Segmentation of Ultrasound Images based on Scatterer Density using U-Net

Quantitative ultrasound can provide an objective estimation of different tissue properties, which may be used for tissue characterization and detection of abnormal tissue. The effective number of scatterers in different parts of a tissue is one of the important tissue properties that can be estimated by quantitative ultrasound techniques. The envelope echo is the signal which is usually used to estimate the scatterer density. In this study, we proposed using deep learning to estimate the effective number of scatterers. We generated 2000 simulated phantom data containing randomly distributed inclusions with three different values for number of scatterers per resolution cell. We used U-Net to segment the envelope data and to distinguish three different values of scatterer densities. We show that U-Net can discriminate different scattering regimes, particularly, when the difference between the number of scatterers is substantial. The overall accuracy of the network is 83.9%, and the average sensitivity and specificity among the three classes are 83.1% and 92.3% respectively. This study confirms the potential of deep learning framework in quantitative ultrasound and estimation of tissue properties using ultrasound images.