Super-resolution of 3D Magnetic Resonance Images by Random Shifting and Convolutional Neural Networks

Abstract

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 Bhattacharrya 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.

Resolution Enhancement of Brain MRI Images Using Deep Learning

“…They recover high-resolution images from low-resolution images, providing insights into specific diseases and aiding doctors in diagnosing brain illnesses [1,2]. Interpolation methods, including reconstruction, learning, and interpolation, are used to reconstruct high-resolution images from low-resolution data [3,4]. The paper's primary objectives are:…”

Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting

“…In this work, an improved CNN model based on a testtime regularly spaced shifting technique is proposed. Other shifting techniques like random shifting have been successfully applied to increase the resolution of magnetic resonance images [29]. In this research a shifting technique with a regular displacement for the test input image is proposed.…”