干旱区生态环境知识资源中心(Arid): Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI

Arid

DOI	10.1007/s10278-024-01205-8
	Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI
	Javadi, Mohammad; Sharma, Rishabh; Tsiamyrtzis, Panagiotis; Webb, Andrew G.; Leiss, Ernst; Tsekos, Nikolaos V.
通讯作者	Tsekos, NV
来源期刊	JOURNAL OF IMAGING INFORMATICS IN MEDICINE
ISSN	2948-2925
EISSN	2948-2933
出版年	2024
英文摘要	Adversarial training has attracted much attention in enhancing the visual realism of images, but its efficacy in clinical imaging has not yet been explored. This work investigated adversarial training in a clinical context, by training 206 networks on the OASIS-1 dataset for improving low-resolution and low signal-to-noise ratio (SNR) magnetic resonance images. Each network corresponded to a different combination of perceptual and adversarial loss weights and distinct learning rate values. For each perceptual loss weighting, we identified its corresponding adversarial loss weighting that minimized structural disparity. Each optimally weighted adversarial loss yielded an average SSIM reduction of 1.5%. We further introduced a set of new metrics to assess other clinically relevant image features: Gradient Error (GE) to measure structural disparities; Sharpness to compute edge clarity; and Edge-Contrast Error (ECE) to quantify any distortion of the pixel distribution around edges. Including adversarial loss increased structural enhancement in visual inspection, which correlated with statistically consistent GE reductions (p-value << 0.05). This also resulted in increased Sharpness; however, the level of statistical significance was dependent on the perceptual loss weighting. Additionally, adversarial loss yielded ECE reductions for smaller perceptual loss weightings, while showing non-significant increases (p-value >> 0.05) when these weightings were higher, demonstrating that the increased Sharpness does not adversely distort the pixel distribution around the edges in the image. These studies clearly suggest that adversarial training significantly improves the performance of an MRI enhancement pipeline, and highlights the need for systematic studies of hyperparameter optimization and investigation of alternative image quality metrics.
英文关键词	Generative Adversarial Networks Adversarial loss REAL-ESRGAN UNet Mixed effects modeling
类型	Article ; Early Access
语种	英语
收录类别	SCI-E
WOS记录号	WOS:001281849000001
WOS关键词	DEEP ; SUPERRESOLUTION ; NETWORKS
WOS类目	Radiology, Nuclear Medicine & Medical Imaging
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/404635
推荐引用方式 GB/T 7714	Javadi, Mohammad,Sharma, Rishabh,Tsiamyrtzis, Panagiotis,et al. Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI[J],2024.
APA	Javadi, Mohammad,Sharma, Rishabh,Tsiamyrtzis, Panagiotis,Webb, Andrew G.,Leiss, Ernst,&Tsekos, Nikolaos V..(2024).Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI.JOURNAL OF IMAGING INFORMATICS IN MEDICINE.
MLA	Javadi, Mohammad,et al."Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI".JOURNAL OF IMAGING INFORMATICS IN MEDICINE (2024).