Hybrid deep-learning-based denoising method for compressed sensing in pituitary MRI: comparison with the conventional wavelet-based denoising method.

OBJECTIVES: This study aimed to evaluate the efficacy of a combined wavelet and deep-learning reconstruction (DLR) method for under-sampled pituitary MRI. METHODS: This retrospective study included 28 consecutive patients who underwent under-sampled pituitary T2-weighted images (T2WI). Images were reconstructed using either the conventional wavelet denoising method (wavelet method) or the wavelet and DLR methods combined (hybrid DLR method) at five denoising levels. The signal-to-noise ratio (SNR) of the CSF, hypothalamic, and pituitary images and the contrast between structures were compared between the two image types. Noise quality, contrast, sharpness, artifacts, and overall image quality were evaluated by two board-certified radiologists. The quantitative and the qualitative analyses were performed with robust two-way repeated analyses of variance. RESULTS: Using the hybrid DLR method, the SNR of the CSF progressively increased as denoising levels increased. By contrast, with the wavelet method, the SNR of the CSF, hypothalamus, and pituitary did not increase at higher denoising levels. There was a significant main effect of denoising methods (p < 0.001) and denoising levels (p < 0.001), and an interaction between denoising methods and denoising levels (p < 0.001). For all five qualitative scores, there was a significant main effect of denoising methods (p < 0.001) and an interaction between denoising methods and denoising levels (p < 0.001). CONCLUSIONS: The hybrid DLR method can provide higher image quality for T2WI of the pituitary with compressed sensing (CS) than the wavelet method alone, especially at higher denoising levels. KEY POINTS: • The signal-to-noise ratios of cerebrospinal fluid progressively increased with the hybrid DLR method, with an increase in the denoising level for cerebrospinal fluid in pituitary T2WI with CS. • The signal-to-noise ratios of cerebrospinal fluid using the conventional wavelet method did not increase at higher denoising levels. • All qualitative scores of hybrid deep-learning reconstructions at all denoising levels were higher than those for the wavelet denoising method.

Effects of Deep Learning Reconstruction Technique in High-Resolution Non-contrast Magnetic Resonance Coronary Angiography at a 3-Tesla Machine.

PURPOSE: To evaluate the effects of deep learning reconstruction (DLR) in qualitative and quantitative image quality of non-contrast magnetic resonance coronary angiography (MRCA). METHODS: Ten healthy volunteers underwent conventional MRCA (C-MRCA) and high-resolution (HR) MRCA on a 3T magnetic resonance imaging with a voxel size of 1.8 × 1.1 × 1.7 mm3 and 1.8 × 0.6 × 1.0 mm3, respectively, for C-MRCA and HR-MRCA. High-resolution magnetic resonance coronary angiography was also reconstructed with the DLR technique (DLR-HR-MRCA). We compared the contrast-to-noise ratio (CNR) and visual evaluation scores for vessel sharpness and traceability of proximal and distal coronary vessels on a 4-point scale among 3 image series. RESULTS: The vascular CNR value on the C-MRCA and the DLR-HR-MRCA was significantly higher than that on the HR-MRCA in the proximal and distal coronary arteries (13.9 ± 6.4, 11.3 ± 4.4, and 7.8 ± 2.6 for C-MRCA, DLR-HR-MRCA, and HR-MRCA, P < .05, respectively). Mean visual evaluation scores for the vessel sharpness and traceability of proximal and distal coronary vessels were significantly higher on the HR-DLR-MRCA than the C-MRCA (P < .05, respectively). CONCLUSION: Deep learning reconstruction significantly improved the CNR of coronary arteries on HR-MRCA, resulting in both higher visual image quality and better vessel traceability compared with C-MRCA.

Effect of the Surrounding Magnetic Environment of Temporal Bone on the Fluid Signal Intensity in Human Inner Ear Using a Combined T2 Preparation Pulse and Fluid Attenuated Inversion Pulse Technique.

PURPOSE: Recently, the utility of non-contrast MR endolymphatic hydrops imaging was reported, but the pitfall was indicated based on T2 preparation pulse sensitiveness to local static magnetic field (B0) inhomogeneity. The purpose of this study is to clarify the effects of surrounding magnetic environment of temporal bone to lymphatic fluid signal intensity on the T2 preparation and fluid attenuated inversion recovery pulse combination (T2prep 3D-FLAIR) technique in human inner ear study. METHODS: We prepared a custom-made phantom comprising a chicken leg bone submersed in saline. To evaluate signal characteristics of saline close to bone, multiple TE gradient echoes, T2 relaxation time measurement, and T2prep 3D-FLAIR image were acquired. In the vicinity of the vestibule of a healthy volunteer, similar examinations were executed. Additionally, to investigate the influence of the magnetic environment from B0, the evaluation was performed in five head position settings relative to B0. RESULTS: In both the phantom case and volunteer case, together with T2 star signal intensity attenuation, T2 relaxation time shortening was observed on fluid around bone. Specifically, at the outer edge in the vestibule and cochlea of the volunteer, T2 relaxation time was shorter than that of center of vestibule and that of cochlea. In the T2prep 3D-FLAIR image, higher signal intensity was observed at the same location on the outer edge of them. These results showed that bone affects surrounding fluid magnetic environment. Also, for B0 influence, despite a large area variation ratio, there is no statistically significant difference correlated to orientation within B0. CONCLUSION: The surrounding magnetic environment of the temporal bone affects lymphatic fluid signals of the peripheral part of the human inner ear on T2prep 3D-FLAIR technique.