Abstract

Image processing techniques are used to extract meaningful information from medical images. A major concern in de-noising low-field MR brain images is the poor quality images secondary to a worsening signal-to-noise ratio (SNR) compared with the high-field MRI scanners. Low-field Magnetic Resonance Imaging (MRI) is vital in sensitive surgeries to allow real-time imaging in the operation theatre. Since low-field MRI uses low strength electromagnetic fields, noisy low resolution images are produced. In contrast, high-field MRI machines (approximately 7T) are able to produce clear detailed images with almost no noise at all. Considering the above, it is required to enhance the low-field images, so that the same conventional and high-field MRI processing techniques and applications could be applied to pre-processed low-field MRI images. In this paper, pre-processing steps are applied to low-field MR brain images for improving quality of the image.

References

• U. Vovk, F. Pernu, B. Likar, “Simultaneous correlation of intensity inhomogeneity inmultichannel MR images”, 27th Annual Conf. Engineering in Medicine and Biology, pp. 4290-4293, 2005.
• N.I. Weisenfeld, S.K. Warfield, “Normalization of joint image-intensity statistics in MRI using the Kullback-Leibler divergence”, IEEE Symposium on Biomedical Imaging : Nano to Macro, vol. 1, pp. 101-104, 2004.
• A. Madabhushi, J.K. Udupa, “Interplay between intensity standardization and inhomogeneity correction in MR image processing”, IEEE Trans. on Medical Imaging, vol. 24, pp. 561-576, 2005.
• U. Vovk, F. Pernus, B. Likar, “A review of methods for correction of intensity inhomogeneity in MRI”, IEEE Trans. on Medical Imaging, vol. 26, pp. 405-421, 2007.
• Y.L. Liao, N.T. Chiu, C.M. Weng, Y.N. Sun, “Registration and normalization techniques for assessing brain functional images”, Biomedical Engineering Applications, Basis & Communications, 2003.
• J.G. Park, T. Jeong, C. Lee, “Automated brain segmentation algorithm for 3D magnetic resonance brain images”, 2nd Intl. Workshop on Soft Computing Applications (SOFA), pp. 57-61, 2007.
• Majos C, Julia-Sape M, Alonso J, Serrallonga M, Aguilera C, Juan J, Gilli J. Brain tumor classification by proton MR spectroscopy:Comparison of diagnostic accuracy at short andlong TE. AJNR 2004;25:1696-704.
• Li G, Yang J, Ye C, Geng D. Degree prediction of malignancy in brain glioma using support vector machines. Computers in Biology and Medicine 2006;36:313-25.
• Messen W, Wehrens R, Buydens L. Supervised Kohonen networks for classification problems. Chemometrics and Intelligent Laboratory Systems 2006;83:99-113.
• Chaplot S, Patnaik M, Jagannathan N. Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network.Biomedical Signal Processing and Control 2006;1:86-92.
• Luts J, Heerschap A, Johan A, Huffel S. A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection. Artificial Intelligence in Medicine 2007;40:87-102.