Focal loss for artefact detection in medical endoscopy
Kayser M, Soberanis-Mukul RD, Albarqouni S, Navab N (2019)
Publication Type: Conference contribution
Publication year: 2019
Publisher: CEUR-WS
Book Volume: 2366
Conference Proceedings Title: CEUR Workshop Proceedings
Event location: Venice, ITA
Abstract
Endoscopic video frames tend to be corrupted by various artefacts impairing their visibility. Automated detection of these artefacts will foster advances in computer-assisted diagnosis, post-examination procedures and frame restoration software. In this work, we propose an ensemble of deep learning object detectors to automate multi-class artefact detection in video endoscopy. Our approach achieved a mean average precision (mAP) of 0.3087 and an average intersection-over-union (IoU) of 0.3997 on the EAD2019 test set. This resulted in a final score of 0.3451 and the 3rd rank in the EAD 2019 object detection sub-challenge leaderboard.
Involved external institutions
Germany (DE)How to cite
APA:
Kayser, M., Soberanis-Mukul, R.D., Albarqouni, S., & Navab, N. (2019). Focal loss for artefact detection in medical endoscopy. In CEUR Workshop Proceedings. Venice, ITA: CEUR-WS.
MLA:
Kayser, Maxime, et al. "Focal loss for artefact detection in medical endoscopy." Proceedings of the 2019 Challenge on Endoscopy Artefacts Detection: Multi-Class Artefact Detection in Video Endoscopy, EAD 2019, Venice, ITA CEUR-WS, 2019.
BibTeX: Download