Self-supervised learning for medical image analysis using image context restoration

被引:363
作者
Chen, Liang [1 ,2 ]
Bentley, Paul [2 ]
Mori, Kensaku [3 ]
Misawa, Kazunari [4 ]
Fujiwara, Michitaka [5 ]
Rueckert, Daniel [1 ]
机构
[1] Imperial Coll London, BioMediA Grp, Dept Comp, 180 Queens Gate, London SW7 2AZ, England
[2] Imperial Coll London, Dept Med, Div Brain Sci, London, England
[3] Nagoya Univ, Grad Sch Informat, Nagoya, Aichi, Japan
[4] Aichi Canc Ctr, Nagoya, Aichi, Japan
[5] Nagoya Univ Hosp, Nagoya, Aichi, Japan
基金
英国惠康基金;
关键词
Self-supervised learning; Context restoration; Medical image analysis; SEGMENTATION; LOCALIZATION;
D O I
10.1016/j.media.2019.101539
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine learning, particularly deep learning has boosted medical image analysis over the past years. Training a good model based on deep learning requires large amount of labelled data. However, it is often difficult to obtain a sufficient number of labelled images for training. In many scenarios the dataset in question consists of more unlabelled images than labelled ones. Therefore, boosting the performance of machine learning models by using unlabelled as well as labelled data is an important but challenging problem. Self-supervised learning presents one possible solution to this problem. However, existing self-supervised learning strategies applicable to medical images cannot result in significant performance improvement. Therefore, they often lead to only marginal improvements. In this paper, we propose a novel self-supervised learning strategy based on context restoration in order to better exploit unlabelled images. The context restoration strategy has three major features: 1) it learns semantic image features; 2) these image features are useful for different types of subsequent image analysis tasks; and 3) its implementation is simple. We validate the context restoration strategy in three common problems in medical imaging: classification, localization, and segmentation. For classification, we apply and test it to scan plane detection in fetal 2D ultrasound images; to localise abdominal organs in CT images; and to segment brain tumours in multi-modal MR images. In all three cases, self-supervised learning based on context restoration learns useful semantic features and lead to improved machine learning models for the above tasks. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页数:12
相关论文
共 54 条
[1]   Learning to See by Moving [J].
Agrawal, Pulkit ;
Carreira, Joao ;
Malik, Jitendra .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :37-45
[2]  
[Anonymous], 2017, CVPR
[3]  
[Anonymous], P 3 INT C LEARNING R
[4]  
[Anonymous], P CVPR
[5]  
[Anonymous], PROC CVPR IEEE
[6]  
[Anonymous], 2015, ARXIV PREPRINT ARXIV
[7]  
[Anonymous], 2017, P IEEE C COMP VIS PA
[8]  
[Anonymous], 2017, P IEEE C COMP VIS PA
[9]  
[Anonymous], 2016, PROC MICCAI BRATS WO
[10]  
[Anonymous], 2015, FETAL ANOMALY SCREEN