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

被引:8
作者
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 ]
机构
[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
关键词
Lesions; Image segmentation; Computed tomography; Uncertainty; Training; Predictive models; Data models; Semi-supervised learning; lesion segmentation; unreliable pseudo labels; LUNG NODULE SEGMENTATION; COVID-19; FRAMEWORK; CLASSIFICATION; SCANS;
D O I
10.1109/TMI.2022.3232572
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
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.
引用
收藏
页码:1546 / 1562
页数:17
相关论文
共 76 条
[1]  
[Anonymous], 2011, ADV NEURAL INF PROCE
[2]   The Lung Image Database Consortium, (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans [J].
Armato, Samuel G., III ;
McLennan, Geoffrey ;
Bidaut, Luc ;
McNitt-Gray, Michael F. ;
Meyer, Charles R. ;
Reeves, Anthony P. ;
Zhao, Binsheng ;
Aberle, Denise R. ;
Henschke, Claudia I. ;
Hoffman, Eric A. ;
Kazerooni, Ella A. ;
MacMahon, Heber ;
van Beek, Edwin J. R. ;
Yankelevitz, David ;
Biancardi, Alberto M. ;
Bland, Peyton H. ;
Brown, Matthew S. ;
Engelmann, Roger M. ;
Laderach, Gary E. ;
Max, Daniel ;
Pais, Richard C. ;
Qing, David P-Y ;
Roberts, Rachael Y. ;
Smith, Amanda R. ;
Starkey, Adam ;
Batra, Poonam ;
Caligiuri, Philip ;
Farooqi, Ali ;
Gladish, Gregory W. ;
Jude, C. Matilda ;
Munden, Reginald F. ;
Petkovska, Iva ;
Quint, Leslie E. ;
Schwartz, Lawrence H. ;
Sundaram, Baskaran ;
Dodd, Lori E. ;
Fenimore, Charles ;
Gur, David ;
Petrick, Nicholas ;
Freymann, John ;
Kirby, Justin ;
Hughes, Brian ;
Casteele, Alessi Vande ;
Gupte, Sangeeta ;
Sallam, Maha ;
Heath, Michael D. ;
Kuhn, Michael H. ;
Dharaiya, Ekta ;
Burns, Richard ;
Fryd, David S. .
MEDICAL PHYSICS, 2011, 38 (02) :915-931
[3]  
Berthelot D, 2019, ADV NEUR IN, V32
[4]   Longitudinal Assessment of COVID-19 Using a Deep Learning-based Quantitative CT Pipeline: Illustration of Two Cases [J].
Cao, Yukun ;
Xu, Zhanwei ;
Feng, Jianjiang ;
Jin, Cheng ;
Han, Xiaoyu ;
Wu, Hanping ;
Shi, Heshui .
RADIOLOGY-CARDIOTHORACIC IMAGING, 2020, 2 (02)
[5]   Semi-supervised and Task-Driven Data Augmentation [J].
Chaitanya, Krishna ;
Karani, Neerav ;
Baumgartner, Christian F. ;
Becker, Anton ;
Donati, Olivio ;
Konukoglu, Ender .
INFORMATION PROCESSING IN MEDICAL IMAGING, IPMI 2019, 2019, 11492 :29-41
[6]   Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision [J].
Chen, Xiaokang ;
Yuan, Yuhui ;
Zeng, Gang ;
Wang, Jingdong .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :2613-2622
[7]   The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository [J].
Clark, Kenneth ;
Vendt, Bruce ;
Smith, Kirk ;
Freymann, John ;
Kirby, Justin ;
Koppel, Paul ;
Moore, Stephen ;
Phillips, Stanley ;
Maffitt, David ;
Pringle, Michael ;
Tarbox, Lawrence ;
Prior, Fred .
JOURNAL OF DIGITAL IMAGING, 2013, 26 (06) :1045-1057
[8]   Hypergraph learning for identification of COVID-19 with CT imaging [J].
Di, Donglin ;
Shi, Feng ;
Yan, Fuhua ;
Xia, Liming ;
Mo, Zhanhao ;
Ding, Zhongxiang ;
Shan, Fei ;
Song, Bin ;
Li, Shengrui ;
Wei, Ying ;
Shao, Ying ;
Han, Miaofei ;
Gao, Yaozong ;
Sui, He ;
Gao, Yue ;
Shen, Dinggang .
MEDICAL IMAGE ANALYSIS, 2021, 68
[9]   Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images [J].
Fan, Deng-Ping ;
Zhou, Tao ;
Ji, Ge-Peng ;
Zhou, Yi ;
Chen, Geng ;
Fu, Huazhu ;
Shen, Jianbing ;
Shao, Ling .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (08) :2626-2637
[10]  
French G., 2020, BRIT MACH VIS C, P1