Endoscopic computer vision challenges 2.0

4th International Endoscopy Computer Vision Challenge and Workshop  

In conjunction with IEEE International Symposium on Biomedical Imaging (ISBI2022)

New 📌
  • Test set inference and leaderboard instructions to be sent-out to teams soon!  Please make sure that you have submitted the method summary report by 15th Febraury 2022
  • Challenge round details are now available here 
  • Leaderboard submission for PolypGen2.0 is open!!! Good luck teams!!! Happy participation.
  • CMT open for submission to all participantshttps://cmt3.research.microsoft.com/EndoCV2022 (Deadline: 7th March, 2022  10th March 2022)
  • All participants can submit 4 page IEEE ISBI format papers for peer-review process.
  • All papers will be published in an online CEUR proceeding
Introduction to EndoCV 2.0:

Accurate detection of artefacts is a core challenge in a wide-range of endoscopic applications addressing multiple different disease areas. The importance of precise detection of these artefacts is essential for high-quality endoscopic video acquisition crucial for realising reliable computer assisted endoscopy tools for improved patient care. In particular, colonoscopy requires colon preparation and cleaning to obtain improved adenoma detection rate. Computer aided systems can help to guide both expert and trainee endoscopists to obtain consistent high quality surveillance and detect, localize and segment widely known cancer precursor lesion, “polyps”. While deep learning has been successfully applied in the medical imaging, generalization is still an open problem. Generalizability issue of deep learning models need to be clearly defined and tackled to build more reliable technology for clinical translation. Inspired by the enthusiasm of participants on our previous challenges, this year we put forward a 2.0 version of two sub-challenges (Endoscopy artefact detection) EAD 2.0 and (Polyp generalization) PolypGen 2.0. Both the sub-challenges consists of multi-center and diverse population datasets with tasks for both detection and segmentation but focus on assessing generalizability of algorithms. In this challenge, we aim to add more sequence/video data and multimodality data from different centers. The participants will be evaluated on both standard and generalization metrics presented in our previous challenges. However, unlike previous challenges in 2.0 we will benchmark methods on larger test-set comprising of mostly video sequences as in the real-world clinical scenario.

About methods:

  • Novel Deep Learning (DL) methods with real-time performance
  • Methods that uses sequence learning, e.g., RNN and transformers but with close to real-time performance

Challenge accepted: 

EndoCV2022 is aimed at promoting "novel DL method development in endoscopy" and reduce the attempts to participate to win concept with repetitively same method at various venues. We have come with three round approach:

  • Round 1: Teams using widely used benchmarking methods directly (e.g., UNet, DeepLab, Mask R-CNN, YOLO, RetinaNet, ensemble techniques ... ) will be eliminated*
  • Round 2: Teams with high-latency (computation cost) will be eliminated*
  • Round 3: Winner of EndoCV2022 --> score on unseen videos (80%) + novel methodology (20%)

*All participants can submit their paper for review @EndoCV2022 proceeding but eliminated teams will not qualify for joint-journal

Organisers:

Sharib AliDepartment of Engineering Science, Big Data Institute, University of Oxford, UK (Lead)

Noha GhatwaryComputer Engineering Department, Arab Academy for Science and Technology, Alexandria, Egypt (co-lead)

Assisting:

Mohamed Ramzy Ibrahim Mahmoud, Computer Engineering Department, Arab Academy for Science and Technology, Alexandria, Egypt

Clinical colleagues (supporting reviews):

Thomas de LangeMedical Department, Sahlgrenska University Hospital-Mölndal, Sweden

Stefano Realdon, Istituto Oncologico Veneto, IOV-IRCCS, Padova, Italy

Renato Cannizzaro,  Centro di Riferimento Oncologico di Aviano (CRO) IRCCS, Italy

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



Contact: @EndoCV

Follow us on twitter: cv_endo

Past workshop proceedings:

EAD2019:  http://ceur-ws.org/Vol-2366/
EndoCV2020: http://ceur-ws.org/Vol-2595/

EndoCV2021: http://ceur-ws.org/Vol-2886/


Number of participants: 369