Segmenting Teeth from Volumetric CT Data with a Hierarchical CNN-based Approach

Macho, Philipp Marten; Kurz, Nadja; Ulges, Adrian; Brylka, Robert; Gietzen, Thomas; Schwanecke, Ulrich

Segmenting Teeth from Volumetric CT Data with a Hierarchical CNN-based Approach

Files

109-113.pdf (4.28 MB)

Date

2018

Authors

Macho, Philipp Marten
Kurz, Nadja
Ulges, Adrian
Brylka, Robert
Gietzen, Thomas
Schwanecke, Ulrich

Publisher

The Eurographics Association

Abstract

This paper addresses the automatic segmentation of teeth in volumetric Computed Tomography (CT) scans of the human skull. Our approach is based on a convolutional neural network employing 3D volumetric convolutions. To tackle data scale issues, we apply a hierarchical coarse-to fine approach combining two CNNs, one for low-resolution detection and one for highresolution refinement. In quantitative experiments on 40 CT scans with manually acquired ground truth, we demonstrate that our approach displays remarkable robustness across different patients and device vendors. Furthermore, our hierarchical extension outperforms a single-scale segmentation, and network size can be reduced compared to previous architectures without loss of accuracy.

        @inproceedings{10.2312:cgvc.20181213
,
booktitle = {Computer Graphics and Visual Computing (CGVC)
},
editor = {{Tam, Gary K. L.  and Vidal, Franck
},
title = {{Segmenting Teeth from Volumetric CT Data with a Hierarchical CNN-based Approach
}},
author = {Macho, Philipp Marten and 
Kurz, Nadja and 
Ulges, Adrian and 
Brylka, Robert and 
Gietzen, Thomas and 
Schwanecke, Ulrich
},
year = {2018
},
publisher = {The Eurographics Association
},
ISBN = {978-3-03868-071-0
},
DOI = {10.2312/cgvc.20181213
}
}