Department of Radiology, The Second Affiliated Hospital of Anhui Medical University, 678 Furong Road, Hefei 230601, Anhui, China.
GE Healthcare China, Pudong New Town, No. 1, Huatuo Road, Shanghai 210000, China.
Can J Gastroenterol Hepatol. 2022 Jun 21;2022:2249447. doi: 10.1155/2022/2249447. eCollection 2022.
To develop and validate a radiomic nomogram based on texture features from out-of-phase T1W images and clinical biomarkers in prediction of liver fibrosis.
Patients clinically diagnosed with chronic liver fibrosis who underwent liver biopsy and noncontrast MRI were enrolled. All patients were assigned to the nonsignificant fibrosis group with fibrosis stage <2 and the significant fibrosis group with stage ≥2. Texture parameters were extracted from out-of-phase T1-weighted (T1W) images and calculated using the Artificial Intelligent Kit (AK). Boruta and LASSO regressions were used for feature selection and a multivariable logistic regression was used for construction of a combinational model integrating radiomics and clinical biomarkers. The performance of the models was assessed by using the receiver operator curve (ROC) and decision curve.
ROC analysis of the radiomics model that included the most discriminative features showed AUCs of the training and test groups were 0.80 and 0.78. A combinational model integrating RADscore and fibrosis 4 index was established. ROC analysis of the training and test groups showed good to excellent performance with AUC of 0.93 and 0.86. Decision curves showed the combinational model added more net benefit than radiomic and clinical models alone.
The study presents a combinational model that incorporates RADscore and clinical biomarkers, which is promising in classification of liver fibrosis.
基于反相位 T1W 图像的纹理特征和临床生物标志物，开发并验证一种列线图模型，用于预测肝纤维化。
本研究纳入了经临床诊断为慢性肝纤维化并接受肝活检和非对比 MRI 检查的患者。所有患者被分为纤维化分期<2 期的无显著纤维化组和纤维化分期≥2 期的显著纤维化组。从反相位 T1 加权（T1W）图像中提取纹理参数，并使用人工智能工具包（AK）进行计算。Boruta 和 LASSO 回归用于特征选择，多变量逻辑回归用于构建整合放射组学和临床生物标志物的组合模型。使用受试者工作特征曲线（ROC）和决策曲线评估模型的性能。
包含最具鉴别力特征的放射组学模型的 ROC 分析显示，训练组和测试组的 AUC 分别为 0.80 和 0.78。建立了一个整合 RADscore 和纤维化 4 指数的组合模型。训练组和测试组的 ROC 分析显示出良好到优异的性能，AUC 分别为 0.93 和 0.86。决策曲线显示，与单独的放射组学和临床模型相比，组合模型增加了更多的净收益。
本研究提出了一种整合 RADscore 和临床生物标志物的组合模型，有望用于肝纤维化的分类。
