发明名称 ENDOSCOPE SYSTEM, PROCESSOR DEVICE OF ENDOSCOPE SYSTEM, AND IMAGE PROCESSING METHOD
摘要 Broadband light BB and narrowband light NB are simultaneously irradiated to a subject. A blue signal B, a green signal G, and a red signal R are obtained by imaging the subject using a color CCD 33. A base image is generated from the signals B, G, and R of three colors. A B/G image having a B/G ratio is generated. A superficial blood vessel extraction image is obtained by extracting a pixel, in which the B/G ratio is equal to or less than a boundary value Ls between the mucous membrane and the superficial blood vessel, from the B/G image. A medium-deep blood vessel extraction image is obtained by extracting a pixel, in which the B/G ratio is equal to or greater than a boundary value Ld between the mucous membrane and the medium-deep blood vessel. The boundary values Ls and Ld differ depending on each observation mode.
申请公布号 US2014316195(A1) 申请公布日期 2014.10.23
申请号 US201414322670 申请日期 2014.07.02
申请人 FUJIFILM Corporation 发明人 KAKU Toshihiko;IIDA Takayuki
分类号 A61B1/06 主分类号 A61B1/06
代理机构 代理人
主权项 1. An endoscope system, comprising: an illumination unit for irradiating a subject with illumination light including a blue component and a green component; an image signal acquisition unit for acquiring two or more color signals having different pieces of color information by receiving and imaging return light from the subject using an imaging element; a multi-color image generation unit for generating a multi-color image formed from calculated values obtained by performing predetermined calculation for each pixel using the two or more color signals; and a blood vessel extraction image generation unit for generating at least one of a first layer blood vessel extraction image, which is obtained by extracting a first layer blood vessel at a specific depth from the multi-color image, and a second layer blood vessel extraction image, which is obtained by extracting a second layer blood vessel at a position deeper than the first layer blood vessel from the multi-color image, by performing blood vessel extraction processing, which differs depending on each of a plurality of observation modes, on the multi-color image, wherein the blood vessel extraction image generation unit includes a plurality of calculated value tables, which store a correlation between a mucous membrane, the first layer blood vessel, and the second layer blood vessel of the subject and the calculated values, and a blood vessel extraction image generation section that generates at least one of the first layer blood vessel extraction image and the second layer blood vessel extraction image by performing blood vessel extraction processing using a calculated value table corresponding to the set observation mode, the calculated value table is set for each of the plurality of observation modes, wherein in each of the calculated value tables, a calculated value indicating a boundary between the mucous membrane and the first layer blood vessel is stored as a first boundary value, and a calculated value indicating a boundary between the mucous membrane and the second layer blood vessel is stored as a second boundary value, and the first and second boundary values differ depending on each calculated value table.
地址 Tokyo JP