Open AccessAutomated cartilage segmentation and quantification using 3D ultrashort echo time (UTE) cones MR imaging with deep convolutional neural networks
Author(s) -
Yanling Xue,
Hyungseok Jang,
Michał Byra,
Zhenyu Cai,
Mei Wu,
Eric Y. Chang,
Yajun Ma,
Jiang Du
Publication year - 2021
Publication title -
european radiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.606
H-Index - 149
eISSN - 1432-1084
pISSN - 0938-7994
DOI - 10.1007/s00330-021-07853-6
Subject(s) - intraclass correlation , segmentation , convolutional neural network , sørensen–dice coefficient , pearson product moment correlation coefficient , artificial intelligence , cartilage , pattern recognition (psychology) , medicine , nuclear medicine , computer science , image segmentation , anatomy , mathematics , statistics , clinical psychology , psychometrics
To develop a fully automated full-thickness cartilage segmentation and mapping of T1, T1ρ, and T2*, as well as macromolecular fraction (MMF) by combining a series of quantitative 3D ultrashort echo time (UTE) cones MR imaging with a transfer learning-based U-Net convolutional neural networks (CNN) model.