Pollack Brian L, Batmanghelich Kayhan, Cai Stephen S, Gordon Emile, Wallace Stephen, Catania Roberta, Morillo-Hernandez Carlos, Furlan Alessandro, Borhani Amir A
Department of Biomedical Informatics (B.L.P., K.B.) and Department of Radiology (C.M.H.), University of Pittsburgh School of Medicine, Pittsburgh, Pa; and Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pa (S.S.C., E.G., S.W., R.C., A.F., A.A.B.).
Radiol Artif Intell. 2021 Sep 29;3(6):e200274. doi: 10.1148/ryai.2021200274. eCollection 2021 Nov.
To reconstruct virtual MR elastography (MRE) images based on traditional MRI inputs with a machine learning algorithm.
In this single-institution, retrospective study, 149 patients (mean age, 58 years ± 12 [standard deviation]; 71 men) with nonalcoholic fatty liver disease who underwent MRI and MRE between January 2016 and January 2019 were evaluated. Nine conventional MRI sequences and clinical data were used to train a convolutional neural network to reconstruct MRE images at the per-voxel level. The architecture was further modified to accept multichannel three-dimensional inputs and to allow inclusion of clinical and demographic information. Liver stiffness and fibrosis category (F0 [no fibrosis] to F4 [significant fibrosis]) of reconstructed images were assessed by using voxel- and patient-level agreement by correlation, sensitivity, and specificity calculations; in addition, classification by receiver operator characteristic analyses was performed, and Dice score was used to evaluate hepatic stiffness locality.
The model for predicting liver stiffness incorporated four image sequences (precontrast T1-weighted liver acquisition with volume acquisition [LAVA] water and LAVA fat, 120-second-delay T1-weighted LAVA water, and single-shot fast spin-echo T2 weighted) and clinical data. The model had a patient-level and voxel-level correlation of 0.50 ± 0.05 and 0.34 ± 0.03, respectively. By using a stiffness threshold of 3.54 kPa to make a binary classification into no fibrosis or mild fibrosis (F0-F1) versus clinically significant fibrosis (F2-F4), the model had sensitivity of 80% ± 4, specificity of 75% ± 5, accuracy of 78% ± 3, area under the receiver operating characteristic curve of 84 ± 0.04, and a Dice score of 0.74.
The generation of virtual elastography images is feasible by using conventional MRI and clinical data with a machine learning algorithm. MR Imaging, Abdomen/GI, Liver, Cirrhosis, Computer Applications/Virtual Imaging, Experimental Investigations, Feature Detection, Classification, Reconstruction Algorithms, Supervised Learning, Convolutional Neural Network (CNN) © RSNA, 2021.
使用机器学习算法基于传统MRI输入重建虚拟磁共振弹性成像（MRE）图像。
在这项单机构回顾性研究中，评估了2016年1月至2019年1月期间接受MRI和MRE检查的149例非酒精性脂肪性肝病患者（平均年龄58岁±12[标准差]；71例男性）。使用九个传统MRI序列和临床数据训练卷积神经网络，以在体素水平重建MRE图像。对该架构进行了进一步修改，以接受多通道三维输入并纳入临床和人口统计学信息。通过相关性、敏感性和特异性计算，使用体素和患者水平的一致性评估重建图像的肝脏硬度和纤维化类别（F0[无纤维化]至F4[显著纤维化]）；此外，通过接受者操作特征分析进行分类，并使用Dice评分评估肝脏硬度局部性。
预测肝脏硬度的模型纳入了四个图像序列（预对比T1加权肝脏容积采集[LAVA]水和LAVA脂肪、延迟120秒的T1加权LAVA水以及单次激发快速自旋回波T2加权）和临床数据。该模型在患者水平和体素水平的相关性分别为0.50±0.05和0.34±0.03。使用3.54kPa的硬度阈值进行二元分类，分为无纤维化或轻度纤维化（F0-F1）与临床显著纤维化（F2-F4），该模型的敏感性为80%±4，特异性为75%±5，准确性为78%±3，接受者操作特征曲线下面积为84±0.04，Dice评分为0.74。
使用传统MRI和临床数据以及机器学习算法生成虚拟弹性成像图像是可行的。MR成像、腹部/胃肠道、肝脏、肝硬化、计算机应用/虚拟成像、实验研究、特征检测、分类、重建算法、监督学习、卷积神经网络（CNN） ©RSNA，2021。
