LV Segmentation Challenge

One major challenge for developing a 4D segmentation algorithm is the lack of available large set of ground truth that are defined for the whole cardiac frames and slices. Initiated from the 2011 LV Segmentation Challenge that was held for the 2011 STACOM Workshop, we have started up a larger collaborative project to establish the ground truth or the consensus segmentation images for myocardium. The segmentation challenge is therefore set to open for new algorithms to participate. We aim to establish consensus segmentation images from a large set of data. We used modified STAPLE method to generate the consensus images from the contributing participants (raters).  However, before the consensus images can be robustly established, we need a lot of participants, which are semi or fully automated segmentation methods. The more people join this work, the better the consensus images. Everybody can participate in this work, particularly for students and researchers in the field of fully automatic segmentation of the heart.

2011 LV Segmentation Challenge Consensus Paper

A Suinesiaputra, BR Cowan, AO Al-Agamy, MA Elattar, N Ayache, AS Fahmy, AM Khalifa, P Medrano-Gracia, M-P. Jolly, AH Kadish, DC Lee, J Margeta, SK Warfield, and AA Young. A collaborative resource to build consensus for automated left ventricular segmentation of cardiac MR images. Medical Image Analysis, 18(1):50 – 62, 2014.

Benefits

Why should you join this project?
  • directly download 200 cardiac cases, where 100 cases of them have reference contours derived from our semi-automated LV analysis software,
  • use the 100 cases with reference contours for testing and your own validation,
  • work directly on these data set without normal CAP approval process, because we have received approval from the Data Contributor to use them only for segmentation purposes,
  • publish your work using these data with citation to CAP references (see the guidelines), and
  • benchmark your results with participants of the STACOM 2011 LV Segmentation Challenge.

Requirements

  1. You must only use these data set to develop a semi or fully automated segmentation algorithm.
  2. You must send us your segmentation results on the other 100 cases, known as the validation set.

Participate

Follow these 5 simple steps to join:
  1. Read carefully the  Terms & Conditions and CAP Data Use Agreement documents.
  2. Complete and sign CONSENSUS-AUTO Rater Agreement Form.
  3. Send the agreement form to Avan.
  4. If approved, then we will send you back direct links to the whole data set.
  5. Send us your segmentation results from the validation data set.