装置 | |
| WO2023200043A1 (ko) | 엑스선 촬영 장치 및 이를 이용하는 엑스선 촬영 방법 | |
| CN105374023B (zh) | 一种分割目标区域方法,及其图像重建方法和装置 | |
| JP7408867B2 (ja) | 画像処理装置、方法およびプログラム | |
| WO2022145898A1 (ko) | 인공지능 기반 실시간 자동 엑스레이 원시 영상 판독 방법 및 시스템 | |
| US20040101185A1 (en) | Comparing images | |
| WO1998052011A2 (en) | Systems and methods for analyzing phantom images | |
| CN111127371B (zh) | 图像增强参数自动优化方法、存储介质和x射线扫描装置 | |
| Mol et al. | Application of digital image analysis in dental radiography for the description of periapical bone lesions: a preliminary study | |
| CN2465181Y (zh) | 台式骨龄骨密度测定仪 | |
| JP2009054013A (ja) | 画像処理装置 | |
| WO2023195443A1 (ja) | 画像処理装置、画像処理装置の作動方法、およびプログラム | |
| WO2016080736A1 (ko) | 의료영상을 이용한 진단 보조 정보 제공 방법 및 그 시스템 | |
| US12493955B2 (en) | Image processing apparatus, image processing method, image processing system and recording medium |
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: 22937556 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024540674 Country of ref document: JP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2022937556 Country of ref document: EP Ref document number: 22937556.3 Country of ref document: EP |
|
| ENP | Entry into the national phase |
Ref document number: 2022937556 Country of ref document: EP Effective date: 20240708 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202280089828.1 Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |











