Wavelet-based Image Compression and Cancer Detection

J.T. Bialasiewicz (USA)


Medical Image Processing, Image Compression, Wavelets


The research project reported in this paper consists of two parts. Part one focuses on the compression of digital medical images using wavelets. We have developed a highly efficient image compression algorithm with a high enough convergence rate of the reconstruction process. Our technique allows the compressed image representation to include only those wavelet transform coefficients that correspond to the wavelet transform modulus maxima that are determined for each resolution level. Part two of the project focuses on early cancer detection, adopting techniques developed in part one. The problem is to design a system that can enhance image features that are not visually apparent. In this project, the transient behavior of pixel intensities (that corresponds to edges and singular points) is used for image enhancement. In particular, wavelets are used to locate and characterize transients in the images. The detection of edges is realized by detecting modulus maxima in a two-dimensional dyadic wavelet transform at the proper scale. This part of the project aims at determining cancer signatures represented by image edges. The ultimate goal of our research is to provide a viable alternative in such cases when routine interpretation of CT scans is inconclusive and biopsy would be required.

Important Links:

Go Back