A high performance parallel approach to medial imaging

Research into medical imaging using general-purpose parallel-processing architectures is described, and a review of the performance of previous medical imaging machines is provided. Results demonstrating that general-purpose parallel architectures can achieve performance comparable to that of other specialized medical imaging machine architectures are presented. A back-to-front hidden-surface removal algorithm is described. It is shown that computational savings can be obtained by using the modified back-to-front hidden-surface removal algorithm. Performance figures for forming a full-scale medical image on a mesh interconnected multiprocessor are presented.<
>