• Home
  • Search
  • Handling Imbalanced Data: Uncertainty-Guided Virtual Adversarial Training With Batch Nuclear-Norm Optimization for Semi-Supervised Medical Image Classification.
  • Cite Icon22
  • https://doi.org/10.1109/jbhi.2022.3162748Copy DOI Icon

Handling Imbalanced Data: Uncertainty-Guided Virtual Adversarial Training With Batch Nuclear-Norm Optimization for Semi-Supervised Medical Image Classification.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In manyclinical settings, a lot of medical image datasets suffer from imbalance problems, which makes predictions of trained models to be biased toward majority classes. Semi-supervised Learning (SSL) algorithms trained with such imbalanced datasets become more problematic since pseudo-supervision of unlabeled data are generated from the model's biased predictions. To address these issues, in this work, we propose a novel semi-supervised deep learning method, i.e., uncertainty-guided virtual adversarial training (VAT) with batch nuclear-norm (BNN) optimization, for large-scale medical image classification. To effectively exploit useful information from both labeled and unlabeled data, we leverage VAT and BNN optimization to harness the underlying knowledge, which helps to improve discriminability, diversity and generalization of the trained models. More concretely, our network is trained by minimizing a combination of four types of losses, including a supervised cross-entropy loss, a BNN loss defined on the output matrix of labeled data batch (lBNN loss), a negative BNN loss defined on the output matrix of unlabeled data batch (uBNN loss), and a VAT loss on both labeled and unlabeled data. We additionally propose to use uncertainty estimation to filter out unlabeled samples near the decision boundary when computing the VAT loss. We conduct comprehensive experiments to evaluate the performance of our method on two publicly available datasets and one in-house collected dataset. The experimental results demonstrated that our method achieved better results than state-of-the-art SSL methods.

Similar Papers
  • Research Article
  • Citations107

Deep virtual adversarial self-training with consistency regularization for semi-supervised medical image classification.

  • Feb 22, 2021
  • Medical Image Analysis
  • Xi Wang +5
  • Research Article
  • Citations8

Semisupervised Learning for Seismic Monitoring Applications

  • Oct 21, 2020
  • Seismological Research Letters
  • Lisa Linville +4
  • Research Article
  • Citations65

Semi-Supervised Concept Learning by Concept-Cognitive Learning and Concept Space

  • Jul 21, 2020
  • IEEE Transactions on Knowledge and Data Engineering
  • Yunlong Mi +3
  • Conference Article
  • Citations1

A semi-supervised deep learning method in network intrusion detection

  • Jun 01, 2023
  • Zhanbo Li +1
  • Book Chapter
  • Citations87

Semi-supervised Deep Learning with Memory

  • Jan 01, 2018
  • Yanbei Chen +2
  • Research Article
  • Citations33

Semi-supervised medical image classification with adaptive threshold pseudo-labeling and unreliable sample contrastive loss

  • Sep 19, 2022
  • Biomedical Signal Processing and Control
  • Zhen Peng +5
  • Research Article
  • Citations107

Semi-supervised learning for medical image classification using imbalanced training data

  • Jan 14, 2022
  • Computer Methods and Programs in Biomedicine
  • Tri Huynh +2
  • Research Article
  • Citations19

Automatic detection of retinopathy with optical coherence tomography images via a semi-supervised deep learning method.

  • Apr 13, 2021
  • Biomedical Optics Express
  • Yuemei Luo +4
  • Research Article
  • Citations55

Prediction of energy use intensity of urban buildings using the semi-supervised deep learning model

  • Mar 15, 2022
  • Energy
  • Feifeng Jiang +3
  • Research Article
  • Citations31

Safe Semi-Supervised Extreme Learning Machine for EEG Signal Classification

  • Jan 01, 2018
  • IEEE Access
  • Qingshan She +6
  • Research Article
  • Citations1

Fault Diagnosis of Semi-Supervised Electromechanical Transmission Systems Under Imbalanced Unlabeled Sample Class Information Screening.

  • Feb 06, 2025
  • Entropy (Basel, Switzerland)
  • Chaoge Wang +5
  • Conference Article
  • Citations36

Tangent-Normal Adversarial Regularization for Semi-Supervised Learning

  • Nov 16, 2018
  • Bing Yu +3
  • Research Article
  • Citations29

Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency.

  • Jan 01, 2020
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Junshen Xu +6
  • Book Chapter
  • Citations1

Estimate Unlabeled-Data-Distribution for Semi-supervised PU Learning

  • Jan 01, 2012
  • Haoji Hu +3
  • Research Article
  • Citations77

Scalable Graph-Based Semi-Supervised Learning through Sparse Bayesian Model

  • Dec 01, 2017
  • IEEE Transactions on Knowledge and Data Engineering
  • Bingbing Jiang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.