Background, Motivation and Objective Compressive sensing (CS) is a recent theory allowing the recovery of a signal sampled below the limit set by Shannon's theorem. The application of CS to medical ultrasound (US) imaging is a very recent field and the few existing studies mostly focus on fixed sparsifying transforms. In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries. Such dictionaries allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images