This paper proposes an idea to compress and decompress an ultrasound image with better reconstruction when compared to the existing systems by using the data-driven threshold for image denoising via wavelet soft-threshold and Bayesshrink algorithm. The threshold is derived in a Bayesian framework. The Wavelet transform is capable of providing the time and frequency information simultaneously. So that it enables the easy application of algorithms for compression and decompression. The reason for choosing an ultrasound image is that they are complex in resolution. This proposed technique achieves high PSNR (Peak Signal to Noise Ratio) and a low MSE (Mean Squared Error), when compared to the existing systems.Thus the experimental result shows that the proposed compression method does indeed remove noise significantly.