Abstract
In this paper, we adopt a kernel regression approach with steering kernel estimation using fractional order gradients and a Taylor series representation involving integer and fractional order. TV regularization using Fractional-order gradients is known to enhance textural details in smooth regions along with suppression of staircase artifacts. Thus, introducing the fractional-order gradient will make the adaptation of steering kernel more effective. With this motivation, we model a kernel regression framework using TV functional with local fractional-order Taylor series signal representation termed Fractional-order Adaptive Kernel Total Variation (FO-AKTV). Noise suppression in the texture region is achieved by Weighted Non-Local Nuclear Norm (WNLNN) based spectral low rank prior. To achieve the desired super-resolution solution, the cost function with aforementioned priors is minimized using the Alternating Direction Method of Multipliers (ADMM). The proposed method outperforms the state-of-the-art methods such as low rank total variation (LRTV), dictionary learning (DL) and adaptive kernel total variaton (AKTV) in terms of the output signal-to-noise ratio (SNR) at different input noise levels.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
E. Carmi, S. Liu, N. Alon, A. Fiat, D. Fiat et al., Resolution enhancement in MRI. Magn. Reson. Imaging 24(2), 133-154 (2006)
A. Gholipour, J.A. Estroff, S.K. Warfield et al., Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI. IEEE Trans. Med. Imaging 29(10), 1739-1758 (2010)
A.P. Mahmoudzadeh, N.H. Kashou et al., Interpolation-based super-resolution reconstruction: effects of slice thickness. J. Med. Imaging 1(3), 034007 (2014)
J.V. Manjón, P. Coupé, A. Buades, V. Fonov, D.L. Collins, M. Robles et al., Non-local MRI upsampling. Med. Image Anal. 14(6), 784–792 (2010)
Y. Li, B. Song, J. Guo, X. Du, M. Guizani et al., Super-resolution of brain MRI images using overcomplete dictionaries and nonlocal similarity. IEEE Access 7, 25897–25907 (2019)
J. Yang, W. John, S. Huang Thomas, Y. Ma et al., Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861-2873 (2010)
A.S. Chaudhari et al., Super-resolution musculoskeletal MRI using deep learning. Magn. Reson. Med. 80(5), 2139-2154 (2018)
L.I. Rudin, S. Osher, E. Fatemi et al., Nonlinear total variation based noise removal algorithms. Physica D Nonlin. Phenomena 60(1-4), 259-268 (1992)
A. Chambolle, V. Caselles, D. Cremers, M. Novaga, T. Pock et al., An introduction to total variation for image analysis. Theor. Found. Num. Methods Sparse Recov. 9(263-340), 227 (2010)
T. Chan, A. Marquina, P. Mulet, et al., High-order total variation-based image restoration. SIAM J. Sci. Comput. 22(2), 503–516 (2000)
M. Aghagolzadeh, A. Segall et al., Kernel smoothing for jagged edge reduction, in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2013), pp. 2474–2478
H. Liu, Z. Wei et al., An edge-adaptive structure tensor kernel regression for image interpolation, in 2010 2nd International Conference on Future Computer and Communication, vol. 2, (IEEE, 2010), pp. V2-681-V2-685
H. Takeda, S. Farsiu, P. Milanfar et al., Kernel regression for image processing and reconstruction. IEEE Trans. Image Process 16(2), 349-366 (2007)
H. Takeda, S. Farsiu, P. Milanfar et al., Deblurring using regularized locally adaptive kernel regression. IEEE Trans. Image Process. 17(4), 550-563 (2008)
S. Lefkimmiatis, A. Roussos, P. Maragos, M. Unser et al., Structure tensor total variation. SIAM J. Imaging Sci. 8(2), 1090–1122 (2015)
F. Shi, J. Cheng, L. Wang, P.-T. Yap, aD. Shen et al., LRTV: MR image super-resolution with low-rank and total variation regularizations. IEEE Trans. Med. Imaging 34(120, 2459-2466 (2015)
E.J. Candès, X. Li, Y. Ma, J. Wright et al., Robust principal component analysis? J. ACM (JACM) 58(3), 11 (2011)
J.-F. Cai, E. J. Candès, Z. Shen et al., A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956-1982 (2010)
S. Gu, L. Zhang, W. Zuo, X. Feng et al., Weighted nuclear norm minimization with application to image denoising, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2862–2869 (2014)
S. Gu, Q. **e, D. Meng, W. Zuo, X. Feng, L. Zhang et al., Weighted nuclear norm minimization and its applications to low level vision. Int. J. Comput. Vision 121(2), 183-208 (2017)
Z. Ren, C. He, Q. Zhang et al., Fractional order total variation regularization for image super-resolution. Signal Process. 93(9), 2408–2421 (Elsevier, 2013)
K. Yang, W. **a, P. Bao, J. Zhou, Y. Zhang et al., Nonlocal weighted nuclear norm minimization based sparse-sampling CT image reconstruction, in IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) (IEEE, 2019), pp. 1700–1703
Acknowledgements
This work was supported in part by the Scientific and Engineering Research Board (SERB) under Grant CRG/2019/002060 and planning board of Government of Kerala (GO(Rt)No.101/2017/ITD.GOK(02/05/2017)).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ibrahim, V., Paul, J.S. (2022). Super-Resolution MRI Using Fractional Order Kernel Regression and Total Variation. In: Tiwari, R., Mishra, A., Yadav, N., Pavone, M. (eds) Proceedings of International Conference on Computational Intelligence. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-16-3802-2_15
Download citation
DOI: https://doi.org/10.1007/978-981-16-3802-2_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3801-5
Online ISBN: 978-981-16-3802-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)