Superhuman Accuracy on the SNEMI3D Connectomics Challenge

Understand

For the past decade, convolutional networks have been used for 3D reconstruction of neurons from electron microscopic (EM) brain images.

• Recent years have seen great improvements in accuracy, as evidenced by submissions to the SNEMI3D benchmark challenge.
• Here we report the first submission to surpass the estimate of human accuracy provided by the SNEMI3D leaderboard.
• A variant of 3D U-Net is trained on a primary task of predicting affinities between nearest neighbor voxels, and an auxiliary task of predicting long-range affinities.