Medical Image Segmentation Based Image Compression with Secure Cloud Data Storage

Abstract

Scanning rates and distinction rates in imaging equipment have been considerably improved with the development of CT, MRI, EBCT, SMRI, etc. Medical images may be extensively processed using compression techniques to the benefit of the image information and to improve the diagnosis, by means of de noises, enhancements, edge extraction, etc . Since medical images are available in digital format, the technology is to produce more time-saving and cost-effective image compression to minimise the volume of image data. This article aims at proposing a novel approach for compression of the images, which is processed in different sequences. Here Preprocessing is performed by contrast Curvature based shearlet filter with Contrast Limited Golay Histogram Equalization is used. After the pre- processing process is the image segmentation and is handled by Adaptive Contour in depth watershed segmentation Model (ACIWS), which divides or segments the image into two regions: ROI (Region of Interest) and non ROI. In this, the wavelet iterative cuckoo herd optimization algorithm for compressing the ROI and Non ROI regions . Then the image can be securely stored in a cloud by using crack tetrolet elgamal algorithm. Subsequently, the compressed image is subjected for image decompression, which will be the reverse process of compression. Finally, the original image is attained precisely. The whole experimentation can carried out in a 3DIRCADB public available liver cancer dataset. The simulations were run in the MATLAB simulation environment and included metrics for both the proposed and current protocols. It is obvious from the comparison that the present mechanism performs poorly when compared to the suggested method.