Colonoscopic Polyp Detection with Deep Learning Assist

Alexandre Neto, Alexandre Neto, Diogo Couto, Miguel Coimbra, Miguel Coimbra, António Cunha, António Cunha

2023

Abstract

Colorectal cancer is the third most common cancer and the second cause of cancer-related deaths in the world. Colonoscopic surveillance is extremely important to find cancer precursors such as adenomas or serrated polyps. Identifying small or flat polyps can be challenging during colonoscopy and highly dependent on the colonoscopist’s skills. Deep learning algorithms can enable improvement of polyp detection rate and consequently assist to reduce physician subjectiveness and operation errors. This study aims to compare YOLO object detection architecture with self-attention models. In this study, the Kvasir-SEG polyp dataset, composed of 1000 colonoscopy annotated still images, were used to train (700 images) and validate (300images) the performance of polyp detection algorithms. Well-defined architectures such as YOLOv4 and different YOLOv5 models were compared with more recent algorithms that rely on self-attention mechanisms, namely the DETR model, to understand which technique can be more helpful and reliable in clinical practice. In the end, the YOLOv5 proved to be the model achieving better results for polyp detection with 0.81 mAP, however, the DETR had 0.80 mAP proving to have the potential of reaching similar performances when compared to more well-established architectures.

Paper Citation

in Harvard Style

Neto A., Couto D., Coimbra M. and Cunha A. (2023). Colonoscopic Polyp Detection with Deep Learning Assist. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 928-935. DOI: 10.5220/0011792300003417

in Bibtex Style

@conference{visapp23,
author={Alexandre Neto and Diogo Couto and Miguel Coimbra and António Cunha},
title={Colonoscopic Polyp Detection with Deep Learning Assist},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={928-935},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011792300003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Colonoscopic Polyp Detection with Deep Learning Assist
SN - 978-989-758-634-7
AU - Neto A.
AU - Couto D.
AU - Coimbra M.
AU - Cunha A.
PY - 2023
SP - 928
EP - 935
DO - 10.5220/0011792300003417
PB - SciTePress