Open challenge: automatic 3D segmentation of neurites in EM

SNEMI3D started!

3D reconstruction of neurites in mouse cortex from EM images Group of pyramidal neurons of mouse cortex reconstructed from EM sections (D. Berger).

We have just lunched SNEMI3D, the first public challenge on 3D segmentation of neurites in EM images!

The challenge is organized in the context of the IEEE International Symposium on Biomedical Imaging (San Francsico, CA, April 7-11th 2013). If you wish to participate, please register now to be able to download the training and test data sets and upload your own results.

Background and set-up

A full stack of serial section scanning electron microscopy (ssSEM) slices will be used to train machine-learning algorithms for the purpose of automatic segmentation of neurites in 3D. This imaging technique visualizes the resulting volumes in a highly anisotropic way, i.e., the x- and y-directions have a high resolution, whereas the z-direction has a low resolution, primarily dependent on the precision of serial cutting. EM produces the images as a projection of the whole section, so some of the neural membranes that are not orthogonal to a cutting plane can appear very blurred. None of these problems led to major difficulties in the manual labeling of each neurite in the image stack by an expert human neuro-anatomist.

In order to gauge the current state-of-the-art in automated neurite segmentation on EM and compare between different methods, we are organizing the SNEMI3D challenge in conjunction with the ISBI 2013 conference. For this purpose, we are making available a large training dataset of mouse cortex in which the neurites have been manually delineated. In addition, we also provide a test dataset where the 3D labels are not available. The aim of the challenge is to compare and rank the different competing methods based on their object classification accuracy in three dimensions.

Challenge format

The challenge is open to everybody. Teams wishing to participate should register and download the training data for algorithmic tweaking and tuning. The teams should then evaluate their segmentation performance on two test sets: one already released with the training set and a second set that will be released five days before the final deadline. Finally, the participants are expected to submit an abstract describing the method that they used together with the final results by the established deadline (see important dates below). On the day of the challenge workshop itself, the best methods will be explained in an oral presentation. The day will conclude with a round-table discussion of the obtained results.
In the weeks following the challenge participating teams will be invited to contribute to a joint paper describing and summarizing the challenge outcome, which we will then submit to a high-impact journal in the field.

Important dates

  • January 15th, 2013: training and (first) test data sets released.
  • March 10th, 2013: second and final test set released.
  • March 15th, 2013: deadline for submitting final test results and method abstract.
  • March 17th, 2013: final ranking based on second test set and notification of acceptance/presentation type.
  • April 7th, 2013: method presentations at the challenge workshop (ISBI 2013 conference).
For more information, please visit the challenge official site:  http://brainiac2.mit.edu/SNEMI3D/home

Leave a Reply

Your email address will not be published.