干旱区生态环境知识资源中心(Arid): A Deep Learning Approach to Upscaling Low-Quality MR Images: An In Silico Comparison Study Based on the UNet Framework

Arid

DOI	10.3390/app122211758
	A Deep Learning Approach to Upscaling Low-Quality MR Images: An In Silico Comparison Study Based on the UNet Framework
	Sharma, Rishabh; Tsiamyrtzis, Panagiotis; Webb, Andrew G.; Seimenis, Ioannis; Loukas, Constantinos; Leiss, Ernst; Tsekos, Nikolaos, V
通讯作者	Tsekos, N
来源期刊	APPLIED SCIENCES-BASEL
EISSN	2076-3417
出版年	2022
卷号	12 期号:22
英文摘要	MR scans of low-gamma X-nuclei, low-concentration metabolites, or standard imaging at very low field entail a challenging tradeoff between resolution, signal-to-noise, and acquisition duration. Deep learning (DL) techniques, such as UNets, can potentially be used to improve such low-quality (LQ) images. We investigate three UNets for upscaling LQ MRI: dense (DUNet), robust (RUNet), and anisotropic (AUNet). These were evaluated for two acquisition scenarios. In the same-subject High-Quality Complementary Priors (HQCP) scenario, an LQ and a high quality (HQ) image are collected and both LQ and HQ were inputs to the UNets. In the No Complementary Priors (NoCP) scenario, only the LQ images are collected and used as the sole input to the UNets. To address the lack of same-subject LQ and HQ images, we added data from the OASIS-1 database. The UNets were tested in upscaling 1/8, 1/4, and 1/2 undersampled images for both scenarios. As manifested by non-statically significant differences of matrices, also supported by subjective observation, the three UNets upscaled images equally well. This was in contrast to mixed effects statistics that clearly illustrated significant differences. Observations suggest that the detailed architecture of these UNets may not play a critical role. As expected, HQCP substantially improves upscaling with any of the UNets. The outcomes support the notion that DL methods may have merit as an integral part of integrated holistic approaches in advancing special MRI acquisitions; however, primary attention should be paid to the foundational step of such approaches, i.e., the actual data collected.
英文关键词	upscaling MRI mixed effects model deep learning with-prior upscaling without-prior upscaling
类型	Article
语种	英语
开放获取类型	Green Published, gold
收录类别	SCI-E
WOS记录号	WOS:000887053600001
WOS关键词	SUPERRESOLUTION ; NOISE ; RECONSTRUCTION ; RESOLUTION ; NETWORK
WOS类目	Chemistry, Multidisciplinary ; Engineering, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/391871
推荐引用方式 GB/T 7714	Sharma, Rishabh,Tsiamyrtzis, Panagiotis,Webb, Andrew G.,et al. A Deep Learning Approach to Upscaling Low-Quality MR Images: An In Silico Comparison Study Based on the UNet Framework[J],2022,12(22).
APA	Sharma, Rishabh.,Tsiamyrtzis, Panagiotis.,Webb, Andrew G..,Seimenis, Ioannis.,Loukas, Constantinos.,...&Tsekos, Nikolaos, V.(2022).A Deep Learning Approach to Upscaling Low-Quality MR Images: An In Silico Comparison Study Based on the UNet Framework.APPLIED SCIENCES-BASEL,12(22).
MLA	Sharma, Rishabh,et al."A Deep Learning Approach to Upscaling Low-Quality MR Images: An In Silico Comparison Study Based on the UNet Framework".APPLIED SCIENCES-BASEL 12.22(2022).