ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Multiscale Sparse Appearance Modeling and Simulation of Pathological Deformations


Affiliations
1 Department of Electronics and Communication Engineering, University of Alberta, Canada
     

   Subscribe/Renew Journal


Machine learning and statistical modeling techniques has drawn much interest within the medical imaging research community. However, clinically-relevant modeling of anatomical structures continues to be a challenging task. This paper presents a novel method for multiscale sparse appearance modeling in medical images with application to simulation of pathological deformations in X-ray images of human spine. The proposed appearance model benefits from the non-linear approximation power of Contourlets and its ability to capture higher order singularities to achieve a sparse representation while preserving the accuracy of the statistical model. Independent Component Analysis is used to extract statistical independent modes of variations from the sparse Contourlet-based domain. The new model is then used to simulate clinically-relevant pathological deformations in radiographic images.

Keywords

Appearance Model, Contourlet, Sparsity, Independent Component Analysis, Pathology Deformations.
Subscription Login to verify subscription
User
Notifications
Font Size

  • T.F. Cootes, G.J. Edwards and C.J. Taylor, “Active Appearance Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, pp. 681685, 2001.

  • M. Roberts, T. Cootes and J. Adams, “Automatic Segmentation of Lumbar Vertebrae on Digitised Radiographs using Linked Active Appearance Models”, Proceedings of Medical Image Understanding and Analysis, Vol. 2, pp. 120-124, 2006.

  • K. Delac, M. Grgic and P. Liatsis, “Appearance-based Statistical methods for Face Recognition”, Proceedings of 47th International Symposium Focus on Multimedia Systems and Applications, pp. 151-158, 2005.

  • X. Xu, C. Zhang and T. Huang, “Active Morphable Model: An Efficient Method for Face Analysis”, Proceedings of 6th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 837-842, 2004.

  • Mikkel B. Stegmann, Karl Sjostrand and Rasmus Larsen, “Sparse Modeling of Landmark and Texture Variability using the Orthomax Criterion”, Proceedings of International Symposium on Medical Imaging, Vol. 6144, pp. 1-12, 2006.

  • C. Wolstenholme and C. Taylor, “Wavelet Compression of Active Appearance Models”, Proceedings of 2nd International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 544-554, 1999.

  • M.B. Stegmann, S. Forchhammer and T.F. Cootes, “Wavelet Enhanced Appearance Modelling”, Proceedings of Symposium on Medical Imaging, Vol. 5370, pp. 1823-1832, 2004.

  • R. Larsen, M.B. Stegmann, S. Darkner, S. Forchhammer, T.F. Cootes and B.K. Ersboll, “Texture Enhanced Appearance Models”, Computer Vision and Image Understanding, Vol. 106, No. 1, pp. 20-30, 2007.

  • Ki Gia Quach, Chi Nhann Duong, Khou Luu and Bac Le, “Gabor Wavelet-based Appearance Models”, Proceedings of International Conference of Computing and Communication Technologies, Research, Innovation, and Vision for the Future, pp. 1-6, 2012.

  • Qiang Zhang, Abhir Bhalerao, Caron Parsons, Emma Helm and Charles Hutchinson, “Wavelet Appearance Pyramids for Landmark Detection and Pathology Classification: Application to Lumbar Spinal Stenosis”, Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 274-282, 2016.

  • Abbas Hanon Hassin Al Asadi, “Contourlet Transform based Medical Image Denoising”, International Journal of Image Processing, Vol. 9, No. 1, pp. 22-31, 2015.

  • B. Abboud, F. Davoine, and M. Dang, “Facial Expression Recognition and Synthesis based on An Appearance Model”, Signal Processing: Image Communication, Vol. 19, No. 8, pp. 723-740, 2004.

  • W. Seales and C. Yaun, “Improved Image Classification using Morphing”, Proceedings of 3rd Asian Conference on Computer Vision, pp. 233-240, 1998.

  • S. Wolberg and G. Shin, “Polymorph: Morphing among Multiple Images”, IEEE Computer Graphics and Applications, Vol. 18, No. 1, pp. 58-71, 1998.

  • Ghassan Hamarneh, Preet Jassi and Lisa Tang, “Simulation of Ground Truth Validation Data via physically-and Statistically-based Warps”, International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 459-467, 2008.

  • C.J. Rose and C.J. Taylor, “A Statistical Model of Texture for Medical Image Synthesis and Analysis”, Proceedings of Medical Image Understanding and Analysis, pp. 1-4, 2003.

  • Ahmed Elsafi, Rami Zewail, and Nelson Durdle, “Statistical Simulation of Deformations using Wavelet Independent Component Analysis”, Proceedings of Symposium on Security and Defence Visual Information Processing, Vol. 6978, pp. 1-8, 2008.

  • Z. Xue, D. Shen, B. Karacali, J. Stern, D. Rottenberg, and C. Davatzikos, “Simulating Deformations of MR Brain Images for Validation of Atlas-based Segmentation and Registration Algorithms”, Neuroimage, Vol. 33, No. 3, pp. 855-866, 2006.

  • Ruida Cheng et al., “Active Appearance Model and Deep Learning for more Accurate Prostate Segmentation on MRI”, Proceedings of Medical Imaging, pp. 1-9, 2016.

  • R. Nithya and S.Elayaraja, “Medical Image Fusion Schemes using Contourlet Transform and PCA Bases”, Asian Journal of Electronics Sciences, Vol. 4, No. 1, pp. 27-33, 2015.

  • M.N. Do and M. Vetterli, “Contourlets in Beyond Wavelets”, Academic Press, 2003.

  • M. Nordstom et al., “The IMM Face Database: An Annotated Dataset of 240 Face Images, Informatics and Mathematical Modelling”, Technical University of Denmark, 2004.

  • L. Long, S. Antani and G. Thoma, “Image informatics at a National Research Center”, Computerized Medical Imaging and Graphics, Vol. 29, No. 2-3, pp. 171-193, 2005.

  • Rami Zewail, Ahmed ElSafi and Nelson Durdle, “Vertebral segmentation using Contourlet-based Salient Matching and Localized Multi-Scale Shape Prior”, Proceedings of Medical Imaging, pp. 1-9, 2009.


Abstract Views: 235

PDF Views: 6




  • Multiscale Sparse Appearance Modeling and Simulation of Pathological Deformations

Abstract Views: 235  |  PDF Views: 6

Authors

Rami Zewail
Department of Electronics and Communication Engineering, University of Alberta, Canada
Ahmed Hag-Elsafi
Department of Electronics and Communication Engineering, University of Alberta, Canada

Abstract


Machine learning and statistical modeling techniques has drawn much interest within the medical imaging research community. However, clinically-relevant modeling of anatomical structures continues to be a challenging task. This paper presents a novel method for multiscale sparse appearance modeling in medical images with application to simulation of pathological deformations in X-ray images of human spine. The proposed appearance model benefits from the non-linear approximation power of Contourlets and its ability to capture higher order singularities to achieve a sparse representation while preserving the accuracy of the statistical model. Independent Component Analysis is used to extract statistical independent modes of variations from the sparse Contourlet-based domain. The new model is then used to simulate clinically-relevant pathological deformations in radiographic images.

Keywords


Appearance Model, Contourlet, Sparsity, Independent Component Analysis, Pathology Deformations.

References