Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 7-Day Trial for You or Your Team.

Learn More →

Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features

Brain tumor detection and segmentation in a CRF (conditional random fields) framework with... Int J CARS (2014) 9:241–253 DOI 10.1007/s11548-013-0922-7 ORIGINAL ARTICLE Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features Wei Wu · Albert Y. C. Chen · Liang Zhao · Jason J. Corso Received: 28 January 2013 / Accepted: 3 July 2013 / Published online: 17 July 2013 © CARS 2013 Abstract a maximum a posteriori fashion given the smoothness prior Purpose Detection and segmentation of a brain tumor such defined by our affinity model. Finally, labeling noise was as glioblastoma multiforme (GBM) in magnetic resonance removed using “structural knowledge” such as the symmet- (MR) images are often challenging due to its intrinsically rical and continuous characteristics of the tumor in spatial heterogeneous signal characteristics. A robust segmentation domain. method for brain tumor MRI scans was developed and tested. Results The system was evaluated with 20 GBM cases and the Methods Simple thresholds and statistical methods are unable BraTS challenge data set. Dice coefficients were computed, to adequately segment the various elements of the GBM, such and the results were highly consistent with those reported by as local contrast enhancement, necrosis, and edema. Most Zikic et al. (MICCAI 2012, Lecture notes http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Computer Assisted Radiology and Surgery Springer Journals

Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features

Download PDF
13 pages

Loading next page...
 
/lp/springer-journals/brain-tumor-detection-and-segmentation-in-a-crf-conditional-random-B3BOtUO1M3

References (43)

Publisher
Springer Journals
Copyright
Copyright © 2013 by CARS
Subject
Medicine & Public Health; Imaging / Radiology; Surgery; Health Informatics; Computer Imaging, Vision, Pattern Recognition and Graphics; Computer Science, general
ISSN
1861-6410
eISSN
1861-6429
DOI
10.1007/s11548-013-0922-7
pmid
23860630
Publisher site
See Article on Publisher Site

Abstract

Int J CARS (2014) 9:241–253 DOI 10.1007/s11548-013-0922-7 ORIGINAL ARTICLE Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features Wei Wu · Albert Y. C. Chen · Liang Zhao · Jason J. Corso Received: 28 January 2013 / Accepted: 3 July 2013 / Published online: 17 July 2013 © CARS 2013 Abstract a maximum a posteriori fashion given the smoothness prior Purpose Detection and segmentation of a brain tumor such defined by our affinity model. Finally, labeling noise was as glioblastoma multiforme (GBM) in magnetic resonance removed using “structural knowledge” such as the symmet- (MR) images are often challenging due to its intrinsically rical and continuous characteristics of the tumor in spatial heterogeneous signal characteristics. A robust segmentation domain. method for brain tumor MRI scans was developed and tested. Results The system was evaluated with 20 GBM cases and the Methods Simple thresholds and statistical methods are unable BraTS challenge data set. Dice coefficients were computed, to adequately segment the various elements of the GBM, such and the results were highly consistent with those reported by as local contrast enhancement, necrosis, and edema. Most Zikic et al. (MICCAI 2012, Lecture notes

Journal

International Journal of Computer Assisted Radiology and Surgery – Springer Journals

Published: Jul 17, 2013

There are no references for this article.