Bayesian statistics-guided label refurbishment mechanism: Mitigating label noise in medical image classification.

Journal: Medical physics
Published Date: Jun 22, 2022

Abstract

PURPOSE: Deep neural networks (DNNs) have been widely applied in medical image classification, benefiting from its powerful mapping capability among medical images. However, these existing deep learning-based methods depend on an enormous amount of carefully labeled images. Meanwhile, noise is inevitably introduced in the labeling process, degrading the performance of models. Hence, it is significant to devise robust training strategies to mitigate label noise in the medical image classification tasks.

Authors

  • Mengdi Gao
  • Ximeng Feng
    Department of Biomedical Engineering, College of Future Technology, Peking University, Beijing, China.
  • Mufeng Geng
  • Zhe Jiang
    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, China.
  • Lei Zhu
    School of Civil and Hydraulic Engineering, Ningxia University, Yinchuan, China.
  • Xiangxi Meng
    Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute, Beijing, China.
  • Chuanqing Zhou
    Institute of Biomedical Engineering, Shenzhen Bay Laboratory, Shenzhen, China.
  • Qiushi Ren
    Department of Biomedical Engineering, Peking University, 100871, Beijing, China.
  • Yanye Lu
    Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Martensstr. 3, 91058, Erlangen, Germany. yanye.lu@fau.de.

Keywords

External Resources

Popular Topics
Recent Journals