GAN-based disentanglement learning for chest X-ray rib suppression

doi:10.1016/j.media.2022.102369

	GAN-based disentanglement learning for chest X-ray rib suppression
	Han, Luyi 1,2; Lyu, Yuanyuan 3; Peng, Cheng 4; Zhou, S. Kevin 5,6,7
	2022-04-01
发表期刊	MEDICAL IMAGE ANALYSIS
ISSN	1361-8415
卷号	77 页码:14
摘要	Clinical evidence has shown that rib-suppressed chest X-rays (CXRs) can improve the reliability of pulmonary disease diagnosis. However, previous approaches on generating rib-suppressed CXR face challenges in preserving details and eliminating rib residues. We hereby propose a GAN-based disentanglement learning framework called Rib Suppression GAN, or RSGAN, to perform rib suppression by utilizing the anatomical knowledge embedded in unpaired computed tomography (CT) images. In this approach, we employ a residual map to characterize the intensity difference between CXR and the corresponding rib-suppressed result. To predict the residual map in CXR domain, we disentangle the image into structure-and contrast-specific features and transfer the rib structural priors from digitally reconstructed radiographs (DRRs) computed by CT. Furthermore, we employ additional adaptive loss to suppress rib residue and preserve more details. We conduct extensive experiments based on 1673 CT volumes, and four benchmarking CXR datasets, totaling over 120K images, to demonstrate that (i) our proposed RSGAN achieves superior image quality compared to the state-of-the-art rib suppression methods; (ii) combining CXR with our rib-suppressed result leads to better performance in lung disease classification and tuberculosis area detection. (c) 2022 Elsevier B.V. All rights reserved.
关键词	CXR Rib suppression Domain adaptation Disentanglement learning
DOI	10.1016/j.media.2022.102369
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000793655000002
出版者	ELSEVIER
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19549
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhou, S. Kevin
作者单位	1.Radboud Univ Nijmegen Med Ctr, Dept Radiol & Nucl Med, Geert Grootepl 10, NL-6525 GA Nijmegen, Netherlands 2.Netherlands Canc Inst NKI, Dept Radiol, Plesmanlaan 121, NL-1066 CX Amsterdam, Netherlands 3.Z2Sky Technol Inc, Suzhou 215123, Peoples R China 4.Johns Hopkins Univ, Artificial Intelligence Engn & Med Lab, Baltimore, MD 21218 USA 5.Univ Sci & Technol China, Sch Biomed Engn, Suzhou 215123, Peoples R China 6.Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou 215123, Peoples R China 7.Chinese Acad Sci, Inst Comp Technol, CAS, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Han, Luyi,Lyu, Yuanyuan,Peng, Cheng,et al. GAN-based disentanglement learning for chest X-ray rib suppression[J]. MEDICAL IMAGE ANALYSIS,2022,77:14.
APA	Han, Luyi,Lyu, Yuanyuan,Peng, Cheng,&Zhou, S. Kevin.(2022).GAN-based disentanglement learning for chest X-ray rib suppression.MEDICAL IMAGE ANALYSIS,77,14.
MLA	Han, Luyi,et al."GAN-based disentanglement learning for chest X-ray rib suppression".MEDICAL IMAGE ANALYSIS 77(2022):14.