A Wavelet-packet-based approach for breast cancer classification.

In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We observed that the proposed method improves the detection accuracy of Architectural Distortion disease compared to previous works and also is very effective for diagnosis of Spiculated Mass and MISC diseases.