Cylindrical Shape Decomposition for 3D Segmentation of Tubular Objects
This work addresses the segmentation of complex tubular structures in 3D data, such as in medical imaging, but it is incremental as it builds on existing decomposition techniques.
The authors tackled the problem of segmenting tubular objects in 3D by developing a cylindrical shape decomposition algorithm that decomposes objects into semantic components using curve skeletons and translational sweeps. They demonstrated robustness to surface noise and outperformed state-of-the-art methods in applications like axon segmentation and vascular network decomposition.
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.