# US 12,112,473 B2 · Image processing apparatus, image processing method, and non-transitory computer-readable storage medium that use a plurality of captured radiation images to obtain, by sequential approximation solution by iterative calculation, an output image > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,473 B2 - Document ID: US12112473B2 - Status: Granted - Kind: B2 - Application number: 17/526,697 - Filed: 2021-11-15 - Published: 2022-03-10 - Granted: 2024-10-08 - Earliest claimed: 2019-05-30 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kubushiki Kaisha - Inventors: Akira Tsukuda; Atsushi Iwashita; Sota Torii; Takeshi Noda; Kosuke Terui - Web page: https://patentgrep.com/patent/US12112473B2 ## CPC - G06T 5/70: Denoising; Smoothing - G06T 7/0012: {Biomedical image inspection} - A61B 6/00: Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment (instruments measuring radiation intensity for application in the field of nuclear medicine, e.g. in vivo counting, G01T1/161) - G06T 2207/10116: X-ray image - G06T 2207/20076: Probabilistic image processing - G06T 2207/30008: Bone - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) ## Abstract An image processing apparatus includes a planar distribution obtaining unit configured, using a plurality of radiation images captured using different radiation energies as input images, to obtain, by a sequential approximation solution by an iterative calculation, an output image representing a planar distribution for a substance contained in the input image. Based on a likelihood and a prior probability using one of a pixel value of a pixel of interest or a pixel value of a peripheral pixel as an input, the planar distribution obtaining unit decides the output image such that a probability that an output is a value of the planar distribution when an input is the input image that is maximized. ## Claims ### Claim 1 An image processing apparatus comprising: a planar distribution obtaining unit configured, using a plurality of radiation images captured using different radiation energies as input images, to obtain, by a sequential approximation solution by an iterative calculation, an output image representing a planar distribution for a substance contained in the input image, wherein, based on a likelihood and a prior probability using one of a pixel value of a pixel of interest or a pixel value of a peripheral pixel as an input, the planar distribution obtaining unit decides the output image such that a probability that an output is a value of the planar distribution when an input is the input image that is maximized. ### Claim 2 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit obtains the prior probability based on a difference between the pixel value of the pixel of interest and the pixel value of the peripheral pixel in the output image. ### Claim 3 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit obtains the prior probability based on the pixel value of the pixel of interest in the output image. ### Claim 4 (depends on 2) The image processing apparatus according to claim 2, wherein the planar distribution obtaining unit evaluates continuity of the planar distribution by the difference, and reduces noise in the output image based on the evaluation. ### Claim 5 (depends on 1) The image processing apparatus according to claim 1, wherein, in accordance with an iteration count of the iterative calculation, the planar distribution obtaining unit updates a setting of a coefficient representing a speed of iteration such that the coefficient becomes small. ### Claim 6 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit performs the iterative calculation using, as an initial value, a value of a planar distribution in a case in which noise is assumed to be absent. ### Claim 7 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit performs the iterative calculation using, as an initial value, a value of a planar distribution obtained by a smoothing process for the output image. ### Claim 8 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit obtains the output image by adding pixel values of images obtained based on radiation spectra corresponding to the different radiation energies. ### Claim 9 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit obtains the output image by approximating radiation spectra corresponding to the different radiation energies as a radiation spectrum of a single color. ### Claim 10 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit uses one of a normal distribution and a Poisson distribution as a probability distribution of the likelihood. ### Claim 11 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit obtains, as the output image, an image separated to each of a plurality of substances contained in the plurality of radiation images. ### Claim 12 (depends on 11) The image processing apparatus according to claim 11, wherein the planar distribution obtaining unit obtains, as the output image, each of a thickness image of a soft tissue that constitutes a subject and a thickness image of a hard tissue that constitutes the subject. ### Claim 13 (depends on 12) The image processing apparatus according to claim 12, wherein the planar distribution obtaining unit evaluates continuity in the thickness image of the soft tissue based on a difference between a pixel value of a pixel of interest and a pixel value of a peripheral pixel in the thickness image of the soft tissue. ### Claim 14 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit changes a regularization coefficient representing a degree of an influence of the prior probability based on an imaging condition. ### Claim 15 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit changes a regularization coefficient representing a degree of an influence of the prior probability based on a radiation irradiation condition. ### Claim 16 (depends on 1) The image processing apparatus according to claim 1, wherein the planar distribution obtaining unit changes a regularization coefficient representing a degree of an influence of the prior probability based on information concerning a body shape of a subject. ### Claim 17 An image processing method comprising: using a plurality of radiation images captured using different radiation energies as input images; and obtaining, by a sequential approximation solution by an iterative calculation, an output image representing a planar distribution for a substance contained in the image, wherein, based on a likelihood and a prior probability using one of a pixel value of a pixel of interest or a pixel value of a peripheral pixel as an input, in the obtaining, the output image is decided such that a probability that an output is a value of the planar distribution when an input is the input image that is maximized. ### Claim 18 (depends on 17) A non-transitory computer-readable storage medium storing a program configured to cause a computer to execute the method according to claim 17. ### Claim 19 An image processing apparatus comprising: a planar distribution obtaining unit configured, using a plurality of radiation images captured using different radiation energies as input images, to obtain an output image representing a planar distribution for a substance contained in the input image, wherein, based on a likelihood and a prior probability using one of a pixel value of a pixel of interest or a pixel value of a peripheral pixel as an input, the planar distribution obtaining unit decides the output image such that a probability that an output is a value of the planar distribution when an input is the input image that is maximized, the planar distribution obtaining unit obtains: the output image by adding pixel values of images obtained based on radiation spectra corresponding to the different radiation energies, or the output image by approximating radiation spectra corresponding to the different radiation energies as a radiation spectrum of a single color.