The ultimate goal of any medical image compression method is to reduce the bit rate and enhance the compression efficiency for the transmission and storage, while maintaining an acceptable diagnostic image quality. To achieve high image compression rate with acceptable quality, a partial region based compression method is applied. It is often observed that most of the medical images do contains regions of interest which play a key role in diagnosis that are to be extracted and ensure that it is reconstructed with high quality. This paper presents a deep learning approach for extracting the region of interest from MR brain images, thus obtained extracted region is applied with lossless compression method and others with lossy methods.
Volume 11 | 05-Special Issue
Pages: 2356-2367