Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net

Christian Payer, Darko Å tern, Horst Bischof, Martin Urschler

Abstract

Localization and segmentation of vertebral bodies from spine CT volumes are crucial for pathological diagnosis, surgical planning, and postoperative assessment. However, fully automatic analysis of spine CT volumes is difficult due to the anatomical variation of pathologies, noise caused by screws and implants, and the large range of different field-of-views. We propose a fully automatic coarse to fine approach for vertebrae localization and segmentation based on fully convolutional CNNs. In a three-step approach, at first, a U-Net localizes the rough position of the spine. Then, the SpatialConfiguration-Net performs vertebrae localization and identification using heatmap regression. Finally, a U-Net performs binary segmentation of each identified vertebrae in a high resolution, before merging the individual predictions into the resulting multi-label vertebrae segmentation. The evaluation shows top performance of our approach, ranking first place and winning the MICCAI 2019 Large Scale Vertebrae Segmentation Challenge (VerSe 2019).

Download


Paper Citation


in Harvard Style

Payer C., Å tern D., Bischof H. and Urschler M. (2020). Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2, pages 124-133. DOI: 10.5220/0008975201240133


in Bibtex Style

@conference{visapp20,
author={Christian Payer and Darko Å tern and Horst Bischof and Martin Urschler},
title={Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={124-133},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008975201240133},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net
SN - 978-989-758-402-2
AU - Payer C.
AU - Å tern D.
AU - Bischof H.
AU - Urschler M.
PY - 2020
SP - 124
EP - 133
DO - 10.5220/0008975201240133