Pet image reconstruction using ANN-EM method

Imaging is a broad field which covers all aspects of the analysis, modification, compression, visualization, and generation of images. There are at least two major areas in imaging science in which applied mathematics has a strong impact: image processing, and image reconstruction. In image processing the input is a (digital) image such as a photograph, while in image reconstruction the input is a set of data. Image processing techniques treat an image and apply numerical algorithms to either improve the given image or to extract different features of it. Image reconstruction refers to the technique used to create an image of the interior of a body (or region) non-invasively, from data collected on its boundary. Current imaging problems deal with the image quality and the computational tools used to create the image. The performance of ANN-EM algorithm is compared with the simultaneous version of co-ordinate descent algorithm (CD) and de-noising algorithm. Algorithms are compared in terms of prediction and parameters like Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Root Mean Square Error (RMSE) and Elapsed time for the algorithms. The results shows that ANN-EM based algorithm provides better reconstructed time compared to other two techniques.