Dilated transformer: residual axial attention for breast ultrasound image segmentation

BACKGROUND: The segmentation of breast ultrasound (US) images has been a challenging task, mainly due to limited data and the inherent image characteristics involved, such as low contrast and speckle noise. Although convolutional neural network-based (CNN-based) methods have made significant progres...

Descripción completa

Detalles Bibliográficos
Autores principales: Shen, Xiaoyan, Wang, Liangyu, Zhao, Yu, Liu, Ruibo, Qian, Wei, Ma, He
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AME Publishing Company 2022
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9403584/
https://www.ncbi.nlm.nih.gov/pubmed/36060605
http://dx.doi.org/10.21037/qims-22-33

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9403584/
https://www.ncbi.nlm.nih.gov/pubmed/36060605
http://dx.doi.org/10.21037/qims-22-33

Ejemplares similares