WO2024157532A1 - 画像処理方法、訓練方法、訓練済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム - Google Patents

画像処理方法、訓練方法、訓練済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム Download PDF

Info

Publication number
WO2024157532A1
WO2024157532A1 PCT/JP2023/033577 JP2023033577W WO2024157532A1 WO 2024157532 A1 WO2024157532 A1 WO 2024157532A1 JP 2023033577 W JP2023033577 W JP 2023033577W WO 2024157532 A1 WO2024157532 A1 WO 2024157532A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
noise
blur
map
spatial
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2023/033577
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
智 土屋
達也 大西
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hamamatsu Photonics KK
Original Assignee
Hamamatsu Photonics KK
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hamamatsu Photonics KK filed Critical Hamamatsu Photonics KK
Priority to KR1020257027061A priority Critical patent/KR20250137636A/ko
Priority to CN202380092113.6A priority patent/CN120958478A/zh
Priority to JP2024572836A priority patent/JPWO2024157532A1/ja
Priority to EP23918489.8A priority patent/EP4623827A1/en
Publication of WO2024157532A1 publication Critical patent/WO2024157532A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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
    • A61B6/5258—Devices using data or image processing specially adapted for radiation diagnosis involving detection or reduction of artifacts or noise
    • 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
    • A61B6/42—Arrangements for detecting radiation specially adapted for radiation diagnosis
    • A61B6/4208—Arrangements for detecting radiation specially adapted for radiation diagnosis characterised by using a particular type of detector
    • A61B6/4225—Arrangements for detecting radiation specially adapted for radiation diagnosis characterised by using a particular type of detector using image intensifiers
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Definitions

  • One aspect of the embodiment relates to an image processing method, a training method, a trained model, a radiation image processing module, a radiation image processing program, and a radiation image processing system.
  • Patent Document 1 discloses an image processing method for removing noise from radiological images.
  • an evaluation value is derived from the pixel values of each pixel of a radiological image based on relational data indicating the relationship between pixel values (brightness values) and an evaluation value that evaluates the spread of noise
  • a noise map is generated as data that associates the derived evaluation value with each pixel of the radiological image
  • the noise map and the radiological image are input to a trained model.
  • noise in an image is removed by taking into account the spread of noise in the luminance direction.
  • noise in an image is removed by taking into account the relationship between luminance values and the standard deviation of pixel values.
  • the noise blur which is the spread of noise in the spatial direction, changes in the image, a sufficient noise removal effect may not be obtained.
  • one aspect of the embodiment has been made in consideration of such problems, and aims to provide an image processing method, a training method, a trained model, a radiation image processing module, a radiation image processing program, and a radiation image processing system that can respond to changes in noise blur in an image.
  • An image processing method includes an image acquisition step of irradiating an object with an energy beam and acquiring an image of the energy beam passing through the object, a spatial blur map generation step of generating a spatial blur map showing the distribution of spatial blur of noise based on the image, and a processing step of inputting the image and the spatial blur map into a trained model previously constructed by machine learning, and executing image processing to remove noise from the image.
  • a radiation image processing module includes an image acquisition unit that acquires a radiation image in which an object is irradiated with radiation and the radiation that has passed through the object is captured, a spatial blur map generation unit that generates a spatial blur map that indicates the distribution of spatial blur of noise based on the radiation image, and a processing unit that inputs the radiation image and the spatial blur map into a trained model that has been constructed in advance by machine learning, and executes image processing to remove noise from the radiation image.
  • a radiation image processing program causes the processor to function as an image acquisition unit that acquires a radiation image in which radiation is irradiated onto an object and the radiation that has passed through the object is captured, a spatial blur map generation unit that generates a spatial blur map that indicates the distribution of spatial blur of noise based on the radiation image, and a processing unit that inputs the radiation image and the spatial blur map into a trained model that has been constructed in advance by machine learning, and executes image processing to remove noise from the radiation image.
  • a radiation image processing system includes the above-mentioned radiation image processing module, a radiation source that irradiates an object with radiation, and an imaging device that captures the radiation that has passed through the object to obtain a radiation image.
  • an image processing method it is possible to provide an image processing method, a training method, a trained model, a radiation image processing module, a radiation image processing program, and a radiation image processing system that can respond to changes in noise blur in an image.
  • FIG. 1 is a schematic configuration diagram of an image acquisition device 1 according to an embodiment.
  • 2 is a block diagram showing an example of a hardware configuration of a control device 20 in FIG. 1 .
  • 2 is a block diagram showing a functional configuration of a control device 20 in FIG. 1 .
  • 4 is a diagram showing an example of an X-ray image acquired by the image acquisition unit 201 in FIG. 3 .
  • 4 is a diagram showing an example of a noise map generated by the noise map generating unit 202 in FIG. 3 .
  • 4 is a diagram showing an example of a spatial blur map generated by the spatial blur map generating unit 203 in FIG. 3 .
  • FIG. 7 is a diagram for explaining spatial blur evaluated by blur evaluation information in the spatial blur map of FIG. 6 .
  • FIG. 7 is a diagram for explaining spatial blur evaluated by blur evaluation information in the spatial blur map of FIG. 6 .
  • FIG. 7 is a diagram for explaining a method of deriving second relationship data G70 indicating the correspondence between the pixel value and the sigma value in FIG. 6.
  • 7 is a graph showing a relationship referenced when deriving second relationship data G70 indicating the correspondence relationship between the pixel value and the sigma value in FIG. 6.
  • 7 is a diagram for explaining a method of deriving second relationship data G70 indicating the correspondence between the pixel value and the sigma value in FIG. 6.
  • FIG. 4 is a diagram showing an example of input/output data of the trained model 207 in FIG. 3 .
  • FIG. 4 is a diagram showing an example of training data generated by the training data generating unit 206 in FIG. 3 .
  • 4 is a flowchart showing the procedure of an observation process by the image acquisition device 1.
  • 3A to 3C are diagrams showing examples of X-ray images acquired by the image acquisition device 1 before and after noise removal processing.
  • the image acquisition device 1 is a device that irradiates an object F conveyed in a conveying direction TD with X-rays (energy rays) (radiation) and acquires an X-ray image (image) (radiation image) of the object F based on the X-rays that have passed through the object F.
  • the image acquisition device 1 uses the X-ray image to perform foreign body inspection, weight inspection, and inspection of the object F, and examples of applications include food inspection, baggage inspection, board inspection, battery inspection, and material inspection.
  • the image acquisition device 1 is configured to include a belt conveyor (conveying means) 60, an X-ray irradiator (generation source) 50, an X-ray detection camera (imaging device) 10, a control device (radiation image processing module) 20, a display device 30, and an input device 40 for performing various inputs.
  • the image may be an image of an energy ray that has passed through the object F.
  • the energy rays may be, for example, radiation such as X-rays and gamma rays, or any of visible light, infrared rays, ultraviolet rays, and electron beams.
  • the image is a radiation image such as an X-ray image, but may be other images.
  • the belt conveyor 60 has a belt portion on which the object F is placed, and the belt portion is moved in the conveying direction TD to convey the object F in the conveying direction TD at a predetermined conveying speed.
  • the conveying speed of the object F is, for example, 48 m/min.
  • the belt conveyor 60 can change the conveying speed to, for example, 24 m/min or 96 m/min as necessary.
  • the belt conveyor 60 can also change the height position of the belt portion as appropriate to change the distance between the X-ray irradiator 50 and the object F.
  • the object F conveyed by the belt conveyor 60 can include various items such as meat, seafood, agricultural products, confectionery, and other foods, rubber products such as tires, resin products, metal products, mineral resources, and waste, as well as electronic components and electronic boards.
  • the X-ray irradiator 50 is a device that irradiates (outputs) X-rays to the object F as an X-ray source.
  • the X-ray irradiator 50 is a point light source, and irradiates X-rays in a certain irradiation direction by diffusing them within a predetermined angle range.
  • the X-ray irradiator 50 is disposed above the belt conveyor 60 at a predetermined distance from the belt conveyor 60 so that the X-ray irradiation direction is directed toward the belt conveyor 60 and the diffusing X-rays cover the entire width direction (direction intersecting with the conveying direction TD) of the object F.
  • the irradiation range of the X-ray irradiator 50 is a predetermined divided range in the length direction (direction parallel to the conveying direction TD) of the object F, and the object F is conveyed in the conveying direction TD by the belt conveyor 60, so that the entire length direction of the object F is irradiated with X-rays.
  • the tube voltage and tube current of the X-ray irradiator 50 are set by the control device 20.
  • the X-ray irradiator 50 irradiates X-rays with a predetermined energy and a predetermined radiation amount according to the set tube voltage and tube current toward the belt conveyor 60.
  • a filter 51 that transmits a predetermined wavelength range of X-rays is provided near the belt conveyor 60 side of the X-ray irradiator 50.
  • the filter 51 is not necessarily required and may be omitted as appropriate.
  • the X-ray detection camera 10 detects X-rays that have passed through the object F among the X-rays irradiated to the object F by the X-ray irradiator 50, and outputs a signal based on the X-rays.
  • the X-ray detection camera 10 is a dual line X-ray camera in which two sets of X-ray detection configurations are arranged. In the image acquisition device 1 according to this embodiment, X-ray images are generated based on the X-rays detected on each line (first line and second line) of the dual line X-ray camera.
  • the X-ray detection camera 10 may be configured as a single line X-ray camera in which one set of X-ray detection configurations is arranged, a multi-line X-ray camera in which two or more sets of X-ray detection configurations are arranged, or two or more single line X-ray cameras.
  • the X-ray detection camera 10 has a filter 19, scintillators 11a and 11b, line scan cameras 12a and 12b, a sensor control unit 13, amplifiers 14a and 14b, AD converters 15a and 15b, correction circuits 16a and 16b, output interfaces 17a and 17b, and an amplifier control unit 18.
  • the scintillator 11a, line scan camera 12a, amplifier 14a, AD converter 15a, correction circuit 16a, and output interface 17a are electrically connected to each other and constitute a first line.
  • the scintillator 11b, line scan camera 12b, amplifier 14b, AD converter 15b, correction circuit 16b, and output interface 17b are electrically connected to each other and constitute a second line.
  • the line scan camera 12a of the first line and the line scan camera 12b of the second line are arranged side by side along the transport direction TD. In the following, the configuration common to the first and second lines will be explained using the configuration of the first line as a representative.
  • the scintillator 11a is fixed on the line scan camera 12a by adhesive or the like, and converts the X-rays that have passed through the object F into scintillation light.
  • the scintillator 11a outputs the scintillation light to the line scan camera 12a.
  • the filter 19 transmits a predetermined wavelength range of X-rays toward the scintillator 11a.
  • the filter 19 is not necessarily required, and may be omitted as appropriate.
  • the line scan camera 12a detects the scintillation light from the scintillator 11a, converts it into an electric charge, and outputs it to the amplifier 14a as a detection signal (electrical signal).
  • the line scan camera 12a has multiple line sensors arranged in parallel in a direction intersecting the transport direction TD.
  • the line sensors are, for example, CCD (Charge Coupled Device) image sensors or CMOS (Complementary Metal-Oxide Semiconductor) image sensors, and include multiple photodiodes.
  • the sensor control unit 13 controls the line scan cameras 12a and 12b to repeatedly capture images at a predetermined detection period so that the line scan cameras 12a and 12b can capture X-rays that have passed through the same area of the object F.
  • the predetermined detection period may be set as a common period for the line scan cameras 12a and 12b based on, for example, the distance between the line scan cameras 12a and 12b, the speed of the belt conveyor 60, the distance between the X-ray irradiator 50 and the object F on the belt conveyor 60 (FOD (Focus Object Distance)), and the distance between the X-ray irradiator 50 and the line scan cameras 12a and 12b (FDD (Focus Detector Distance)).
  • the predetermined period may also be set individually for each of the line scan cameras 12a and 12b based on the pixel width of the photodiode in a direction perpendicular to the pixel array direction of the line sensor.
  • the deviation (delay time) in the detection period between the line scan cameras 12a and 12b may be determined according to the distance between the line scan cameras 12a and 12b, the speed of the belt conveyor 60, the distance (FOD) between the X-ray irradiator 50 and the object F on the belt conveyor 60, and the distance (FDD) between the X-ray irradiator 50 and the line scan cameras 12a and 12b, and individual periods may be set.
  • the amplifier 14a amplifies the detection signal at a predetermined set amplification factor to generate an amplified signal, and outputs the amplified signal to the AD converter 15a.
  • the set amplification factor is an amplification factor set by the amplifier control unit 18.
  • the amplifier control unit 18 sets the set amplification factors of the amplifiers 14a and 14b based on predetermined imaging conditions.
  • the AD converter 15a converts the amplified signal (voltage signal) output by the amplifier 14a into a digital signal and outputs it to the correction circuit 16a.
  • the correction circuit 16a performs a predetermined correction, such as signal amplification, on the digital signal and outputs the corrected digital signal to the output interface 17a.
  • the output interface 17a outputs the digital signal to the outside of the X-ray detection camera 10.
  • the AD converter, the correction circuit, and the output interface are each present separately, but they may be integrated into one.
  • the control device 20 is a computer such as a PC (Personal Computer).
  • the control device 20 generates an X-ray image based on a digital signal (amplified signal) output from the X-ray detection camera 10 (more specifically, the output interfaces 17a and 17b).
  • the control device 20 generates one X-ray image by averaging or adding two digital signals output from the output interfaces 17a and 17b.
  • the generated X-ray image is output to the display device 30 after noise removal processing described later, and is displayed by the display device 30.
  • the control device 20 also controls the X-ray irradiator 50, the amplifier control unit 18, and the sensor control unit 13. Note that the control device 20 in this embodiment is a device independently provided outside the X-ray detection camera 10, but may be integrated inside the X-ray detection camera 10.
  • FIG. 2 shows the hardware configuration of the control device 20.
  • the control device 20 is physically a computer or the like including a processor such as a CPU (Central Processing Unit) 101 and a GPU (Graphic Processing Unit) 105, a recording medium such as a RAM (Random Access Memory) 102 and a ROM (Read Only Memory) 103, a communication module 104, and an input/output module 106, each of which is electrically connected.
  • the control device 20 may include a display, keyboard, mouse, touch panel display, etc. as the input device 40 and the display device 30, or may include a data recording device such as a hard disk drive and semiconductor memory.
  • the control device 20 may also be composed of multiple computers.
  • the control device 20 includes an image acquisition unit 201, a noise map generation unit 202, a spatial blur map generation unit 203, a processing unit 204, a construction unit 205, and a training data generation unit 206.
  • Each functional unit of the control device 20 shown in FIG. 3 is realized by loading a program (the radiation image processing program of this embodiment) onto hardware such as the CPU 101, the GPU 105, and the RAM 102, and operating the communication module 104 and the input/output module 106 under the control of the CPU 101 and the GPU 105, and reading and writing data in the RAM 102.
  • the CPU 101 and the GPU 105 of the control device 20 execute this computer program to make the control device 20 function as each functional unit of FIG.
  • the CPU 101 and the GPU 105 may be standalone hardware, or only one of them may be used.
  • the CPU 101 and the GPU 105 may be implemented in a programmable logic such as an FPGA, as in a software processor.
  • the RAM and the ROM may be standalone hardware, or may be built into a programmable logic such as an FPGA. All of the various data required to execute the computer program and the various data generated by the execution of the computer program are stored in built-in memories such as the ROM 103 and the RAM 102, or in storage media such as a hard disk drive.
  • the built-in memory or storage media in the control device 20 also stores a trained model 207 that is read by the CPU 101 and the GPU 105 to cause the CPU 101 and the GPU 105 to perform noise removal processing on an image (described later).
  • the image acquisition unit 201 acquires an image in which an energy ray is irradiated onto the object F and the energy ray that has passed through the object F is captured. Specifically, the image acquisition unit 201 generates an X-ray image based on a digital signal (amplified signal) output from the X-ray detection camera 10 (more specifically, the output interfaces 17a and 17b). The image acquisition unit 201 generates one X-ray image by averaging or adding two digital signals output from the output interfaces 17a and 17b.
  • FIG. 4 is a diagram showing an example of an X-ray image acquired by the image acquisition unit 201.
  • the image acquisition unit 201 cuts out the image into a plurality of partial images (a plurality of first partial images). For example, as shown in FIG. 5, the image acquisition unit 201 divides an image (radiation image) G1 into a plurality of partial images G2.
  • the noise map generating unit 202 derives a noise evaluation value from the pixel value of each pixel of the image based on first relationship data indicating the relationship between the pixel value and the noise evaluation value that evaluates the spread of the noise value.
  • the noise map generating unit 202 generates a noise map, which is data in which the derived noise evaluation value is associated with each pixel of the image.
  • the noise map generating unit 202 acquires a plurality of partial images generated by the image acquiring unit 201.
  • the noise map generating unit 202 derives a standard deviation of pixel values from the pixel values of each pixel of the partial images based on the first relationship data.
  • the noise map generating unit 202 generates a noise map, which is data in which the derived standard deviation of pixel values is associated with each pixel of the partial image. At this time, the noise map generating unit 202 derives a noise evaluation value from the average energy related to the energy ray that has passed through the object F and the pixel value of each pixel of the partial image.
  • the noise map generating unit 202 calculates the average energy of the energy rays that have passed through the object F.
  • the noise map generating unit 202 calculates the average energy of the X-rays (radiation) that have passed through the object F based on condition information input by the input device 40 or the like.
  • the condition information is information that indicates either the conditions of the energy ray source or the imaging conditions when irradiating the energy ray to image the object F.
  • the noise map generating unit 202 may accept the input of the condition information as a direct input of information such as a numerical value, or may accept it as a selection input for information such as a numerical value that has been set in advance in an internal memory.
  • the noise map generating unit 202 accepts the input of the above condition information from the user, but may also acquire some of the condition information (tube voltage, etc.) according to the detection result of the control state by the control device 20.
  • the condition information is, for example, information indicating the operating conditions of the X-ray irradiator (source) 50 when capturing an X-ray image of the object F, or the imaging conditions by the X-ray detection camera 10.
  • the operating conditions may include all or some of the type of X-ray source, tube voltage, tube current, target angle, target material, etc.
  • the condition information indicating the imaging conditions includes all or part of the following: the material, thickness, and density of the filters 51, 19 arranged between the X-ray irradiator 50 and the X-ray detection camera 10; the distance (FDD) between the X-ray irradiator 50 and the X-ray detection camera 10; the type and thickness of the window material of the X-ray detection camera 10; and information on the scintillators 11a, 11b of the X-ray detection camera 10 (e.g., thickness, material, density, multiplication factor, surface reflectance, diffusion coefficient, or absorption coefficient), X-ray detection camera information (e.g., gain setting value, circuit noise value, saturation charge amount, conversion coefficient value (e-/count), camera line rate (Hz) or line speed (m/min)), information on the object F (measurement substance, thickness, density), etc.
  • FDD distance between the X-ray irradiator 50 and the X-ray detection camera 10
  • the noise map generating unit 202 calculates the spectrum of X-rays detected by the X-ray detection camera 10 using, for example, a known approximation formula such as Tucker's, based on information included in the condition information, such as the tube voltage, target angle, target material, material and thickness of the filters 51, 19, presence or absence of the filters 51, 19, type of window material of the X-ray detection camera 10 and its presence or absence, and material and thickness of the scintillators 11a, 11b of the X-ray detection camera 10.
  • a known approximation formula such as Tucker's
  • the noise map generating unit 202 further calculates a spectral intensity integral value and a photon number integral value from the X-ray spectrum, and calculates the average energy value of the X-rays by dividing the spectral intensity integral value by the photon number integral value. Note that the calculation of the X-ray spectrum may use known approximation formulas by Kramers or Birch et al.
  • the noise map generating unit 202 uses first relationship data indicating the relationship between pixel values and the standard deviation of pixel values (noise evaluation value that evaluates the spread of noise values) to derive the standard deviation of pixel values from the calculated average energy of the energy rays and the pixel values of each pixel of the partial image.
  • the noise map generating unit 202 generates a noise map by associating each pixel of the partial image with the derived standard deviation of pixel values.
  • the noise map generating unit 202 derives the first relationship data indicating the relationship between the pixel value and the noise evaluation value that evaluates the spread of the noise value by simulation.
  • the relationship between the pixel value, the average energy of X-rays, and the standard deviation of the pixel value used by the noise map generating unit 202 is expressed by the following formulas (1) to (4).
  • the variable Noise is the standard deviation of the pixel values
  • the variable Signal is the signal value of the pixel (pixel value)
  • the constant F is the noise factor
  • the variable Em is the average energy of the X-rays
  • the constant M is the multiplication factor by the scintillator
  • the constant coeff M is a coefficient for adjusting the multiplication factor by the scintillator
  • the constant C is the coupling efficiency between the line scan camera 12a and the scintillator 11a, or between the line scan camera 12b and the scintillator 11b in the X-ray detection camera 10
  • the constant Q is information indicating the quantum efficiency of the line scan camera 12a or the line scan camera 12b.
  • the constant cf is a conversion coefficient for converting pixel signal values into electric charges in the line scan camera 12a or line scan camera 12b
  • the constant R is information indicating the read noise in the line scan camera 12a or line scan camera 12b.
  • the conversion coefficient cf and the read noise R are determined by the gain setting in the line scan camera 12a or line scan camera 12b.
  • the constant M Si is the multiplication factor of the line scan camera (silicon) when the X-rays incident on the scintillator 11a or scintillator 11b are incident on the line scan camera 12a or line scan camera 12b without being converted into visible light
  • the constant rate si is the silicon direct incidence rate indicating the probability that the X-rays incident on the scintillator 11a or scintillator 11b are incident on the line scan camera 12a or line scan camera 12b without being converted into visible light
  • the constant C S is the shading correction value
  • the constant offset is the camera offset indicating the offset value of the line scan cameras 12a and 12b.
  • the constant N is information indicating the number of sensors.
  • the constant N may be, for example, information indicating the number of line scan cameras (number of lines), or may be information indicating the binning setting in the line scan camera 12a or line scan camera 12b.
  • coeff noise is a coefficient for adjusting noise.
  • the constant Fp is information indicating a coefficient indicating blur
  • the constant coeff Fp is information indicating a coefficient for adjusting the coefficient indicating blur.
  • the noise map generating unit 202 substitutes the pixel value of each pixel of the X-ray image acquired by the image acquiring unit 201 into the variable Signal, and substitutes the numerical value of the average energy calculated by the noise map generating unit 202 into the variable E m . Then, the noise map generating unit 202 obtains the variable Noise calculated by using the above formulas (1) to (4) as the numerical value of the standard deviation of the pixel values. Note that the other parameters including the average energy may be acquired by receiving input by the noise map generating unit 202, or may be set in advance.
  • the noise map generating unit 202 may derive the first relationship data indicating the relationship between pixel values and the standard deviation of pixel values based on an image obtained by actually capturing an image.
  • the noise map generating unit 202 may obtain an X-ray image obtained by irradiating a jig with X-rays.
  • the jig may be a flat plate-like member or the like with a known thickness and material.
  • the noise map generating unit 202 may derive the relationship data indicating the relationship between pixel values and the standard deviation of pixel values from the obtained X-ray image.
  • the noise map generating unit 202 which represents the relationship between pixel values and the standard deviation of pixel values, from an X-ray image of a jig.
  • a member whose thickness changes stepwise in one direction may be used for the jig.
  • the noise map generating unit 202 derives pixel values (hereinafter referred to as true pixel values) in the case where there is no noise for each step of the jig in the X-ray image of the jig, and derives the standard deviation of the pixel values based on the true pixel values.
  • the noise map generating unit 202 derives the average value of the pixel values at a certain step of the jig.
  • the noise map generating unit 202 sets the derived average value of the pixel values as the true pixel value at that step.
  • the noise map generating unit 202 derives the difference between each pixel value and the true pixel value at that step as a noise value.
  • the noise map generating unit 202 derives the standard deviation of the pixel values from the derived noise value for each pixel value.
  • the noise map generating unit 202 derives the first relationship data based on the relationship between the true pixel values and the standard deviation of the pixel values. Specifically, the noise map generating unit 202 derives the true pixel values and the standard deviation of the pixel values for each step of the jig. The noise map generating unit 202 plots the derived relationship between the true pixel values and the standard deviation of the pixel values on a graph and draws an approximation curve to derive a relationship graph that shows the relationship between the pixel values and the standard deviation of the pixel values. Note that for the approximation curve, exponential approximation, linear approximation, logarithmic approximation, polynomial approximation, power approximation, or the like is used.
  • the noise map generation unit 202 derives a relationship graph G4 (first relationship data) that represents the correspondence between pixel values in an image in which an energy beam is captured and the standard deviation of pixel values.
  • the noise map generation unit 202 acquires a plurality of partial images G2 generated by the image acquisition unit 201.
  • the noise map generation unit 202 then derives relationship data G3 that represents the correspondence between each pixel position and pixel value from the partial image G2.
  • the noise map generation unit 202 derives the standard deviation of pixel values corresponding to the pixels at each pixel position in the partial image by applying the correspondence shown in the relationship graph G4 to each pixel value in the relationship data G3.
  • the noise map generation unit 202 associates the derived standard deviation of pixel values with each pixel position, and derives relationship data G5 that represents the correspondence between each pixel position and the standard deviation of pixel values. Then, the noise map generation unit 202 generates a noise map G6 based on the derived relationship data G5.
  • the spatial blur map generating unit 203 generates a spatial blur map indicating the distribution of spatial blur of noise based on the image. Specifically, the spatial blur map generating unit 203 generates a spatial blur map for each of the multiple partial images.
  • the spatial blur map generating unit 203 acquires a plurality of partial images generated by the image acquiring unit 201.
  • FIG. 6 is a diagram showing an example of the generation of a spatial blur map by the spatial blur map generating unit 203.
  • the spatial blur map generating unit 203 acquires a partial image G2 generated by the image acquiring unit 201 by cutting out an image G1.
  • the spatial blur map generating unit 203 derives blur evaluation information from the pixel values of each pixel of the partial image based on second relationship data indicating the relationship between pixel values and blur evaluation information that evaluates the spatial blur of noise.
  • the spatial blur map generating unit 203 derives second relationship data G70 indicating the correspondence between pixel values and sigma values in an image in which energy rays are captured.
  • the spatial blur map generating unit 203 derives blur evaluation information corresponding to the pixel at each pixel position in the partial image G2 by applying the correspondence indicated by the second relationship data G70 to each pixel value in the partial image G2.
  • the blur evaluation information is an index for evaluating the spatial blur of noise (magnitude of noise blur), and is, for example, a sigma value.
  • the sigma value is an index that indicates the spatial spread in a Gaussian distribution or the like.
  • the blur evaluation information may be, for example, at least one of a half-width, a point spread function (PSF), a contrast transfer function (CTF), and a modulation transfer function (MTF). Note that when the blur evaluation information is a contrast transfer function or a modulation transfer function, it has multiple parameters. In this case, the spatial blur map is expressed using multiple channels.
  • FIG. 7(a) and (b) are diagrams showing the spread of luminance from a given pixel (spatial spread).
  • the vertical axis indicates the relative value of luminance
  • the horizontal axis indicates the pixel value.
  • the spatial blur of noise refers to the spread of luminance (pixel value) at a given pixel to the periphery of the pixel.
  • a change in the spatial blur of noise refers to a change in the spread of luminance (noise frequency). For example, when the spread of luminance in FIG. 7(a) increases (when the noise frequency decreases), the half-width of the graph in FIG. 7(b) increases. Also, when the spread of luminance in FIG. 7(a) decreases (when the noise frequency increases), the half-width of the graph in FIG. 7(b) decreases.
  • the spatial blur of noise changes depending on the operating conditions of the energy ray source and the type and thickness of the scintillator.
  • the spatial blur map generating unit 203 generates second relationship data indicating a relationship between pixel values and blur evaluation information that evaluates spatial blur of noise by simulation. Specifically, first, the spatial blur map generating unit 203 acquires condition information. Next, as shown in FIG. 8, the spatial blur map generating unit 203 generates a point spread function (PSF) for each transmittance in the X-ray image by executing a Monte Carlo simulation or the like based on parameters included in the condition information.
  • the transmittance in the X-ray image may be, for example, a value obtained by dividing the pixel value of each pixel by the background luminance, or a value obtained by dividing the pixel value of each pixel by a pixel value set in advance.
  • the spatial blur map generating unit 203 derives a sigma value ⁇ as blur evaluation information for each point spread function by approximating the generated point spread function with a Gaussian function, as shown in the following formula (5). Finally, the spatial blur map generation unit 203 derives the correspondence between the transmittance and the sigma value, and generates second relationship data indicating the relationship between the pixel value and the sigma value by multiplying the transmittance by the background luminance or a preset pixel value.
  • variable ⁇ is information indicating the sigma value
  • the function PSF sim is information indicating a point spread function generated by simulation
  • the variable x is information indicating the x coordinate in the point spread function and the Gaussian function
  • the variable y is information indicating the y coordinate in the point spread function and the Gaussian function.
  • the spatial blur map generating unit 203 generates point spread functions F1 to F4 for each transmittance in the X-ray image by executing a Monte Carlo simulation based on the condition information.
  • the spatial blur map generating unit 203 approximates the point spread functions F1 to F4 with a Gaussian function to derive the sigma values ⁇ to be 0.36, 0.358, 0.348, and 0.322, respectively.
  • the spatial blur map generating unit 203 derives the correspondence relationship G71 between the transmittance and the sigma value shown in FIG. 9 by associating the derived sigma value with the transmittance.
  • the horizontal axis indicates the transmittance
  • the vertical axis indicates the sigma value.
  • the second relationship data G70 indicating the relationship between the pixel value and the sigma value shown in FIG. 6 is derived by multiplying the transmittance of the correspondence relationship G71 by the background luminance or a preset luminance.
  • the spatial blur map generating unit 203 may generate second relationship data indicating the relationship between pixel values and blur evaluation information that evaluates the spatial blur of noise, based on an image obtained by actually capturing an image. Specifically, the spatial blur map generating unit 203 may generate the second relationship data based on an image obtained by actually capturing an image of a jig.
  • FIG. 10 shows an example of the structure of the jig.
  • the jig used is a jig P1, which is a member whose thickness changes in a step-like manner in one direction.
  • a resolution chart P2 is provided for each step of the jig P1.
  • the spatial blur map generating unit 203 acquires an image of an energy beam transmitted through the jig P1 and the resolution chart P2.
  • the spatial blur map generating unit 203 derives a modulation transfer function (MTF) or a contrast transfer function (CTF) for each step of the jig P1 based on the resolution chart P2 shown in the acquired image.
  • the spatial blur map generating unit 203 derives a point spread function (PSF) for each step of the jig P1 from the derived modulation transfer function or contrast transfer function.
  • the spatial blur map generating unit 203 derives a sigma value ⁇ for each step of the jig P1 by approximating the generated point spread function with a Gaussian function.
  • the spatial blur map generating unit 203 derives a correspondence between the transmittance and the sigma value by associating the transmittance derived for each step of the jig P1 with the sigma value of each step of the jig P1. Finally, the spatial blur map generating unit 203 generates second relationship data indicating the relationship between the pixel value and the sigma value by multiplying the transmittance by the background luminance or a preset pixel value. Note that the derivation of the point spread function from the above-mentioned modulation transfer function can be realized by various methods and configurations using publicly known technologies.
  • the spatial blur map generating unit 203 generates data in which the derived blur evaluation information is associated with each pixel of the partial image as a spatial blur map.
  • the spatial blur map generating unit 203 associates the derived blur evaluation information with each pixel position of the partial image G2, and generates a spatial blur map G8 that indicates the distribution of spatial blur of noise.
  • the processing unit 204 inputs the image, the noise map, and the spatial blur map into a trained model 207 constructed in advance by machine learning, and executes image processing to remove noise from the image. Specifically, as shown in FIG. 11, the processing unit 204 acquires a trained model 207 (described later) constructed by the construction unit 205 from an internal memory or a storage medium in the control device 20. The processing unit 204 inputs the partial image G2 generated by the image acquisition unit 201, the noise map G6 generated by the noise map generation unit 202, and the spatial blur map G8 generated by the spatial blur map generation unit 203 into the trained model 207. The processing unit 204 uses the noise map G6 as a noise weight and the spatial blur map G8 as a noise frequency weight, respectively.
  • the processing unit 204 uses the trained model 207 to execute image processing to remove noise from each of the multiple partial images G2, thereby generating multiple noise-removed images G9 from which noise has been removed.
  • the processing unit 204 then integrates the multiple noise-removed images G9 to generate an image G10 from which noise has been removed, and outputs the image G10 to the display device 30, etc.
  • the construction unit 205 uses as training data a plurality of partial images (second partial images) generated as training images by cutting out an image (hereinafter referred to as the "whole image"), a noise map and a spatial blur map generated from the partial images, and a noise image obtained by adding noise to the partial images, to construct a trained model 207 by machine learning, which uses the noise map, spatial blur map, and noise image as inputs and outputs a denoised image obtained by removing noise from the noise image so that the denoised image approximates the partial image.
  • the construction unit 205 stores the constructed trained model 207 in an internal memory or storage medium in the control device 20.
  • Machine learning includes supervised learning, unsupervised learning, and reinforcement learning, and among these learning methods are deep learning, neural network learning, and the like.
  • a two-dimensional convolutional neural network described in the paper "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising” by Kai Zhang et al. is used as an example of a deep learning algorithm.
  • the trained model 207 may be constructed by the construction unit 205, or may be generated by an external computer or the like and downloaded to the control device 20.
  • the training data generation unit 206 generates training data used in the construction unit 205 to construct the trained model 207. Specifically, the training data generation unit 206 first acquires an overall image and cuts out multiple partial images from the overall image as training images.
  • the overall image used for machine learning may be, for example, an image generated by simulation, or may be a standard image available via an internet line or the like. In the example shown in FIG. 12, the training data generation unit 206 cuts out multiple partial images G12 from the acquired overall image G11.
  • the training data generation unit 206 sets a noise evaluation value that evaluates the spread of noise as a noise setting value for each partial image.
  • the training data generation unit 206 generates a noise map, which is data in which a noise evaluation value is associated with each pixel of a partial image based on the noise setting value, for multiple partial images.
  • the training data generation unit 206 generates a noise map G13 from multiple partial images G12.
  • the training data generating unit 206 sets a different noise evaluation value as the noise setting value for each partial image by one of the following three methods.
  • the training data generating unit 206 generates data in which a noise setting value is associated with each pixel of the partial image and set as a noise map.
  • the training data generating unit 206 sets an arbitrary noise setting value for one partial image. That is, the noise setting value is set uniformly in one partial image, and at the same time, the noise setting value is set randomly in the entire image.
  • the training data generating unit 206 further cuts out one partial image into multiple regions.
  • the training data generating unit 206 sets an arbitrary noise setting value uniformly in one region. That is, the noise setting value is set randomly in one partial image.
  • the training data generating unit 206 like the noise map generating unit 202, sets the noise evaluation value derived from the pixel value of each pixel of the partial image as a noise setting value for each pixel of the partial image based on the first relationship data indicating the relationship between the pixel value and the noise evaluation value that evaluates the spread of the noise value.
  • the training data generating unit 206 may derive the first relationship data by simulation as described above, or may derive the first relationship data based on an image obtained by actually capturing an image (actual measurement).
  • the training data generation unit 206 sets blur evaluation information that evaluates the spatial blur of the noise as blur setting information for each partial image.
  • the training data generation unit 206 generates a spatial blur map that indicates the distribution of spatial blur of the noise based on the blur setting information for multiple partial images.
  • the training data generation unit 206 sets different blur evaluation information as blur setting information for each partial image by one of the following three methods selected.
  • the training data generation unit 206 generates data in which blur setting information is associated with each pixel of the partial image as a spatial blur map.
  • the training data generation unit 206 sets arbitrary blur setting information for one partial image. That is, the blur setting information is set uniformly in one partial image, and at the same time, the blur setting information is set randomly in the entire image.
  • the training data generation unit 206 further cuts out one partial image into multiple regions.
  • the training data generation unit 206 sets arbitrary blur evaluation information uniformly in one region. That is, the blur evaluation information is set randomly in one partial image.
  • the training data generating unit 206 sets the blur evaluation information derived from the pixel values of each pixel of the partial image as blur setting information for each pixel of the partial image based on the second relationship data indicating the relationship between the pixel values and the blur evaluation information, in the same manner as the spatial blur map generating unit 203. At this time, the training data generating unit 206 generates the second relationship data based on a simulation or an image that is actually captured (actual measurement), as described above.
  • the training data generation unit 206 generates a noise image by adding noise to the partial image based on the noise map and the spatial blur map.
  • the training data generation unit 206 generates noise data G15 based on the noise map G13 and the spatial blur map G14, and generates a noise image G16 by adding the generated noise data G15 to the partial image G12.
  • the training data generation unit 206 generates a noise distribution of the same size as the partial image based on the noise map. Specifically, the training data generation unit 206 determines a noise value for each pixel of the partial image based on the noise map. The training data generation unit 206 generates a noise distribution by associating the determined noise value with each pixel of the partial image.
  • the training data generating unit 206 blurs the noise distribution based on the spatial blur map to generate noise data. Specifically, the training data generating unit 206 predetermines a correspondence between the blur evaluation information and the point spread function. The training data generating unit 206 determines the point spread function for each pixel by applying the determined correspondence to the spatial blur map. The training data generating unit 206 generates noise data by blurring the noise distribution based on the point spread function determined for each pixel. In the example shown in FIG. 12, the training data generating unit 206 blurs the noise distribution based on the spatial blur map G14 to generate noise data G15. Note that when the blur evaluation information is a point spread function, the training data generating unit 206 generates noise data using the spatial blur map since the point spread function has already been determined for each pixel in the spatial blur map.
  • the training data generation unit 206 predetermines the correspondence between the sigma value and the point spread function by one of the following three methods.
  • the training data generation unit 206 regards the Gaussian distribution corresponding to the sigma value as the point spread function. In this case, the closer the Gaussian distribution is to the point spread function in the actual scintillator, the more effective the noise removal that can be achieved by constructing a trained model 207.
  • a point spread function is calculated for each scintillator by simulation, taking into account the type and thickness of the scintillator.
  • the simulation is, for example, a photon Monte Carlo simulation in the scintillator.
  • the training data generation unit 206 determines the sigma value of the Gaussian distribution that is most similar to the calculated point spread function as the sigma value corresponding to the point spread function.
  • the correspondence between the sigma value and the point spread function can be determined taking into account changes in the point spread function (light spread function) (blur) due to differences in the type and thickness of the scintillator, etc. This makes it possible to generate a noise image as training data using a point spread function that is more similar to the blur in an actually captured image. As a result, it becomes possible to achieve more effective noise removal in the trained model 207 constructed using the training data.
  • the training data generating unit 206 may determine the sigma value of the point spread function by further considering the X-ray energy spectrum.
  • the training data generating unit 206 acquires the operating conditions (tube voltage, filter, radiation source information) of the X-ray irradiator 50 included in the condition information, and calculates the X-ray energy spectrum reaching the scintillators 11a and 11b based on the operating conditions.
  • the training data generating unit 206 determines the sigma value of the point spread function by using the above-mentioned eighth method by considering the X-ray energy spectrum.
  • the proportion of light emitted on the surface side of the scintillator is high, and the distance that the light reaches to the line scan cameras 12a and 12b becomes longer, resulting in a larger point spread function.
  • the proportion of light emitted on the back side of the scintillator is greater than in the case of a low energy, and the distance that the light travels to the line scan cameras 12a and 12b is shorter, resulting in a smaller point spread function.
  • the point spread function is calculated taking into consideration that the spread of light in the scintillator differs depending on the X-ray energy. This makes it possible to generate a noise image as training data using a point spread function that more closely resembles the blur in an actually captured image. Therefore, it becomes possible to achieve more effective noise removal in the trained model 207 constructed using the training data.
  • the training data generating unit 206 acquires an actually measured point spread function.
  • the training data generating unit 206 sets the sigma value of the Gaussian distribution that is most similar to the acquired point spread function as the sigma value corresponding to the point spread function.
  • the point spread function may be measured for each case where the scintillator type and thickness are different, or for each case where the X-ray energy is different.
  • the training data generation unit 206 generates a noise image G16 by adding noise to the partial image G12 based on the generated noise data.
  • FIG. 13 is a flowchart showing the procedure for observation processing using the image acquisition device 1.
  • steps S100 and S101 correspond to the training method in this embodiment.
  • steps S102 to S106 correspond to the image processing method in this embodiment.
  • training data is generated by the control device 20 (step S100: training data generation step). Specifically, first, the control device 20 acquires an entire image and cuts the entire image into a plurality of partial images.
  • the control device 20 sets the noise evaluation value that evaluates the noise spread as the noise setting value for each partial image.
  • the control device 20 sets a different noise evaluation value for each partial image as the noise setting value.
  • the control device 20 uses the third method described above to set the noise evaluation value derived from the pixel value of each pixel of the partial image as the noise setting value for each pixel of the partial image based on the first relationship data that indicates the relationship between the pixel value and the noise evaluation value that evaluates the spread of the noise value.
  • the control device 20 generates a noise map that is data that associates the noise evaluation value with each pixel of the image based on the noise setting value for multiple partial images.
  • the control device 20 generates a noise map that is data that associates the noise evaluation value with each pixel of the partial image.
  • the control device 20 sets blur evaluation information that evaluates the spatial blur of the noise as blur setting information for each partial image.
  • the control device 20 sets different blur evaluation information for each partial image as blur setting information.
  • the control device 20 uses the sixth method described above to set blur evaluation information derived from the pixel value of each pixel of the partial image as blur setting information based on the second relationship data indicating the relationship between the pixel value and the blur evaluation information that evaluates the spatial blur of the noise to the pixels of each partial image.
  • the control device 20 generates a spatial blur map that indicates the distribution of spatial blur of the noise based on the blur setting information for multiple partial images.
  • the control device 20 generates data that is set by associating the blur setting information with each pixel of the partial image as the spatial blur map.
  • control device 20 generates a noise image by adding noise to the partial image based on the generated noise map and spatial blur map.
  • the noise map, spatial blur map, and noise image are generated by the control device 20.
  • control device 20 constructs a trained model 207 (step S101: construction step). Specifically, the control device 20 uses the partial image, the spatial blur map, and the noise image as training data, and constructs the trained model 207 by machine learning to input the spatial blur map and the noise image and output a noise-removed image in which noise has been removed from the noise image so that the noise-removed image approximates the partial image.
  • the object F is set in the image acquisition device 1, the object F is imaged, and the control device 20 acquires an image of the object F (step S102: image acquisition step). Then, the control device 20 generates a noise map (step S103: noise map generation step). Specifically, the control device 20 cuts out the acquired image into a plurality of partial images. The control device 20 derives a noise evaluation value from the pixel values of each pixel of the partial image based on first relationship data indicating the relationship between the pixel value and the noise evaluation value that evaluates the spread of the noise value, and generates a noise map, which is data that associates the derived noise evaluation value with each pixel of the partial image.
  • the control device 20 generates a spatial blur map showing the distribution of the spatial blur of the noise based on the acquired image (step S104: spatial blur map generation step). Specifically, the control device 20 derives blur evaluation information from the pixel values of each pixel of the partial image based on second relationship data showing the relationship between the pixel values and blur evaluation information that evaluates the spatial blur of the noise, and generates data in which the derived blur evaluation information is associated with each pixel of the partial image as a spatial blur map.
  • control device 20 executes image processing to remove noise from the image (step S105: processing step). Specifically, the control device 20 inputs the partial image, noise map, and spatial blur map to the trained model 207, and executes image processing to remove noise from the partial image. The multiple partial images from which noise has been removed are integrated to generate an image from which noise has been removed.
  • the processing unit 204 outputs the output image, which is the image that has been subjected to the noise removal process, to the display device 30 (step S106).
  • a spatial blur map showing the distribution of spatial blur of noise is generated based on an image captured of an energy ray that has passed through an object F, and the image and spatial blur map are input to a trained model 207 constructed in advance by machine learning, and image processing is performed to remove noise from the image.
  • changes in the blur of noise are taken into consideration and the noise in the image is removed by machine learning. For example, even if the measurement conditions of the energy ray change and the blur of noise changes, the noise in the image is effectively removed. This makes it possible to realize noise removal that corresponds to changes in the blur of noise in the image using the trained model 207. As a result, noise in the image can be effectively removed.
  • noise in an image is removed by taking into account the spread of noise in the luminance direction.
  • noise in an image is removed by taking into account the relationship between the luminance value and the standard deviation of the pixel value.
  • the noise blur which is the spread of noise in the spatial direction, changes in the image, a sufficient noise removal effect may not be obtained.
  • the noise frequency changes due to a difference in the type of scintillator, etc., it may not be possible to remove the noise appropriately.
  • noise is removed from an image by taking into account the change in the noise frequency (change in the blur of the noise). This makes it possible to optimally remove noise in an image even in situations where the noise frequency is various. For example, it is possible to effectively remove multiple types of noise with different frequencies.
  • the control device 20 of this embodiment also derives a noise evaluation value from the pixel value of each pixel of the image based on first relationship data indicating the relationship between the pixel value and the noise evaluation value evaluating the spread of the noise value, and generates a noise map, which is data in which the derived noise evaluation value is associated with each pixel of the image.
  • the control device 20 inputs the image, the spatial blur map, and the noise map to the trained model 207, and executes image processing to remove noise from the image.
  • the spread of the noise value evaluated from the pixel value of each pixel of the image is further taken into consideration, and the noise in each pixel of the image is removed by machine learning.
  • the trained model 207 can be used to realize noise removal that further corresponds to the relationship between the pixel value in the image and the spread of the noise. As a result, noise in the image can be removed more effectively.
  • FIG. 14(a) shows an image before noise is removed.
  • FIG. 14(b) shows an image after noise has been removed by a conventional image processing method.
  • FIG. 14(c) shows an image after noise has been removed by the image processing method according to this embodiment.
  • the fine structure of a subject is judged as noise and removed from the image, so that the fine structure of the subject becomes blurred in the image.
  • the fine structure of the subject is not judged as noise, as shown in FIG. 14(c).
  • noise can be effectively removed without blurring the fine structure in the image, and appropriate noise removal is possible.
  • the control device 20 of this embodiment also generates a spatial blur map for each of the multiple partial images cut out from the image, inputs the multiple partial images into the trained model 207 and executes image processing to remove noise from the multiple partial images, and integrates the multiple partial images from which noise has been removed to generate an image from which noise has been removed.
  • noise in the image can be removed by simple processing by executing image processing to remove noise for each of the multiple partial images cut out from the image.
  • the control device 20 of this embodiment also derives blur evaluation information from the pixel values of each pixel of the image based on second relationship data indicating the relationship between pixel values and blur evaluation information that evaluates the spatial blur of noise, and generates data in which the derived blur evaluation information is associated with each pixel of the image as a spatial blur map.
  • the spatial blur of noise evaluated from the pixel values of each pixel of the image is taken into consideration, and noise in each pixel of the image is removed by machine learning. This makes it possible to more effectively remove noise in the image.
  • the control device 20 of this embodiment also cuts out a plurality of partial images from the entire image as training images, sets blur evaluation information that evaluates the spatial blur of the noise as blur setting information, and generates a spatial blur map that indicates the distribution of the spatial blur of the noise for the plurality of partial images based on the blur setting information.
  • the control device 20 generates a noise image by adding noise to the partial image based on the generated spatial blur map.
  • the control device 20 uses the partial image, the spatial blur map, and the noise image as training data, and constructs a trained model 207 by machine learning to input the spatial blur map and the noise image and output a noise-removed image in which noise has been removed from the noise image so that the noise-removed image approximates the partial image.
  • the trained model 207 used for noise removal from the image is constructed by machine learning using training data.
  • noise removal corresponding to changes in the spatial blur of the noise can be realized.
  • noise in the image can be effectively removed.
  • control device 20 of this embodiment sets the blur setting information as different blur evaluation information for each partial image.
  • noise removal that can respond to various changes in noise blur can be achieved.
  • noise in the image can be removed more effectively.
  • the control device 20 of this embodiment also sets blur evaluation information derived from the pixel values of each pixel of the partial image as blur setting information for each pixel of the partial image based on second relationship data indicating the relationship between pixel values and the standard deviation of pixel values, and generates data in which the blur setting information is associated with each pixel of the partial image and set as a spatial blur map.
  • noise removal can be achieved that takes into account the spatial blur of noise evaluated from the pixel values of each pixel of the image. As a result, noise in the image can be removed more effectively.
  • control device 20 of this embodiment generates the second relationship data by simulation. With this configuration, it is possible to obtain second relationship data that is more suitable for removing noise from an image. As a result, noise in an image can be removed more effectively.
  • control device 20 of this embodiment generates the second relationship data based on the image that is actually captured. With this configuration, it is possible to obtain second relationship data that is more suitable for removing noise from the image. As a result, noise in the image can be removed more effectively.
  • the blur evaluation information is at least one of the sigma value, half-width, point spread function, contrast transfer function, and modulation transfer function.
  • the trained model 207 is a model constructed as described above, and causes the processor to execute image processing to remove noise from an image of an energy beam that has passed through the object F.
  • the trained model 207 can be used to achieve noise removal that corresponds to changes in the blur of noise in the image. As a result, noise in the image can be effectively removed.
  • the processing unit 204 inputs the partial image, the spatial blur map, and the noise map to the trained model 207 and performs image processing to remove noise from the partial image, but the noise map does not have to be input to the trained model 207.
  • the training data generating unit 206 may not generate a noise map as training data.
  • the training data generating unit 206 may generate a spatial blur map as in the above embodiment, and may generate a noise image by adding noise to the partial image based on the generated spatial blur map.
  • the training data generating unit 206 may determine a noise value for each pixel of the partial image and generate a noise distribution of the same size as the partial image.
  • Each noise value in the noise distribution may be determined based on a preset standard deviation, or may be determined arbitrarily by a method other than the above.
  • the training data generating unit 206 may use the partial image, the spatial blur map, and the noise image as training data, and may construct a trained model 207 by machine learning to input the spatial blur map and the noise image and output a noise-removed image obtained by removing noise from the noise image so that the noise-removed image approximates the partial image.
  • control device 20 may not include the noise map generation unit 202.
  • the processing unit 204 may input the partial image and the spatial blur map to the trained model 207 and perform image processing to remove noise from the partial image.
  • the control device 20 may generate a noise image by adding noise to the partial image based on the generated spatial blur map in step S100.
  • the control device 20 may use the partial image, spatial blur map, and noise image as training data to construct a trained model 207 by machine learning, which uses the spatial blur map and the noise image as inputs and outputs a noise-removed image in which noise has been removed from the noise image so that the noise-removed image approximates the partial image.
  • the control device 20 may not execute step S103.
  • step S105 the control device 20 may input the partial image and spatial blur map to the trained model 207 and execute image processing to remove noise from the partial image.
  • the image acquisition unit 201 may not need to cut out an image into a plurality of partial images.
  • the noise map generation unit 202 may generate a noise map for each image.
  • the noise map generation unit 202 may derive relational data G3 representing the correspondence between each pixel position and pixel value from the image G1 instead of the partial image G2.
  • the noise map generation unit 202 may derive the standard deviation of pixel values corresponding to the pixels at each pixel position in the image G1 by applying the correspondence shown in the relational graph G4 to each pixel value in the relational data G3.
  • the noise map generation unit 202 may associate the derived standard deviation of pixel values with each pixel position, and derive relational data G5 indicating the correspondence between each pixel position and the standard deviation of pixel values. Then, the noise map generation unit 202 may generate a noise map G6 based on the derived relational data G5.
  • the spatial blur map generating unit 203 may generate a spatial blur map for each image.
  • the spatial blur map generating unit 203 may derive blur evaluation information corresponding to pixels at each pixel position in image G1 by applying the correspondence indicated by the second relationship data G70 to each pixel value in image G1.
  • the spatial blur map generating unit 203 may associate the derived blur evaluation information with each pixel position in image G1, and generate a spatial blur map G8 indicating the distribution of spatial blur of noise.
  • the processing unit 204 may input the image, the spatial blur map, and the noise map to the trained model 207, and perform image processing to remove noise from the image.
  • the control device 20 may input the image G1, the noise map G6, and the spatial blur map G8 to the trained model 207 instead of the partial image G2, and perform image processing to remove noise from the image G1.
  • the control device 20 generates a plurality of noise-removed images G9 from which noise has been removed, and outputs the noise-removed images G9 to the display device 30, etc.
  • the overall image used for machine learning may be an image generated by simulation or may be a standard image available via an internet line or the like, but is not limited to this.
  • the overall image used for machine learning may be a high-output image.
  • the overall image used for machine learning may be a Noise2Noise image.
  • the control device 20 may generate a noise map and a sigma map from the Noise2Noise image.
  • the control device 20 may use the Noise2Noise image, the noise map, and the sigma map as training data to construct a trained model 207 by unsupervised learning or the like.
  • a spatial blur map showing the distribution of spatial blur of noise is generated based on an image captured of an energy beam that has passed through an object, and the image and spatial blur map are input to a trained model previously constructed by machine learning, and image processing is performed to remove noise from the image.
  • noise in the image is removed by machine learning, taking into account changes in noise blur. For example, even if the measurement conditions of the energy beam change and the like, causing the noise blur to change, the noise in the image is effectively removed. This makes it possible to realize noise removal that corresponds to changes in noise blur in the image using the trained model. As a result, noise in the image can be effectively removed.
  • the method further includes a noise map generation step of deriving a noise evaluation value from the pixel value of each pixel of the image based on the first relationship data indicating the relationship between the pixel value and the noise evaluation value evaluating the spread of the noise value, and generating a noise map that is data in which the derived noise evaluation value is associated with each pixel of the image, and in the processing step, the image, the spatial blur map, and the noise map are input to a trained model, and image processing is performed to remove noise from the image.
  • the method further includes a noise map generation unit that derives a noise evaluation value from the pixel value of each pixel of the radiographic image based on the first relationship data indicating the relationship between the pixel value and the noise evaluation value evaluating the spread of the noise value, and generates a noise map that is data in which the derived noise evaluation value is associated with each pixel of the radiographic image, and the processing unit preferably inputs the radiographic image, the spatial blur map, and the noise map to a trained model, and performs image processing to remove noise from the radiographic image.
  • the spread of the noise value evaluated from the pixel value of each pixel of the image is further taken into consideration, and the noise in each pixel of the image is removed by machine learning. This allows the use of a trained model to achieve noise removal that better accounts for the relationship between pixel values in an image and the spread of noise. As a result, noise in an image can be removed more effectively.
  • a spatial blur map is generated for each of the first partial images cut out from the image, and in the processing step, the first partial images are input to the trained model instead of the image, image processing is performed to remove noise from the first partial images, and the first partial images from which noise has been removed are integrated to generate an image from which noise has been removed.
  • the spatial blur map generating unit generates a spatial blur map for each of the first partial images cut out from the radiographic image
  • the processing unit inputs the first partial images to the trained model instead of the radiographic image, image processing is performed to remove noise from the first partial images, and the first partial images from which noise has been removed are integrated to generate an image from which noise has been removed.
  • noise in the image can be removed by simple processing by performing image processing to remove noise for each of the first partial images cut out from the image.
  • blur evaluation information is derived from the pixel value of each pixel of the image based on the second relationship data indicating the relationship between the pixel value and the blur evaluation information evaluating the spatial blur of the noise, and data in which the derived blur evaluation information is associated with each pixel of the image is generated as a spatial blur map.
  • the spatial blur map generation unit derives blur evaluation information from the pixel value of each pixel of the radiological image based on the second relationship data indicating the relationship between the pixel value and the blur evaluation information evaluating the spatial blur of the noise, and data in which the derived blur evaluation information is associated with each pixel of the radiological image is generated as a spatial blur map.
  • the training method includes a training data generation step of extracting a plurality of second partial images from an overall image as training images, setting blur evaluation information evaluating the spatial blur of the noise as blur setting information for each second partial image, generating a spatial blur map indicating the distribution of the spatial blur of the noise based on the blur setting information for the plurality of second partial images, and generating a noise image by adding noise to the second partial image based on the generated spatial blur map; and a construction step of constructing a trained model by machine learning using the second partial images, the spatial blur map, and the noise image as training data, and using the spatial blur map and the noise image as input to output a noise-removed image in which noise has been removed from the noise image, so that the noise-removed image approximates the second partial image.
  • a training data generation unit that cuts out a plurality of second partial images from the entire image as training images, sets blur evaluation information evaluating the spatial blur of noise as blur setting information for each second partial image, generates a spatial blur map showing the distribution of the spatial blur of noise based on the blur setting information for the plurality of second partial images, and generates a noise image by adding noise to the second partial image based on the generated spatial blur map, and a construction unit that uses the second partial image, the spatial blur map, and the noise image as training data, inputs the spatial blur map and the noise image, and constructs a trained model by machine learning to output a noise-removed image in which noise is removed from the noise image so that the noise-removed image is similar to the second partial image.
  • the trained model used for noise removal from the image is constructed by machine learning using the training data.
  • the blur setting information is set as blur evaluation information that differs from one another for each second partial image.
  • the training data generation unit sets the blur setting information as blur evaluation information that differs from one another for each second partial image.
  • the blur evaluation information derived from the pixel value of each pixel of the second partial image is set as blur setting information for each pixel of the second partial image based on the second relationship data indicating the relationship between the pixel value and the blur evaluation information evaluating the spatial blur of the noise, and data set by associating the blur setting information with each pixel of the second partial image is generated as a spatial blur map.
  • the training data generation unit sets the blur evaluation information derived from the pixel value of each pixel of the second partial image as blur setting information for each pixel of the second partial image based on the second relationship data indicating the relationship between the pixel value and the blur evaluation information evaluating the spatial blur of the noise, and data set by associating the blur setting information with each pixel of the second partial image is generated as a spatial blur map.
  • the second relationship data is generated by simulation. Also, in the above embodiment, it is preferable that the training data generation unit generates the second relationship data by simulation. With this configuration, it is possible to obtain second relationship data that is more suitable for removing noise from an image. As a result, noise in an image can be removed more effectively.
  • the second relationship data is generated based on images obtained by actually capturing images. Also, in the above embodiment, it is preferable that the training data generation unit generates the second relationship data based on radiological images obtained by actually capturing images. With this configuration, it is possible to obtain second relationship data that is more suitable for removing noise from the images. As a result, it is possible to more effectively remove noise from the images.
  • the blur evaluation information is at least one of the sigma value, half-width, point spread function, contrast transfer function, and modulation transfer function.
  • the trained model of the embodiment is a trained model constructed by the training data generation step and construction step described above, and it is preferable to have the processor execute image processing to remove noise from an image of an energy ray that has passed through an object. This makes it possible to use the trained model to achieve noise removal that corresponds to changes in the blur of noise in the image. As a result, noise in the image can be effectively removed.
  • the image processing method of the embodiment is [1] "an image processing method comprising an image acquisition step of irradiating an object with an energy beam and acquiring an image of the energy beam that has passed through the object, a spatial blur map generation step of generating a spatial blur map showing the distribution of spatial blur of noise based on the image, and a processing step of inputting the image and the spatial blur map into a trained model previously constructed by machine learning, and executing image processing to remove noise from the image.”
  • the image processing method of the embodiment may be the image processing method described in [1] above, further comprising a noise map generation step of deriving a noise evaluation value from the pixel value of each pixel of the image based on first relationship data indicating the relationship between the pixel value and a noise evaluation value that evaluates the spread of the noise value, and generating a noise map that is data in which the noise evaluation value derived is associated with each pixel of the image, and in the processing step, the image, the spatial blur map, and the noise map are input to a trained model, and image processing is performed to remove noise from the image.
  • the image processing method of the embodiment may be [3] "the image processing method described in [1] or [2] above, in which in the spatial blur map generation step, a spatial blur map is generated for each of a plurality of first partial images cut out from an image, and in the processing step, the plurality of first partial images are input to a trained model instead of an image to perform image processing to remove noise from the plurality of first partial images, and the plurality of first partial images from which noise has been removed are integrated to generate an image from which noise has been removed.”
  • the image processing method of the embodiment may be [4] "an image processing method according to any one of [1] to [3] above, in which in the spatial blur map generation step, blur evaluation information is derived from the pixel values of each pixel of the image based on second relationship data indicating the relationship between pixel values and blur evaluation information that evaluates the spatial blur of noise, and data in which the derived blur evaluation information is associated with each pixel of the image is generated as a spatial blur map.”
  • the training method of the embodiment is [5] a training method including: a training data generation step of cutting out a plurality of second partial images from an entire image as training images, setting blur evaluation information evaluating the spatial blur of noise as blur setting information for each second partial image, generating a spatial blur map showing the distribution of the spatial blur of noise for the plurality of second partial images based on the blur setting information, and generating a noise image by adding noise to the second partial image based on the generated spatial blur map; and a construction step of constructing a trained model by machine learning using the second partial images, the spatial blur map, and the noise image as training data, and using the spatial blur map and the noise image as inputs to output a noise-removed image in which noise has been removed from the noise image, such that the noise-removed image approximates the second partial image.
  • the training method of the embodiment may be [6] "the training method described in [5] above, in which in the training data generation step, the blur setting information is set as different blur evaluation information for each second partial image.”
  • the training method of the embodiment may be [7] "the training method described in either [5] or [6] above, in which in the training data generation step, blur evaluation information derived from the pixel value of each pixel of the second partial image is set as blur setting information for each pixel of the second partial image based on second relationship data indicating the relationship between the pixel value and blur evaluation information evaluating the spatial blur of noise, and data set by associating the blur setting information with each pixel of the second partial image is generated as a spatial blur map.”
  • the training method of the embodiment may be [8] "the training method described in [7] above, in which in the training data generation step, the second relationship data is generated by simulation.”
  • the training method of the embodiment may be [9] "the training method described in [7] above, in which in the training data generation step, the second relationship data is generated based on images actually captured.”
  • the training method of the embodiment may be [10] "the training method described in any one of [5] to [9] above, in which the blur evaluation information is at least one of the sigma value, the half-width, the point spread function, the contrast transfer function, and the modulation transfer function.”
  • the trained model of the embodiment may be [11] "a trained model constructed by the training method described in any one of [5] to [10] above, which causes a processor to perform image processing to remove noise from an image of an energy beam that has passed through an object.”
  • the radiation image processing module of the embodiment is [12] "a radiation image processing module including: an image acquisition unit that acquires a radiation image in which an object is irradiated with radiation and the radiation that has passed through the object is captured; a spatial blur map generation unit that generates a spatial blur map that indicates the distribution of spatial blur of noise based on the radiation image; and a processing unit that inputs the radiation image and the spatial blur map into a trained model that has been constructed in advance by machine learning, and executes image processing to remove noise from the radiation image.”
  • the radiation image processing module of the embodiment may be the radiation image processing module described in [12] above, further comprising: [13] "a noise map generating unit that derives a noise evaluation value from the pixel values of each pixel of the radiation image based on first relationship data indicating the relationship between pixel values and a noise evaluation value that evaluates the spread of noise values, and generates a noise map that is data in which each pixel of the radiation image is associated with the derived noise evaluation value, and the processing unit inputs the radiation image, the spatial blur map, and the noise map to a trained model, and executes image processing to remove noise from the radiation image.”
  • the radiation image processing module of the embodiment may be [14] "the radiation image processing module described in [12] or [13] above, in which the spatial blur map generation unit generates a spatial blur map for each of a plurality of first partial images cut out from the radiation image, and the processing unit inputs the plurality of first partial images instead of the radiation image into the trained model and executes image processing to remove noise from the plurality of first partial images, and integrates the plurality of first partial images from which noise has been removed to generate a radiation image from which noise has been removed.”
  • the radiation image processing module of the embodiment may be [15] "a radiation image processing module according to any one of [12] to [14] above, in which the spatial blur map generating unit derives blur evaluation information from the pixel values of each pixel of the radiation image based on second relationship data indicating the relationship between the pixel values and blur evaluation information that evaluates the spatial blur of noise, and generates data in which the derived blur evaluation information is associated with each pixel of the radiation image as a spatial blur map.”
  • the radiation image processing module of the embodiment is [16] "a training data generation unit that cuts out a plurality of second partial images from an entire image as training images, sets blur evaluation information evaluating the spatial blur of noise as blur setting information for each second partial image, generates a spatial blur map showing the distribution of the spatial blur of noise based on the blur setting information for the plurality of second partial images, and generates a noise image by adding noise to the second partial image based on the generated spatial blur map; and a construction unit that uses the second partial image, the spatial blur map, and the noise image as training data, and constructs a trained model by machine learning to output a noise-removed image by removing noise from the noise image using the spatial blur map and the noise image as input, so that the noise-removed image approximates the second partial image.”
  • the radiation image processing module of the embodiment may be [17] "the radiation image processing module described in [16] above, in which the training data generation unit sets the blur setting information as different blur evaluation information for each second partial image.”
  • the radiation image processing module of the embodiment may be [18] "a radiation image processing module according to either of [16] or [17] above, in which the training data generating unit sets blur evaluation information derived from the pixel values of each pixel of the second partial image as blur setting information for each pixel of the second partial image based on second relationship data indicating the relationship between pixel values and blur evaluation information that evaluates the spatial blur of noise, and generates data in which the blur setting information is associated with each pixel of the second partial image and set as a spatial blur map.”
  • the radiation image processing module of the embodiment may be [19] "the radiation image processing module described in [18] above, in which the training data generation unit generates the second relationship data by simulation.”
  • the radiation image processing module of the embodiment may be [20] "the radiation image processing module described in [18] above, in which the training data generation unit generates the second relationship data based on radiation images actually captured.”
  • the radiation image processing module of the embodiment may be [21] "a radiation image processing module according to any one of [16] to [20] above, in which the blur evaluation information is at least one of a sigma value, a half-width, a point spread function, a contrast transfer function, and a modulation transfer function.”
  • the radiation image processing program of the embodiment may be [22] "a radiation image processing program that causes a processor to function as an image acquisition unit that acquires a radiation image in which radiation is irradiated onto an object and the radiation that has passed through the object is captured, a spatial blur map generation unit that generates a spatial blur map that indicates the distribution of spatial blur of noise based on the radiation image, and a processing unit that inputs the radiation image and the spatial blur map into a trained model that has been constructed in advance by machine learning, and executes image processing to remove noise from the radiation image.”
  • the radiation image processing system of the embodiment may be [23] "a radiation image processing system including a radiation image processing module described in [12] to [21] above, a radiation source that irradiates an object with radiation, and an imaging device that captures the radiation that has passed through the object to obtain a radiation image.”

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Optics & Photonics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physiology (AREA)
  • Image Processing (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
PCT/JP2023/033577 2023-01-23 2023-09-14 画像処理方法、訓練方法、訓練済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム Ceased WO2024157532A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020257027061A KR20250137636A (ko) 2023-01-23 2023-09-14 화상 처리 방법, 훈련 방법, 훈련 완료 모델, 방사선 화상 처리 모듈, 방사선 화상 처리 프로그램, 및 방사선 화상 처리 시스템
CN202380092113.6A CN120958478A (zh) 2023-01-23 2023-09-14 图像处理方法、训练方法、训练完毕模型、放射线图像处理模块、放射线图像处理程序和放射线图像处理系统
JP2024572836A JPWO2024157532A1 (https=) 2023-01-23 2023-09-14
EP23918489.8A EP4623827A1 (en) 2023-01-23 2023-09-14 Image processing method, training method, trained model, radiological image processing module, radiological image processing program, and radiological image processing system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2023008185 2023-01-23
JP2023-008185 2023-01-23

Publications (1)

Publication Number Publication Date
WO2024157532A1 true WO2024157532A1 (ja) 2024-08-02

Family

ID=91970214

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/033577 Ceased WO2024157532A1 (ja) 2023-01-23 2023-09-14 画像処理方法、訓練方法、訓練済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム

Country Status (5)

Country Link
EP (1) EP4623827A1 (https=)
JP (1) JPWO2024157532A1 (https=)
KR (1) KR20250137636A (https=)
CN (1) CN120958478A (https=)
WO (1) WO2024157532A1 (https=)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120411293A (zh) * 2025-06-30 2025-08-01 长沙亦月科技有限公司 基于图转图扩散模型的打印-拍摄过程图像退化模拟方法、装置及设备
CN120563363A (zh) * 2025-07-31 2025-08-29 武汉工程大学 基于rbf曲面的热效应和条带噪声的同步渐进校正方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190005686A1 (en) * 2017-06-28 2019-01-03 Shanghai United Imaging Healthcare Co., Ltd. Systems and methods for correcting projection data
JP2019208990A (ja) * 2018-06-07 2019-12-12 キヤノンメディカルシステムズ株式会社 医用画像診断装置
JP2021019714A (ja) * 2019-07-25 2021-02-18 株式会社日立製作所 画像処理装置、画像処理方法及びｘ線ｃｔ装置
US20210330274A1 (en) * 2020-04-22 2021-10-28 Siemens Healthcare Gmbh Computer-implemented method, computer program, systems and x-ray facility for correction of x-ray image data with regard to noise effects
WO2022172506A1 (ja) 2021-02-15 2022-08-18 浜松ホトニクス株式会社 放射線画像処理方法、機械学習方法、学習済みモデル、機械学習の前処理方法、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190005686A1 (en) * 2017-06-28 2019-01-03 Shanghai United Imaging Healthcare Co., Ltd. Systems and methods for correcting projection data
JP2019208990A (ja) * 2018-06-07 2019-12-12 キヤノンメディカルシステムズ株式会社 医用画像診断装置
JP2021019714A (ja) * 2019-07-25 2021-02-18 株式会社日立製作所 画像処理装置、画像処理方法及びｘ線ｃｔ装置
US20210330274A1 (en) * 2020-04-22 2021-10-28 Siemens Healthcare Gmbh Computer-implemented method, computer program, systems and x-ray facility for correction of x-ray image data with regard to noise effects
WO2022172506A1 (ja) 2021-02-15 2022-08-18 浜松ホトニクス株式会社 放射線画像処理方法、機械学習方法、学習済みモデル、機械学習の前処理方法、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
KAI ZHANG ET AL., BEYOND A GAUSSIAN DENOISER: RESIDUAL LEARNING OF DEEP CNN FOR IMAGE DENOISING
See also references of EP4623827A1

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120411293A (zh) * 2025-06-30 2025-08-01 长沙亦月科技有限公司 基于图转图扩散模型的打印-拍摄过程图像退化模拟方法、装置及设备
CN120563363A (zh) * 2025-07-31 2025-08-29 武汉工程大学 基于rbf曲面的热效应和条带噪声的同步渐进校正方法

Also Published As

Publication number Publication date
CN120958478A (zh) 2025-11-14
KR20250137636A (ko) 2025-09-18
JPWO2024157532A1 (https=) 2024-08-02
EP4623827A1 (en) 2025-10-01

Similar Documents

Publication Publication Date Title
WO2024157532A1 (ja) 画像処理方法、訓練方法、訓練済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム
JP7546047B2 (ja) 放射線画像処理方法、学習済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、放射線画像処理システム、及び機械学習方法
JP7546048B2 (ja) 放射線画像処理方法、学習済みモデル、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム
US20140023252A1 (en) Image processing apparatus, image processing method and image processing program
JP7712967B2 (ja) 放射線画像処理方法、機械学習方法、学習済みモデル、機械学習の前処理方法、放射線画像処理モジュール、放射線画像処理プログラム、及び放射線画像処理システム
EP4357818A1 (en) Radiographic image acquiring device, radiographic image acquiring system, and radiographic image acquisition method
JP7579333B2 (ja) 放射線画像取得装置、放射線画像取得システム、及び放射線画像取得方法
EP4679360A1 (en) Image processing method, image processing device, and image processing program
TWI885189B (zh) 放射線圖像處理方法、學習完成模型、放射線圖像處理模組、放射線圖像處理程式、放射線圖像處理系統及機器學習方法
TW202307785A (zh) 放射線圖像處理方法、學習完成模型、放射線圖像處理模組、放射線圖像處理程式及放射線圖像處理系統

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: 23918489

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024572836

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 2023918489

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2023918489

Country of ref document: EP

Effective date: 20250625

ENP Entry into the national phase

Ref document number: 1020257027061

Country of ref document: KR

Free format text: ST27 STATUS EVENT CODE: A-0-1-A10-A15-NAP-PA0105 (AS PROVIDED BY THE NATIONAL OFFICE)

WWE Wipo information: entry into national phase

Ref document number: 1020257027061

Country of ref document: KR

NENP Non-entry into the national phase

Ref country code: DE

WWP Wipo information: published in national office

Ref document number: 2023918489

Country of ref document: EP