Journal article
Mohammad Azam Khan, J. Choo
2019
2019
Semantic Scholar
Cite
Cite
APA
Click to copy
Khan, M. A., & Choo, J. (2019). Multi-class artefact detection in video endoscopy via convolution neural networks.
Chicago/Turabian
Click to copy
Khan, Mohammad Azam, and J. Choo. “Multi-Class Artefact Detection in Video Endoscopy via Convolution Neural Networks” (2019).
MLA
Click to copy
Khan, Mohammad Azam, and J. Choo. Multi-Class Artefact Detection in Video Endoscopy via Convolution Neural Networks. 2019.
BibTeX Click to copy
@article{mohammad2019a,
title = {Multi-class artefact detection in video endoscopy via convolution neural networks},
year = {2019},
author = {Khan, Mohammad Azam and Choo, J.}
}
Abstract
This paper describes our approach for EAD2019: Multi-class artefact detection in video endoscopy. We optimized focal loss for dense object detection based RetinaNet network pretrained with the ImageNet dataset and applied several data augmentation and hyperparmeter tuning strategies, obtaining a weighted final score of 0.2880 for multi-class artefact detection task and mean average precision (mAP) score of 0.2187 with deviation 0.0770 for multi-class artefact generalisation task. In addition, we developed a U-Net based convolutional neural networks (CNNs) for multi-class artefact region segmentation task and achieved a final score of 0.4320 for the online test set in the competition.
