EAD2019: Multi-class artefact detection in video endoscopy



๐Ÿ“จ Join our google groups for updates and share your problems or help others (click here
๐Ÿ“ŒTest data has been released for all 3 tasks.
๐Ÿ“ŒRecent release (see download page) of 1300+ more training data for artefact detection challenge (task-1) 

"Accepting leaderboard submission ๐Ÿ‘ To prepare your data, please see leaderboardSubmissionWiki"

"!!!  We have extended the leaderboard closing deadline to 24th March 2019 27th March 2019 !!!" Please note that the top scorers will be awarded with cash prizes at EAD2019 workshop in Venice, Italy. Attendance is mandatory to receive your awards! See here: https://ead2019.grand-challenge.org/Rules/

Final deadline for 2-3 page abstract submission is on 31st March 2019. However, you will receive an email based on your scores for participation by 25th March 2019.


๐Ÿ‡ฎ๐Ÿ‡นTravel Grants Available:

Last date to apply: 15th March 2019. 
Winners will be announced on 16th March 2019

Travel Grant Winners of EAD2019:
1. Maxime Kayser, TUM, Germany
2. Refika Sultan Dogan, Abdullah Gul University, Turkey
3. Shanka Subhra Mondal, IIT, Kharagpur, India

โ–บ !!!!Big news!!!! MedIAN will be sponsoring 3 grants for travel and challenge registration (includes up to ยฃ250 for travel and fully covered challenge registration)
โ–บ  TO APPLY PLEASE FILL THIS FORM (EAD2019-grantApplication)

๐Ÿ“ŒChallenge workshop news:

โ–บ IEEE International Symposium on Biomedical Imaging (ISBI'19) Challenge workshop confirmed: 8th April, 2019 (morning session), in Venice, Italy
(please note that you can also only book for challenge, see IEEE ISBI registration page)
โ–บ Confirmed keynote speakers:  Adrien Bartoli and James East 
โ–บ Know opinion regarding importance of this challenge from our clinical expert: Adam Bailey
โ–บ Please find the preliminary schedule of this challenge workshop here: challenge-workshop-preliminarySchedule

๐Ÿ“… Important dates:
    Test data release: 2nd March 2019 (Released!!! ๐Ÿ‘)
    Leaderboard setup and submission start: 5th March 2019
    Leaderboard submission closing: 20th March 2019  24th March 2019 27th March 2019
    2-4 pages (abstract submission*): 31st March 2019

*Abstract submission will only be asked for top 10 performing teams. Please note that this will not be included in ISBI proceedings. However, this is needed if you want to present your work at our workshop and be considered in a joint journal publication planned.

๐Ÿ–‡Tools:
    Please visit our GitHub repository for tools that you might find useful.




Summary:

Endoscopic Artefact Detection (EAD) is a core challenge in facilitating diagnosis and treatment of diseases in hollow organs. Precise detection of specific artefacts like pixel saturations, motion blur, specular reflections, bubbles and debris is essential for high-quality frame restoration and is crucial for realising reliable computer-assisted tools for improved patient care. The challenge is sub-divided into three tasks: 
  1. Multi-class artefact detection: Localization of bounding boxes and class labels for 6 7  artefact classes for given frames. 
  2.  Region segmentation: Precise boundary delineation of detected artefacts. 
  3.  Detection generalization: Detection performance independent of specific data type and source.

 

The Challenge (in detail)

Endoscopy is a widely used clinical procedure for the early detection of numerous cancers (e.g., nasopharyngeal, oesophageal adenocarcinoma, gastric, colorectal cancers, bladder cancer etc.), therapeutic procedures and minimally invasive surgery (e.g., laparoscopy). During this procedure an endoscope is used; a long, thin, rigid or flexible tube having a light source and a camera at the tip which allows to visualize inside of affected organs on a screen. A major drawback of these video frames is that they are heavily corrupted with multiple artefacts (e.g., pixel saturations, motion blur, defocus, specular reflections, bubbles, fluid, debris etc.). These artefacts not only present difficulty in visualizing the underlying tissue during diagnosis but also affect any post-analysis methods required for follow-ups (e.g., video mosaicking done for follow-ups and archival purposes, and video-frame retrieval needed for reporting). 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 frame restoration and crucial for realising reliable computer assisted endoscopy tools for improved patient care.  

This challenge proposal aims to address the following key problems inherent in all video endoscopy: 

1) Multi-class artefact detection:  

Existing endoscopy workflows detect only one artefact class which is insufficient to obtain high-quality frame restoration. In general, the same video frame can be corrupted with multiple artefacts, e.g. motion blur, specular reflections, and low contrast can be present in the same frame. Further, not all artefact types contaminate the frame equally. So, unless multiple artefacts present in the frame are known with their precise spatial location, clinically relevant frame restoration quality cannot be guaranteed. Another advantage of such detection is that frame quality assessments can be guided to minimise the number of frames that gets discarded during automated video analysis. 

2) Multi-class artefact region segmentation: 

Frame artefacts typically have irregular shapes that are non-rectangular and consequently are overestimated by the detected bounding boxes. Development of accurate semantic segmentation methods to precisely delineate the boundaries of each detected frame artefact will enable optimized restoration of video frames without sacrificing information.  

3) Multi-class artefact generalisation: 

It is important for algorithms to avoid biases induced by specific training data sets. Also, it is well known that expert annotation generation is time consuming and can be infeasible for many data institutions. In this challenge, we encourage the participants to develop machine learning algorithms that can be used across different endoscopic datasets worldwide based on our large combined dataset from 6 different institutions. 

This challenge is of immediate interest to the endoscopic community comprising: 

Image analysts โ€“ precise artefact detection for video restoration can assist in downstream analysis such as mosaicking, image retrieval, automated diagnosis. 

Clinical endoscopists โ€“ artefact detection algorithm can help to train endoscopists to develop better imaging protocols. 

Manufacturers/Industry - even though hardware specifications of endoscopes have improved allowing hi-definition acquisition, frame artefacts are inevitably still present. Precise identification of artefacts can lead to affective frame corrections. Thus, this challenge offers new opportunities for industries to correct for the frame quality issues in endoscopic video acquisition present widely due to motion (blur), view-point changes (pixel saturations or low contrast or specular reflection), and floating objects (debris, occlusion).  

In addition, this challenge aims to target larger audience that includes people working on data obtained from different optical-based instruments (not limited to endoscopy) where different types of artefacts and noise are a serious issue. Also, detection methods have been widely used to solve various computer vision problems, so this challenge will offer a new insight towards video quality improvements. 


Sponsors



Statistics


Number of users: 456