Linear fine-tuning: a linear transformation based transfer strategy for deep MRI reconstruction

Linear fine-tuning: a linear transformation based transfer strategy for deep MRI reconstruction

IntroductionFine-tuning (FT) is a generally adopted transfer learning method for deep learning-based magnetic resonance imaging (MRI) reconstruction. In this approach, the reconstruction model is initialized with pre-trained weights derived from a source domain with ample data and subsequently updat...

Full description

Bibliographic Details
Main Authors: Wanqing Bi, Jianan Xv, Mengdie Song, Xiaohan Hao, Dayong Gao, Fulang Qi
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-06-01
Series:Frontiers in Neuroscience
Subjects:
magnetic resonance imaging reconstruction
deep learning
transfer learning
fine-tuning
transfer strategy
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2023.1202143/full

Internet

https://www.frontiersin.org/articles/10.3389/fnins.2023.1202143/full

Similar Items