Classification of the Stages of Hyperplasia in Breast Ducts by Analyzing Different Depths and Segmentation of Ultrasound Breast Scans into Ductal Areas

In this paper, we study in depth the potential of detection of epithelium hyperplastic growth in the breast ducts leading to early breast cancer detection. Towards that end, we use a stochastic decomposition algorithm of the RF echo into its coherent and diffuse components that yields image parameters related to the structural parameters of the hyperplastic stages of the breast tissue. Previously, we proved that the two parameters, in particular the number of coherent scatterers and the Rayleigh scattering degree show very high ability to discriminate between various stages of hyperplasia even in cases of low resolution and low SNR values. In this paper, the discrimination power of the other parameters is studied further considering different depths using a point scatterer model simulator that mimics epithelium hyperplastic growth in the breast ducts. Significant improvement is obtained in the performance with the newly adopted method considering depth. Values of A_z up to 0.974 are obtained when discriminating between pairs of stages using the parameter residual error variance. In addition, this paper presents a fast nonparametric segmentation procedure to locate the ducts illustrated using phantom data. The performance of the segmentation procedure is obtained as Az>0.948 for various regions of breast scans