Endoscopy Disease Detection and Segmentation (EDD2020)

Warning message

You must login to view this form.

Endoscopy Disease Detection and Segmentation (EDD2020)

Citation Author(s):
Sharib
Ali
University of Oxford, Big Data Institute, Department of Engineering Science
Barbara
Braden
University of Oxford, Translational Gastroenterology Unit, Nuffield Department of Medicine, Experimental Medicine Div., John Radcliffe
Dominique
Lamarque
Université de Versailles St-Quentin en Yvelines, Hôpital Ambroise Paré
Stefano
Realdon
Instituto Onclologico Veneto, IOV-IRCCS, Padova, Italy
Adam
Bailey
University of Oxford, Translational Gastroenterology Unit, Nuffield Department of Medicine, Experimental Medicine Div., John Radcliffe
Renato
Cannizzaro
CRO Centro Riferimento Oncologico IRCCS Aviano Italy
Noha
Ghatwary
University of Lincoln, UK
Jens
Rittscher
University of Oxford, Big Data Institute, Department of Engineering Science
Christian
Daul
CRAN UMR 7039, University of Lorraine, CNRS, Nancy, France
James
East
University of Oxford, Translational Gastroenterology Unit, Nuffield Department of Medicine, Experimental Medicine Div., John Radcliffe
Submitted by:
sharib ali
Last updated:
Tue, 02/11/2020 - 00:40
DOI:
10.21227/f8xg-wb80
Data Format:
Links:
Competition Views:
859
Share / Embed Cite

Login to Submit an Analysis

03/06/2020
Abstract: 

Endoscopy is a widely used clinical procedure for the early detection of cancers in hollow-organs such as oesophagus, stomach, and colon. Computer-assisted methods for accurate and temporally consistent localisation and segmentation of diseased region-of-interests enable precise quantification and mapping of lesions from clinical endoscopy videos which is critical for monitoring and surgical planning. Innovations have the potential to improve current medical practices and refine healthcare systems worldwide. However, well-annotated, representative publically-available datasets for disease detection for assessing reproducibility and facilitating standardised comparison of methods is still lacking. Many methods to detect diseased regions in endoscopy have been proposed however these have primarily focussed on the task of polyp detection in the gastrointestinal tract with demonstration on datasets acquired from at most a few data centres and single modality imaging, most commonly white light. Here, we present our multi-class disease detection and segmentation challenge in clinical endoscopy. With this sub-challenge we aim to establish a comprehensive dataset to benchmark algorithms for disease detection.

Specifically we aim to assess: Precise spatio-temporal localisation of disease regions using bounding boxes and exact pixel-level segmentation. Clinical applicability by assessing the online sequential for real-time monitoring and offline performance of algorithms for improved accuracy and better quantitative reporting. Participants will be provided with a set of annotated dataset labelled by medical experts and experienced doctoral/post-doctoral researchers with frames from 5 different international centres and multi organs targeting multiple populations and varied endoscopy video modalities associated with pre-malignant and diseased regions as follows:

Organ 1: Colon-rectal, associated disease: polyp, cancer
Organ 2: Oesophagus, associated disease: Barrett’s, dysplasia and cancer
Organ 3: Stomach and duodenum, associated disease: pyloric inflammation, dysplasia, cancer

Instructions: 

ABOUT DATA

[1] Annotated data consists of 5 different disease classes

``BE, suspicious, HGD, cancer, polyp`` (see *class_list.txt* in the folder)

[2] Each image file is annotated for single or multiple disease classes

[3] Same disease class is merged in masks while kept as separate bounding boxes for detection task

[4] Bounding boxes are presented in VOC format. Please see fileFormatConverters of EAD2019 (https://github.com/sharibox/EAD2019/tree/master/fileFormatConverters)

[5] Getting started: we encourage to use EAD2019 github software tool for getting started (https://github.com/sharibox/EAD2019

[6] Please note that you will have to replace 'class_list.txt' with the new one. Additionally, please add this information in the code where required *(we will update this soon!)*

 

Participation

  • Event webpage where you will need to submit your results for online evaluation (https://edd2020.grand-challenge.org/Home/)
  • Only registered users at the EDD challenge webpage are allowed to download data and participate in this challenge
  • All evaluation results will be made publicly available on the leaderboard
  • Only maximum of 2 submissions per day will be allowed 
  • Participation in all three tasks is not mandatory. However, to be eligible for awards you will need to accomplish all three tasks
  • Participants willing to only submit their result for detection or semantic segmentation, however might be invited for presentation at the challenge-workshop depending upon their performance and scientific contribution
  • All participants are required to submit a short description of their method 
  • Top performing individual or team will be contacted for 4 page paper detailing their methods based on which they will be invited to present their work and an online CEUR proceeding will be compiled 
  • Self-publication or any other sort of publication of results or data is not allowed and strictly forbidden (also see EDD_readme.md)
  • Challenge organisers will have the right to disqualify any individual or team submission in case of the breach of rules

 

AWARDS

We have planned to award a total of 4 prizes:  
  • one each for each of the 3 sub-tasks, and
  • one more for the team which ranks overall best across all 3 sub-tasks

 

We encourage everyone to submit results to all 3 sub-challenges. Please note that the top scorers will be awarded with prizes at the EDD2020 workshop at Iowa, USA on 3rd April 2020 (see here: http://2020.biomedicalimaging.org/challenges). Attendance is mandatory to receive your awards

Comments

Compitition data

where can we download the data?

I submitted the data application, more than ten days later, why haven't I received an email? and where can I download the data? Plese 

I submitted the data application, more than ten days later, why haven't I received an email? and where can I download the data? Plese 

I submitted the data application, more than ten days later, why haven't I received an email? and where can I download the data? Plese 

I submitted the data application, more than ten days later, why haven't I received an email? and where can I download the data? Plese 

Dear all,

 

Our apologies. We have now released this data without requiring anyone to login and request. However, we suggest you to download it from our challenge website https://edd2020.grand-challenge.org, where we have provided a python script to download this. 

 

Many thanks,

 

Best wishes,

Sharib 

Dataset Files


Copy All URIs to the Clipboard
View AWS Security Credentials
Your browser does not support copy-to-clipboard. Please press Ctrl+C (win) or Cmd+C (mac).

Documentation

AttachmentSize
Binary Data Data usage rules apply3.26 KB
Plain text icon classList33 bytes

Embed this dataset on another website

Copy and paste the HTML code below to embed your dataset:

Share via email or social media

Click the buttons below:

facebooktwittermailshare
[1] , "Endoscopy Disease Detection and Segmentation (EDD2020)", IEEE Dataport, 2020. [Online]. Available: http://dx.doi.org/10.21227/f8xg-wb80. Accessed: Feb. 28, 2020.
@data{f8xg-wb80-20,
doi = {10.21227/f8xg-wb80},
url = {http://dx.doi.org/10.21227/f8xg-wb80},
author = { },
publisher = {IEEE Dataport},
title = {Endoscopy Disease Detection and Segmentation (EDD2020)},
year = {2020} }
TY - DATA
T1 - Endoscopy Disease Detection and Segmentation (EDD2020)
AU -
PY - 2020
PB - IEEE Dataport
UR - 10.21227/f8xg-wb80
ER -
. (2020). Endoscopy Disease Detection and Segmentation (EDD2020). IEEE Dataport. http://dx.doi.org/10.21227/f8xg-wb80
, 2020. Endoscopy Disease Detection and Segmentation (EDD2020). Available at: http://dx.doi.org/10.21227/f8xg-wb80.
. (2020). "Endoscopy Disease Detection and Segmentation (EDD2020)." Web.
1. . Endoscopy Disease Detection and Segmentation (EDD2020) [Internet]. IEEE Dataport; 2020. Available from : http://dx.doi.org/10.21227/f8xg-wb80
. "Endoscopy Disease Detection and Segmentation (EDD2020)." doi: 10.21227/f8xg-wb80