QR-Code

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...

Ausführliche Beschreibung

Gespeichert in:
Hauptverfasser: Guanliang Dong, Zhangquan Wang, Yourong Chen, Yuliang Sun, Hongbo Song, Liyuan Liu, Haidong Cui
Format: Artigo
Sprache:Inglês
Veröffentlicht: Nature Portfolio 2024-08-01
Schriftenreihe:Scientific Reports
Schlagworte:
Segment anything model
Medical image
Lightweight encoder
Decoupled distillation
Fine tuning adapter
Online-Zugang:https://doi.org/10.1038/s41598-024-70288-8
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

Ähnliche Einträge