干旱区生态环境知识资源中心(Arid): Arbitrary Scale Super-Resolution for Medical Images

Arid

DOI	10.1142/S0129065721500374
	Arbitrary Scale Super-Resolution for Medical Images
	Zhu, Jin; Tan, Chuan; Yang, Junwei; Yang, Guang; Lio, Pietro
通讯作者	Zhu, J (corresponding author), Univ Cambridge, Dept Comp Sci & Technol, Cambridge CB3 0FD, England. ; Yang, G (corresponding author), Royal Brompton Hosp, Cardiovasc Res Ctr, London SW3 6NP6, England. ; Yang, G (corresponding author), Imperial Coll London, Natl Heart & Lung Inst, London SW7 2AZ, England.
来源期刊	INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
ISSN	0129-0657
EISSN	1793-6462
出版年	2021
卷号	31 期号:10
英文摘要	Single image super-resolution (SISR) aims to obtain a high-resolution output from one low-resolution image. Currently, deep learning-based SISR approaches have been widely discussed in medical image processing, because of their potential to achieve high-quality, high spatial resolution images without the cost of additional scans. However, most existing methods are designed for scale-specific SR tasks and are unable to generalize over magnification scales. In this paper, we propose an approach for medical image arbitrary-scale super-resolution (MIASSR), in which we couple meta-learning with generative adversarial networks (GANs) to super-resolve medical images at any scale of magnification in (1, 4]. Compared to state-of-the-art SISR algorithms on single-modal magnetic resonance (MR) brain images (OASIS-brains) and multi-modal MR brain images (BraTS), MIASSR achieves comparable fidelity performance and the best perceptual quality with the smallest model size. We also employ transfer learning to enable MIASSR to tackle SR tasks of new medical modalities, such as cardiac MR images (ACDC) and chest computed tomography images (COVID-CT). The source code of our work is also public. Thus, MIASSR has the potential to become a new foundational pre-/post-processing step in clinical image analysis tasks such as reconstruction, image quality enhancement, and segmentation.
英文关键词	Super-resolution medical image analysis image processing generative adversarial networks meta learning transfer learning
类型	Article
语种	英语
开放获取类型	hybrid
收录类别	SCI-E
WOS记录号	WOS:000696596800001
WOS类目	Computer Science, Artificial Intelligence
WOS研究方向	Computer Science
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/363654
作者单位	[Zhu, Jin; Tan, Chuan; Yang, Junwei] Univ Cambridge, Dept Comp Sci & Technol, Cambridge CB3 0FD, England; [Yang, Guang] Royal Brompton Hosp, Cardiovasc Res Ctr, London SW3 6NP6, England; [Yang, Guang] Imperial Coll London, Natl Heart & Lung Inst, London SW7 2AZ, England; [Lio, Pietro] Univ Cambridge, Dept Comp Sci & Technol, Cambridge CB3 0FD, England
推荐引用方式 GB/T 7714	Zhu, Jin,Tan, Chuan,Yang, Junwei,et al. Arbitrary Scale Super-Resolution for Medical Images[J],2021,31(10).
APA	Zhu, Jin,Tan, Chuan,Yang, Junwei,Yang, Guang,&Lio, Pietro.(2021).Arbitrary Scale Super-Resolution for Medical Images.INTERNATIONAL JOURNAL OF NEURAL SYSTEMS,31(10).
MLA	Zhu, Jin,et al."Arbitrary Scale Super-Resolution for Medical Images".INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 31.10(2021).