DeepEMC-T2 Mapping: Deep Learning-Enabled T2 Mapping Based on Echo Modulation Curve Modeling
arxiv(2024)
摘要
Purpose: Echo modulation curve (EMC) modeling can provide accurate and
reproducible quantification of T2 relaxation times. The standard EMC-T2 mapping
framework, however, requires sufficient echoes and cumbersome pixel-wise
dictionary-matching steps. This work proposes a deep learning version of EMC-T2
mapping, called DeepEMC-T2 mapping, to efficiently estimate accurate T2 maps
from fewer echoes without a dictionary.
Methods: DeepEMC-T2 mapping was developed using a modified U-Net to estimate
both T2 and Proton Density (PD) maps directly from multi-echo spin-echo (MESE)
images. The modified U-Net employs several new features to improve the accuracy
of T2/PD estimation. MESE datasets from 68 subjects were used for training and
evaluation of the DeepEMC-T2 mapping technique. Multiple experiments were
conducted to evaluate the impact of the proposed new features on DeepEMC-T2
mapping.
Results: DeepEMC-T2 mapping achieved T2 estimation errors ranging from 3
in different T2 ranges and 0.8
which yielded more accurate parameter estimation than standard EMC-T2 mapping.
The new features proposed in DeepEMC-T2 mapping enabled improved parameter
estimation. The use of a larger echo spacing with fewer echoes can maintain the
accuracy of T2 and PD estimations while reducing the number of 180-degree
refocusing pulses.
Conclusions: DeepEMC-T2 mapping enables simplified, efficient, and accurate
T2 quantification directly from MESE images without a time-consuming
dictionary-matching step and requires fewer echoes. This allows for increased
volumetric coverage and/or decreased SAR by reducing the number of 180-degree
refocusing pulses.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要