Classification and performance of denoising algorithms for low signal-to-noise ratio magnetic resonance images

2000 ◽  
Author(s):  
Wilfred L. Rosenbaum ◽  
M. Stella Atkins ◽  
Gordon E. Sarty
Keyword(s):  
Magnetic Resonance ◽  
Signal To Noise Ratio ◽  
Magnetic Resonance Images ◽  
Signal To Noise ◽  
Noise Ratio ◽  
And Performance

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

2021 ◽  
Vol 10 (6) ◽  
pp. 205846012110239
Author(s):  
Nobuo Kashiwagi ◽  
Hisashi Tanaka ◽  
Yuichi Yamashita ◽  
Hiroto Takahashi ◽  
Yoshimori Kassai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Image Quality ◽  
Signal To Noise Ratio ◽  
Magnetic Resonance Images ◽  
Reconstruction Method ◽  
Signal To Noise ◽  
Scanning Time ◽  
Noise Ratio ◽  
Weighted Sequences

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.

Estimation of sufficient signal to noise ratio for texture analysis of magnetic resonance images

2011 ◽  
Author(s):  
Sami Savio ◽  
Lara Harrison ◽  
Pertti Ryymin ◽  
Prasun Dastidar ◽  
Seppo Soimakallio ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Texture Analysis ◽  
Signal To Noise Ratio ◽  
Magnetic Resonance Images ◽  
Signal To Noise ◽  
Noise Ratio

Artificial Intelligence based myelinated white Matter Segmentation for a Pediatricbrain –a Challenging Task

2020 ◽  
Vol 13 ◽  
Author(s):  
S. Jacily Jemila ◽  
A. Brintha Therese
Keyword(s):  
Artificial Intelligence ◽  
White Matter ◽  
Magnetic Resonance ◽  
Signal To Noise Ratio ◽  
Medical Image Analysis ◽  
Magnetic Resonance Images ◽  
Signal To Noise ◽  
Fuzzy C Means ◽  
Fuzzy C Means Clustering ◽  
Noise Ratio

Background: Segmentation of a baby brain,in particular myelinated white matter is a very challenging and important task in medical image analysis, because of the ongoing process of myelination and structural differences present in magnetic resonance images of a baby. Most available algorithms for segmentation of a baby brain are atlas based segmentations, which may not accurate because baby brain Magnetic Resonance Images (MRI) are very subjective. Objective: Artificial intelligence based methods for myelinated white matter segmentation. Method: Fuzzy C-means Clustering with Level Set Method (FCMLSM), Adaptively Regularized Kernel-based Fuzzy C-means clustering (ARKFCM), Multiplicative Intrinsic Component Optimization (MICO) and Particle Swarm Optimization (PSO). Results: Signal to Noise Ratio (SNR), Edge Preservation Index (EPI), Structural Similarity Index (SSIM) and Peak Signal to noise Ratio (PSNR) Accuracy, Precision, Dice and Jaccard values are maintained good and Mean squared error (MSE) is less for FCMLSM. Conclusion: FCMLSM is a very suitable method for myelinated white matter segmentation when compared to ARKFCM, MICO and PSO.

scholarly journals Accuracy of Signal-to-noise Ratio Measurement Method for Magnetic Resonance Images

2003 ◽  
Vol 59 (4) ◽  
pp. 508-513 ◽  
Author(s):  
AKIO OGURA ◽  
AKIRA MIYAI ◽  
FUMIE MAEDA ◽  
HIROYUKI FUKUTAKE ◽  
RIKIYA KIKUMOTO
Keyword(s):  
Magnetic Resonance ◽  
Measurement Method ◽  
Signal To Noise Ratio ◽  
Magnetic Resonance Images ◽  
Signal To Noise ◽  
Ratio Measurement ◽  
Noise Ratio
Sign in / Sign up

Export Citation Format

Share Document