A Hybrid Medical Image Registration Framework Integrating Fiducial Markers and Wavelet-Based Mutual Information
DOI:
https://doi.org/10.22399/ijcesen.4846Keywords:
Hybrid registration , Fiducial markers, Daubechies wavelet, Mutual information, Multimodal brain MRIAbstract
This paper proposes a hybrid medical image registration framework aimed at improving the alignment accuracy of multimodal brain MRI images. The proposed approach integrates the geometric robustness of fiducial markers with the multi-resolution frequency analysis capability of the Daubechies wavelet transform (db2). Initially, three artificial circular fiducial markers are placed at stable anatomical landmarks and automatically detected using the Circular Hough Transform with radii ranging from 6 to 20 pixels, enabling reliable estimation of an initial affine transformation and reducing gross alignment errors. Subsequently, a two-dimensional Discrete Wavelet Transform (DWT) is applied to the reference and moving images, where the low-frequency (LL) sub-bands are exploited to perform fine registration using Mutual Information (MI) as the similarity metric. This frequency-domain refinement enhances robustness against noise and intensity variations. Experimental evaluations on healthy and tumor-affected brain MRI datasets demonstrate that the proposed hybrid framework outperforms conventional intensity-based methods relying on MSE, SSIM, and PSNR, particularly in challenging pathological scenarios.
References
[1] Shen, X., Darmon, F., Efros, A. A., & Aubry, M. (2020, August). Ransac-flow: generic two-stage image alignment. In European Conference on Computer Vision (pp. 618-637). Cham: Springer International Publishing.
[2] Wang, X., & Tian, J. (2005). Image registration based on maximization of gradient code mutual information. Image Analysis and Stereology, 24(1), 1-7.
[3] Kharbach, A., Merdani, A., Bellach, B., Rahmoune, M., & Rahmoun, M. (2016). A novel Approach of Image Registration Based on Normalized Dissimilarity Index. IJVIPNS-IJENS, 16(03).
[4] Brown, L. G. (1992). A survey of image registration techniques. ACM computing surveys (CSUR), 24(4), 325-376.
[5] M. Mudrova, A. Proch_azka, Image registration in the Matlab environment, Institute of Chemical Technology, Department of Computing and Control Engineering
[6] Kluckner, S. (2006). Non-linear 3D-volume registration using a local affine model. na.
[7] https://www.kaggle.com/datasets.
[8] Shakir, H., Ahsan, S. T., & Faisal, N. (2015, September). Multimodal medical image registration using discrete wavelet transform and Gaussian pyramids. In 2015 IEEE International Conference on Imaging Systems and Techniques (IST) (pp. 1-6). IEEE.
[9] Chan, M. F., Cohen, G. A. N., & Deasy, J. O. (2015). Qualitative evaluation of fiducial markers for radiotherapy imaging. Technology in cancer research & treatment, 14(3), 298-304.
[10] Fitzpatrick, J. M., Hill, D. L., & Maurer, C. R. (2000). Image registration. Handbook of medical imaging, 2, 447-513.
[11] Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., & Suetens, P. (2002). Multimodality image registration by maximization of mutual information. IEEE transactions on Medical Imaging, 16(2), 187-198.
[12] Cahill, N. D., Schnabel, J. A., Noble, J. A., & Hawkes, D. J. (2009, March). Overlap invariance of cumulative residual entropy measures for multimodal image alignment. In Medical Imaging 2009: Image Processing (Vol. 7259, pp. 184-195). SPIE.
[13] Kokila, R., & Thangavel, P. (2014). Image registration based on fast fourier transform using gabor filter. International Journal of Computer Science and Electronics Engineering (IJCSEE), 2(1), 31-37.
[14] Medical image fusion: A survey of the state of the art. Information fusion
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
