CPC A61B 1/00009 (2013.01) [A61B 1/0005 (2013.01); A61B 1/31 (2013.01); G06T 7/0012 (2013.01); G16H 40/20 (2018.01); G06T 2207/30028 (2013.01); G06T 2207/30168 (2013.01)] | 15 Claims |
1. A computer-implemented method for evaluating colonoscopy performance, comprising steps of:
(S1) splitting a video acquired during a colonoscopy examination into a plurality of colonoscopy images;
(S2) assigning each of the colonoscopy images into an inadequate-view group or an adequate-view group according to a first classification criterion, and assigning each colonoscopy image in the adequate-view group into a fold-inspection group or a lumen-inspection group according to a second classification criterion,
wherein the first classification criterion comprises at least one of clarity, exposure, level of tissue wrinkling, and level of occlusion in each of the colonoscopy images; the second classification criterion comprises at least one of an amount of haustrum, an amount of colonic lumen, and a position of the colonic lumen in each of the colonoscopy images and
wherein the colonoscopy image in the adequate-view group is assigned into the fold-inspection group if the colonoscopy image meets one of the requirements of:
(R1) colonic wall is shown, but in absence of haustrum or colonic lumen;
(R2) colonic wall and haustrum are shown, but in absence of colonic lumen; and
(R3) colonic wall, haustrum and colonic lumen are shown, the amount of the haustrum shown falls within a range of 1 to 5, and the colonic lumen falls outside of a central area of the colonoscopy image; or
the colonoscopy image in the adequate-view group is assigned into the lumen-inspection group if the colonoscopy image does not meet any of the requirements of (R1)-(R3); and
(S3) determining a performance rating of the colonoscopy examination according to an elapsed time of at least one of the fold-inspection group, the lumen-inspection group, and the inadequate-view group.
|