A Radiomics-based Approach for Predicting Early Recurrence in Intrahepatic Cholangiocarcinoma after Surgical Resection: A Multicenter Study

• Published in: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) Vol. 2021; pp. 3659 - 3662
• Main Authors: Hao, Xiaohan, Liu, Bing, Hu, Xiaofei, Wei, Jingwei, Han, Yuqi, Liu, Xianchuang, Chen, Zhiyu, Li, Jiaping, Bai, Jie, Chen, Yongliang, Wang, Jian, Niu, Meng, Tian, Jie
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.11.2021
• Subjects: Bile Duct Neoplasms - diagnostic imaging; Bile Duct Neoplasms - surgery; Bile Ducts, Intrahepatic - diagnostic imaging; Bile Ducts, Intrahepatic - surgery; Biological system modeling; Cholangiocarcinoma - diagnostic imaging; Cholangiocarcinoma - surgery; Computed tomography; Hospitals; Humans; Predictive models; Retrospective Studies; Surgery; Surveillance; Tomography, X-Ray Computed; Training
• ISSN: 2694-0604
• DOI: 10.1109/EMBC46164.2021.9630029

This work aimed to develop a noninvasive and reliable computed tomography (CT)-based imaging biomarker to predict early recurrence (ER) of intrahepatic cholangiocarcinoma (ICC) via radiomics analysis. In this retrospective study, a total of 177 ICC patients were enrolled from three independent hospitals. Radiomic features were extracted on CT images, then 11 feature selection algorithms and 4 classifiers were to conduct a multi-strategy radiomics modeling. Six established radiomics models were selected as stable ones by robustness-based rule. Among those models, Max-Relevance Min-Redundancy (MRMR) combined with Gradient Boosting Machine (GBM) yielded the highest areas under the receiver operating characteristics curve (AUCs) of 0.802 (95% confidence interval [CI]: 0.727-0.876) and 0.781 (95% CI: 0.655-0.907) in the training and test cohorts, respectively. To evaluate the generalization of the developed radiomics model, stratification analysis was performed regarding different centers. The MRMR-GBM-based model manifested good generalization with comparable AUCs in each hospital (p > 0.05 for paired comparison). Thus, the MRMR-GBM-based model could offer a potential imaging biomarker to assist the prediction of ER in ICC in a noninvasive manner.Clinical Relevance-The proposed radiomics model achieved satisfactory accuracy and good generalization ability in predicting ER in ICC, which might assist personalized surveillance and clinical treatment strategy making.