The Perinatal Institute and Section of Neonatology, Perinatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
Pediatr Radiol. 2021 Mar;51(3):392-402. doi: 10.1007/s00247-020-04854-3. Epub 2020 Oct 13.
Although MR elastography allows for quantitative evaluation of liver stiffness to assess chronic liver diseases, it has associated drawbacks related to additional scanning time, patient discomfort, and added costs.
To develop a machine learning model that can categorically classify the severity of liver stiffness using both anatomical T2-weighted MRI and clinical data for children and young adults with known or suspected pediatric chronic liver diseases.
We included 273 subjects with known or suspected chronic liver disease. We extracted data including axial T2-weighted fast spin-echo fat-suppressed images, clinical data (e.g., demographic/anthropomorphic data, particular medical diagnoses, laboratory values) and MR elastography liver stiffness measurements. We propose DeepLiverNet (a deep transfer learning model) to classify patients into one of two groups: no/mild liver stiffening (<3 kPa) or moderate/severe liver stiffening (≥3 kPa). We conducted internal cross-validation using 178 subjects, and external validation using an independent cohort of 95 subjects. We assessed diagnostic performance using accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AuROC).
In the internal cross-validation experiment, the combination of clinical and imaging data produced the best performance (AuROC=0.86) compared to clinical (AuROC=0.83) or imaging (AuROC=0.80) data alone. Using both clinical and imaging data, the DeepLiverNet correctly classified patients with accuracy of 88.0%, sensitivity of 74.3% and specificity of 94.6%. In our external validation experiment, this same deep learning model achieved an accuracy of 80.0%, sensitivity of 61.1%, specificity of 91.5% and AuROC of 0.79.
A deep learning model that incorporates clinical data and anatomical T2-weighted MR images might provide a means of risk-stratifying liver stiffness and directing the use of MR elastography.
虽然磁共振弹性成像（MR 弹性成像）允许对肝硬度进行定量评估，以评估慢性肝病，但它也存在与额外的扫描时间、患者不适和增加的成本相关的缺点。
开发一种机器学习模型，该模型可以使用解剖 T2 加权磁共振成像和临床数据对患有已知或疑似儿科慢性肝病的儿童和年轻人进行分类，以评估肝硬度的严重程度。
我们纳入了 273 名患有已知或疑似慢性肝病的患者。我们提取的数据包括轴向 T2 加权快速自旋回波脂肪抑制图像、临床数据（例如，人口统计学/人体测量数据、特定的医学诊断、实验室值）和磁共振弹性成像肝硬度测量值。我们提出了 DeepLiverNet（一种深度迁移学习模型），用于将患者分为两组之一：无/轻度肝硬度增加（<3kPa）或中度/重度肝硬度增加（≥3kPa）。我们使用 178 名患者进行内部交叉验证，使用 95 名独立患者进行外部验证。我们使用准确性、敏感性、特异性和接收器工作特征曲线（ROC）下面积（AuROC）来评估诊断性能。
在内部交叉验证实验中，与仅使用临床（AuROC=0.83）或影像（AuROC=0.80）数据相比，临床和影像数据的组合产生了最佳的性能（AuROC=0.86）。使用临床和影像数据，DeepLiverNet 正确分类患者的准确率为 88.0%，敏感性为 74.3%，特异性为 94.6%。在我们的外部验证实验中，相同的深度学习模型的准确性为 80.0%，敏感性为 61.1%，特异性为 91.5%，ROC 为 0.79。
一种结合临床数据和解剖 T2 加权磁共振成像的深度学习模型可能提供一种风险分层肝硬度和指导磁共振弹性成像使用的方法。
