Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI

被引:197
作者
Feng, Shi-Ting [1 ]
Jia, Yingmei [1 ]
Liao, Bing [2 ]
Huang, Bingsheng [3 ]
Zhou, Qian [4 ]
Li, Xin [5 ]
Wei, Kaikai [1 ]
Chen, Lili [2 ]
Li, Bin [4 ]
Wang, Wei [6 ]
Chen, Shuling [6 ]
He, Xiaofang [7 ]
Wang, Haibo [4 ]
Peng, Sui [4 ,8 ]
Chen, Ze-Bin [9 ]
Tang, Mimi [8 ]
Chen, Zhihang [9 ]
Hou, Yang [10 ]
Peng, Zhenwei [11 ]
Kuang, Ming [6 ,9 ]
机构
[1] Sun Yat Sen Univ, Dept Radiol, Affiliated Hosp 1, Guangzhou, Guangdong, Peoples R China
[2] Sun Yat Sen Univ, Affiliated Hosp 1, Dept Pathol, Guangzhou, Guangdong, Peoples R China
[3] Shenzhen Univ, Natl Reg Key Technol Engn Lab Med Ultrasound, Guangdong Key Lab Biomed Measurements & Ultrasoun, Sch Biomed Engn,Hlth Sci Ctr, Shenzhen, Peoples R China
[4] Sun Yat Sen Univ, Affiliated Hosp 1, Clin Trials Unit, Guangzhou, Guangdong, Peoples R China
[5] GE Healthcare, Shanghai, Peoples R China
[6] Sun Yat Sen Univ, Dept Med Ultrason, Div Intervent Ultrasound, Affiliated Hosp 1, Guangzhou, Guangdong, Peoples R China
[7] Sun Yat Sen Univ, Dept Radiat Oncol, Affiliated Hosp 1, Guangzhou, Guangdong, Peoples R China
[8] Sun Yat Sen Univ, Dept Gastroenterol & Hepatol, Affiliated Hosp 1, Guangzhou, Guangdong, Peoples R China
[9] Sun Yat Sen Univ, Dept Liver Surg, Affiliated Hosp 1, 58 Thong Shan Rd 2, Guangzhou 510080, Guangdong, Peoples R China
[10] Jinan Univ, Guangzhou, Guangdong, Peoples R China
[11] Sun Yat Sen Univ, Dept Oncol, Affiliated Hosp 1, 58 Thong Shan Rd 2, Guangzhou 510080, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Hepatocellular cancer; Radiomics; Magnetic resonance imaging; Gd-EOB-DTPA; RISK-FACTORS; INTRAHEPATIC RECURRENCE; COMPUTED-TOMOGRAPHY; TEXTURE ANALYSIS; CONTRAST AGENT; CARCINOMA; RESECTION; HEPATECTOMY; EXPRESSION; PATTERNS;
D O I
10.1007/s00330-018-5935-8
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Objectives Preoperative prediction of microvascular invasion (MVI) in patients with hepatocellular cancer (HCC) is important for surgery strategy making. We aimed to develop and validate a combined intratumoural and peritumoural radiomics model based on gadolinium-ethoxybenzyl-diethylenetriamine (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) for preoperative prediction of MVI in primary HCC patients. Methods This study included a training cohort of 110 HCC patients and a validating cohort of 50 HCC patients. All the patients underwent preoperative Gd-EOB-DTPA-enhanced MRI examination and curative hepatectomy. The volumes of interest (VOIs) around the hepatic lesions including intratumoural and peritumoural regions were manually delineated in the hepatobiliary phase of MRI images, from which quantitative features were extracted and analysed. In the training cohort, machine-learning method was applied for dimensionality reduction and selection of the extracted features. Results The proportion of MVI-positive patients was 38.2% and 40.0% in the training and validation cohort, respectively. Supervised machine learning selected ten features to establish a predictive model for MVI. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity of the combined intratumoural and peritumoural radiomics model in the training and validation cohort were 0.85 (95% confidence interval (CI), 0.77-0.93), 88.2%, 76.2%, and 0.83 (95% CI, 0.71-0.95), 90.0%, 75.0%, respectively. Conclusions We evaluate quantitative Gd-EOB-DTPA-enhanced MRI image features of both intratumoural and peritumoural regions and provide an effective radiomics-based model for the prediction of MVI in HCC patients, and may therefore help clinicians make precise decisions regarding treatment before the surgery.
引用
收藏
页码:4648 / 4659
页数:12
相关论文
共 34 条
[1]   Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].
Aerts, Hugo J. W. L. ;
Velazquez, Emmanuel Rios ;
Leijenaar, Ralph T. H. ;
Parmar, Chintan ;
Grossmann, Patrick ;
Cavalho, Sara ;
Bussink, Johan ;
Monshouwer, Rene ;
Haibe-Kains, Benjamin ;
Rietveld, Derek ;
Hoebers, Frank ;
Rietbergen, Michelle M. ;
Leemans, C. Rene ;
Dekker, Andre ;
Quackenbush, John ;
Gillies, Robert J. ;
Lambin, Philippe .
NATURE COMMUNICATIONS, 2014, 5
[2]   A computed tomography radiogenomic biomarker predicts microvascular invasion and clinical outcomes in hepatocellular carcinoma [J].
Banerjee, Sudeep ;
Wang, David S. ;
Kim, Hyun J. ;
Sirlin, Claude B. ;
Chan, Michael G. ;
Korn, Ronald L. ;
Rutman, Aaron M. ;
Siripongsakun, Surachate ;
Lu, David ;
Imanbayev, Galym ;
Kuo, Michael D. .
HEPATOLOGY, 2015, 62 (03) :792-800
[3]   Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI [J].
Braman, Nathaniel M. ;
Etesami, Maryam ;
Prasanna, Prateek ;
Dubchuk, Christina ;
Gilmore, Hannah ;
Tiwari, Pallavi ;
Pletcha, Donna ;
Madabhushi, Anant .
BREAST CANCER RESEARCH, 2017, 19
[4]   Hepatocellular Carcinoma: Imaging Patterns on Gadoxetic Acid-enhanced MR Images and Their Value as an Imaging Biomarker [J].
Choi, Jin Woo ;
Lee, Jeong Min ;
Kim, Soo Jin ;
Yoon, Jeong-Hee ;
Baek, Jee Hyun ;
Han, Joon Koo ;
Choi, Byung Ihn .
RADIOLOGY, 2013, 267 (03) :776-786
[5]  
CLEMENT O, 1992, INVEST RADIOL, V27, P612
[6]   Preoperative prediction of hepatocellular carcinoma tumour grade and micro-vascular invasion by means of artificial neural network: A pilot study [J].
Cucchetti, Alessandro ;
Piscaglia, Fabio ;
Grigioni, Antonia D'Errico ;
Ravaioli, Matteo ;
Cescon, Matteo ;
Zanello, Matteo ;
Grazi, Gian Luca ;
Golfieri, Rita ;
Grigioni, Walter Franco ;
Pinna, Antonio Daniele .
JOURNAL OF HEPATOLOGY, 2010, 52 (06) :880-888
[7]   Dermatologist-level classification of skin cancer with deep neural networks [J].
Esteva, Andre ;
Kuprel, Brett ;
Novoa, Roberto A. ;
Ko, Justin ;
Swetter, Susan M. ;
Blau, Helen M. ;
Thrun, Sebastian .
NATURE, 2017, 542 (7639) :115-+
[8]   Minkowski functionals: An MRI texture analysis tool for determination of the aggressiveness of breast cancer [J].
Fox, Michael J. ;
Gibbs, Peter ;
Pickles, Martin D. .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2016, 43 (04) :903-910
[9]   Non-Small Cell Lung Cancer: Histopathologic Correlates for Texture Parameters at CT [J].
Ganeshan, Balaji ;
Goh, Vicky ;
Mandeville, Henry C. ;
Quan Sing Ng ;
Hoskin, Peter J. ;
Miles, Kenneth A. .
RADIOLOGY, 2013, 266 (01) :326-336
[10]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577