Level Set Formulation Based on Edge and Region Information with Application to Accurate Lesion Segmentation of Brain Magnetic Resonance Images

Yunyun Yang (), Wenjing Jia (), Xiu Shu () and Boying Wu ()
Additional contact information
Yunyun Yang: Harbin Institute of Technology
Wenjing Jia: Harbin Institute of Technology
Xiu Shu: Harbin Institute of Technology
Boying Wu: Harbin Institute of Technology

Journal of Optimization Theory and Applications, 2019, vol. 182, issue 2, No 16, 797-815

Abstract: Abstract Magnetic resonance images have great significance for doctors’ analysis and diagnosis of diseases. One difficulty in segmenting magnetic resonance images is associated with the intensity inhomogeneity. In this paper, we propose an improved active contour model combining local and global information dynamically to segment images with intensity inhomogeneity. Besides, the atlas term is added into our energy functional, which improves the segmentation accuracy by restricting the segmented range around the location of the given atlas and making the contour move toward a position near the atlas. In this paper, we first present the multi-phase formulation of our model. Then, our model is applied to segment a total of 35 different brain magnetic resonance images with lesions. We also compare the performance of our model with other models, which can handle inhomogeneous images to some extent. Experimental results demonstrate that our model has promising performance for these challenging brain magnetic resonance images. Accuracy, efficiency and robustness of the proposed model have also been demonstrated by the numerical results and comparisons with other models.

Keywords: Image segmentation; Split Bregman method; Intensity inhomogeneity; MRI; Level set formulation (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-018-01451-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joptap:v:182:y:2019:i:2:d:10.1007_s10957-018-01451-1

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1007/s10957-018-01451-1

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().