Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training

Cheng Xue, Lequan Yu, Pengfei Chen, Qi Dou, Pheng Ann Heng

Research output: Journal article publicationJournal articleAcademic researchpeer-review

6 Citations (Scopus)


Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifier. This problem is even more severe in the medical image analysis field, as the annotation quality of medical images heavily relies on the expertise and experience of annotators. In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data. Specifically, we employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples. Then, the clean samples are trained by a collaborative training strategy to eliminate the disturbance from imperfect labeled samples. Notably, we further design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples in a self-supervised manner. We evaluated our proposed robust learning strategy on four public medical image classification datasets with three types of label noise, i.e., random noise, computer-generated label noise, and inter-observer variability noise. Our method outperforms other learning from noisy label methods and we also conducted extensive experiments to analyze each component of our method.

Original languageEnglish
Pages (from-to)1371-1382
Number of pages12
JournalIEEE Transactions on Medical Imaging
Issue number6
Publication statusPublished - 1 Jun 2022
Externally publishedYes


  • Biomedical imaging
  • collaborative training
  • Deep learning
  • Image analysis
  • Medical diagnostic imaging
  • Noise measurement
  • Noisy label
  • representation learning
  • self-supervision
  • Training
  • Training data

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training'. Together they form a unique fingerprint.

Cite this