Automatic segmentation of spinal cord injury using coarse-to-fine strategy

DOI

10.2991/aest-16.2016.16How to use a DOI?

Keywords

medical image segmentation; automatic segmentation; spinal cord injury; coarse-to-fine strategy.

Abstract

Medical image segmentation is a key issue in the field of medical image processing and analysis. Segmentation of spinal cord injury draws interests of researchers recently. To eliminate human computer interaction in segmentation of spinal cord injury, an automatic segmentation of spinal cord injury is proposed. A self-adaptive non-edge information smoothing algorithm was presented to realize filtering processing of spinal cord injury (SCI) images. The first time to use Deformable Parts Model (DPM) algorithm on the positioning detection of spine in an SCI image. A large number of non-scar information noises were removed and the detection range of scars was further reduced. Based on Coarse-to-fine strategy, a fully-automated spinal cord scar injury segmentation algorithm is put forward. The experimental results demonstrated the effectiveness of this algorithm.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jiali Cui
AU  - Yubo Ma
AU  - Wei Xie
AU  - Yiding Wang
AU  - Ruiming Jia
PY  - 2016/11
DA  - 2016/11
TI  - Automatic segmentation of spinal cord injury using coarse-to-fine strategy
BT  - Proceedings of the 2016 International Conference on Advanced Electronic Science and Technology (AEST 2016)
PB  - Atlantis Press
SP  - 124
EP  - 132
SN  - 1951-6851
UR  - https://doi.org/10.2991/aest-16.2016.16
DO  - 10.2991/aest-16.2016.16
ID  - Cui2016/11
ER  -