# US 2021/0241016 A1 · Weighted image generation apparatus, method, and program, determiner learning apparatus, method, and program, region extraction apparatus, method, and program, and determiner > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241016 A1 - Document ID: US20210241016A1 - Status: Published application - Kind: A1 - Application number: 17/237,076 - Filed: 2021-04-22 - Published: 2021-08-05 - Earliest claimed: 2018-10-25 - Assignees: FUJIFILM Corporation - Applicants: FUJIFILM Corporation - Inventors: Takayuki HASHIMOTO - Web page: https://patentgrep.com/patent/US20210241016A1 ## CPC - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - A61B 6/03: Computed tomography [CT] - G01T 1/161: Applications in the field of nuclear medicine, e.g. in vivo counting {(apparatus for radiation diagnosis A61B6/00)} - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06T 7/00: Image analysis - G06T 7/136: involving thresholding - G06V 2201/03: Recognition of patterns in medical or anatomical images - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G01T: MEASUREMENT OF NUCLEAR OR X-RADIATION (radiation analysis of materials, mass spectrometry G01N23/00; tubes for determining the presence, intensity, density or energy of radiation or particles H01J47/00) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A display control unit displays a medical image from which at least one region of interest is extracted on a display unit. A correction unit corrects a boundary of the region of interest according to a correction instruction for the boundary of the region of interest extracted from the displayed medical image. An image generation unit generates a weighted image in which each pixel in the medical image has, as a pixel value of each pixel, a weight coefficient representing a weight of being within the region of interest, by setting an initial weight coefficient for the extracted region of interest and setting a corrected weight coefficient for a corrected region for which the correction instruction is given in the medical image. ## Claims ### Claim 1 A weighted image generation apparatus comprising at least one processor, wherein the processor is configured to: display a medical image from which at least one region of interest is extracted on a display; correct a boundary of the region of interest according to a correction instruction for the extracted region of interest; and generate a weighted image in which each pixel in the medical image has, as a pixel value of each pixel, a weight coefficient representing a certainty of being within the region of interest, by setting an initial weight coefficient for the extracted region of interest and setting a corrected weight coefficient for a corrected region based on the correction instruction in the medical image. ### Claim 2 (depends on 1) The weighted image generation apparatus according to claim 1, wherein the processor is configured to set at least one of corrected weight coefficients having different values according to content of the correction instruction. ### Claim 3 (depends on 2) The weighted image generation apparatus according to claim 2, wherein the processor is configured to set a corrected weight coefficient having a positive value for the corrected region in a case where the correction instruction is a region addition instruction, and set a corrected weight coefficient having a negative value for the corrected region in a case where the correction instruction is a region deletion instruction. ### Claim 4 (depends on 1) The weighted image generation apparatus according to claim 1, wherein, in a case where a plurality of regions of interest are extracted from the medical image, the processor is configured to correct a boundary of each of the plurality of regions of interest according to the correction instruction for each of the plurality of regions of interest, and set the weight coefficients for each of the plurality of regions of interest. ### Claim 5 (depends on 4) The weighted image generation apparatus according to claim 4, wherein, in a case where the plurality of regions of interest are adjacent to each other, the processor is configured to set boundaries of the plurality of regions of interest in the weighted image according to the weight coefficients which are set for each of the plurality of regions of interest. ### Claim 6 (depends on 4) The weighted image generation apparatus according to claim 4, wherein the processor is configured to set, according to the correction instruction for one region of interest among the plurality of regions of interest, the corrected weight coefficients for other regions of interest other than the one region of interest. ### Claim 7 (depends on 4) The weighted image generation apparatus according to claim 4, wherein the processor is configured to set boundaries of the plurality of regions of interest according to a threshold value which is set for the weight coefficient of at least one region of interest among the plurality of regions of interest. ### Claim 8 (depends on 1) The weighted image generation apparatus according to claim 1, wherein the processor is configured to set at least one of corrected weight coefficients having different values according to a type of the region of interest. ### Claim 9 (depends on 1) The weighted image generation apparatus according to claim 1, wherein, in a case where the medical image is a three-dimensional image, the processor is configured to set, in the medical image displayed on the display, the corrected weight coefficient for a visually recognizable pixel to be larger than the corrected weight coefficient for a visually unrecognizable pixel. ### Claim 10 (depends on 1) The weighted image generation apparatus according to claim 1, wherein the processor is configured to: set a threshold value for the weight coefficient; and extract, from the medical image, a corresponding region corresponding to a region for which the weight coefficient is equal to or larger than the threshold value in the weighted image. ### Claim 11 (depends on 10) A determiner learning apparatus comprising at least one processor, wherein the processor is configured to: acquire, as learning data, the weighted image generated by the weighted image generation apparatus according to claim 10 and an image of the corresponding region extracted from the medical image; and learn a determiner, which outputs a determination result of a region of interest included in the medical image in a case where the medical image is input, using a plurality of pieces of the learning data. ### Claim 12 (depends on 11) A determiner learned by the determiner learning apparatus according to claim 11. ### Claim 13 (depends on 12) A region extraction apparatus comprising at least one processor, wherein the processor is configured to: acquire a medical image including a region of interest as a determination target; and determine the region of interest in the medical image by the determiner according to claim 12. ### Claim 14 (depends on 13) The region extraction apparatus according to claim 13, wherein the processor is configured to display a determination result of the region of interest by the determiner. ### Claim 15 A weighted image generation method comprising: displaying a medical image from which at least one region of interest is extracted on a display; correcting a boundary of the region of interest according to a correction instruction for the extracted region of interest; and generating a weighted image in which each pixel in the medical image has, as a pixel value of each pixel, a weight coefficient representing a certainty of being within the region of interest, by setting an initial weight coefficient for the extracted region of interest and setting a corrected weight coefficient for a corrected region based on the correction instruction in the medical image. ### Claim 16 (depends on 15) A determiner learning method comprising: acquiring, as learning data, the weighted image generated by the weighted image generation method according to claim 15 and an image of a corresponding region extracted from the medical image and corresponding to a region for which the weight coefficient is equal to or larger than a threshold value in the weighted image; and learning a determiner, which outputs a determination result of a region of interest included in the medical image in a case where the medical image is input, using a plurality of pieces of the learning data. ### Claim 17 (depends on 12) A region extraction method comprising: acquiring a medical image including a region of interest as a determination target; and determining the region of interest in the medical image by the determiner according to claim 12. ### Claim 18 A non-transitory computer-readable storage medium that stores a weighted image generation program causing a computer to execute: displaying a medical image from which at least one region of interest is extracted on a display; correcting a boundary of the region of interest according to a correction instruction for the extracted region of interest; and generating a weighted image in which each pixel in the medical image has, as a pixel value of each pixel, a weight coefficient representing a certainty of being within the region of interest, by setting an initial weight coefficient for the extracted region of interest and setting a corrected weight coefficient for a corrected region based on the correction instruction in the medical image. ### Claim 19 (depends on 15) A non-transitory computer-readable storage medium that stores a determiner learning program causing a computer to execute: acquiring, as learning data, the weighted image generated by the weighted image generation method according to claim 15 and an image of a corresponding region extracted from the medical image and corresponding to a region for which the weight coefficient is equal to or larger than a threshold value in the weighted image; and learning a determiner, which outputs a determination result of a region of interest included in the medical image in a case where the medical image is input, using a plurality of pieces of the learning data. ### Claim 20 (depends on 12) A non-transitory computer-readable storage medium that stores a region extraction program causing a computer to execute: acquiring a medical image including a region of interest as a determination target; and determining the region of interest in the medical image via the determiner according to claim 12.