Crowdsourcing the creation of image segmentation algorithms for connectomics

Abstract

To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic(EM) images of the brain. Participants submitted boundary map spredicted for a test set of images, and were scored based on their agreement with a on sensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This “deeplearning” approach has since become accepted as a standard for segmentation of EM images. The challenge has continued to accept submissions, and the best so far has resulted from co-operation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test data set. Retrospective evaluation of the challenges coring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge.