Computing requirements of modern medical diagnostic ultrasound machines

Abstract

Ultrasound is one of the leading medical imaging modalities because it is safe, noninvasive, portable, easy to use, relatively inexpensive and displays images in real-time. Due to its real-time nature, an ultrasound machine must be able to process its incoming data quickly. High computational and throughput requirements in modern ultrasound machines have restricted their internal design to algorithm-specific hardware with limited programmability. Adding new ultrasound imaging applications or improving a machine's internal algorithms can require costly hardware redesigns and replacements of boards or of the entire machine. In an effort to address these problems, we have reviewed each of the essential functions in modern ultrasound machines and analyzed their computational requirements in programmable systems. These functions include dynamic downconversion, tissue signal processing, color flow processing, scan conversion, and tissue/flow decision. Our estimate of the total computing requirement to current ultrasound machines is 54.71 billion operations per second (BOPS) when transcendental functions are implemented in software and 31.26 BOPS when transcendental functions are implemented in lookup tables taking 160.26 Mbytes of memory. To investigate the feasibility of programmable generalized ultrasound systems, we have designed a flexible and parallel programmable ultrasound processing subsystem, called the Programmable Ultrasound Image Processor (PUIP). As the need for programmable ultrasound machines increases in the future due to various advantages (e.g., lower system cost, faster clinical use and lower research/development expenses), it will be crucial to develop not only a high-performance, scalable, reconfigurable parallel computer architecture meeting the computing requirement, but also efficient ultrasound algorithms that can be optimally mapped into the parallel architecture.