Share Email Print

Journal of Medical Imaging

Visual saliency-based active learning for prostate magnetic resonance imaging segmentation
Author(s): Dwarikanath Mahapatra; Joachim M. Buhmann
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 19 February 2016
PDF: 11 pages
J. Med. Img. 3(1) 014003 doi: 10.1117/1.JMI.3.1.014003
Published in: Journal of Medical Imaging Volume 3, Issue 1
Show Author Affiliations
Dwarikanath Mahapatra, ETH Zürich (Switzerland)
Joachim M. Buhmann, ETH Zürich (Switzerland)

© SPIE. Terms of Use
Back to Top