PMID- 34674948 OWN - NLM STAT- MEDLINE DCOM- 20220803 LR - 20220803 IS - 1499-3872 (Print) VI - 21 IP - 4 DP - 2022 Aug TI - CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma: A multicenter study. PG - 325-333 LID - S1499-3872(21)00198-3 [pii] LID - 10.1016/j.hbpd.2021.09.011 [doi] AB - BACKGROUND: Macrovascular invasion (MaVI) occurs in nearly half of hepatocellular carcinoma (HCC) patients at diagnosis or during follow-up, which causes severe disease deterioration, and limits the possibility of surgical approaches. This study aimed to investigate whether computed tomography (CT)-based radiomics analysis could help predict development of MaVI in HCC. METHODS: A cohort of 226 patients diagnosed with HCC was enrolled from 5 hospitals with complete MaVI and prognosis follow-ups. CT-based radiomics signature was built via multi-strategy machine learning methods. Afterwards, MaVI-related clinical factors and radiomics signature were integrated to construct the final prediction model (CRIM, clinical-radiomics integrated model) via random forest modeling. Cox-regression analysis was used to select independent risk factors to predict the time of MaVI development. Kaplan-Meier analysis was conducted to stratify patients according to the time of MaVI development, progression-free survival (PFS), and overall survival (OS) based on the selected risk factors. RESULTS: The radiomics signature showed significant improvement for MaVI prediction compared with conventional clinical/radiological predictors (P < 0.001). CRIM could predict MaVI with satisfactory areas under the curve (AUC) of 0.986 and 0.979 in the training (n = 154) and external validation (n = 72) datasets, respectively. CRIM presented with excellent generalization with AUC of 0.956, 1.000, and 1.000 in each external cohort that accepted disparate CT scanning protocol/manufactory. Peel9_fos_InterquartileRange [hazard ratio (HR) = 1.98; P < 0.001] was selected as the independent risk factor. The cox-regression model successfully stratified patients into the high-risk and low-risk groups regarding the time of MaVI development (P < 0.001), PFS (P < 0.001) and OS (P = 0.002). CONCLUSIONS: The CT-based quantitative radiomics analysis could enable high accuracy prediction of subsequent MaVI development in HCC with prognostic implications. CI - Copyright (c) 2021. Published by Elsevier B.V. FAU - Wei, Jing-Wei AU - Wei JW AD - Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China. FAU - Fu, Si-Rui AU - Fu SR AD - Zhuhai Interventional Medical Center, Zhuhai Precision Medical Center, Zhuhai People's Hospital, Zhuhai Hospital of Jinan University, Zhuhai 519000, China. FAU - Zhang, Jie AU - Zhang J AD - Department of Radiology, Zhuhai Precision Medical Center, Zhuhai People's Hospital, Zhuhai Hospital of Jinan University, Zhuhai 519000, China. FAU - Gu, Dong-Sheng AU - Gu DS AD - Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China. FAU - Li, Xiao-Qun AU - Li XQ AD - Department of Interventional Treatment, Zhongshan City People's Hospital, Zhongshan 528400, China. FAU - Chen, Xu-Dong AU - Chen XD AD - Department of Radiology, Shenzhen People's Hospital, Shenzhen 518000, China. FAU - Zhang, Shuai-Tong AU - Zhang ST AD - Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China. FAU - He, Xiao-Fei AU - He XF AD - Interventional Diagnosis and Treatment Department, Nanfang Hospital, Southern Medical University, Guangzhou, 510000, China. FAU - Yan, Jian-Feng AU - Yan JF AD - Department of Radiology, Yangjiang People's Hospital, Yangjiang 529500, China. FAU - Lu, Li-Gong AU - Lu LG AD - Zhuhai Interventional Medical Center, Zhuhai Precision Medical Center, Zhuhai People's Hospital, Zhuhai Hospital of Jinan University, Zhuhai 519000, China. Electronic address: llg0902@sina.com. FAU - Tian, Jie AU - Tian J AD - Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; Beijing Key Laboratory of Molecular Imaging, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China; Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing 100191, China; Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an 710126, China. Electronic address: tian@ieee.org. LA - eng PT - Journal Article PT - Multicenter Study DEP - 20211003 PL - Singapore TA - Hepatobiliary Pancreat Dis Int JT - Hepatobiliary & pancreatic diseases international : HBPD INT JID - 101151457 SB - IM MH - *Carcinoma, Hepatocellular/diagnostic imaging/surgery MH - Humans MH - *Liver Neoplasms/diagnostic imaging/surgery MH - Prognosis MH - Retrospective Studies MH - Tomography, X-Ray Computed/methods OTO - NOTNLM OT - Computed tomography OT - Hepatocellular carcinoma OT - Macrovascular invasion OT - Prognosis OT - Radiomics EDAT- 2021/10/23 06:00 MHDA- 2022/08/04 06:00 CRDT- 2021/10/22 05:44 PHST- 2021/06/30 00:00 [received] PHST- 2021/09/24 00:00 [accepted] PHST- 2021/10/23 06:00 [pubmed] PHST- 2022/08/04 06:00 [medline] PHST- 2021/10/22 05:44 [entrez] AID - S1499-3872(21)00198-3 [pii] AID - 10.1016/j.hbpd.2021.09.011 [doi] PST - ppublish SO - Hepatobiliary Pancreat Dis Int. 2022 Aug;21(4):325-333. doi: 10.1016/j.hbpd.2021.09.011. Epub 2021 Oct 3.