Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy

Ali, Sharib
Dmitrieva, Mariia
Ghatwary, Noha
Bano, Sophia
Polat, Gorkem
Temizel, Alptekin
Krenzer, Adrian
Hekalo, Amar
Guo, Yun Bo
Matuszewski, Bogdan
Gridach, Mourad
Voiculescu, Irina
Yoganand, Vishnusai
Chavan, Arnav
Raj, Aryan
Nguyen, Nhan T.
Tran, Dat Q.
Huynh, Le Duy
Boutry, Nicolas
Rezvy, Shahadate
Chen, Haijian
Choi, Yoon Ho
Subramanian, Anand
Balasubramanian, Velmurugan
Gao, Xiaohong W.
Hu, Hongyu
Liao, Yusheng
Stoyanov, Danail
Daul, Christian
Realdon, Stefano
Cannizzaro, Renato
Lamarque, Dominique
Tran-Nguyen, Terry
Bailey, Adam
Braden, Barbara
East, James E.
Rittscher, Jens
© 2021 The AuthorsThe Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.
Citation Formats
S. Ali et al., “Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy,” pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: