Wang Kang, Mamidipalli Adrija, Retson Tara, Bahrami Naeim, Hasenstab Kyle, Blansit Kevin, Bass Emily, Delgado Timoteo, Cunha Guilherme, Middleton Michael S, Loomba Rohit, Neuschwander-Tetri Brent A, Sirlin Claude B, Hsiao Albert
Artificial Intelligence and Data Analytic Laboratory (AiDA lab), Department of Radiology, University of California, San Diego. La Jolla, CA 92092.
Liver Imaging Group, Department of Radiology, University of California, San Diego. La Jolla, CA 92092.
Radiol Artif Intell. 2019 Mar;1(2). doi: 10.1148/ryai.2019180022. Epub 2019 Mar 27.
To assess feasibility of training a convolutional neural network (CNN) to automate liver segmentation across different imaging modalities and techniques used in clinical practice and apply this to enable automation of liver biometry.
We trained a 2D U-Net CNN for liver segmentation in two stages using 330 abdominal MRI and CT exams acquired at our institution. First, we trained the neural network with non-contrast multi-echo spoiled-gradient-echo (SGPR)images with 300 MRI exams to provide multiple signal-weightings. Then, we used transfer learning to generalize the CNN with additional images from 30 contrast-enhanced MRI and CT exams.We assessed the performance of the CNN using a distinct multi-institutional data set curated from multiple sources (n = 498 subjects). Segmentation accuracy was evaluated by computing Dice scores. Utilizing these segmentations, we computed liver volume from CT and T1-weighted (T1w) MRI exams, and estimated hepatic proton- density-fat-fraction (PDFF) from multi-echo T2*w MRI exams. We compared quantitative volumetry and PDFF estimates between automated and manual segmentation using Pearson correlation and Bland-Altman statistics.
Dice scores were 0.94 ± 0.06 for CT (n = 230), 0.95 ± 0.03 (n = 100) for T1w MR, and 0.92 ± 0.05 for T2*w MR (n = 169). Liver volume measured by manual and automated segmentation agreed closely for CT (95% limit-of-agreement (LoA) = [-298 mL, 180 mL]) and T1w MR (LoA = [-358 mL, 180 mL]). Hepatic PDFF measured by the two segmentations also agreed closely (LoA = [-0.62%, 0.80%]).
Utilizing a transfer-learning strategy, we have demonstrated the feasibility of a CNN to be generalized to perform liver segmentations across different imaging techniques and modalities. With further refinement and validation, CNNs may have broad applicability for multimodal liver volumetry and hepatic tissue characterization.
评估训练卷积神经网络（CNN）以自动分割临床实践中使用的不同成像模态和技术下的肝脏，并将其应用于实现肝脏生物测量自动化的可行性。
我们使用在本机构获取的330例腹部MRI和CT检查，分两个阶段训练用于肝脏分割的二维U-Net CNN。首先，我们使用300例MRI检查的非对比多回波扰相梯度回波（SGPR）图像训练神经网络，以提供多种信号加权。然后，我们使用迁移学习，用另外30例对比增强MRI和CT检查的图像使CNN泛化。我们使用从多个来源精心挑选的不同多机构数据集（n = 498名受试者）评估CNN的性能。通过计算Dice分数评估分割准确性。利用这些分割结果，我们从CT和T1加权（T1w）MRI检查中计算肝脏体积，并从多回波T2*w MRI检查中估计肝脏质子密度脂肪分数（PDFF）。我们使用Pearson相关性和Bland-Altman统计方法比较自动分割和手动分割之间的定量体积测量和PDFF估计。
CT（n = 230）的Dice分数为0.94±0.06，T1w MR（n = 100）为0.95±0.03，T2*w MR（n = 169）为0.92±0.05。手动和自动分割测量的肝脏体积在CT（95%一致性界限（LoA）= [-298 mL，180 mL]）和T1w MR（LoA = [-358 mL，180 mL]）方面密切一致。两种分割方法测量的肝脏PDFF也密切一致（LoA = [-0.62%，0.80%]）。
利用迁移学习策略，我们证明了CNN泛化以跨不同成像技术和模态执行肝脏分割的可行性。经过进一步完善和验证，CNN可能在多模态肝脏体积测量和肝组织特征分析方面具有广泛的适用性。
