# US 10,482,326 B2 · Image processing system, processing method, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,326 B2 - Document ID: US10482326B2 - Status: Granted - Kind: B2 - Application number: 15/789,226 - Filed: 2017-10-20 - Published: 2018-02-08 - Granted: 2019-11-19 - Earliest claimed: 2013-01-24 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Yoshihiko Iwase; Hiroyuki Shinbata; Makoto Sato - Web page: https://patentgrep.com/patent/US10482326B2 ## CPC - G06V 40/197: {Matching; Classification} - A61B 3/0025: {characterised by electronic signal processing, e.g. eye models} - G06T 7/0012: {Biomedical image inspection} - G06T 7/64: of convexity or concavity - G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT] - G06T 2207/30041: Eye; Retina; Ophthalmic - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An image processing system includes: an analysis unit configured to obtain information indicating a degree of curvature of a retina from a tomographic image of an eye to be examined; and an obtaining unit configured to obtain a category of the eye to be examined based on an analysis result. ## Claims ### Claim 1 An image processing system comprising: a memory that stores a program; and a processor that executes the program stored in the memory so as to function as units including: a detection unit configured to detect a retinal layer of a fundus retina in each of a plurality of tomographic images captured by a tomographic imaging apparatus; an obtaining unit configured to obtain a shape feature amount of the retinal layer of the fundus retina based on the detected retinal layer of the each of the tomographic images, the shape feature amount being a plurality of curvatures calculated at respective parts on the detected retinal layer in the tomographic image; and an analysis unit configured to obtain shape analysis information by comparing the shape feature amount of the retinal layer of the fundus retina with a database in which a plurality of shape feature amounts are stored, the plurality of shape feature amounts being classified based on ophthalmic axis length-dependent parameter. ### Claim 2 (depends on 1) The image processing system according to claim 1, wherein the units further include a selecting unit configured to select the retinal layer for an analysis target layer, and wherein the analysis unit obtains the shape analysis information with reference to the shape feature amount of the retinal layer selected by the selecting unit. ### Claim 3 (depends on 2) The image processing system according to claim 2, wherein the units further include a display control unit configured to display a tomographic image and the retinal layer selected by the selecting unit in a discriminating state on the tomographic image. ### Claim 4 (depends on 3) The image processing system according to claim 3, further comprising a generating unit configured to generate a curvature map by using the shape feature amount the retinal layer, and wherein the display control unit displays the curvature map. ### Claim 5 (depends on 1) The image processing system according to claim 1, wherein the image processing system further includes a plurality of imaging modes including an imaging mode for myopia analysis, and wherein the obtaining unit obtains the shape feature amount of the plurality of tomographic images in a case where the imaging mode is the imaging mode for myopia analysis when the plurality of tomographic images are captured. ### Claim 6 An image processing system comprising; a memory that stores a program; and a processor that executes the program stored in the memory so as to function as units including: an obtaining unit configured to obtain a plurality of tomographic images captured by a tomographic imaging apparatus; a detecting unit configured to detect a retinal layer of a fundus retina in each of the plurality of tomographic images; and an analysis unit configured to obtain a shape feature amount of a fundus retina by processing the plurality of tomographic images, wherein the shape feature amount of the retinal layer is a plurality of signed curvature values calculated a respective parts on the detected retinal layer in the tomographic image, and wherein each of the plurality of signed curvature values reveals that a partial shape of the retinal layer is upward or downward concave. ### Claim 7 (depends on 6) The image processing system according to claim 6, wherein the units further include: a generating unit configured to generate a curvature map based on the plurality of signed curvature values; and a display control unit configured to display the curvature map. ### Claim 8 (depends on 7) The image processing system according to claim 7, wherein the units further include: a fundus image capturing unit configured to capture a fundus image of the fundus; and an alignment unit configured to align the fundus image and the curvature map, wherein the display control unit is configured to display the curvature map superimposed on the fundus image based on a result of alignment by the alignment unit. ### Claim 9 (depends on 7) The image processing system according to claim 7, wherein the units further include a database configured to hold a plurality of feature amounts obtained from a plurality of eyes to be examined. ### Claim 10 An image processing method comprising: detecting a retinal layer of a fundus retina in each of a plurality of tomographic images captured by a tomographic imaging apparatus; obtaining a shape feature amount of the retinal layer of a fundus retina based on the detected retinal layer of the each of the plurality of tomographic images, the shape feature amount being a plurality of curvatures calculated at respective parts on the detected retinal layer in the tomographic image; and obtaining shape analysis information by comparing the shape feature amount of the retinal layer of the fundus retina with a database in which a plurality of feature amounts are stored, the plurality of feature amounts being classified based on ophthalmic axis length-dependent parameter. ### Claim 11 An image processing method comprising: obtaining a plurality of tomographic images captured by a tomographic imaging apparatus; detecting a retinal layer of a fundus retina in each of the plurality of tomographic images; and obtaining a shape feature amount of a fundus retina by processing the plurality of tomographic images, wherein the shape feature amount of the retinal layer is a plurality of signed curvature values calculated respective parts on the detected retinal layer in the tomographic image, wherein each of the plurality of signed curvature values reveals a partial shape of the retinal layer is upward or downward concave. ### Claim 12 A computer-readable storage medium storing a program which causes a computer to realize respective units of an image processing system, wherein the image processing system comprises: a detection unit configured to detect a retinal layer of a fundus retina in each of a plurality of tomographic images captured by a tomographic imaging apparatus; an obtaining unit configured to obtain a shape feature amount of the retinal layer of the fundus retina based on the detected retinal layer of the each of the plurality of tomographic images, the shape feature amount being a plurality of curvatures calculated at respective parts on the detected retinal layer in the tomographic image; and an analysis unit configured to obtain shape analysis information by comparing the shape feature amount of the retinal layer of the fundus retina with a database in which a plurality of feature amounts are stored, the plurality of feature amounts being classified based on ophthalmic axis length-dependent parameter. ### Claim 13 A computer-readable storage medium storing a program which causes a computer to realize respective units of an image processing system, wherein the image processing system comprises: an obtaining unit configured to obtain a plurality of tomographic images captured by a tomographic imaging apparatus; a detecting unit configured to detect a retinal layer of a fundus retina in each of the plurality of tomographic images; and an analysis unit configured to obtain a shape feature amount of a fundus retina by processing the plurality of tomographic images, wherein the shape feature amount of the retinal layer is a plurality of signed curvature values calculated at respective parts on the detected retinal layer in the tomographic image, and wherein each of the plurality of signed curvature values reveals that a partial shape of the retinal layer is upward or downward concave.