Image compression addresses the problem of reducing the amount of data required to present a digital image with acceptable image quality. The underlying basis of the reduction process is the removal of redundant data. Medical image compression plays a key role as healthcare industry move towards filmless imaging and goes completely digital. The problem of medical image compression is a continuing research field and most of the researches being proposed concentrate either on developing a new technique or enhance the existing techniques. The medical community has been reluctant to adopt lossless methods for image compression. The main goal has been to produce an exact replica of the original image, suffering high file size. Only recently, attention to use lossy image compression, which maximizes compression while maintaining clinical relevance data, has been probed. Four solutions to answer the above problem statement have been selected, namely, Block Truncation Coding (BTC), Discrete Cosine Transformation (DCT), Discrete Wavelet Transformation (DWT) and Singular Value Decomposition (SVD) were selected because of their predominant place in general image processing field. Various experiments were conducted to analyze the performance of the four image compression models on medical image compression.