Image Processing

Visual saliency-based active learning for prostate magnetic resonance imaging segmentation

[+] Author Affiliations
Dwarikanath Mahapatra, Joachim M. Buhmann

ETH Zurich, Department of Computer Science, CAB E65.1, Universitaetstrasse 6, Zurich 8092, Switzerland

J. Med. Imag. 3(1), 014003 (Feb 19, 2016). doi:10.1117/1.JMI.3.1.014003
History: Received August 8, 2015; Accepted February 5, 2016
Text Size: A A A

Abstract.  We propose an active learning (AL) approach for prostate segmentation from magnetic resonance images. Our label query strategy is inspired from the principles of visual saliency that have similar considerations for choosing the most salient region. These similarities are encoded in a graph using classification maps and low-level features. Random walks are used to identify the most informative node, which is equivalent to the label query sample in AL. To reduce computation time, a volume of interest (VOI) is identified and all subsequent analysis, such as probability map generation using semisupervised random forest classifiers and label query, is restricted to this VOI. The negative log-likelihood of the probability maps serves as the penalty cost in a second-order Markov random field cost function, which is optimized using graph cuts for prostate segmentation. Experimental results on the Medical Image Computing and Computer Assisted Intervention (MICCAI) 2012 prostate segmentation challenge show the superior performance of our approach to conventional methods using fully supervised learning.

Figures in this Article
© 2016 Society of Photo-Optical Instrumentation Engineers

Citation

Dwarikanath Mahapatra and Joachim M. Buhmann
"Visual saliency-based active learning for prostate magnetic resonance imaging segmentation", J. Med. Imag. 3(1), 014003 (Feb 19, 2016). ; http://dx.doi.org/10.1117/1.JMI.3.1.014003


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.