SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks

• Published in: Tomography (Ann Arbor) Vol. 8; no. 2; pp. 905 - 919
• Main Authors: Zhang, Kuan, Hu, Haoji, Philbrick, Kenneth, Conte, Gian Marco, Sobek, Joseph D., Rouzrokh, Pouria, Erickson, Bradley J.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI 24.03.2022; MDPI AG
• Subjects: 3D perceptual loss; deep learning; generative adversarial networks (GAN); Humans; Imaging, Three-Dimensional; Magnetic Resonance Imaging; magnetic resonance imaging (MRI); medical imaging interpolation; Motion; super-resolution; magnetic resonance imaging (MRI); deep learning; medical imaging interpolation; 3D perceptual loss; super-resolution; generative adversarial networks (GAN)
• ISSN: 2379-139X; 2379-1381; 2379-139X
• DOI: 10.3390/tomography8020073

There is a growing demand for high-resolution (HR) medical images for both clinical and research applications. Image quality is inevitably traded off with acquisition time, which in turn impacts patient comfort, examination costs, dose, and motion-induced artifacts. For many image-based tasks, increasing the apparent spatial resolution in the perpendicular plane to produce multi-planar reformats or 3D images is commonly used. Single-image super-resolution (SR) is a promising technique to provide HR images based on deep learning to increase the resolution of a 2D image, but there are few reports on 3D SR. Further, perceptual loss is proposed in the literature to better capture the textural details and edges versus pixel-wise loss functions, by comparing the semantic distances in the high-dimensional feature space of a pre-trained 2D network (e.g., VGG). However, it is not clear how one should generalize it to 3D medical images, and the attendant implications are unclear. In this paper, we propose a framework called SOUP-GAN: Super-resolution Optimized Using Perceptual-tuned Generative Adversarial Network (GAN), in order to produce thinner slices (e.g., higher resolution in the ‘Z’ plane) with anti-aliasing and deblurring. The proposed method outperforms other conventional resolution-enhancement methods and previous SR work on medical images based on both qualitative and quantitative comparisons. Moreover, we examine the model in terms of its generalization for arbitrarily user-selected SR ratios and imaging modalities. Our model shows promise as a novel 3D SR interpolation technique, providing potential applications for both clinical and research applications.