• Aucun résultat trouvé

Preface

N/A
N/A
Protected

Academic year: 2022

Partager "Preface"

Copied!
5
0
0

Texte intégral

(1)

Sharib Ali, Felix Zhou, Christian Daul (Eds.)

Proceedings of the

EAD 2019

Workshop on Endoscopic Artefact Detection Challenge

Co-located with the 16th International Symposium on Biomedical Imaging (ISBI)

Venice, Italy, April 8, 2019

https://biomedicalimaging.org/2019/challenges/

(2)

Preface

Endoscopy is a widely used clinical procedure for the early detection of numerous cancers (e.g., nasopharyngeal, oesophageal adenocar- cinoma, gastric, colorectal and bladder cancers) therapeutic proce- dures and minimally invasive surgery (e.g., laparoscopy). A major drawback of endoscopy video frames is that they are heavily cor- rupted with multiple imaging artefacts (e.g., pixel saturations, mo- tion blur, defocus, specular reflections, bubbles, fluid and debris).

These artefacts not only present difficulty in visualizing the underly- ing tissue during diagnosis but also affect any post-analysis methods such as lesion detection and video image retrieval required for infor- mative reporting and follow-ups. Accurate detection of artefacts is therefore a core challenge in a wide-range of endoscopic applications across multiple disease areas. The precise detection of endoscopic artefacts is crucial to achieve high-quality endoscopic frame restora- tion and necessary to realize reliable computer assisted endoscopy tools for improved patient care.

Together with six international clinical data providers, we col- lated a large set of multi-organ, multi-modal and multi-population endoscopy video frames corrupted with different artefacts. Gold stan- dard ground truths were established and made publicly available to the community. This challenge comprised of three sub-challenges:

1) detection, 2) semantic segmentation and 3) detection generaliza- tion. All algorithms were evaluated online with the same evaluation metrics. We attracted nearly 29 AI algorithm developers and 529 enthusiasts to participate in the EAD2019 challenge.

This volume contains the proceedings of the first edition of the EAD challenge workshop, which was held in Venice, Italy, on April 8, 2019 co-located with the 16th International Symposium on Biomed- ical Imaging (ISBI). This editiion of the EAD workshop has been compiled from the 10 accepted papers submitted by top performing teams (12 out of 29) in an endoscopy artefact detection challenge1. Each paper was reviewed by at least 2 reviewers in the field.

Workshop and Challenge Organizers: Sharib Ali, Felix Zhou and Christian Daul

1 https://ead2019.grand-challenge.org

(3)

EAD2019 Challenge Organization

Organizing committee

Sharib Ali Institute of Biomedical Engineering, Big Data Institute, University of Oxford, Ofx- ord, UK

Felix Zhou Ludwig Cancer Institute, University of Oxford, Oxford, UK

Christian Daul University of Lorraine, CNRS, CRAN, UMR 7039, Nancy, France

Maxim Loshchenov Prokhorov General Physics Institute of the Russian Academy of Sciences, Moscow, Russia

Program committee

Jens Rittscher Department of Engineering Science, Uni- versity of Oxford, Oxford, UK

Simon Leedham Welcome Trust Centre for Human Genet- ics, Oxford, UK

Walter Blondel University of Lorraine, CNRS, CRAN, UMR 7039, Nancy, France

Enrico Grisan Department of Information Engineering, University of Padova, Padova, Italy Georges Wagnieres EPFL, Lausanne, Switzerland

Victor Loschenov Prokhorov General Physics Institute of the Russian Academy of Sciences, Moscow, Russia

Faisal Mahmood Johns Hopkins University, Baltimore, USA

(4)

Clinical collaborators

James East Translational Gastroenterology Unit, John Radcliffe Hospital, Oxford, UK Barbara Braden Translational Gastroenterology Unit,

John Radcliffe Hospital, Oxford, UK Adam Bailey Translational Gastroenterology Unit,

John Radcliffe Hospital, Oxford, UK Stefano Realdon Istituto Oncologico Veneto, IOV-IRCCS,

Padova, Italy Event manager

Denise Power Institute of Biomedical Engineering, Ox- ford, UK

Sponsors

Medical Image Analysis Network (MedIAN), UK Cancer Research UK (CR UK) Oxford, UK

(5)

Workshop Organization

Workshop (co)-chair(s)

Jens Rittscher Department of Engineering Science, Uni- versity of Oxford, Oxford, UK

Christian Daul University of Lorraine, CNRS, CRAN, UMR 7039, Nancy, France

Proceedings (co)-chair(s)

Sharib Ali IBME, BDI, Department of Engineering Science, University of Oxford, Ofxord, UK Felix Zhou Ludwig Cancer Institute, University of

Oxford, Oxford, UK Keynote Speakers

Adrien Bartoli Universit´e Clermont Auvergne, Clermont- Ferrand, France

James East Translational Gastroenterology Unit, John Radcliffe Hospital, Oxford, UK Adam Bailey Translational Gastroenterology Unit,

John Radcliffe Hospital, Oxford, UK Reviewers

Qi, Huan

Dmitrieva, Mariia Wollmann, Thomas

Gao, Yuan Xu, Zhenghua Gupta, Soumya

Daul, Christian Khanal, Bishesh

Références

Documents relatifs

Stability is achieved by suitably upwinded test functions, generalizing the classical α-quadratically upwinded and the Hemker test-functions for piecewise linear trial spaces see,

The relationship between maize con- sumption and risk of cancer of the up- per digestive tract was investigated in 107 patients with oral cancer, 107 with pharyngeal cancer, 68

La contribution sur l’Inde (Daud Ali) comporte deux parties : la première porte sur les sources en sanskrit – elle traite des purāṇa, des chroniques de grandes

31 Although none of the London schools provided as complete a range of instruction as did the University of Edinburgh or the Paris Faculty, overall there was as much scope for

L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des

Second, an adapted version of Brown’s (2004) theoretical framework is used to guide the discussion and to orient and prepare counsellors toward a social justice paradigm that

The remaining patterns did not share identical HEs and were named from 2 to 7. Patterns 2 and 3 grouped genotypes classi- fied as Pisang Awak (Fig. 4), with the exception of

We could achieve a data collapse for small forces when plotting the penetration depth depending on the applied force divided by the density.. For higher forces or penetration