Image synthesis with disentangled attributes for chest X-ray nodule augmentation and detection

doi:10.1016/j.media.2022.102708

	Image synthesis with disentangled attributes for chest X-ray nodule augmentation and detection
	Shen, Zhenrong 1; Ouyang, Xi 2; Xiao, Bin 1; Cheng, Jie-Zhi 2; Shen, Dinggang2,3,4 ; Wang, Qian3,4
	2023-02
发表期刊	MEDICAL IMAGE ANALYSIS (IF:10.7[JCR-2023],11.9[5-Year])
ISSN	1361-8415
EISSN	1361-8423
卷号	84
DOI	10.1016/j.media.2022.102708
摘要	Lung nodule detection in chest X-ray (CXR) images is common to early screening of lung cancers. Deep-learning-based Computer-Assisted Diagnosis (CAD) systems can support radiologists for nodule screening in CXR images. However, it requires large-scale and diverse medical data with high-quality annotations to train such robust and accurate CADs. To alleviate the limited availability of such datasets, lung nodule synthesis methods are proposed for the sake of data augmentation. Nevertheless, previous methods lack the ability to generate nodules that are realistic with the shape/size attributes desired by the detector. To address this issue, we introduce a novel lung nodule synthesis framework in this paper, which decomposes nodule attributes into three main aspects including the shape, the size, and the texture, respectively. A GAN-based Shape Generator firstly models nodule shapes by generating diverse shape masks. The following Size Modulation then enables quantitative control on the diameters of the generated nodule shapes in pixel-level granularity. A coarse-to-fine gated convolutional Texture Generator finally synthesizes visually plausible nodule textures conditioned on the modulated shape masks. Moreover, we propose to synthesize nodule CXR images by controlling the disentangled nodule attributes for data augmentation, in order to better compensate for the nodules that are easily missed in the detection task. Our experiments demonstrate the enhanced image quality, diversity, and controllability of the proposed lung nodule synthesis framework. We also validate the effectiveness of our data augmentation strategy on greatly improving nodule detection performance. © 2022 Elsevier B.V.
关键词	iological organs Computer aided diagnosis Computer aided instruction Deep learning Image enhancement Chest X-ray Chest X-ray image Computer assisted diagnosis Data augmentation Image Inpainting Images synthesis Lung Cancer Lung nodule Lung nodules detection Nodule detection
URL	查看原文
收录类别	EI ; SCOPUS
语种	英语
出版者	Elsevier B.V.
EI入藏号	20225013252133
EI主题词	Textures
EI分类号	461.1 Biomedical Engineering ; 461.2 Biological Materials and Tissue Engineering ; 461.4 Ergonomics and Human Factors Engineering ; 723.5 Computer Applications ; 901.2 Education
原始文献类型	Journal article (JA)
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/282023
专题	生物医学工程学院_PI研究组_王乾组生物医学工程学院_PI研究组_沈定刚组
通讯作者	Wang, Qian
作者单位	1.School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai; 200030, China; 2.Shanghai United Imaging Intelligence Co., Ltd., Shanghai; 200232, China; 3.School of Biomedical Engineering, ShanghaiTech University, Shanghai; 201210, China; 4.Shanghai Clinical Research and Trial Center, Shanghai; 201210, China
通讯作者单位	生物医学工程学院
推荐引用方式 GB/T 7714	Shen, Zhenrong,Ouyang, Xi,Xiao, Bin,et al. Image synthesis with disentangled attributes for chest X-ray nodule augmentation and detection[J]. MEDICAL IMAGE ANALYSIS,2023,84.
APA	Shen, Zhenrong,Ouyang, Xi,Xiao, Bin,Cheng, Jie-Zhi,Shen, Dinggang,&Wang, Qian.(2023).Image synthesis with disentangled attributes for chest X-ray nodule augmentation and detection.MEDICAL IMAGE ANALYSIS,84.
MLA	Shen, Zhenrong,et al."Image synthesis with disentangled attributes for chest X-ray nodule augmentation and detection".MEDICAL IMAGE ANALYSIS 84(2023).