Projet RV Segmentation Challenge in Cardiac MRI

[Sept 2017] Planning on using deep learning with the  RVSC dataset? Check this blog post by Chuck-Hou Yee, an Insight AI Fellow!

[Aug 2017] Our RVSC challenge is featured on François Chollet’s AI Open Network!

[Feb 2017] The process to download the data has been updated to an online registration form.

[May 2015] The RVSC website has been updated (at last ;-))

[May 2015] As of today, 5 papers using RVSC data have been published! please see the Post-challenge submissions section.

[Oct 2014] The challenge results have been accepted in Medical Image Analysis! The paper is downloadable here: RSCVMedIApaper_finalversion.

Reference: C. Petitjean, M.A. Zuluaga, W. Bai, JN Dacher, D. Grosgeorge, J. Caudron, S. Ruan, I. Ben Ayed, M.Jorge Cardoso, H.-C. Cheng, D. Jimenez-Carretero, M. J. Ledesma-Carbayo, C. Davatzikos, J. Doshi, G. Erus, O.M.O. Maier, C.M.S. Nambakhsh, Y. Ou, S. Ourselin, C.-W. Peng, N.S. Peters, T.M. Peters, M. Rajchl, D. Rueckert, A. Santos, W. Shi, C.-W. Wang, H. Wang, J. Yuan, Right Ventricle Segmentation From Cardiac MRI: A Collation Study, Medical Image Analysis, vol. 19, pp 187-202, 2015

The Right Ventricle Segmentation Challenge

The goal of this contest is to compare right ventricle (RV) segmentation methods by providing a common database of cardiac cine MR images and associated expert contours, as well as an evaluation system. Challengers are invited to enter their segmentation algorithm to automatically find RV endocardium and epicardium, with little or no user intervention.

This challenge was part of a MICCAI’12 workshop. Participants were provided with a Training Set (images+ground truth) and a Test1 Set (images only). They were invited to submit a paper describing their methods and results to our MICCAI’12 challenge. On the day of the workshop (October 1st 2012, at MICCAI), participants were provided with a new Test2 Set and organizers evaluated the results and presented them during the conference. Workshop papers are available with a simple request to caroline.petitjean at

Today, MR images and contours are still available. Please see the How to download the data? section.


Caroline Petitjean
Université de Rouen
Technopole du Madrillet
Avenue de l'Université
tel: +33 232 955 215
fax: +33 232 955 022