What Properties are Desirable from an Electron Microscopy Segmentation Algorithm
This work addresses the high human labor costs in annotating groundtruth and correcting errors for EM segmentation, which is incremental as it builds on existing segmentation frameworks.
The study tackled the problem of reducing manual effort in electron microscopy segmentation for neural reconstruction by proposing a novel classifier training algorithm that uses active learning for sparse labeling and prioritizes minimizing false-merges. The result is segmentation outputs more amenable to neural reconstruction than existing methods, as shown in experiments on 2D and 3D data.
The prospect of neural reconstruction from Electron Microscopy (EM) images has been elucidated by the automatic segmentation algorithms. Although segmentation algorithms eliminate the necessity of tracing the neurons by hand, significant manual effort is still essential for correcting the mistakes they make. A considerable amount of human labor is also required for annotating groundtruth volumes for training the classifiers of a segmentation framework. It is critically important to diminish the dependence on human interaction in the overall reconstruction system. This study proposes a novel classifier training algorithm for EM segmentation aimed to reduce the amount of manual effort demanded by the groundtruth annotation and error refinement tasks. Instead of using an exhaustive pixel level groundtruth, an active learning algorithm is proposed for sparse labeling of pixel and boundaries of superpixels. Because over-segmentation errors are in general more tolerable and easier to correct than the under-segmentation errors, our algorithm is designed to prioritize minimization of false-merges over false-split mistakes. Our experiments on both 2D and 3D data suggest that the proposed method yields segmentation outputs that are more amenable to neural reconstruction than those of existing methods.