SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation
Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use a scoring function to determine region merging. Such functions are usually
- PDF / 5,306,490 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 42 Downloads / 164 Views
2
Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT, USA {ting,mehran,nshramesh,tolga}@sci.utah.edu CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA [email protected]
Abstract. Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use a scoring function to determine region merging. Such functions are usually learned with supervised algorithms that demand considerable ground truth data, which are costly to collect. We propose a semi-supervised approach that reduces this demand. Based on a merge tree structure, we develop a differentiable unsupervised loss term that enforces consistent predictions from the learned function. We then propose a Bayesian model that combines the supervised and the unsupervised information for probabilistic learning. The experimental results on three EM data sets demonstrate that by using a subset of only 3 % to 7 % of the entire ground truth data, our approach consistently performs close to the state-of-the-art supervised method with the full labeled data set, and significantly outperforms the supervised method with the same labeled subset. Keywords: Image segmentation · Electron microscopy · Semi-supervised learning · Hierarchical segmentation · Connectomics
1
Introduction
Connectomics researchers study structures of nervous systems to understand their function [1]. Electron microscopy (EM) is the only modality capable of imaging substantial tissue volumes at sufficient resolution and has been used for the reconstruction of neural circuitry [2–4]. The high resolution leads to image data sets at enormous scale, for which manual analysis is extremely laborious and can take decades to complete [5]. Therefore, reliable automatic connectome Electronic supplementary material The online version of this chapter (doi:10. 1007/978-3-319-46448-0 9) contains supplementary material, which is available to authorized users. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part I, LNCS 9905, pp. 144–159, 2016. DOI: 10.1007/978-3-319-46448-0 9
SSHMT: Semi-supervised HMT for EM Image Segmentation
145
reconstruction from EM images, and as the first step, automatic segmentation of neuronal structures is crucial. However, due to the anisotropic nature, deformation, complex cellular structures and semantic ambiguity of the image data, automatic segmentation still remains challenging after years of active research. Similar to the boundary detection/region segmentation pipeline for natural image segmentation [6–9], most recent EM image segmentation methods use a membrane detection/cell segmentation pipeline. First, a membrane detector generates pixel-wise confidence maps of membrane predictions using local image cues [10–12]. Next, region-based methods are applied to transforming the membrane confidence maps into cell segments. It has been shown that region-based methods are necessary for improving the segmentat
Data Loading...