RT Generic
T1 Supercomputación gráfica aplicada al análisis de imágenes cerebrales con niftyreg
T2 Graphycs supercomputing applied to brain image analysis with niftyreg
A1 Álvarez González, Francisco Nurudín
K1 Ingeniería biomédica
K1 Computación de altas prestaciones
K1 Diagnóstico por imagen
K1 Superordenadores
K1 Grado en Ingeniería Informática - Trabajos Fin de Grado
K1 Informática - Trabajos Fin de Grado
AB Abstract: Medical image processing in general and brain image processing inparticular are computationally intensive tasks. Luckily, their use can be liberalized bymeans of techniques such as GPU programming. In this article we study NiftyReg, abrain image processing library with a GPU implementation using CUDA, and analysedifferent possible ways of further optimising the existing codes. We will focus on fullyusing the memory hierarchy and on exploiting the computational power of the CPU. Theideas that lead us towards the different attempts to change and optimize the code willbe shown as hypotheses, which we will then test empirically using the results obtainedfrom running the application. Finally, for each set of related optimizations we will studythe validity of the obtained results in terms of both performance and the accuracy ofthe resulting images.
YR 2016
FD 2016-05-19
LK http://hdl.handle.net/10630/11431
UL http://hdl.handle.net/10630/11431
LA eng
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 4 mar 2026