Skip to main navigation Skip to search Skip to main content

Hierarchical Bias Mitigation for Semi-Supervised Medical Image Classification

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

Abstract

Semi-supervised learning (SSL) has demonstrated remarkable advances on medical image classification, by harvesting beneficial knowledge from abundant unlabeled samples. The pseudo labeling dominates current SSL approaches, however, it suffers from intrinsic biases within the process. In this paper, we retrospect the pseudo labeling and identify three hierarchical biases: perception bias, selection bias and confirmation bias, at feature extraction, pseudo label selection and momentum optimization stages, respectively. In this regard, we propose a HierArchical BIas miTigation (HABIT) framework to amend these biases, which consists of three customized modules including Mutual Reconciliation Network (MRNet), Recalibrated Feature Compensation (RFC) and Consistency-aware Momentum Heredity (CMH). Firstly, in the feature extraction, MRNet is devised to jointly utilize convolution and permutator-based paths with a mutual information transfer module to exchanges features and reconcile spatial perception bias for better representations. To address pseudo label selection bias, RFC adaptively recalibrates the strong and weak augmented distributions to be a rational discrepancy and augments features for minority categories to achieve the balanced training. Finally, in the momentum optimization stage, in order to reduce the confirmation bias, CMH models the consistency among different sample augmentations into network updating process to improve the dependability of the model. Extensive experiments on three semi-supervised medical image classification datasets demonstrate that HABIT mitigates three biases and achieves state-of-the-art performance. Our codes are available at https://github.com/ CityU-AIM-Group/HABIT. © 2023 IEEE.
Original languageEnglish
Pages (from-to)2200-2210
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume42
Issue number8
Online published22 Feb 2023
DOIs
Publication statusPublished - Aug 2023

Funding

This work was supported in part by the Innovation and Technology Commission, Innovation and Technology Fund, under Grant ITS/100/20; in part by the National Natural Science Foundation of China under Grant 62001410; in part by the Hong Kong Research Grants Council (RGC) Early Career Scheme under Grant 21207420; and in part by the Hong Kong RGC Collaborative Research Fund under Grant C4063-18G.

Research Keywords

  • Bias mitigation
  • Biomedical imaging
  • Consistency-aware heredity
  • Feature compensation
  • Feature extraction
  • Labeling
  • Medical image classification
  • Optimization
  • Permutator-based network
  • Predictive models
  • Semi-supervised learning
  • Semisupervised learning
  • Training

RGC Funding Information

  • RGC-funded

Fingerprint

Dive into the research topics of 'Hierarchical Bias Mitigation for Semi-Supervised Medical Image Classification'. Together they form a unique fingerprint.

Cite this