Intelligent Masking: Deep Q-Learning for Context Encoding in Medical Image Analysis

被引:0
|
作者
Bahrami, Mojtaba [1 ,2 ]
Ghorbani, Mahsa [1 ,2 ]
Yeganeh, Yousef [1 ]
Navab, Nassir [1 ,3 ]
机构
[1] Tech Univ Munich, Comp Aided Med Procedures, Munich, Germany
[2] Sharif Univ Technol, Tehran, Iran
[3] Johns Hopkins Univ, Whiting Sch Engn, Baltimore, MD USA
来源
MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2022 | 2022年 / 13583卷
关键词
Self-supervised learning; Context encoding; Reinforcement learning; Medical image analysis;
D O I
10.1007/978-3-031-21014-3_40
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The need for a large amount of labeled data in the supervised setting has led recent studies to utilize self-supervised learning to pre-train deep neural networks using unlabeled data. Many self-supervised training strategies have been investigated especially for medical datasets to leverage the information available in the much fewer unlabeled data. One of the fundamental strategies in image-based self-supervision is context prediction. In this approach, a model is trained to reconstruct the contents of an arbitrary missing region of an image based on its surroundings. However, the existing methods adopt a random and blind masking approach by focusing uniformly on all regions of the images. This approach results in a lot of unnecessary network updates that cause the model to forget the rich extracted features. In this work, we develop a novel self-supervised approach that occludes targeted regions to improve the pre-training procedure. To this end, we propose a reinforcement learning-based agent which learns to intelligently mask input images through deep Q-learning. We show that training the agent against the prediction model can significantly improve the semantic features extracted for downstream classification tasks. We perform our experiments on two public datasets for diagnosing breast cancer in the ultrasound images and detecting lower-grade glioma with MR images. In our experiments, we show that our novel masking strategy advances the learned features according to the performance on the classification task in terms of accuracy, macro F1, and AUROC.
引用
收藏
页码:387 / 396
页数:10
相关论文
共 50 条
  • [1] An intelligent financial portfolio trading strategy using deep Q-learning
    Park, Hyungjun
    Sim, Min Kyu
    Choi, Dong Gu
    EXPERT SYSTEMS WITH APPLICATIONS, 2020, 158 (158)
  • [2] Active deep Q-learning with demonstration
    Si-An Chen
    Voot Tangkaratt
    Hsuan-Tien Lin
    Masashi Sugiyama
    Machine Learning, 2020, 109 : 1699 - 1725
  • [3] Active deep Q-learning with demonstration
    Chen, Si-An
    Tangkaratt, Voot
    Lin, Hsuan-Tien
    Sugiyama, Masashi
    MACHINE LEARNING, 2020, 109 (9-10) : 1699 - 1725
  • [4] An Online Home Energy Management System using Q-Learning and Deep Q-Learning
    Izmitligil, Hasan
    Karamancioglu, Abdurrahman
    SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2024, 43
  • [5] Deep Q-Learning with Prioritized Sampling
    Zhai, Jianwei
    Liu, Quan
    Zhang, Zongzhang
    Zhong, Shan
    Zhu, Haijun
    Zhang, Peng
    Sun, Cijia
    NEURAL INFORMATION PROCESSING, ICONIP 2016, PT I, 2016, 9947 : 13 - 22
  • [6] Q-learning Approach in the Context of Virtual Learning Environment
    Liviu, Ionita
    Irina, Tudor
    PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON VIRTUAL LEARNING, 2008, : 209 - 214
  • [7] Intelligent Traffic Light Control by Exploring Strategies in an Optimised Space of Deep Q-Learning
    Liu, Junxiu
    Qin, Sheng
    Luo, Yuling
    Wang, Yanhu
    Yang, Su
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (06) : 5960 - 5970
  • [8] Deep Learning in Medical Image Analysis
    Shen, Dinggang
    Wu, Guorong
    Suk, Heung-Il
    ANNUAL REVIEW OF BIOMEDICAL ENGINEERING, VOL 19, 2017, 19 : 221 - 248
  • [9] Deep Q-Learning with Phased Experience Cooperation
    Wang, Hongbo
    Zeng, Fanbing
    Tu, Xuyan
    COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING, CHINESECSCW 2019, 2019, 1042 : 752 - 765
  • [10] REQIBA: Regression and Deep Q-Learning for Intelligent UAV Cellular User to Base Station Association
    Galkin, Boris
    Fonseca, Erika
    Amer, Ramy
    DaSilva, Luiz A.
    Dusparic, Ivana
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (01) : 5 - 20