Deep Learning Prediction of Voxel-Level Liver Stiffness in Patients with Nonalcoholic Fatty Liver Disease.
Deep Learning Prediction of Voxel-Level Liver Stiffness in Patients with Nonalcoholic Fatty Liver Disease.
复制标题
DOI：
10.1148/ryai.2021200274
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Brian L Pollack;K. Batmanghelich;Stephen S Cai;E. Gordon;Stephen Wallace;R. Catania;Carlos Morillo-Hernandez;A. Furlan;A. Borhani
中科院分区：
文献类型：
--
作者：
Brian L Pollack;K. Batmanghelich;Stephen S Cai;E. Gordon;Stephen Wallace;R. Catania;Carlos Morillo-Hernandez;A. Furlan;A. Borhani
目的利用机器学习算法，在传统MRI输入的基础上重建虚拟MR弹性成像图像。在这项单机构回顾性研究中，对2016年1月至2019年1月期间接受MRI和MRE的149例非酒精性脂肪肝患者（平均年龄58岁± 12岁[标准差]; 71例男性）进行了评价。使用9个常规MRI序列和临床数据来训练卷积神经网络，以在每个体素水平上重建MRE图像。进一步修改了架构，以接受多通道三维输入，并允许纳入临床和人口统计信息。通过相关性、灵敏度和特异性计算，使用体素和患者水平一致性评估重建图像的肝硬度和纤维化类别（F0 [无纤维化]至F4 [显著纤维化]）;此外，通过接收者操作员特征分析进行分类，并使用Dice评分评价肝硬度位置。结果预测肝脏硬度的模型包括四个图像序列（增强前T1加权肝脏采集与体积采集[LAVA]水和LAVA脂肪，120秒延迟T1加权LAVA水，和单次激发快速自旋回波T2加权）和临床数据。该模型的患者水平和体素水平相关性分别为0.50 ± 0.05和0.34 ± 0.03。通过使用3.54 kPa的刚度阈值将其二元分类为无纤维化或轻度纤维化（F0-F1）与临床显着纤维化（F2-F4），该模型的灵敏度为80% ± 4，特异性为75% ± 5，准确度为78% ± 3，受试者操作特征曲线下面积为84 ± 0.04，Dice评分为0.74。结论虚拟弹性成像图像的生成是可行的，通过使用传统的MRI和临床数据与机器learning algorithm.Keywords：MR成像，腹部/GI，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）补充材料可用于这篇文章。© RSNA，2021.
Purpose To reconstruct virtual MR elastography (MRE) images based on traditional MRI inputs with a machine learning algorithm. Materials and Methods 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. Results 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. Conclusion The generation of virtual elastography images is feasible by using conventional MRI and clinical data with a machine learning algorithm.Keywords: MR Imaging, Abdomen/GI, Liver, Cirrhosis, Computer Applications/Virtual Imaging, Experimental Investigations, Feature Detection, Classification, Reconstruction Algorithms, Supervised Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2021.