Generative adversarial networks to improve fetal brain fine-grained plane classification

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 a...

ver descrição completa

Detalhes bibliográficos
Autores: Montero Agudo, Alberto, Bonet Carné, Elisenda|||0000-0003-0567-6141, Burgos Artizzu, Xavier Paolo
Formato: artículo
Fecha de publicación:2021
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/358692
Acesso em linha:https://hdl.handle.net/2117/358692
https://dx.doi.org/10.3390/s21237975
Access Level:acceso abierto
Palavra-chave:Deep learning
Brain -- Imaging
Generative adversarial networks
Ultrasound image classification
Aprenentatge profund
Cervell -- Imatgeria
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
Descrição
Resumo: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.