Radiology, Mayo Clinic, Rochester, Minnesota, USA.
GI and Hepatology, Mayo Clinic, Rochester, Minnesota, USA.
J Magn Reson Imaging. 2021 Jul;54(1):122-131. doi: 10.1002/jmri.27549. Epub 2021 Feb 15.
Nonalcoholic fatty liver disease (NAFLD) affects 25% of the global population. The standard of diagnosis, biopsy, is invasive and affected by sampling error and inter-reader variability. We hypothesized that widely available rapid MRI techniques could be used to predict nonalcoholic steatohepatitis (NASH) noninvasively by measuring liver stiffness, with magnetic resonance elastography (MRE), and liver fat, with chemical shift-encoded (CSE) MRI. Besides, we validate an automated image analysis technique to maximize the utility of these methods.
To implement and test an automated system for analyzing CSE-MRI and MRE data coupled with model-based prediction of NASH.
Prospective.
Eighty-three patients with suspected NAFLD.
FIELD STRENGTH/SEQUENCE: A 1.5 T using a flow-compensated motion-encoded gradient echo MRE sequence and a multiecho CSE-MRI sequence.
The MRE and CSE-MRI data were analyzed by two readers (5+ and 1 years of experience) and an automated algorithm. A logistic regression model to predict pathology-diagnosed NASH was trained based on stiffness and proton density fat fraction, and the area under the receiver operating characteristic curve (AUROC) was calculated using 10-fold cross validation for models based on both automated and manual measurements. A separate model was trained to predict the NASH severity score (NAS).
Pearson's correlation, Bland-Altman, AUROC, C-statistic.
The agreement between automated measurements and the more experienced reader (R = 0.87 for stiffness and R = 0.99 for proton density fat fraction [PDFF]) was slightly better than the agreement between readers (R = 0.85 and 0.98). The model for predicting biopsy-diagnosed NASH had an AUROC of 0.87. The NAS-prediction model had a C-statistic of 0.85.
We demonstrated a workflow that used a limited MRI acquisition protocol and fully automated analysis to predict NASH with high accuracy. These methods show promise to provide a reliable noninvasive alternative to biopsy for NASH-screening in populations with NAFLD.
2 TECHNICAL EFFICACY STAGE: 2.
非酒精性脂肪性肝病（NAFLD）影响全球 25%的人口。诊断的标准是活检，但这种方法具有侵入性，且受到采样误差和读者间变异性的影响。我们假设，通过测量肝脏硬度（磁共振弹性成像，MRE）和肝脏脂肪（化学位移编码 CSE-MRI），广泛应用的快速 MRI 技术可以无创地预测非酒精性脂肪性肝炎（NASH）。此外，我们验证了一种自动图像分析技术，以最大限度地利用这些方法。
实现并测试一种用于分析 CSE-MRI 和 MRE 数据的自动化系统，并结合基于模型的 NASH 预测。
前瞻性。
83 例疑似 NAFLD 的患者。
磁场强度/序列：1.5T 采用流动补偿的运动编码梯度回波 MRE 序列和多回波 CSE-MRI 序列。
两名读者（5 年和 1 年经验）和自动算法分析 MRE 和 CSE-MRI 数据。基于硬度和质子密度脂肪分数，训练预测病理诊断 NASH 的逻辑回归模型，并使用 10 折交叉验证计算基于自动和手动测量的模型的接收者操作特征曲线下面积（AUROC）。还训练了一个单独的模型来预测 NASH 严重程度评分（NAS）。
Pearson 相关、Bland-Altman、AUROC、C 统计量。
自动化测量与经验更丰富的读者（硬度 R 为 0.87，质子密度脂肪分数[PDFF] R 为 0.99）之间的一致性稍好于读者之间的一致性（R 为 0.85 和 0.98）。预测活检诊断 NASH 的模型 AUROC 为 0.87。NAS 预测模型的 C 统计量为 0.85。
我们展示了一个使用有限的 MRI 采集方案和全自动分析的工作流程，能够以高精度预测 NASH。这些方法有望为 NASH 筛查提供一种可靠的、替代活检的方法，适用于 NAFLD 人群。
2 技术功效分期：2
