Generative adversarial network-based post-processed image super-resolution technology for accelerating brain MRI: comparison with compressed sensing

Abstract

Background It is unclear whether deep-learning–based super-resolution technology (SR) or compressed sensing technology (CS) can accelerate magnetic resonance imaging (MRI) . Purpose To compare SR accelerated images with CS images regarding the image similarity to reference 2D- and 3D gradient-echo sequence (GRE) brain MRI. Material and Methods We prospectively acquired 1.3× and 2.0× faster 2D and 3D GRE images of 20 volunteers from the reference time by reducing the matrix size or increasing the CS factor. For SR, we trained the generative adversarial network (GAN), upscaling the low-resolution images to the reference images with twofold cross-validation. We compared the structural similarity (SSIM) index of accelerated images to the reference image. The rate of incorrect answers of a radiologist discriminating faster and reference image was used as a subjective image similarity (ISM) index. Results The SR demonstrated significantly higher SSIM than the CS (SSIM=0.9993–0.999 vs. 0.9947–0.9986; P < 0.001). In 2D GRE, it was challenging to discriminate the SR image from the reference image, compared to the CS (ISM index 40% vs. 17.5% in 1.3×; P = 0.039 and 17.5% vs. 2.5% in 2.0×; P = 0.034). In 3D GRE, the CS revealed a significantly higher ISM index than the SR (22.5% vs. 2.5%; P = 0.011) in 2.0 × faster images. However, the ISM index was identical for the 2.0× CS and 1.3× SR (22.5% vs. 27.5%; P = 0.62) with comparable time costs. Conclusion The GAN-based SR outperformed CS in image similarity with 2D GRE for MRI acceleration. In addition, CS was more advantageous in 3D GRE than SR.

ICRICS: Iterative Compensation Recovery for Image Compressive Sensing

“…Y. Harada et al employ K-SVD dictionary learning to improve image quality for capsule endoscopy based on compressed sensing [59]. W. Ueki et al adopted generative adversarial network-based image superresolution for accelerating brain magnetic resonance imaging [60]. C.J.…”

“…The advanced transformer structure in deep learning has also been considered for image compressive sensing [56][57][58]. Third, some methods, such as dictionary learning, super resolution, denoising, optimization and regularization, are utilized to upgrade the rebuilding capacity of image compressive sensing [59][60][61][62][63]. Y. Harada et al employ K-SVD dictionary learning to improve image quality for capsule endoscopy based on compressed sensing [59].…”

Comparison Between a Modified Fast 3-Dimensional Turbo Spin-Echo and Diffusion-Weighted Imaging With Background Suppression in Evaluation of Lumbosacral Plexus and Its Branches

“…7 By using compressed sensing (CS) technology, fast 3D NerveVIEW (Philips Healthcare, Best, the Netherlands) is a newly developed fast sequence for data acquisition and signal recovery. 9,10 Numerous studies [11][12][13] have shown that CS can efficiently accelerate magnetic resonance imaging (MRI) scans in various parts of the body. However, its usage in combination with MRN in the lumbosacral plexus has never been reported so far.…”