Cylindrical Shape Decomposition for 3D Segmentation of Tubular Objects

TL;DR

This paper introduces a novel cylindrical shape decomposition algorithm that segments 3D tubular objects into meaningful components using curve skeletons and translational sweeps, demonstrating robustness and superior performance.

Contribution

The paper presents a new CSD method that effectively decomposes complex 3D tubular structures into semantic parts with improved accuracy and noise robustness.

Findings

Successfully segments axons in electron microscopy images

Decomposes vascular networks into meaningful components

Outperforms existing decomposition techniques

Abstract

We develop a cylindrical shape decomposition (CSD) algorithm to decompose an object, a union of several tubular structures, into its semantic components. We decompose the object using its curve skeleton and restricted translational sweeps. For that, CSD partitions the curve skeleton into maximal-length sub-skeletons over an orientation cost, each sub-skeleton corresponds to a semantic component. To find the intersection of the tubular components, CSD translationally sweeps the object in decomposition intervals to identify critical points at which the shape of the object changes substantially. CSD cuts the object at critical points and assigns the same label to parts along the same sub-skeleton, thereby constructing a semantic component. The proposed method further reconstructs the acquired semantic components at the intersection of object parts using generalized cylinders. We apply CSD for segmenting axons in large 3D electron microscopy images and decomposing vascular networks and synthetic objects. We show that our proposal is robust to severe surface noise and outperforms state-of-the-art decomposition techniques in its applications.