MRI brain image compression using spatial fuzzy clustering technique

Medical imaging has a great impact in the field of diagnosis and surgical planning. The coding of medical images differ from standard image coding as it incorporates the integrity of preserving the clinically critical information with reduction in storage space. Efficient image compression technique is essential to make the compact representation of the medical data. The goal of the proposed technique is to preserve the clinical useful information with significant improvement in peak signal to noise ratio (PSNR) and compression ratio. In the proposed work modified set partitioning in hierarchical tree (MSPIHT) is used to code the curvelet coefficients of the clinical region of interest (CROI) and SPIHT to code the Biorthogonal Wavelet coefficients of the background segmented with spatial fuzzy C means (sFCM) clustering. The proposed work compresses the MRI brain images with increased PSNR and provide efficient representation of edges in DICOM (Digital Imaging and Communications in Medicine) images.