• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Is one label all you need? Single positive multi-label training in medical image analysis
 
  • Details
  • Full
Options
2023
Conference Paper
Title

Is one label all you need? Single positive multi-label training in medical image analysis

Abstract
Deep Learning is proving its immense potential in medical image processing. However, noisy label data can weaken the generalization ability of the model and cause significant performance degradation. This issue can be more prevalent in multi-label classification tasks, since their annotation is more challenging. With too many labels, human annotators may have difficulties mentioning all possible classes, which leads to an increased number of false negative labels. Single Positive Multi-Label (SPML) training deals with the most severe version of this problem, in which for each sample only one positive label is available. All other labels are not observed, i.e. not confirmed as positive or negative. While SPML has already achieved good results for the multi-label detection of objects, its impact on the extremely pertinent medical imaging use case has not yet been explored. In this work, we therefore investigate the performance of state-of-the-art SPML loss functions in the analysis of chest X-rays, both on the public CheXpert and on an in-house data set of the University Hospital Bonn. In addition, we propose our new SPML loss functions, the Generalized Assume Negative and Implicit Weighting Assume Negative loss, which increase the mean average precision by up to 4.6% compared to the popular binary cross-entropy loss.
Author(s)
Schneider, Helen
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Priya, Priya
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Biesner, David  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Kador, Rebecca
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Layer, Yannik C.
Uniklinikum Bonn
Theis, Maike
Uniklinikum Bonn
Nowak, Sebastian
Uniklinikum Bonn
Sprinkart, Alois M.
Uniklinikum Bonn
Attenberger, Ulrike I.
Uniklinikum Bonn
Sifa, Rafet  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Mainwork
IEEE International Conference on Big Data 2023. Proceedings  
Conference
International Conference on Big Data 2023  
DOI
10.1109/BigData59044.2023.10386758
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Keyword(s)
  • Training

  • Degradation

  • Deep learning

  • Image analysis

  • Hospital

  • Data models

  • Noise measurement

  • Single positive multi-label

  • Chest X-rays

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024