• Login
    View Item 
    •   Home
    • Research
    • Articles
    • View Item
    •   Home
    • Research
    • Articles
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    Detecting thoracic diseases via representation learning with adaptive sampling

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Medical_Image.pdf
    Size:
    1.144Mb
    Format:
    PDF
    Description:
    Accepted manuscript
    Download
    Type
    Article
    Authors
    Wang, Hao
    Yang, Yuan Yuan
    Pan, Yang
    Han, Peng
    Li, Zhong Xiao
    Huang, He Guang
    Zhu, Shun Zhi
    KAUST Department
    Computer, Electrical and Mathematical Science and Engineering Division, KAUST, Saudi Arabia
    Date
    2020-04-12
    Online Publication Date
    2020-04-12
    Print Publication Date
    2020-09
    Submitted Date
    2019-04-29
    Permanent link to this record
    http://hdl.handle.net/10754/662740
    
    Metadata
    Show full item record
    Abstract
    The recently released chest X-ray dataset, ChestX-ray14, has attracted more and more attention on automatic detection of thoracic diseases. In this work, we use deep learning techniques to develop a multi-class classifier. Given a chest X-ray image as input, the classifier outputs a vector of probability values, of which each component corresponds to the probability of having one specific thoracic disease. The merit of our proposed solution is based on several major observations of the ChestX-ray14 data. First, the diversity in ChestX-ray14 is much smaller than that in other natural image datasets such as ImageNet due to very similar global outlines of chest X-ray images. Second, ChestX-ray14 is much more imbalanced than the datasets considered in most existing studies. The size of the largest class is 87.57 times larger than that of the smallest class. Third, from the application perspective, the task is not really cost-sensitive to misclassifications, thus it is difficult to manually fix weights for different misclassifications. To deal with these difficulties, we propose an adaptive sampling method that monitors the performance of the model during training and automatically increase the weight of relatively poorly performed classes. Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art algorithms.
    Citation
    Wang, H., Yang, Y.-Y., Pan, Y., Han, P., Li, Z.-X., Huang, H.-G., & Zhu, S.-Z. (2020). Detecting thoracic diseases via representation learning with adaptive sampling. Neurocomputing. doi:10.1016/j.neucom.2019.06.113
    Sponsors
    This work is supported by Joint Funds of Scientific and Technological Innovation Program of Fujian Province (No. 2017Y9059), Sail Fund of Fujian Medical University (No. 2017XQ1027), “Ethicon Excellence in Surgery” Grant of Wujieping Medical Foundation (No. 320.2710.1801), and the Science and Technology Planning Project of Xiamen/Quanzhou City (No. 3502Z20183055, 2017G030).
    Publisher
    Elsevier BV
    Journal
    Neurocomputing
    DOI
    10.1016/j.neucom.2019.06.113
    Additional Links
    https://linkinghub.elsevier.com/retrieve/pii/S092523122030549X
    ae974a485f413a2113503eed53cd6c53
    10.1016/j.neucom.2019.06.113
    Scopus Count
    Collections
    Articles

    entitlement

     
    DSpace software copyright © 2002-2021  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.