CCRA: A colon cleanliness rating algorithm based on colonoscopy video analysis☆

Yu Bo, Shao Wei, Yao Dengju, Wang Yunhao, Zhang Heyi · 2023

Read CCRA: A colon cleanliness rating algorithm based on colonoscopy video analysis☆ by Yu Bo, Shao Wei, Yao Dengju, Wang Yunhao, Zhang Heyi (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10687275.txt.

Description

A colonoscopy only finds what the camera can see, so the bowel must be cleaned well beforehand, yet human ratings of that cleaning vary from doctor to doctor. Bo and co-authors built an algorithm, CCRA, that grades cleanliness from the procedure video itself. It pulls still frames from the video, uses a U-Net network to paint the stool regions in each frame, and compares the average stool area with a standard scale.

The segmentation proved accurate, with pixel accuracy of 97.02 percent and a matching overlap score of 83.67 percent. The final cleanliness grades landed between 92.45 and 99.275 percent agreement in testing. The authors conclude that the system can grade bowel preparation quickly and consistently without staff time, smoothing out the differences between human raters.

Catalog record

CREATORYu Bo, Shao Wei, Yao Dengju, Wang Yunhao, Zhang Heyi
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE33 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10687275

Browse the full library · About the Tower of Babel