An optimized medical image compression algorithm based on wavelet transform and improved vector quantization is introduced. The goal of the proposed method is to maintain the diagnostic-related information of the medical image at a high compression ratio. Wavelet transformation was first applied to the image. For the lowest-frequency subband of wavelet coefficients, a lossless compression method was exploited; for each of the high-frequency subbands, an optimized vector quantization with variable block size was implemented. In the novel vector quantization method, local fractal dimension (LFD) was used to analyze the local complexity of each wavelet coefficients, subband. Then an optimal quadtree method was employed to partition each wavelet coefficients, subband into several sizes of subblocks. After that, a modified K-means approach which is based on energy function was used in the codebook training phase. At last, vector quantization coding was implemented in different types of sub-blocks. In order to verify the effectiveness of the proposed algorithm, JPEG, JPEG2000, and fractal coding approach were chosen as contrast algorithms. Experimental results show that the proposed method can improve the compression performance and can achieve a balance between the compression ratio and the image visual quality. 1. Introduction With the rapid development of modern medical industry, medical images play an important role in accurate diagnosis by physicians. However, the large amount of images put forward a high demand on the capacity of the storage devices. Besides, telemedicine is a development trend of medical industry, while narrow transmission bandwidth limits the development of this project. To solve the problems mentioned above, a large number of researches have been carried out into medical image compression. Medical image compression approaches can simply be divided into two kinds: lossless compression and lossy compression. Lossless compression can reconstruct the original image completely identical. Lossy compression takes advantage of the human weak psychovisual effects to optimize compression results but loses certain image information [1]. Lossless coding method like them Huffman coding [2], LZW [3], arithmetic coding [4], and some other improved methods [5] can code an image and decode it with perfect result. However, such methods can only obtain a low compression ratio around 1 to 4; a higher compression ratio is hard to obtain. Although physicians and scientists prefer to work with uncorrupted data, the modest compression offered by lossless
References
[1]
T. H. Oh, H. S. Lim, and S. Y. Pang, “Medical image processing: from lossless to lossy compression,” in Proceedings of the IEEE Region 10 Conference (TENCON '05), pp. 1–6, November 2005.
[2]
D. A. Huffman, “A method for the construction of minimum-redundancy codes,” Proceedings of the IRE, vol. 40, no. 9, pp. 1098–1101, 1952.
[3]
T. A. Welch, “A technique for high performance data compression,” Computer, vol. 17, no. 6, pp. 8–19, 1984.
[4]
G. G. Langdon and J. Rissanen, “Compression of black-white images with arithmetic coding,” IEEE Transactions on Communications Systems, vol. 29, no. 6, pp. 858–867, 1981.
[5]
Y. W. Nijim, S. D. Stearns, and W. B. Mikhael, “Differentiation applied to lossless compression of medical images,” IEEE Transactions on Medical Imaging, vol. 15, no. 4, pp. 555–559, 1996.
[6]
X. Wu and N. Memon, “Context-based, adaptive, lossless image coding,” IEEE Transactions on Communications, vol. 45, no. 4, pp. 437–444, 1997.
[7]
D. Chikouche, R. Benzid, and M. Bentoumi, “Application of the DCT and arithmetic coding to medical image compression,” in Proceedings of the 3rd International Conference on Information and Communication Technologies: from Theory to Applications (ICTTA '08), pp. 1–5, April 2008.
[8]
K. P. Wong, “Fractal image coding for emission tomographic image compression,” in Proceedings of the IEEE Nuclear Science Symposium Conference Record, vol. 3, pp. 1376–1379, November 2001.
[9]
G. Tu, D. Liu, and C. Zhang, “A new compression algorithm for medical images using wavelet transform,” in Proceedings of the IEEE Networking, Sensing and Control (ICNSC '05), pp. 84–89, March 2005.
[10]
D. B. H. Tay, “Integer wavelet transform for medical image compression,” in Proceedings of the 7th Australian and New Zealand Intelligent Information Systems Conference (ANZIIS '01), pp. 357–360, November 2001.
[11]
A. Al-Fayadh, A. J. Hussain, P. Lisboa, D. Al-Jumeily, and M. Al-Jumaily, “A hybrid image compression method and its application to medical images,” in Proceedings of the 2nd International Conference on Developments in eSystems Engineering (DeSE '09), pp. 107–112, December 2009.
[12]
K. B. Kim, S. Kim, and G. H. Kim, “Vector quantizer of medical image using wavelet transform and enhanced SOM algorithm,” Neural Computing and Applications, vol. 15, no. 3-4, pp. 245–251, 2006.
[13]
N. M. H. Tayarani, A. P. Bennett, M. Beheshti, et al., “A novel initialization for quantum evolutionary algorithms based on spatial correlation in images for fractal image compression,” in Proceedings of the Soft Computing in Industrial Applications, pp. 317–325, 2011.
[14]
D. Zümray, “Compression of medical images by using artificial neural networks,” in Proceedings of the Intelligent Computing, vol. 4113 of Lecture Notes in Computer Science, pp. 337–344, 2006.
[15]
J. M. Shapiro, “Embedded image coding using zerotrees of wavelet coefficients,” IEEE Transactions on Signal Processing, vol. 41, no. 12, pp. 3445–3462, 1993.
[16]
A. Said and W. A. Pearlman, “Image compression using the spatial-orientation tree,” in Proceedings of the IEEE International Symposium on Circuits and Systems, pp. 279–282, May 1993.
[17]
Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Transactions on Communications Systems, vol. 28, no. 1, pp. 84–95, 1980.
[18]
J. Vaisey and A. Gersho, “Image compression with variable block size segmentation,” IEEE Transactions on Signal Processing, vol. 40, no. 8, pp. 2040–2060, 1992.
[19]
O. Yamanaka, T. Yamaguchi, K. Sasazaki, J. Maeda, and Y. Suzuki, “Image compression using wavelet transform and vector quantization with variable block size,” in Proceedings of the IEEE Conference on Soft Computing on Industrial Applications (SMCia '08), pp. 359–364, June 2008.
[20]
K. Sasazaki, S. Saga, J. Maeda, and Y. Suzuki, “Vector quantization of images with variable block size,” Applied Soft Computing Journal, vol. 8, no. 1, pp. 634–645, 2008.
[21]
N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
[22]
N. Sarkar and B. B. Chauduri, “Efficient differential box-counting approach to compute fractal dimension of image,” IEEE Transactions on Systems, Man and Cybernetics, vol. 24, no. 1, pp. 115–120, 1994.
[23]
S. Peleg, J. Naor, R. Hartley, and D. Avnir, “Multiple resolution texture analysis and classification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 6, no. 4, pp. 518–523, 1984.
[24]
B. B. Mandelbrot, The Fractal Geometry of Nature, Library of Congress, 1983.
[25]
R. A. Finkel and J. L. Bentley, “Quad trees a data structure for retrieval on composite keys,” Acta Informatica, vol. 4, no. 1, pp. 1–9, 1974.
[26]
F. Keissarian, “A new quad-tree segmented image compression scheme using histogram analysis and pattern matching,” in Proceedings of the 2nd International Conference on Computer and Automation Engineering (ICCAE '10), pp. 694–698, February 2010.
[27]
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004.
[28]
D. MacKay, “An example inference task: clustering,” in Information Theory, Inference and Learning Algorithms, pp. 284–292, Cambridge University Press, 2003.
[29]
G. Hamerly and C. Elkan, “Alternatives to the k-means algorithm that find better clusterings,” in Proceedings of the 11th International Conference on Information and Knowledge Management (CIKM '02), pp. 600–607, November 2002.
