Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Abstract

Background Several deep learning-based methods have been proposed for addressing the long scanning time of magnetic resonance imaging. Most are trained using brain 3T magnetic resonance images, but is unclear whether performance is affected when applying these methods to different anatomical sites and at different field strengths. Purpose To validate the denoising performance of deep learning-based reconstruction method trained by brain and knee 3T magnetic resonance images when applied to lumbar 1.5T magnetic resonance images. Material and Methods Using a 1.5T scanner, we obtained lumber T2-weighted sequences in 10 volunteers using three different scanning times: 228 s (standard), 119 s (double-fast), and 68 s (triple-fast). We compared the images obtained by the standard sequence with those obtained by the deep learning-based reconstruction-applied faster sequences. Results Signal-to-noise ratio values were significantly higher for deep learning-based reconstruction-double-fast than for standard and did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Contrast-to-noise ratio values also did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Qualitative scores for perceived signal-to-noise ratio and overall image quality were significantly higher for deep learning-based reconstruction-double fast and deep learning-based reconstruction-triple-fast than for standard. Average scores for sharpness, contrast, and structure visibility were equal to or higher for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant. The average scores for artifact were lower for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant. Conclusion The deep learning-based reconstruction method trained by 3T brain and knee images may reduce the scanning time of 1.5T lumbar magnetic resonance images by one-third without sacrificing image quality.

System Analysis of the Learning Behavior Recognition System for Students in a Law Classroom: Based on the Improved SSD Behavior Recognition Algorithm

“…e behavior recognition model design process was obtained as shown in Figure 3. [2,22,26]. e first step was to prepare student behavior images.…”

“…e knowledge is scattered and complex, lacking the complete knowledge structure system that cannot be systematically indepth learning, resulting in the teaching in class being still at the surface level of understanding. e learning e ect has not been substantially changed [2]. With the acceleration of the popularization of higher education in China, knowing how to guarantee and improve the quality of teaching and ensure the quality and scale of coordinated development is one of the main problems faced by Chinese colleges and universities.…”

Deep learning‐based reconstruction for canine brain magnetic resonance imaging could improve image quality while reducing scan time

“…[1][2][3] To obtain optimal image quality in MRI, movement reduction and long acquisition time are required. [4][5][6] These factors limit MRI efficacy, particularly in ani-mals that are prone to motion and require general anesthesia for the procedure. 1,3 Additionally, the recommended MRI slice thickness for dogs is thinner than that for humans because the canine brain is smaller than the human brain.…”

“…5,10 For image denoising, DLR removes only high-frequency components responsible for most of the noise and retains low-frequency components required for image contrast information. 4,[11][12][13] Consequently, a single neural network containing better reconstructed MR images is created regardless of the acquisition method or noise levels. 5 Therefore, this technology has a potential to reduce MRI acquisition times and improve image quality by optimizing other time-reducing techniques.…”

Impact of deep learning reconstruction on intracranial 1.5 T magnetic resonance angiography

“…Deep learning reconstruction (DLR), a new image reconstruction algorithm based on deep learning [18], is an example of this application that is now available from MRI vendors. This algorithm enables the reduction of image noise [18][19][20], which is one disadvantage of 1.5 T MRA.…”