Title :
Wavelets for contrast enhancement of digital mammography
Author :
Laine, Andrew ; Fan, Jian ; Yang, Wuhai
Author_Institution :
Dept. of Comput. & Inf. Sci. & Eng., Florida Univ., Gainesville, FL, USA
Abstract :
Multiresolution representations provided an adaptive mechanism for the local emphasis of features of importance to mammography. In general, improvements in image contrast for multiscale image processing algorithms were superior to those obtained using existing competitive algorithms. These initial results are encouraging and suggest that wavelet based image processing algorithms could play an important role in improving the imaging performance of digital mammography. In part 2, features blended into the mammograms were "idealized" representations of the types of objects that are of primary interest to mammographers. The resultant mammographic images were appropriate for the purpose of demonstrating improved image contrast made possible by wavelet based image processing algorithms. These images were also useful for comparing multiscale wavelet based algorithms with existing image processing algorithms. The test results obtained in this study, however, cannot be directly extrapolated to clinical mammography. In addition, it is also important to study possible image artifacts introduced by new wavelet filters, which may increase the false positive rate
Keywords :
diagnostic radiography; image resolution; medical image processing; wavelet transforms; adaptive mechanism; contrast enhancement; digital mammography; false positive rate; image artifacts; image contrast; local emphasis; mammographic images; multiresolution representations; multiscale image processing algorithms; multiscale wavelet based algorithms; wavelet based image processing algorithms; wavelet filters; Breast cancer; Cancer detection; Diagnostic radiography; Diseases; Filtering; Filters; Image processing; Image resolution; Mammography; Neoplasms; Noise level; Testing;
Journal_Title :
Engineering in Medicine and Biology Magazine, IEEE