Novel Application of Artificial Intelligence to Measure Colonoscopy Inspection Time
Endoscopy · 01.04.2023 · 55 (S 02 S 02) · S273
DOI: 10.1055/s-0043-1765752 ↗Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy, erschienen am 01.04.2023. Verfasst von R. Kader und 11 weiteren Autor:innen. Die Arbeit nennt 1 Literaturangaben.
Abstract (Originalsprache)
Aims
We aimed to develop convolutional neural networks (CNN) to detect cleaning and polypectomy phases during withdrawal to facilitate automated measurement of colonoscopy inspection time (CIT) [ 1 ].
Methods
Videos of withdrawal were annotated with labels of ‘cleaning’ (suctioning/washing), ‘polypectomy’ (injection/polypectomy/inspecting resection margins) and ‘inspection’. Using 98 annotated videos, two ResNet-101 CNNs were developed to detect cleaning (213936 frames) and polypectomy (56273 frames) events. The CNNs was then evaluated with 40 consecutive colonoscoppy videos from 5 expert (ADR>45%) and 40 videos from 6 non-expert (ADR
Zitieren
APA
Kader, R., Carvalho, T. D., Brandao, P., Toth, D., Hussein, M., Aslam, N., Ahmad, O., Seward, E., Vega, R., Mountney, P., Stoyanov, D., & Lovat, L. (2023). Novel Application of Artificial Intelligence to Measure Colonoscopy Inspection Time. Endoscopy, 55(S 02 S 02), S273. https://doi.org/10.1055/s-0043-1765752
Vancouver
Kader R, Carvalho TD, Brandao P, Toth D, Hussein M, Aslam N, et al. Novel Application of Artificial Intelligence to Measure Colonoscopy Inspection Time. Endoscopy. 2023;55(S 02 S 02):S273. doi:10.1055/s-0043-1765752
BibTeX
@article{Kader2023,
author = {Kader, R. and Carvalho, T. D. and Brandao, P. and Toth, D. and Hussein, M. and Aslam, N. and Ahmad, O. and Seward, E. and Vega, R. and Mountney, P. and Stoyanov, D. and Lovat, L.},
title = {Novel Application of Artificial Intelligence to Measure Colonoscopy Inspection Time},
journal = {Endoscopy},
year = {2023},
volume = {55},
number = {S 02 S 02},
pages = {S273},
doi = {10.1055/s-0043-1765752}
}
EUVIMED