Segmentation of SBFSEM Volume Data of Neural Tissue by Hierarchical Classification

This work proposes a hierarchical segmentation procedure based on statistical learning and topology-preserving grouping that is close to human labelings in three-dimensional electron-microscopic image stacks with almost isotropic resolution.

Abstract

Three-dimensional electron-microscopic image stacks with almost isotropic resolution allow, for the first time, to determine the complete connection matrix of parts of the brain. In spite of major advances in staining, correct segmentation of these stacks remains challenging, because very few local mistakes can lead to severe global errors. We propose a hierarchical segmentation procedure based on statistical learning and topology-preserving grouping. Edge probability maps are computed by a random forest classifier (trained on hand-labeled data) and partitioned into supervoxels by the watershed transform. Over-segmentation is then resolved by another random forest. Careful validation shows that the results of our algorithm are close to human labelings.