An efficient segment anything model for the segmentation of medical images

Abstract This paper introduces the efficient medical-images-aimed segment anything model (EMedSAM), addressing the high computational demands and limited adaptability of using SAM for medical image segmentation tasks. We present a novel, compact image encoder, DD-TinyViT, designed to enhance segment...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Guanliang Dong, Zhangquan Wang, Yourong Chen, Yuliang Sun, Hongbo Song, Liyuan Liu, Haidong Cui
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Nature Portfolio 2024-08-01
Colecção:	Scientific Reports
Assuntos:	Segment anything model Medical image Lightweight encoder Decoupled distillation Fine tuning adapter
Acesso em linha:	https://doi.org/10.1038/s41598-024-70288-8
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!