Hierarchical Manifold Clustering on Diffusion Maps for Connectomics (MIT 18.S096 final project)

TL;DR

This paper presents a novel hierarchical clustering algorithm for connectomics segmentation that leverages diffusion maps and manifold learning to improve boundary detection and segmentation accuracy.

Contribution

It introduces a new spectral clustering extension that estimates minimum normalized cuts using manifold learning and a topological split criterion, enhancing existing agglomeration methods.

Findings

Effective segmentation of imperfect boundary maps

Improved boundary detection through manifold learning

Complementary to existing agglomeration approaches

Abstract

In this paper, we introduce a novel algorithm for segmentation of imperfect boundary probability maps (BPM) in connectomics. Our algorithm can be a considered as an extension of spectral clustering. Instead of clustering the diffusion maps with traditional clustering algorithms, we learn the manifold and compute an estimate of the minimum normalized cut. We proceed by divide and conquer. We also introduce a novel criterion for determining if further splits are necessary in a component based on it's topological properties. Our algorithm complements the currently popular agglomeration approaches in connectomics, which overlook the geometrical aspects of this segmentation problem.