Classification of Breast Lesions Using Quantitative Ultrasound Biomarkers

Abstract

Quantitative ultrasound (QUS) based parameters like the effective scatterer diameter (ESD) and mean scatterer spacing (MSS) are gaining attention recently as non-invasive biomarkers for soft tissue characterization. In this work, we propose a multiple QUS parameter based technique that employs ESD and MSS, for binary classification of breast lesions. In order to produce improved ESD estimates, we propose a modified frequency domain technique for ESD estimation of breast tissues from the diffuse component of backscattered radio-frequency (RF) data. Ensemble empirical mode decomposition (EEMD) is performed to separate the diffuse component from the coherent component by decomposing the RF data into their intrinsic mode functions (IMFs). A non-parametric Kolmogorov-Smirnov (K-S) test is employed for automatic IMF selection along with a multi-step system effect minimization process. The ESD is estimated using a nearest neighborhood average regression line fitting algorithm. Furthermore, we use an ameliorated EEMD domain autoregressive (AR) spectral estimation technique for MSS estimation. On using the ESD for binary classification of 159 lesions, we obtain high sensitivity, specificity, accuracy values of 91.07%, 96.12%, and 94.34%, respectively, with an area under the receiver operating characteristics (ROC) curve of 0.94. On combining ESD with MSS we obtain even more improved sensitivity, specificity, and accuracy values of 96.43%, 95.15%, and 95.60%, respectively, with an area under the ROC of 0.96. Such a high classification performance highlights the potential of these QUS parameters to be used as non-invasive biomarkers for breast cancer detection.