Options
GANs for generation of synthetic ultrasound images from small datasets
Citation Link: https://doi.org/10.15480/882.4778
Publikationstyp
Journal Article
Date Issued
2022-07
Sprache
English
Author(s)
TORE-DOI
Volume
8
Issue
1
Start Page
17
End Page
20
Citation
Current Directions in Biomedical Engineering 8 (1): 17-20 (2022-07)
Publisher DOI
Scopus ID
Publisher
De Gruyter
The task of medical image classification is increasingly supported by algorithms. Deep learning methods like convolutional neural networks (CNNs) show superior performance in medical image analysis but need a high-quality training dataset with a large number of annotated samples. Particularly in the medical domain, the availability of such datasets is rare due to data privacy or the lack of data sharing practices among institutes. Generative adversarial networks (GANs) are able to generate high quality synthetic images. This work investigates the capabilities of different state-of-the-art GAN architectures in generating realistic breast ultrasound images if only a small amount of training data is available. In a second step, these synthetic images are used to augment the real ultrasound image dataset utilized for training CNNs. The training of both GANs and CNNs is conducted with systematically reduced dataset sizes. The GAN architectures are capable of generating realistic ultrasound images. GANs using data augmentation techniques outperform the baseline Style- GAN2 with respect to the Frechet Inception distance by up to 64.2%. CNN models trained with additional synthetic data outperform the baseline CNN model using only real data for training by up to 15.3% with respect to the F1 score, especially for datasets containing less than 100 images. As a conclusion, GANs can successfully be used to generate synthetic ultrasound images of high quality and diversity, improve classification performance of CNNs and thus provide a benefit to computer-aided diagnostics.
Subjects
deep learning
generative adversarial networks (GANs)
image classification
medical image analysis
small datasets
synthetic image generation
ultrasound imaging
MLE@TUHH
DDC Class
600: Technik
610: Medizin
Publication version
publishedVersion
Loading...
Name
10.1515_cdbme-2022-0005.pdf
Size
1.29 MB
Format
Adobe PDF