Yasuhiro Nagai's research while affiliated with National Cerebral and Cardiovascular Center and other places

Purpose: To evaluate the image quality of high-spatial-resolution two-dimensional (2D) late gadolinium enhancement (LGE) cardiac MRI compared with conventional normal-resolution LGE MRI. Materials and methods: This prospective study included participants suspected of having cardiomyopathy who underwent cardiac MRI between March 2021 and December 2021. Normal-resolution and high-resolution 2D LGE sequences (inversion recovery [IR] and phase-sensitive inversion recovery [PSIR]) were performed at 3 T. Resolution was compared between normal-resolution and high-resolution images obtained in a quality assurance phantom. In vivo image quality and resolution were evaluated qualitatively using a five-point scoring system. Receiver operating characteristic curve analysis was used for LGE detection performance. Border sharpness was assessed with profile curve measurement. The contrast-to-noise ratio (CNR) between hyperenhancement and remote myocardium and LGE detection performance were calculated using normal-resolution IR images as the reference. Results: In total, 120 participants were evaluated (mean age, 56 years ± 17 [SD]; 72 men). Features smaller than 1 mm were detectable only on high-resolution images of the phantom. In vivo, the image resolution score with high-resolution LGE was 4.14-4.24, which was higher than the normal-resolution LGE reference score of 2.99 (P < .05). Border sharpness was higher in high-resolution images (P < .001). Receiver operating characteristic curve analysis revealed no evidence of a difference in LGE detection between normal-resolution and high-resolution images. There was also no evidence of a change in CNR of LGE in IR and PSIR magnitude compared with reference images. Conclusion: Comparison of image quality in 2D high-resolution and normal-resolution LGE cardiac MRI demonstrated the highest resolution for high-resolution IR and high-resolution PSIR magnitude sequences.Keywords: Cartilage Imaging, MRI, Cardiac, Heart, Imaging Sequences, Comparative Studies Supplemental material is available for this article. © RSNA, 2022.

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.