Advertisement

Gaussian Processes for Slice-Based Super-Resolution MR Images

  • Hernán Darío Vargas CardonaEmail author
  • Andrés F. López-Lopera
  • Álvaro A. Orozco
  • Mauricio A. Álvarez
  • Juan Antonio Hernández Tamames
  • Norberto Malpica
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9475)

Abstract

Magnetic resonance imaging (MRI) is a medical technique used in radiology to obtain anatomical images of healthy and pathological tissues. Due to hardware limitations and clinical protocols, MRI data are often acquired with low-resolution. For this reason, the scientific community has been developing super-resolution (SR) methodologies in order to enhance spatial resolution through post-processing of 2D multi-slice images. The enhancement of spatial resolution in magnetic resonance (MR) images improves clinical procedures such as tissue segmentation, registration and disease diagnosis. Several methods to perform SR-MR images have been proposed. However, they present different drawbacks: sensitivity to noise, high computational cost, and complex optimization algorithms. In this paper, we develop a supervised learning methodology to perform SR-MR images using a patch-based Gaussian process regression (GPR) method. We compare our approach with nearest-neighbor interpolation, B-splines and a SR-GPR scheme based on nearest-neighbors. We test our SR-GPR algorithm in MRI-T1 and MRI-T2 studies, evaluating the performance through error metrics and morphological validation (tissue segmentation). Results obtained with our methodology outperform the other alternatives for all validation protocols.

Keywords

Magnetic Resonance Imaging Study Average Mean Square Error Gaussian Process Regression Tissue Segmentation Joint Gaussian Distribution 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgments

H.D. Vargas Cardona is funded by Colciencias under the program: formación de alto nivel para la ciencia, la tecnología y la innovación - Convocatoria 617 de 2013. This research has been developed under the project: Estimación de los parámetros de neuro modulación con terapia de estimulación cerebral profunda en pacientes con enfermedad de Parkinson a partir del volumen de tejido activo planeado, financed by Colciencias with code 1110-657-40687.

References

  1. 1.
    Hollingworth, W., Todd, C., Bell, M., Arafat, Q., Girling, S., Karia, K., Dixon, A.K.: The diagnostic and therapeutic impact of MRI: an observational multi-centre study. Clin. Radiol. 55, 825–831 (2000)CrossRefGoogle Scholar
  2. 2.
    Isaac, J., Kulkarni, J.: Super resolution techniques for medical image processing. In: International Conference on Technologies for Sustainable Development (ICTSD), pp. 1–6 (2015)Google Scholar
  3. 3.
    Hefnawy, A.: An efficient super-resolution approach for obtaining isotropic 3-D imaging using 2-D multi-slice MRI. Egypt. Inf. J. 14, 117–123 (2013)CrossRefGoogle Scholar
  4. 4.
    Malczewski, K.: Inter-K-space motion based strategy for super-resolution in MRI. In: 17th European Signal Processing Conference, pp. 30–34 (2009)Google Scholar
  5. 5.
    Carmi, E., Liu, S., Alon, N., Fiat, A., Fiat, D.: Resolution enhancement in MRI. Magn. Reson. Imaging 24, 133–154 (2006)CrossRefGoogle Scholar
  6. 6.
    Huang, T., Tsai, R.: Multi-frame image restoration and registration. In: Advances in Computer Vision and Image Processing, vol. 1, pp. 317–339 (1984)Google Scholar
  7. 7.
    Kim, S., Bose, N., Valenzuela, H.: Recursive reconstruction of high resolution image from noisy undersampled frames. IEEE Trans. Acoust. Speech Sig. Process. 38, 1013–1027 (1990)CrossRefGoogle Scholar
  8. 8.
    Patti, A., Sezan, M., Teklap, A.: High-resolution image reconstruction from a low-resolution image sequence in the presence of time-varying motion blur. In: Proceedings of ICIP, pp. 343–337 (1994)Google Scholar
  9. 9.
    Greenspan, H., Oz, G., Kiryati, N., Peled, S.: MRI inter-slice reconstruction using super resolution. Magn. Reson. Imaging 20, 437–446 (2002)CrossRefGoogle Scholar
  10. 10.
    Aguena, M., Mascarenhas, N., Anacleto, J., Fels, S.: MRI iterative super resolution with Wiener filter regularization. In: XXVI Conference on Graphics, Patterns and Images, pp. 155–162 (2013)Google Scholar
  11. 11.
    Jafari-Khouzani, K.: MRI upsampling using feature-based nonlocal means approach. IEEE Trans. Med. Imaging 30, 1969–1985 (2014)CrossRefGoogle Scholar
  12. 12.
    Lu, Y., Yang, R.: Super-resolution reconstruction of dynamic MRI by patch learning. In: 12th International Conference on Control, Automation, Robotics and Vision, pp. 1443–1448 (2012)Google Scholar
  13. 13.
    Rousseau, F., Studholme, C.: A supervised patch-based image reconstruction technique: application to brain MRI super-resolution. In: 10th International Symposium on Biomedical Imaging, pp. 346–349 (2013)Google Scholar
  14. 14.
    Rueda, A., Malpica, N., Romero, E.: Single-image super-resolution of brain MR images using overcomplete dictionaries. Med. Image Anal. 17, 113–132 (2012)CrossRefGoogle Scholar
  15. 15.
    Wang, Y., Qiao, J., Jun-bao, L., Ping-Fu, A., Shu-Chuan, C., Rodd, J.: Sparse representation-based MRI super-resolution reconstruction. Meas. 47, 946–953 (2012)CrossRefGoogle Scholar
  16. 16.
    Jog, A., Carass, A., Prince, J.: Improving magnetic resonance resolution with supervised learning. In: IEEE 11th International Symposium on Biomedical Imaging (ISBI), pp. 987–990 (2014)Google Scholar
  17. 17.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2005)Google Scholar
  18. 18.
    Murphy, K.P.: Machine Learning: A Probabilistic Perspective (Adaptive Computation And Machine Learning Series). The MIT Press, Cambridge (2012)Google Scholar
  19. 19.
    He, H., Siu, W.C.: Single image super-resolution using Gaussian process regression. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 449–456 (2011)Google Scholar
  20. 20.
    Barmpoutis, A., Vemuri, B., Shepherd, T., Forder, J.: Tensor splines for interpolation and approximation of DT-MRI with applications to segmentation of isolated rat hippocampi. IEEE Trans. Med. Imaging 26, 1537–1546 (2007)CrossRefGoogle Scholar
  21. 21.
    Kikinis, R., Pieper, S.D., Vosburgh, K.G.: 3D slicer: a platform for subject-specific image analysis, visualization, and clinical support. In: Jolesz, F.A. (ed.) Intraoperative Imaging and Image-Guided Therapy, pp. 277–289. Springer, New York (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Hernán Darío Vargas Cardona
    • 1
    Email author
  • Andrés F. López-Lopera
    • 1
  • Álvaro A. Orozco
    • 1
  • Mauricio A. Álvarez
    • 1
  • Juan Antonio Hernández Tamames
    • 2
  • Norberto Malpica
    • 2
  1. 1.Faculty of EngineeringUniversidad Tecnológica de PereiraPereiraColombia
  2. 2.Laboratorio de Análisis de Imagen Médica Y BiometríaUniversidad Rey Juan CarlosMóstolesSpain

Personalised recommendations