Compressively Sensed Ultrasound Radio-frequency Data Reconstruction Using the Combined Curvelets and Wave Atoms Basis

In this paper, we propose a novel data reconstruction method for the compressively sensed ultrasound radio-frequency (RF) data using the combined curvelets- and wave atoms- (CCW) based orthonormal basis. Typically, the curvelets-based reconstruction better preserves the image features while the wave atoms-based reconstruction better preserves the oscillatory patterns of the typical ultrasound RF signals. We exploit the advantages from both the sparsifying bases via concatenating them where the RF reconstruction is done from the larger coefficients of the combined basis. We show that the CCW-based reconstruction method better recovers the RF oscillatory patterns as well as preserves the image features better than those of the curvelets- and wave atoms-based reconstruction methods alone. We find improvement with respect to the current methods of approximately 58% and 64% in terms of the normalized mean square error for the reconstructed synthetic phantom and in vivo RF data, respectively. We also show visual performance improvement in the B-mode images of approximately 33% and 44% in terms of the mean structural similarity for the synthetic phantom and in vivo data, respectively.