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

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.

[1]  Simon K. Warfield,et al.  Normalization of joint image-intensity statistics in MRI using the Kullback-Leibler divergence , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[2]  David J. Aldous,et al.  Lower bounds for covering times for reversible Markov chains and random walks on graphs , 1989 .

[3]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[4]  Deepu Rajan,et al.  Random walks on graphs to model saliency in images , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Joachim M. Buhmann,et al.  Prostate MRI Segmentation Using Learned Semantic Knowledge and Graph Cuts , 2014, IEEE Transactions on Biomedical Engineering.

[6]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[7]  M. Bowes,et al.  Fully Automatic Segmentation of the Prostate using Active Appearance Models , 2012 .

[8]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  . Markov Chains and Random Walks on Graphs , .

[10]  M S Cohen,et al.  Rapid and effective correction of RF inhomogeneity for high field magnetic resonance imaging , 2000, Human brain mapping.

[11]  Joachim M. Buhmann,et al.  Semi-Supervised and Active Learning for Automatic Segmentation of Crohn's Disease , 2013, MICCAI.

[12]  L G Nyúl,et al.  On standardizing the MR image intensity scale , 1999, Magnetic resonance in medicine.

[13]  Chunming Li,et al.  A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI , 2011, IEEE Transactions on Image Processing.

[14]  Scott T. Acton,et al.  Region Based Segmentation in Presence of Intensity Inhomogeneity Using Legendre Polynomials , 2015, IEEE Signal Processing Letters.

[15]  Florian Jung,et al.  Evaluation of prostate segmentation algorithms for MRI: The PROMISE12 challenge , 2014, Medical Image Anal..

[16]  Zhuowen Tu,et al.  Combining Generative and Discriminative Models for Semantic Segmentation of CT Scans via Active Learning , 2011, IPMI.

[17]  Anant Madabhushi,et al.  Multifeature Landmark-Free Active Appearance Models: Application to Prostate MRI Segmentation , 2012, IEEE Transactions on Medical Imaging.

[18]  Josien P. W. Pluim,et al.  Patient Specific Prostate Segmentation in 3-D Magnetic Resonance Images , 2012, IEEE Transactions on Medical Imaging.

[19]  Joachim M. Buhmann,et al.  Active learning based segmentation of Crohn's disease using principles of visual saliency , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[20]  Shu Liao,et al.  Representation Learning: A Unified Deep Learning Framework for Automatic Prostate MR Segmentation , 2013, MICCAI.

[21]  Pierre Hellier,et al.  Consistent intensity correction of MR images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[22]  Antonio Criminisi,et al.  Decision Forests for Computer Vision and Medical Image Analysis , 2013, Advances in Computer Vision and Pattern Recognition.

[23]  Maximilien Vermandel,et al.  Automatic segmentation of pelvic structures from magnetic resonance images for prostate cancer radiotherapy. , 2007, International journal of radiation oncology, biology, physics.

[24]  Daniel Rueckert,et al.  An automatic multi-atlas based prostate segmentation using local appearance-speci c atlases and patch-based voxel weighting , 2012 .

[25]  F. Wacker,et al.  A New Method for MRI Intensity Standardization with Application to Lesion Detection in the Brain , 2006 .

[26]  Soumya Ghose,et al.  A Random Forest Based Classification Approach to Prostate Segmentation in MRI , 2012 .

[27]  Mark Craven,et al.  An Analysis of Active Learning Strategies for Sequence Labeling Tasks , 2008, EMNLP.

[28]  Maria Petrou,et al.  Three-Dimensional Nonlinear Invisible Boundary Detection , 2006, IEEE Transactions on Image Processing.

[29]  Joachim M. Buhmann,et al.  Automatic Detection and Segmentation of Crohn's Disease Tissues From Abdominal MRI , 2013, IEEE Transactions on Medical Imaging.

[30]  Stefan Klein,et al.  Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. , 2008, Medical physics.

[31]  Neil Birkbeck,et al.  Region-Specific Hierarchical Segmentation of MR Prostate Using Discriminative Learning , 2012 .

[32]  David D. Lewis,et al.  Heterogeneous Uncertainty Sampling for Supervised Learning , 1994, ICML.

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[34]  Horst Bischof,et al.  On-line Random Forests , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[35]  Ewert Bengtsson,et al.  Smart Paint : A New Interactive Segmentation Method\\ Applied to MR Prostate Segmentation , 2012, MICCAI 2012.

[36]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[37]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[38]  Jocelyne Troccaz,et al.  Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model. , 2010, Medical physics.