Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 113-0033, Japan.
Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 113-0033, Japan.
Eur Radiol. 2018 Jul;28(7):3050-3058. doi: 10.1007/s00330-017-5270-5. Epub 2018 Feb 5.
To determine if texture analysis of non-contrast-enhanced CT (NECT) images is able to predict nonalcoholic steatohepatitis (NASH).
NECT images from 88 patients who underwent a liver biopsy for the diagnosis of suspected NASH were assessed and texture feature parameters were obtained without and with filtration. The patient population was divided into a predictive learning dataset and a validation dataset, and further divided into groups according to the prediction of liver fibrosis as assessed by hyaluronic acid levels. The reference standard was the histological result of a liver biopsy. A predictive model for NASH was developed using parameters derived from the learning dataset that demonstrated areas under the receiver operating characteristic curve (AUC) of >0.65. The resulting model was then applied to the validation dataset.
In patients without suspected fibrosis, the texture parameter mean without filter and skewness with a 2-mm filter were selected for the NASH prediction model. The AUC of the predictive model for the validation dataset was 0.94 and the accuracy was 94%. In patients with suspicion of fibrosis, the mean without filtration and kurtosis with a 4-mm filter were selected for the NASH prediction model. The AUC for the validation dataset was 0.60 and the accuracy was 42%.
In patients without suspicion of fibrosis, NECT texture analysis effectively predicted NASH.
• In patients without suspicion of fibrosis, NECT texture analysis effectively predicted NASH. • The mean without filtration and skewness with a 2-mm filter were modest predictors of NASH in patients without suspicion of liver fibrosis. • Hepatic fibrosis masks the characteristic texture features of NASH.
确定非增强 CT（NECT）图像的纹理分析是否能够预测非酒精性脂肪性肝炎（NASH）。
对 88 例因疑似 NASH 而行肝活检的患者的NECT 图像进行评估，并获取无过滤和过滤后的纹理特征参数。患者人群分为预测学习数据集和验证数据集，并根据透明质酸水平评估的肝纤维化预测进一步分为各组。参考标准是肝活检的组织学结果。使用从学习数据集中获得的参数开发 NASH 预测模型，该模型的受试者工作特征曲线（AUC）>0.65。然后将得到的模型应用于验证数据集。
在无纤维化可疑的患者中，选择无过滤均值和 2mm 过滤偏度作为 NASH 预测模型的纹理参数。验证数据集预测模型的 AUC 为 0.94，准确率为 94%。在有纤维化可疑的患者中，选择无过滤均值和 4mm 过滤峰度作为 NASH 预测模型的纹理参数。验证数据集的 AUC 为 0.60，准确率为 42%。
在无纤维化可疑的患者中，NECT 纹理分析能有效预测 NASH。
在无纤维化可疑的患者中，NECT 纹理分析能有效预测 NASH。
在无纤维化可疑的患者中，无过滤均值和 2mm 过滤偏度是预测 NASH 的适度指标。
肝纤维化掩盖了 NASH 的特征纹理特征。
