Lossless Compression of Medical Images for Better Diagnosis

Region of interest (ROI) based image compression is an intelligent technique in medical image storage and classification applications. A combination of both lossless and lossy compression methods are used for such application. Many wavelet transform derived techniques are proposed in this regard. Embedded zero-tree wavelet (EZW) is among them which is simple and efficient. In this paper, MRI medical images are considered for compression and ROI based image compression is reported. The results reported good image quality in terms of several metrics. Also the comparison of lossless compression using two different wavelets is made possible to analyse the performance of each technique.