Design of a digital wavelet filter to identify edges in medical MRI images
Abstract
The main purpose of this study is edge detection in MRI brain images. This study presents an efficient method in which a band pass filter is designed to apply to two sub-images of frequency sub bands resulted from the discrete wavelet transform of the original MRI image simultaneously and enhance the edge of the image. The simulation results show that band pass filter with noise elimination and amplification of properties with the desired brightness of the texture, created convenient accuracy in identifying the edges of the image compared to existing filters, it is also time-efficient with less computational process compared to complex methods. This method has a useful solution for identifying diseases in which the diagnostic method of MRI imaging has been used. It can also provide good insight to overcome the difficulties in the field of scale and noise in edge recognition
References
[2] Graps A: An introduction to wavelets. IEEE computational science and engineering 1995, 2(2):50-61.
[3] Mallat SG: Multifrequency channel decompositions of images and wavelet models. IEEE Transactions on Acoustics, Speech, and Signal Processing 1989, 37(12):2091-2110.
[4] Vetterli M, Herley C: Wavelets and filter banks: Theory and design. IEEE transactions on signal processing 1992, 40(ARTICLE):2207-2232.
[5] Zhang Y-D, Wu L: An MR brain images classifier via principal component analysis and kernel support vector machine. Progress In Electromagnetics Research 2012, 130:369-388.
[6] Cho W, Chung D, Wu Y, Jeon J: Disease Edge detection of medical CT image using digital wavelet filter. In: 2018 International Conference on Advanced Control, Automation and Artificial Intelligence (ACAAI 2018): 2018: Atlantis Press; 2018.
[7] Cho W, Jeon J: Edge detection in wavelet transform domain. In: 2015 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV): 2015: IEEE; 2015: 1-4.
[8] Shehu A, Hulaj A, Bajrami X: An algorithm for edge detection of the image for application in WSN. In: International Conference on Applied Physics, System Science and Computers: 2017: Springer; 2017: 207-213.
[9] Bin L, Yeganeh MS: Comparison for image edge detection algorithms. IOSR Journal of Computer Engineering 2012, 2(6):1-4.
[10] Solomon C, Breckon T: Fundamentals of Digital Image Processing: A practical approach with examples in Matlab: John Wiley & Sons; 2011.
[11] Huertas A, Medioni G: Detection of intensity changes with subpixel accuracy using Laplacian-Gaussian masks. IEEE Transactions on Pattern Analysis and Machine Intelligence 1986(5):651-664.
[12] Adams JG, Melhem E: Clinical usefulness of T2-weighted fluid-attenuated inversion recovery MR imaging of the CNS. AJR American journal of roentgenology 1999, 172(2):529-536.
[13] Souplet J-C, Lebrun C, Ayache N, Malandain G: An automatic segmentation of T2-FLAIR multiple sclerosis lesions. In: MICCAI-Multiple sclerosis lesion segmentation challenge workshop: 2008; 2008.
[14] Comelli A, Stefano A, Bignardi S, Russo G, Sabini MG, Ippolito M, Barone S, Yezzi A: Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography. Artificial intelligence in medicine 2019, 94:67-78.
[15] Rueckert D, Schnabel JA: Medical image registration. In: Biomedical image processing. edn.: Springer; 2010: 131-154.
[16] Grunert P, Darabi K, Espinosa J, Filippi R: Computer-aided navigation in neurosurgery. Neurosurgical review 2003, 26(2):73-99.
