Skip to content
BY 4.0 license Open Access Published by De Gruyter November 26, 2020

A novel combined level set model for automatic MR image segmentation

  • Jianzhang Li EMAIL logo , Sven Nebelung , Björn Rath , Markus Tingart and Jörg Eschweiler

Abstract

Medical image processing comes along with object segmentation, which is one of the most important tasks in that field. Nevertheless, noise and intensity inhomogeneity in magnetic resonance images challenge the segmentation procedure. The level set method has been widely used in object detection. The flexible integration of energy terms affords the level set method to deal with variable difficulties. In this paper, we introduce a novel combined level set model that mainly cooperates with an edge detector and a local region intensity descriptor. The noise and intensity inhomogeneities are eliminated by the local region intensity descriptor. The edge detector helps the level set model to locate the object boundaries more precisely. The proposed model was validated on synthesized images and magnetic resonance images of in vivo wrist bones. Comparing with the ground truth, the proposed method reached a Dice similarity coefficient of > 0.99 on all image tests, while the compared segmentation approaches failed the segmentations. The presented combined level set model can be used for the object segmentation in magnetic resonance images.

Published Online: 2020-11-26
Published in Print: 2020-09-01

© 2020 by Walter de Gruyter Berlin/Boston

This work is licensed under the Creative Commons Attribution 4.0 International License.

Downloaded on 4.2.2023 from https://www.degruyter.com/document/doi/10.1515/cdbme-2020-3006/html
Scroll Up Arrow