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
  • [31] A configurable deep learning framework for medical image analysis
    Chen, Jianguo
    Yang, Nan
    Zhou, Mimi
    Zhang, Zhaolei
    Yang, Xulei
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (10) : 7375 - 7392
  • [32] Enhanced Machine Learning Algorithms: Deep Learning, Reinforcement Learning, ana Q-Learning
    Park, Ji Su
    Park, Jong Hyuk
    JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2020, 16 (05): : 1001 - 1007
  • [33] Intelligent Traffic Light Control Using Collaborative Q-Learning Algorithms
    Rosyadi, Andhika Rizky
    Wirayuda, Tjokorda Agung Budi
    Al-Faraby, Said
    2016 4TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY (ICOICT), 2016,
  • [34] Intelligent Decision Making in Electricity Markets: Simulated Annealing Q-Learning
    Pinto, T.
    Sousa, T. M.
    Vale, Z.
    Morais, H.
    Praca, I.
    2012 IEEE POWER AND ENERGY SOCIETY GENERAL MEETING, 2012,
  • [35] Collaborative Traffic Signal Automation Using Deep Q-Learning
    Hassan, Muhammad Ahmed
    Elhadef, Mourad
    Khan, Muhammad Usman Ghani
    IEEE ACCESS, 2023, 11 : 136015 - 136032
  • [36] Performing Deep Recurrent Double Q-Learning for Atari Games
    Moreno-Vera, Felipe
    2019 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2019, : 125 - 128
  • [37] Entropy-Based Prioritized Sampling in Deep Q-Learning
    Ramicic, Mirza
    Bonarini, Andrea
    2017 2ND INTERNATIONAL CONFERENCE ON IMAGE, VISION AND COMPUTING (ICIVC 2017), 2017, : 1068 - 1072
  • [38] ADAPTIVE CONTENTION WINDOW DESIGN USING DEEP Q-LEARNING
    Kumar, Abhishek
    Verma, Gunjan
    Rao, Chirag
    Swami, Ananthram
    Segarra, Santiago
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 4950 - 4954
  • [39] Evaluating cooperative-competitive dynamics with deep Q-learning
    Kopacz, Aniko
    Csato, Lehel
    Chira, Camelia
    NEUROCOMPUTING, 2023, 550
  • [40] Q-Learning approach for minutiae extraction from fingerprint image
    Tiwari, Sandeep
    Sharma, Neha
    2ND INTERNATIONAL CONFERENCE ON COMMUNICATION, COMPUTING & SECURITY [ICCCS-2012], 2012, 1 : 82 - 89