Abstract
Bias field in magnetic resonance (MR) images is caused due to the varying gradient driven eddy current in the MR image scanner. This results in intensity inhomogeneity (IIH) in the MR image. Therefore, bias field correction is a fundamental requisite in the tissue investigation procedure. The existing solutions used fuzzy c-means (FCM) algorithm with non-local spatial information. However, the use of only local spatial information may lead to poor segmentation of tissue regions. In this paper, we suggest a nonlocal spatial coherent FCM clustering scheme for bias field correction. A similarity measure is computed using a Gaussian kernel for local spatial information. A nonlocal coherence factor is incorporated into the objective function and membership matrix for separating the non-discriminable tissue regions in the brain MR images. The suggested scheme is analyzed in comparison with different existing methods. It is experimented with different modalities of synthetic and clinical brain MR images. The method is validated using standard cluster validation and quality evaluation indices. The results indicate the superiority of the proposed methodology compared with state-of-the-art approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vovk, U., Pernus, F., Likar, B.: A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans. Med. Imaging 26(3), 405–421 (2007)
Dora, L., Agrawal, S., Panda, R., Abraham, A.: State-of-the-art methods for brain tissue segmentation: a review. IEEE Rev. Biomed. Eng. 10, 235–249 (2017)
Mishro, P.K., Agrawal, S., Panda, R., Abraham A.: A novel type-2 fuzzy C-means clustering for brain MR image segmentation. IEEE Trans. Cybern. (2020)
Ahmed, M.N., Yamany, S.M., Mohamed, N., Farag, A.A., Moriarty, T.: A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data. IEEE Trans. Med. Imaging 21(3), 193–199 (2002)
Szilágyi, L., Szilágyi, S.M., Benyó, B., Benyó, Z.: Intensity inhomogeneity compensation and segmentation of MR brain images using hybrid c-means clustering models. Biomed. Signal Process. Control 6(1), 3–12 (2011)
Despotovic, I., Vansteenkiste, E., Philips, W.: Spatially coherent fuzzy clustering for accurate and noise-robust image segmentation. IEEE Signal Process. Lett. 20(4), 295–298 (2013)
Ji, Z.X., Sun, Q.S., Xia, D.S.: A modified possibilistic fuzzy c-means clustering algorithm for bias field estimation and segmentation of brain MR image. Comput. Med. Imaging Graph. 35(5), 383–397 (2011)
Ji, Z., Liu, J., Cao, G., Sun, Q., Chen, Q.: Robust spatially constrained fuzzy c-means algorithm for brain MR image segmentation. Pattern Recogn. 47(7), 2454–2466 (2014)
Tu, X., Gao, J., Zhu, C., Cheng, J.Z., Ma, Z., Dai, X., Xie, M.: MR image segmentation and bias field estimation based on coherent local intensity clustering with total variation regularization. Med. Biol. Eng. Comput. 54(12), 1807–1818 (2016)
Cong, W., et al.: A modified brain MR image segmentation and bias field estimation model based on local and global information. Comput. Math. Methods Med. 2016, 1–12 (2016)
Shan, X., Gong, X., Nandi, A.K.: Active contour model based on local intensity fitting energy for image segmentation and bias estimation. IEEE Access. 6, 49817–49827 (2018)
Borys, D., Serafin, W., Frackiewicz, M., Psiuk-Maksymowicz, K., Palus, H.: A phantom study of new bias field correction method combining N3 and KHM for MRI imaging. In: International Conference on SITIBS, pp. 314–319. IEEE (2018)
Mahata, N., Kahali, S., Adhikari, S.K., Sing, J.K.: Local contextual information and Gaussian function induced fuzzy clustering algorithm for brain MR image segmentation and intensity inhomogeneity estimation. Appl. Soft Comput. 68, 586–596 (2018)
Song, J., Zhang, Z.: Brain tissue segmentation and Bias field correction of MR image based on spatially coherent FCM with nonlocal constraints. Comput. Math. Methods Med. 201, 1–13 (2019)
Mishro, P.K., Agrawal, S., Panda, R., Abraham, A.: Novel fuzzy clustering based bias field correction technique for brain magnetic resonance images. IET Image Proc. 14(9), 1929–1936 (2020)
Mishro, P.K., Agrawal, S., Panda, R.: A fuzzy C-means clustering approach to HMRF-EM model for MRI brain tissue segmentation. In: International Conference on CERA, pp. 371–376. IEEE (2017)
BrainWeb: Simulated Brain Database. http://bic.mni.mcgill.ca/brainweb/. Accessed: Mar-Apr, 2020
IBSR. http://www.cma.mgh.harvard.edu/ibsr/. Accessed: Mar-Apr, 2020
Wu, K., Yang, M.S.: A cluster validity index for fuzzy clustering. Pattern Recogn. Lett. 26(9), 1275–1291 (2005)
Ndajah, P., Kikuchi, H., Yukawa, M., Watanabe, H., Muramatsu, S.: An investigation on the quality of denoised images. Int. J. Circuit Syst. Signal Process. 5(4), 423–434 (2011)
Acknowledgement
This work is supported by PhD scholarship grant under TEQIP-III, VSS University of Technology, Burla.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mishro, P.K., Agrawal, S., Panda, R. (2021). A Nonlocal Spatial Coherent Fuzzy C-Means Clustering for Bias Field Correction in Brain MR Images. In: Singh, S.K., Roy, P., Raman, B., Nagabhushan, P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1376. Springer, Singapore. https://doi.org/10.1007/978-981-16-1086-8_24
Download citation
DOI: https://doi.org/10.1007/978-981-16-1086-8_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1085-1
Online ISBN: 978-981-16-1086-8
eBook Packages: Computer ScienceComputer Science (R0)