Predicting the Initial Treatment Response to Transarterial Chemoembolization in Intermediate-Stage Hepatocellular Carcinoma by the Integration of Radiomics and Deep Learning.
Predicting the Initial Treatment Response to Transarterial Chemoembolization in Intermediate-Stage Hepatocellular Carcinoma by the Integration of Radiomics and Deep Learning.
复制标题
DOI：
10.3389/fonc.2021.730282
复制
发表时间：
2021
影响因子：
4.7
通讯作者：
Zhang J
中科院分区：
文献类型：
--
作者：
Peng J;Huang J;Huang G;Zhang J
我们的目的是开发基于放射学的模型，用于肝细胞癌（HCC）患者经动脉化疗栓塞（TACE）的初始治疗反应的术前预测，因为放射组学和深度学习（DL）的整合尚未报告用于TACE。从三个独立的医疗中心招募了310名接受TACE的中期HCC患者。基于计算机断层扫描（CT）图像，递归特征消除（RFE）被用来选择最有用的放射组学特征。五个放射组学常规机器学习（CML）模型和DL模型用于训练和验证。分析各模型间的相关性。然后评估整合临床变量、CML和DL模型的准确性。在5个CML模型中，两个队列均显示出良好的预测准确性，尤其是随机森林算法（AUC分别为0.967和0.964）。DL在训练和验证队列中显示出高准确性（AUC分别为0.981和0.972）。5种CML模型及DL模型与肿瘤大小呈显著正相关（P < 0.001）。通过在训练和验证队列中集成DL和随机森林算法实现了最高的准确性（AUC分别为0.995和0.994）。放射组学cML模型和DL模型在预测TACE治疗的初始反应方面显示出显著的准确性。此外，集成模型可以作为一种新的和准确的方法预测中期肝癌。
We aimed to develop radiology-based models for the preoperative prediction of the initial treatment response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) since the integration of radiomics and deep learning (DL) has not been reported for TACE. Three hundred and ten intermediate-stage HCC patients who underwent TACE were recruited from three independent medical centers. Based on computed tomography (CT) images, recursive feature elimination (RFE) was used to select the most useful radiomics features. Five radiomics conventional machine learning (cML) models and a DL model were used for training and validation. Mutual correlations between each model were analyzed. The accuracies of integrating clinical variables, cML, and DL models were then evaluated. Good predictive accuracies were showed across the two cohorts in the five cML models, especially the random forest algorithm (AUC = 0.967 and 0.964, respectively). DL showed high accuracies in the training and validation cohorts (AUC = 0.981 and 0.972, respectively). Significant mutual correlations were revealed between tumor size and the five cML models and DL model (each P < 0.001). The highest accuracies were achieved by integrating DL and the random forest algorithm in the training and validation cohorts (AUC = 0.995 and 0.994, respectively). The radiomics cML models and DL model showed notable accuracy for predicting the initial response to TACE treatment. Moreover, the integrated model could serve as a novel and accurate method for prediction in intermediate-stage HCC.
登录
查看更多内容
影响因子：
--
作者：
He C;Zhang X;Li C;Peng W;Wen TF;Yan LN;Yang J;Lu W
通讯作者：
Lu W
影响因子：
4.1
作者：
Hu HT;Wang W;Chen LD;Ruan SM;Chen SL;Li X;Lu MD;Xie XY;Kuang M
通讯作者：
Kuang M
影响因子：
1.6
作者：
Shen JY;Li C;Wen TF;Yan LN;Li B;Wang WT;Yang JY;Xu MQ;Nazar Highness T
通讯作者：
Nazar Highness T
影响因子：
4.7
作者：
Huang Y;Zeng H;Chen L;Luo Y;Ma X;Zhao Y
通讯作者：
Zhao Y
乙型肝炎病毒相关肝细胞癌术前预测微血管侵犯风险的放射组学列线图
影响因子：
2.1
作者：
Peng, Jie;Zhang, Jing;Liu, Li
通讯作者：
Liu, Li