Your browser doesn't support javascript.
loading
US2Mask: Image-to-mask generation learning via a conditional GAN for cardiac ultrasound image segmentation.
Wang, Gang; Zhou, Mingliang; Ning, Xin; Tiwari, Prayag; Zhu, Haobo; Yang, Guang; Yap, Choon Hwai.
Afiliación
  • Wang G; School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, Chongqing; Department of Bioengineering, Imperial College London, London, UK.
  • Zhou M; School of Computer Science, Chongqing University, Chongqing, Chongqing. Electronic address: mingliangzhou@cqu.edu.cn.
  • Ning X; Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China.
  • Tiwari P; School of Information Technology, Halmstad University, Halmstad, Sweden.
  • Zhu H; University of Oxford, Oxford, UK.
  • Yang G; Department of Bioengineering, Imperial College London, London, UK; Cardiovascular Research Centre, Royal Brompton Hospital, London, UK; National Heart and Lung Institute, Imperial College London, London, UK.
  • Yap CH; Department of Bioengineering, Imperial College London, London, UK.
Comput Biol Med ; 172: 108282, 2024 Apr.
Article en En | MEDLINE | ID: mdl-38503085
ABSTRACT
Cardiac ultrasound (US) image segmentation is vital for evaluating clinical indices, but it often demands a large dataset and expert annotations, resulting in high costs for deep learning algorithms. To address this, our study presents a framework utilizing artificial intelligence generation technology to produce multi-class RGB masks for cardiac US image segmentation. The proposed approach directly performs semantic segmentation of the heart's main structures in US images from various scanning modes. Additionally, we introduce a novel learning approach based on conditional generative adversarial networks (CGAN) for cardiac US image segmentation, incorporating a conditional input and paired RGB masks. Experimental results from three cardiac US image datasets with diverse scan modes demonstrate that our approach outperforms several state-of-the-art models, showcasing improvements in five commonly used segmentation metrics, with lower noise sensitivity. Source code is available at https//github.com/energy588/US2mask.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Inteligencia Artificial / Ecocardiografía Idioma: En Revista: Comput Biol Med Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Inteligencia Artificial / Ecocardiografía Idioma: En Revista: Comput Biol Med Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos