Abstract
Generative adversarial networks (GANs) have been recently applied to medical imaging on different modalities (MRI, CT, X-ray, etc). However there are not many applications on ultrasound modality as a data augmentation technique applied to downstream classification tasks. This study aims to explore and evaluate the generation of synthetic ultrasound fetal brain images via GANs and apply them to improve fetal brain ultrasound plane classification. State of the art GANs stylegan2-ada were applied to fetal brain image generation and GAN-based data augmentation classifiers were compared with baseline classifiers. Our experimental results show that using data generated by both GANs and classical augmentation strategies allows for increasing the accuracy and area under the curve score.
Highlights
Diagnostic ultrasound is an essential tool during pregnancy [1]
The only previous example we found in medical imaging was applied to whole-body magnetic resonance imaging image generation [29] in which deep convolutional GAN (DCGAN) and StyleGAN family of Generative adversarial networks (GANs) architectures are compared and StyleGAN showed clear benefits
With the configurations outlined in Section 3.1.1 we trained a TTA-GAN for about 45 h and a TRV-GAN for about 27 h in a single GPU
Summary
Diagnostic ultrasound is an essential tool during pregnancy [1] It is employed both as a screening tool as well as to better assess high risk patients, both during early [2] or late pregnancy [3]. The acquisition of fetal and maternal ultrasound images is done following international guidelines promoted by scientific committees [7]. These guidelines provide clear protocols on which images need to be acquired depending on the trimester of pregnancy and classification of the patient. This results in each ultrasound examination having a large number of images (typically, more than 20). Three dimensional (3D) images and videos can be acquired to complete the clinical examination
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
