Development and validation of a fully automated transformer-based 3D framework for pancreatic fat quantification in pancreatic steatosis

Purpose: To develop and validate a fully automated TransUNet-based framework for 3D pancreatic segmentation and volumetric fat quantification on PDFF MRI. Specifically, to evaluate the model's performance against state-of-the-art CNN architectures and assess its clinical reproducibility compared to...

ver descrição completa

Detalhes bibliográficos

Principais autores:	You Pang, Gary Ge Ren, Raymond Shing Yan Tang, Winnie Chu, Chileka Chiyanika
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Elsevier 2026-06-01
Colecção:	European Journal of Radiology Open
Assuntos:	Pancreas Adipose Tissue Deep Learning Magnetic Resonance Imaging Adiposity
Acesso em linha:	http://www.sciencedirect.com/science/article/pii/S2352047726000262
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!