Meneses Juan P, Qadir Ayyaz, Surendran Nirusha, Arrieta Cristobal, Tejos Cristian, Andia Marcelo E, Chen Zhaolin, Uribe Sergio
Biomedical Imaging Center, Pontificia Universidad Católica de Chile, Santiago, Chile.
i-HEALTH Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile.
Eur Radiol. 2025 May;35(5):2843-2854. doi: 10.1007/s00330-024-11164-x. Epub 2024 Nov 5.
To estimate proton density fat fraction (PDFF) from chemical shift encoded (CSE) MR images using a deep learning (DL)-based method that is precise and robust to different MR scanners and acquisition echo times (TEs).
Variable echo times neural network (VET-Net) is a two-stage framework that first estimates nonlinear variables of the CSE-MR signal model, to posteriorly estimate water/fat signal components using the least-squares method. VET-Net incorporates a vector with TEs as an auxiliary input, therefore enabling PDFF calculation with any TE setting. A single-site liver CSE-MRI dataset (188 subjects, 4146 axial slices) was considered, which was split into training (150 subjects), validation (18), and testing (20) subsets. Testing subjects were scanned using several protocols with different TEs, which we then used to measure the PDFF reproducibility coefficient (RDC) at two regions of interest (ROIs): the right posterior and left hepatic lobes. An open-source multi-site and multi-vendor fat-water phantom dataset was also used for PDFF bias assessment.
VET-Net showed RDCs of 1.71% and 1.04% on the right posterior and left hepatic lobes, respectively, across different TEs, which was comparable to a reference graph cuts-based method (RDCs = 1.71% and 0.86%). VET-Net also showed a smaller PDFF bias (-0.55%) than graph cuts (0.93%) when tested on a multi-site phantom dataset. Reproducibility (1.94% and 1.59%) and bias (-2.04%) were negatively affected when the auxiliary TE input was not considered.
VET-Net provided unbiased and precise PDFF estimations using CSE-MR images from different hardware vendors and different TEs, outperforming conventional DL approaches.
Question Reproducibility of liver PDFF DL-based approaches on different scan protocols or manufacturers is not validated. Findings VET-Net showed a PDFF bias of -0.55% on a multi-site phantom dataset, and RDCs of 1.71% and 1.04% at two liver ROIs. Clinical relevance VET-Net provides efficient, in terms of scan and processing times, and unbiased PDFF estimations across different MR scanners and scan protocols, and therefore it can be leveraged to expand the use of MRI-based liver fat quantification to assess hepatic steatosis.
使用一种基于深度学习（DL）的方法从化学位移编码（CSE）磁共振成像（MRI）中估计质子密度脂肪分数（PDFF），该方法对不同的MR扫描仪和采集回波时间（TE）精确且稳健。
可变回波时间神经网络（VET-Net）是一个两阶段框架，首先估计CSE-MR信号模型的非线性变量，然后使用最小二乘法估计水/脂肪信号分量。VET-Net将一个包含TE的向量作为辅助输入，因此能够在任何TE设置下进行PDFF计算。考虑了一个单中心肝脏CSE-MRI数据集（188名受试者，4146个轴向切片），将其分为训练集（150名受试者）、验证集（18名）和测试集（20名）。使用几种具有不同TE的协议对测试受试者进行扫描，然后我们在两个感兴趣区域（ROI）：右后叶和左肝叶测量PDFF再现性系数（RDC）。一个开源的多中心和多厂商脂肪-水模体数据集也用于PDFF偏差评估。
VET-Net在不同TE下右后叶和左肝叶的RDC分别为1.71%和1.04%，与基于参考图割的方法相当（RDC分别为1.71%和0.86%）。在多中心模体数据集上测试时，VET-Net的PDFF偏差（-0.55%）也比图割（0.93%）小。当不考虑辅助TE输入时，再现性（1.94%和1.59%）和偏差（-2.04%）受到负面影响。
VET-Net使用来自不同硬件厂商和不同TE的CSE-MR图像提供了无偏差且精确的PDFF估计，优于传统的DL方法。
问题基于DL的肝脏PDFF方法在不同扫描协议或制造商上的再现性未得到验证。发现VET-Net在多中心模体数据集上的PDFF偏差为-0.55%，在两个肝脏ROI处的RDC分别为1.71%和1.04%。临床意义VET-Net在扫描和处理时间方面提供了高效且无偏差的PDFF估计，适用于不同的MR扫描仪和扫描协议，因此可用于扩大基于MRI的肝脏脂肪定量评估肝脂肪变性的应用。
