Synthetic Lung Ultrasound Data Generation Using Autoencoder With Generative Adversarial Network

Class imbalance is a significant challenge in medical image analysis, particularly in lung ultrasound (LUS), where severe patterns are often underrepresented. Traditional oversampling techniques, which simply duplicate original data, have limited effectiveness in addressing this issue. To overcome t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on ultrasonics, ferroelectrics, and frequency control Vol. 72; no. 5; pp. 624 - 635
Main Authors: Fatima, Noreen, Mento, Federico, Afrakhteh, Sajjad, Perrone, Tiziano, Smargiassi, Andrea, Inchingolo, Riccardo, Demi, Libertario
Format: Journal Article
Language:English
Published: United States IEEE 01.05.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Artificial intelligence
Autoencoder
Autoencoders
COVID-19
Data augmentation
deep convolutional (DC) discriminator
generative adversarial network (GAN)
Generative Adversarial Networks
Generative artificial intelligence
Hospitals
Humans
Image analysis
Image Processing, Computer-Assisted - methods
Kernel
Lung - diagnostic imaging
lung ultrasound (LUS)
Lungs
Medical imaging
multiclass classification
Neural networks
Neural Networks, Computer
Pneumonia
supervised autoencoder (SA)
Synthetic data
Training
Ultrasonic imaging
Ultrasonography - methods
ISSN:0885-3010, 1525-8955, 1525-8955
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Class imbalance is a significant challenge in medical image analysis, particularly in lung ultrasound (LUS), where severe patterns are often underrepresented. Traditional oversampling techniques, which simply duplicate original data, have limited effectiveness in addressing this issue. To overcome these limitations, this study introduces a novel supervised autoencoder generative adversarial network (SA-GAN) for data augmentation, leveraging advanced generative artificial intelligence (AI) to create high-quality synthetic samples for minority classes. In addition, the traditional data augmentation technique is used for comparison. The SA-GAN incorporates an autoencoder to develop a conditional latent space, effectively addressing weight clipping issues and ensuring higher quality synthetic data. The generated samples are evaluated using similarity metrics and expert analysis to validate their utility. Furthermore, state-of-the-art neural networks are used for multiclass classification, and their performance is compared when trained with GAN-based augmentation versus traditional data augmentation techniques. These contributions enhance the robustness and reliability of AI models in mitigating class imbalance in LUS analysis.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0885-3010
1525-8955
1525-8955
DOI:10.1109/TUFFC.2025.3555447