Real-Time Simulation of Radiological Images Using CUDA Technology

Abstract

Radiography is nowadays a common medical exam, used for diagnosing several diseases, but has the disadvantage of exposing people to a dose of radiation. For this reason, it is important to study methods for reducing such dose. In this paper we present a digital X-ray simulation tool that simulates a radiological exam on a virtual patient. The software builds a physically-realistic radiography in real-time thanks to GPGPU programming and CUDA technology. It aims to be used in radiological departments, for testing new dose reduction procedures and training health operators. We validated the software comparing the results with real radiographic images, and we tested it on different graphic cards obtaining running times that are 35 to 250 times faster than the corresponding CPU implementation.