2026-05-28T22:45:45Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/163212026-02-03T11:15:56Zcom_10630_2254col_10630_37953

Super-resolution of 3D Magnetic Resonance Images by Random Shifting and Convolutional Neural Networks Thurnhofer Hemsi, Karl López-Rubio, Ezequiel Roé-Vellvé, Núria Domínguez-Merino, Enrique Molina-Cabello, Miguel Ángel Redes neuronales (Informática) Enhancing resolution is a permanent goal in magnetic resonance (MR) imaging, in order to keep improving diagnostic capability and registration methods. Super-resolution (SR) techniques are applied at the postprocessing stage, and their use and development have progressively increased during the last years. In particular, example-based methods have been mostly proposed in recent state-of-the-art works. In this paper, a combination of a deep-learning SR system and a random shifting technique to improve the quality of MR images is proposed, implemented and tested. The model was compared to four competitors: cubic spline interpolation, non-local means upsampling, low-rank total variation and a three-dimensional convolutional neural network trained with patches of HR brain images (SRCNN3D). The newly proposed method showed better results in Peak Signal-to-Noise Ratio, Structural Similarity index, and Bhattacharyya coefficient. Computation times were at the same level as those of these up-to-date methods. When applied to downsampled MR structural T1 images, the new method also yielded better qualitative results, both in the restored images and in the images of residuals. 2018-07-20T09:56:27Z 2018-07-20T09:56:27Z 2018 journal article https://hdl.handle.net/10630/16321 eng 2018 IEEE World Congress on Computational Intelligence Río de Janeiro, Brasil Julio de 2018 open access IEEE