Semi-Supervised CT Lesion Segmentation Using Uncertainty-Based Data Pairing and SwapMix

doi:10.1109/TMI.2022.3232572

	Semi-Supervised CT Lesion Segmentation Using Uncertainty-Based Data Pairing and SwapMix
	Qiao, Pengchong 1,2; Li, Han 3,4; Song, Guoli 2; Han, Hu 2,4,5; Gao, Zhiqiang 2; Tian, Yonghong 1,2; Liang, Yongsheng 2,6; Li, Xi 7; Zhou, S. Kevin 3,4; Chen, Jie 1,2
	2023-05-01
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING
ISSN	0278-0062
卷号	42 期号:5 页码:1546-1562
摘要	Semi-supervised learning (SSL) methods show their powerful performance to deal with the issue of data shortage in the field of medical image segmentation. However, existing SSL methods still suffer from the problem of unreliable predictions on unannotated data due to the lack of manual annotations for them. In this paper, we propose an unreliability-diluted consistency training (UDiCT) mechanism to dilute the unreliability in SSL by assembling reliable annotated data into unreliable unannotated data. Specifically, we first propose an uncertainty-based data pairing module to pair annotated data with unannotated data based on a complementary uncertainty pairing rule, which avoids two hard samples being paired off. Secondly, we develop SwapMix, a mixed sample data augmentation method, to integrate annotated data into unannotated data for training our model in a low-unreliability manner. Finally, UDiCT is trained by minimizing a supervised loss and an unreliability-diluted consistency loss, which makes our model robust to diverse backgrounds. Extensive experiments on three chest CT datasets show the effectiveness of our method for semi-supervised CT lesion segmentation.
关键词	Lesions Image segmentation Computed tomography Uncertainty Training Predictive models Data models Semi-supervised learning lesion segmentation unreliable pseudo labels
DOI	10.1109/TMI.2022.3232572
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[62176249] ; Natural Science Foundation of China[32071459] ; Natural Science Foundation of China[61972217] ; Natural Science Foundation of China[62006133] ; Natural Science Foundation of China[62271465] ; Natural Science Foundation of China[62081360152] ; Natural Science Foundation of Guangdong Province in China[2019B1515120049] ; Natural Science Foundation of Guangdong Province in China[2020B1111340056]
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000982483400026
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[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/2XEOYT63/21472
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; Chen, Jie
作者单位	1.Peking Univ, Sch Elect & Comp Engn, Shenzhen 518055, Peoples R China 2.Peng Cheng Lab, Shenzhen 518055, Peoples R China 3.Univ Sci & Technol China, Suzhou Inst Adv Res, Ctr Med Imaging Robot Analyt Comp & Learning MIRAC, Sch Biomed Engn, Hefei 230052, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100045, Peoples R China 5.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 6.Harbin Inst Technol, Shenzhen Grad Sch, Shenzhen 518055, Peoples R China 7.Peking Univ, Dept Gastroenterol, Shenzhen Hosp, Shenzhen 518036, Peoples R China
推荐引用方式 GB/T 7714	Qiao, Pengchong,Li, Han,Song, Guoli,et al. Semi-Supervised CT Lesion Segmentation Using Uncertainty-Based Data Pairing and SwapMix[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2023,42(5):1546-1562.
APA	Qiao, Pengchong.,Li, Han.,Song, Guoli.,Han, Hu.,Gao, Zhiqiang.,...&Chen, Jie.(2023).Semi-Supervised CT Lesion Segmentation Using Uncertainty-Based Data Pairing and SwapMix.IEEE TRANSACTIONS ON MEDICAL IMAGING,42(5),1546-1562.
MLA	Qiao, Pengchong,et al."Semi-Supervised CT Lesion Segmentation Using Uncertainty-Based Data Pairing and SwapMix".IEEE TRANSACTIONS ON MEDICAL IMAGING 42.5(2023):1546-1562.