학술논문
Neural network reconstruction of MR images from noisy and sparse k-space samples
Document Type
Conference
Author
Source
WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000 Signal processing - Beijing Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on. 3:2115-2118 vol.3 2000
Subject
Language
Abstract
This paper concerns a novel application of artificial neural networks (ANN) to magnetic resonance imaging (MRI) by considering models for solving the problem of image estimation from sparsely sampled and noisy k-space. Effective solutions to this problem are indispensable especially when dealing with MRI of dynamic phenomena since then, rapid sampling in k-space is required. It is proposed here that significant improvements could be achieved concerning image reconstruction if a procedure, based on interpolating ANNs, for estimating the missing samples of complex k-space were introduced. To this end, the viability of involving supervised neural network algorithms for such a problem is considered and it is found that their image reconstruction results are very favorably compared to the ones obtained by the trivial zero-filled k-space approach or traditional more sophisticated interpolation approaches.