Tissue characterization using the continuous wavelet transform part II: Application on breast RF data

In the first part of this work [16], a wavelet-based decomposition algorith m of the RF echo into its coherent and diffuse components was introduced. I n this paper, the proposed algorithm is used to estimate structural paramet ers of the breast tissue such as the number and energy of coherent scattere rs, the energy of the diffuse scatterers, and the correlation between them. Based on these individual parameters, breast tissue characterization is pe rformed. The database used consists of 155 breast scans from 42 patients. T he results are presented in terms of empirical receiver operating character istics (ROC) curves. The results of this study are discussed in relation to the tissue microstructure, Individual estimated parameters are able to dif ferentiate reliably between normal and fibroadenoma or fibrocystic or cance rous tissue (area under the ROC A(z) > 0.93). Also, the differentiation bet ween malignant and benign (normal, fibrocystic, and fibroadenoma) tissue wa s possible (A(z) > 0.89).