Combating Medical Label Noise through more precise partition-correction and progressive hard-enhanced learning.

Journal: Computer methods and programs in biomedicine
PMID:

Abstract

BACKGROUND AND OBJECTIVE: Computer-aided diagnosis systems based on deep neural networks heavily rely on datasets with high-quality labels. However, manual annotation for lesion diagnosis relies on image features, often requiring professional experience and complex image analysis process. This inevitably introduces noisy labels, which can misguide the training of classification models. Our goal is to design an effective method to address the challenges posed by label noise in medical images.

Authors

  • Sanyan Zhang
    Imaging & Intelligence Lab, Taiyuan University of Technology, China.
  • Surong Chu
    Imaging & Intelligence Lab, Taiyuan University of Technology, China.
  • Yan Qiang
    College of Information and Computer, Taiyuan University of Technology, Taiyuan, China.
  • Juanjuan Zhao
    Guanlan Networks (Hangzhou) Co, Ltd, Hangzhou, Zhejiang, China.
  • Yan Wang
    College of Animal Science and Technology, Beijing University of Agriculture, Beijing, China.
  • Xiao Wei
    Guangxi Medical University, Nanning, Guangxi, China.