Context-aware augmentation for liver lesion segmentation: shape uniformity, expansion limit and fusion strategy

BACKGROUND: Data augmentation with context has been an effective way to increase the robustness and generalizability of deep learning models. However, to our knowledge, shape uniformity, expansion limit, and fusion strategy of context have yet to be comprehensively studied, particularly in lesion se...

Descripción completa

Detalles Bibliográficos
Autores principales: He, Qiang, Duan, Yujie, Yang, Zhiyu, Wang, Yaxuan, Yang, Liyu, Bai, Lin, Zhao, Liang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AME Publishing Company 2023
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10423356/
https://www.ncbi.nlm.nih.gov/pubmed/37581084
http://dx.doi.org/10.21037/qims-22-1399

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10423356/
https://www.ncbi.nlm.nih.gov/pubmed/37581084
http://dx.doi.org/10.21037/qims-22-1399

Ejemplares similares