Medical image segmentation based on frequency domain decomposition SVD linear attention

Medical image segmentation based on frequency domain decomposition SVD linear attention

Abstract Convolutional Neural Networks (CNNs) have achieved remarkable segmentation accuracy in medical image segmentation tasks. However, the Vision Transformer (ViT) model, with its capability of extracting global information, offers a significant advantage in contextual information compared to th...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu Qiong, Li Chaofan, Teng Jinnan, Chen Liping, Song Jianxiang
Formato: Artículo
Lenguaje:English
Publicado: Nature Portfolio 2025-01-01
Colección:Scientific Reports
Materias:
Transformer
Frequency domain decomposition
SVD Decomposition
Image segmentation
Acceso en línea:https://doi.org/10.1038/s41598-025-86315-1

Internet

https://doi.org/10.1038/s41598-025-86315-1

Ejemplares similares