CASIA OpenIR  > 中国科学院分子影像重点实验室
CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma: A multicenter study
Jingwei Wei1; Sirui Fu2; Jie Zhang3; Dongsheng Gu1; Xiaoqun Li4; Xudong Chen5; Shuaitong Zhang1; Xiaofei He6; Jianfeng Yan7; Ligong Lu2; Jie Tian1
Source PublicationHepatobiliary & Pancreatic Diseases International
ISSN1499-3872
2021
Volume2021Issue:--Pages:--
Subtypearticle
Abstract

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.

KeywordComputed tomography Hepatocellular carcinoma Macrovascular invasion Prognosis Radiomics
MOST Discipline Catalogue医学
DOI10.1016/j.hbpd.2021.09.011
URL查看原文
Indexed BySCI
Language英语
WOS IDWOS:000880441700004
Sub direction classification医学影像处理与分析
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/47447
Collection中国科学院分子影像重点实验室
Affiliation1.Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences
2.Zhuhai Interventional Medical Center, Zhuhai Precision Medical Center, Zhuhai People's Hospital
3.Department of Radiology, Zhuhai Precision Medical Center, Zhuhai People's Hospital
4.Department of Interventional Treatment, Zhongshan City People's Hospital
5.Department of Radiology, Shenzhen People's Hospital
6.Interventional Diagnosis and Treatment Department, Nanfang Hospital
7.Department of Radiology, Yangjiang People's Hospital
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Jingwei Wei,Sirui Fu,Jie Zhang,et al. CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma: A multicenter study[J]. Hepatobiliary & Pancreatic Diseases International,2021,2021(--):--.
APA Jingwei Wei.,Sirui Fu.,Jie Zhang.,Dongsheng Gu.,Xiaoqun Li.,...&Jie Tian.(2021).CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma: A multicenter study.Hepatobiliary & Pancreatic Diseases International,2021(--),--.
MLA Jingwei Wei,et al."CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma: A multicenter study".Hepatobiliary & Pancreatic Diseases International 2021.--(2021):--.
Files in This Item: Download All
File Name/Size DocType Version Access License
第一作者1-Hepatobiliary (1564KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jingwei Wei]'s Articles
[Sirui Fu]'s Articles
[Jie Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jingwei Wei]'s Articles
[Sirui Fu]'s Articles
[Jie Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jingwei Wei]'s Articles
[Sirui Fu]'s Articles
[Jie Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 第一作者1-Hepatobiliary & Pancreatic Diseases International-2021.10-CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma a multicenter study.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.