Cross-classification clustering : multi-object tracking technique for 3-D instance segmentation in connectomics

Abstract

In this thesis, cross-classification clustering (3C) is designed and implemented, it is a technique that simultaneously tracks complex, interrelated objects in an image stack. The key idea in cross-classification is to efficiently turn a clustering problem into a classification problem by running a logarithmic number of independent classifications per image, letting the cross-labeling of these classifications uniquely classify each pixel to the object labels. The 3C mechanism was applied to achieve state-of- the-art accuracy in connectomics - the nanoscale mapping of neural tissue from electron microscopy volumes. This reconstruction system increases scalability by an order of magnitude over existing single-object tracking methods (such as flood-filling networks). This scalability is important for the deployment of connectomics pipelines, since currently the best performing techniques require computing infrastructures that are beyond the reach of most laboratories. This algorithm may offer benefits in other domains that require pixel-accurate tracking of multiple objects, such as segmentation of videos and medical imagery.