Wavelet octave energy for breast tumor classification on sonography : A new shape feature

Infiltrative nature of lesions is a significant feature of malignant breast lesion in ultrasound images. Characterizing infiltrative nature is crucial for the realization of computer-aided diagnosis system. In this study, the infiltrative nature is regarded as an energy that produces irregularly and considerably local variances in a 1D signal. The local variances can be enhanced by few high octave energies in 1D discrete periodized wavelet transform (DPWT). A test dataset of breast sonograms with the lesion contour delineated by an experienced physician and two inexperienced students are built for feature efficacy evaluation. A high individual performance result implies that the proposed feature is well correlated with radiologist's perception and closer to match those in trained physician than morphometric parameters. Experimental results also reveal that with a great performance improvement, the proposed feature is suitable for the combination with some morphometric parameters.