• Home
  • Search
  • Adversarial Confidence Learning for Medical Image Segmentation and Synthesis
  • Open Access IconOpen Access
  • Cite Icon58
  • https://doi.org/10.1007/s11263-020-01321-2Copy DOI Icon

Adversarial Confidence Learning for Medical Image Segmentation and Synthesis

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

Generative adversarial networks (GAN) are widely used in medical image analysis tasks, such as medical image segmentation and synthesis. In these works, adversarial learning is directly applied to the original supervised segmentation (synthesis) networks. The usage of adversarial learning is effective in improving visual perception performance since adversarial learning works as realistic regularization for supervised generators. However, the quantitative performance often cannot improve as much as the qualitative performance, and it can even become worse in some cases. In this paper, we explore how we can take better advantage of adversarial learning in supervised segmentation (synthesis) models and propose an adversarial confidence learning framework to better model these problems. We analyze the roles of discriminator in the classic GANs and compare them with those in supervised adversarial systems. Based on this analysis, we propose adversarial confidence learning, i.e., besides the adversarial learning for emphasizing visual perception, we use the confidence information provided by the adversarial network to enhance the design of supervised segmentation (synthesis) network. In particular, we propose using a fully convolutional adversarial network for confidence learning to provide voxel-wise and region-wise confidence information for the segmentation (synthesis) network. With these settings, we propose a difficulty-aware attention mechanism to properly handle hard samples or regions by taking structural information into consideration so that we can better deal with the irregular distribution of medical data. Furthermore, we investigate the loss functions of various GANs and propose using the binary cross entropy loss to train the proposed adversarial system so that we can retain the unlimited modeling capacity of the discriminator. Experimental results on clinical and challenge datasets show that our proposed network can achieve state-of-the-art segmentation (synthesis) accuracy. Further analysis also indicates that adversarial confidence learning can both improve the visual perception performance and the quantitative performance.

Similar Papers
  • Research Article
  • Citations47

Difficulty-Aware Attention Network with Confidence Learning for Medical Image Segmentation

  • Jul 17, 2019
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Dong Nie +5
  • Research Article
  • Citations14

Voxel-wise adversarial semi-supervised learning for medical image segmentation

  • Sep 29, 2022
  • Computers in biology and medicine
  • Chae Eun Lee +3
  • Research Article
  • Citations19

Adversarial Representation Mechanism Learning for Network Embedding

  • Jan 01, 2021
  • IEEE Transactions on Knowledge and Data Engineering
  • Dongxiao He +7
  • Dissertation
  • Citations1

An Analysis on Adversarial Machine Learning: Methods and Applications

  • Jan 01, 2022
  • Ali Dabouei
  • Research Article
  • Citations12

Exploring adversarial deep learning for fusion in multi-color channel skin detection applications

  • Aug 14, 2024
  • Information Fusion
  • Mohammed Chyad +8
  • Conference Article
  • Citations25

Adversarial Mutual Information Learning for Network Embedding

  • Jul 01, 2020
  • Dongxiao He +6
  • Research Article
  • Citations45

Annotation-Efficient Learning for Medical Image Segmentation Based on Noisy Pseudo Labels and Adversarial Learning

  • Dec 28, 2020
  • IEEE Transactions on Medical Imaging
  • Lu Wang +3
  • Research Article
  • Citations1

Generative AI-Empowered Resilient Adaptive ISAC Against Adversarial Machine Learning Attacks

  • Dec 01, 2025
  • IEEE Transactions on Vehicular Technology
  • Hamda Bouzabia +2
  • Research Article
  • Citations44

Deep Adversarial Metric Learning.

  • Oct 25, 2019
  • IEEE Transactions on Image Processing
  • Yueqi Duan +3
  • Research Article
  • Citations59

Generative attention adversarial classification network for unsupervised domain adaptation

  • Jun 05, 2020
  • Pattern Recognition
  • Wendong Chen +1
  • Research Article
  • Citations9

Neural adversarial learning for speaker recognition

  • Jun 08, 2019
  • Computer Speech & Language
  • Jen-Tzung Chien +1
  • PDF
  • Research Article
  • Citations7

RAILS: A Robust Adversarial Immune-Inspired Learning System

  • Jan 01, 2022
  • IEEE Access
  • Ren Wang +6
  • Conference Article
  • Citations3

A Generative Adversarial Distribution Matching Framework for Visual Domain Adaptation

  • May 01, 2019
  • Kai Zhang +4
  • Research Article
  • Citations8

Histogram matching‐enhanced adversarial learning for unsupervised domain adaptation in medical image segmentation

  • Mar 18, 2025
  • Medical Physics
  • Xiaoxue Qian +4
  • Conference Article
  • Citations21

Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration

  • Nov 20, 2020
  • Ming Zhang +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.