A Context-aware Delayed Agglomeration Framework for Electron Microscopy Segmentation
This work addresses the challenge of connectomics by enhancing EM segmentation, though it appears incremental as it builds on existing agglomerative methods.
The paper tackles the problem of accurately segmenting neurons in electron microscopy images by proposing a context-aware delayed agglomeration framework, which improves segmentation accuracy over existing methods on 2D and 3D datasets.
Electron Microscopy (EM) image (or volume) segmentation has become significantly important in recent years as an instrument for connectomics. This paper proposes a novel agglomerative framework for EM segmentation. In particular, given an over-segmented image or volume, we propose a novel framework for accurately clustering regions of the same neuron. Unlike existing agglomerative methods, the proposed context-aware algorithm divides superpixels (over-segmented regions) of different biological entities into different subsets and agglomerates them separately. In addition, this paper describes a "delayed" scheme for agglomerative clustering that postpones some of the merge decisions, pertaining to newly formed bodies, in order to generate a more confident boundary prediction. We report significant improvements attained by the proposed approach in segmentation accuracy over existing standard methods on 2D and 3D datasets.