Automated Detection of Anatomical Landmarks During Colonoscopy Using a Deep Learning Model
Journal of the Canadian Association of Gastroenterology · 02.08.2023 · 6 (4) · 145-151
DOI: 10.1093/jcag/gwad017 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Canadian Association of Gastroenterology, online erschienen am 02.05.2023. Verfasst von Mahsa Taghiakbari und 13 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Medicine, Department of Biomedical Sciences, University of Montreal, Montreal, Quebec, Canada. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MEDTEQ.
Abstract (Originalsprache)
Background and aims Identification and photo-documentation of the ileocecal valve (ICV) and appendiceal orifice (AO) confirm completeness of colonoscopy examinations. We aimed to develop and test a deep convolutional neural network (DCNN) model that can automatically identify ICV and AO, and differentiate these landmarks from normal mucosa and colorectal polyps.
Methods
We prospectively collected annotated full-length colonoscopy videos of 318 patients undergoing outpatient colonoscopies. We created three nonoverlapping training, validation, and test data sets with 25,444 unaltered frames extracted from the colonoscopy videos showing four landmarks/image classes (AO, ICV, normal mucosa, and polyps). A DCNN classification model was developed, validated, and tested in separate data sets of images containing the four different landmarks.
Results
After training and validation, the DCNN model could identify both AO and ICV in 18 out of 21 patients (85.7%). The accuracy of the model for differentiating AO from normal mucosa, and ICV from normal mucosa were 86.4% (95% CI 84.1% to 88.5%), and 86.4% (95% CI 84.1% to 88.6%), respectively. Furthermore, the accuracy of the model for differentiating polyps from normal mucosa was 88.6% (95% CI 86.6% to 90.3%).
Conclusion
This model offers a novel tool to assist endoscopists with automated identification of AO and ICV during colonoscopy. The model can reliably distinguish these anatomical landmarks from normal mucosa and colorectal polyps. It can be implemented into automated colonoscopy report generation, photo-documentation, and quality auditing solutions to improve colonoscopy reporting quality.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Medicine, Department of Biomedical Sciences, University of Montreal, Montreal, Quebec, Canada.
- Department of Medicine, Division of Gastroenterology, University of Montreal Hospital Research Center (CRCHUM), Montreal, Quebec, Canada.
- Department of Artificial Intelligence, Imagia Canexia Health Inc., Montreal, Canada.
- Division of Gastroenterology, McGill University Health Center, McGill University, Montreal, Quebec, Canada.
- Division of Gastroenterology, University of Montreal Hospital Center (CHUM), Montreal, Quebec, Canada.
Förderung
- MEDTEQ
Zitieren
APA
Taghiakbari, M., Hamidi Ghalehjegh, S., Jehanno, E., Berthier, T., di Jorio, L., Ghadakzadeh, S., Barkun, A., Takla, M., Bouin, M., Deslandres, E., Bouchard, S., Sidani, S., Bengio, Y., & von Renteln Md, D. (2023). Automated Detection of Anatomical Landmarks During Colonoscopy Using a Deep Learning Model. Journal of the Canadian Association of Gastroenterology, 6(4), 145-151. https://doi.org/10.1093/jcag/gwad017
Vancouver
Taghiakbari M, Hamidi Ghalehjegh S, Jehanno E, Berthier T, di Jorio L, Ghadakzadeh S, et al. Automated Detection of Anatomical Landmarks During Colonoscopy Using a Deep Learning Model. Journal of the Canadian Association of Gastroenterology. 2023;6(4):145-151. doi:10.1093/jcag/gwad017
BibTeX
@article{Taghiakbari2023,
author = {Taghiakbari, Mahsa and Hamidi Ghalehjegh, Sina and Jehanno, Emmanuel and Berthier, Tess and di Jorio, Lisa and Ghadakzadeh, Saber and Barkun, Alan and Takla, Mark and Bouin, Mickael and Deslandres, Eric and Bouchard, Simon and Sidani, Sacha and Bengio, Yoshua and von Renteln Md, Daniel},
title = {Automated Detection of Anatomical Landmarks During Colonoscopy Using a Deep Learning Model},
journal = {Journal of the Canadian Association of Gastroenterology},
year = {2023},
volume = {6},
number = {4},
pages = {145--151},
doi = {10.1093/jcag/gwad017}
}
EUVIMED