An Efficient Hybrid Filtering Method for Noise and Artifacts Removal in Effective Medical Image Segmentation

S. Karthikeyan, V. V. Gomathi, H. Hemalatha

Abstract


Medical imaging technology is becoming a key element for accurate diagnosis in medical domain. Noise and artifacts are the biggest obstacles in processing the medical images.  Medical image pre-processing is a challenging task in the Computer-aided Diagnostic systems. It is very significant, particularly in tumor region segmentation and identification. The exact tumor segmentation is possible if the image is preprocessed accurately. In this paper, we propose a novel Hybrid Filtering method by the combination of wavelet filtering and curvelet filtering technique to reduce the noise and artifacts in Computer Tomography images for effective segmentation.  The performances of Hybrid filtering method is evaluated by using various quantitative measures. It has been found that the Hybrid filtering method performs well in terms of performance metrics, visual quality and also reduces the over segmentation in accurate tumor identification.


Keywords


Artifact, Computer tomography, Curvelet Filter, Hybrid Filter, Noise, Segmentation, Wavelet Filter

Full Text:

PDF

References


Gurmeet Kaur and Rupinder Kaur, “Image De-Noising using Wavelet Transform and Various Filters” , International Journal of Research in Computer Science, vol. 2, no.2, pp.15-21, 2012.

Woods J. and Kim J, “Image identification and restoration in the sub band domain”, In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 1992, San Francisco, vol.3, pp. 297-300,1992.

Bahareh Shalchian, Hossein Rajabi, and Hamid Soltanian-Zadeh, “Assessment of the Wavelet Transform in Reduction of Noise from Simulated PET Images”, Journal of Nuclear Medicine Technology, vol.37, no.4, pp.223–228, 2009.

Priti Naik and Shalini Bhatia, “Image Denoising Using Curvelet Transform”, In Proceedings of SPIT-IEEE Colloquium and International Conference, Mumbai, India, vol. 1, pp.116-120, 2007.

Kingsbury N, “Complex wavelets for shift invariant analysis and altering of signals”, Applied and Computational Harmonic Analysis, vol.10, no.3, pp. 234-253, 2001.

Rammohan, T. and Sankaranarayanan, K, “An Advanced Curvelet Transform Based Image Compression using Dead Zone Quantization”, European Journal of Scientific Research, vol.79,no.4, pp.486-496,2012.

The Role of PET/CT in Radiation Treatment Planning for Cancer Patient Treatment, International Atomic Energy Agency, ISBN: 978-92-0-110408-3, 2008.

Guangming Zhang, Zhiming Cui1, Jianming Chen and Jian Wu, “CT Image De-noising Model Based on Independent Component Analysis and Curvelet Transform”, Journal of Software, vol. 5, no.9, pp.1006-1013,2012.

Jiang Taoa and Zhao Xinb, “Research And Application of Image Denoising Method Based on Curvelet Transform”, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Beijing, vol. 37, Part B, pp.363-368, 2008.

Jianwei Ma and Gerlind Plonka., “The Curvelet Transform”, IEEE Signal Processing Magazine, vol.27, no.2, pp.118-133, 2010.

Kim-Han Thung, Paramesran Raveendran and Chern-Loon Lim,”Content-based image quality metric using similarity measure of moment vectors”, Pattern Recognition , vol.45,no.6, pp.2193-2204,2012.

Kim-Han Thung and Paramesran Raveendran, “A Survey of Image Quality Measures”, In Proceeding of the International Conference for Technical Postgraduates(TECHPOS), pp.1-4, 2009.




DOI (PDF): https://doi.org/10.24203/ajcis.v4i1.3622.g1912

Refbacks

  • There are currently no refbacks.