Advertisement

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

  • Shi-Ting Feng
  • Yingmei Jia
  • Bing Liao
  • Bingsheng Huang
  • Qian Zhou
  • Xin Li
  • Kaikai Wei
  • Lili Chen
  • Bin Li
  • Wei Wang
  • Shuling Chen
  • Xiaofang He
  • Haibo Wang
  • Sui Peng
  • Ze-Bin Chen
  • Mimi Tang
  • Zhihang Chen
  • Yang Hou
  • Zhenwei PengEmail author
  • Ming KuangEmail author
Magnetic Resonance
  • 294 Downloads

Abstract

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.

Key Points

An effective radiomics model for prediction of microvascular invasion in HCC patients is established.

The radiomics model is superior to the radiologist in prediction of MVI.

The radiomics model can help clinicians in pretreatment decision making.

Keywords

Hepatocellular cancer Radiomics Magnetic resonance imaging Gd-EOB-DTPA 

Abbreviations

3D VIBE

Three-dimensional volume interpolated breath-hold test

AFP

Alpha-fetoprotein

AIC

Akaike information criterion

ALT

Alanine aminotransferase

AST

Aspartate aminotransferase

AUC

Area under receiver operating characteristic curve

CI

Confidence interval

CT

Computed tomography

FLASH

Fast low angle shot

FS

Fat suppression

Gd-EOB-DTPA

Gadolinium-ethoxybenzyl-diethylenetriamine

GGT

Gamma-glutamyltransferase

HASTE

Half-Fourier single-shot turbo spin-echo

HBP

Hepatobiliary phase

HCC

Hepatocellular cancer

ICC

Intra-class correlation coefficient

KW

Kruskal-Wallis

LASSO

Least absolute shrinkage and selection operator

MRI

Magnetic resonance imaging

MVI

Microvascular invasion

NPV

Negative predictive value

PPV

Positive predictive value

Rad score

Radiomics score

RFS

Recurrence-free survival

ROI

Region of interest

TSE

Turbo spin-echo

VOI

Volume of interest

Notes

Funding

This study was funded by the National Natural Science Foundation of China (81571750), National Natural Science Foundation of China (81771908), National Natural Science Foundation of China (81770608), Natural Science Foundation of Guangdong Province (2015A030311039), Guangzhou Science and Technology Program key projects (201704020215), and the Kelin Outstanding Young Scientist of the First Affiliated Hospital of Sun Yet-sen University (2017).

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Ming Kuang.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

Two of the authors (Qian Zhou and Bin Li) have significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Supplementary material

330_2018_5935_MOESM1_ESM.docx (3.4 mb)
ESM 1 (DOCX 3520 kb)

References

  1. 1.
    Poon RT, Fan ST, Ng IO, Lo CM, Liu CL, Wong J (2000) Different risk factors and prognosis for early and late intrahepatic recurrence after resection of hepatocellular carcinoma. Cancer 89:500–507CrossRefGoogle Scholar
  2. 2.
    Imamura H, Matsuyama Y, Tanaka E et al (2003) Risk factors contributing to early and late phase intrahepatic recurrence of hepatocellular carcinoma after hepatectomy. J Hepatol 38:200–207CrossRefGoogle Scholar
  3. 3.
    Lim KC, Chow PK, Allen JC et al (2011) Microvascular invasion is a better predictor of tumour recurrence and overall survival following surgical resection for hepatocellular carcinoma compared to the Milan criteria. Ann Surg 254:108–113CrossRefGoogle Scholar
  4. 4.
    Zhou YM, Yang JM, Li B et al (2010) Risk factors for early recurrence of small hepatocellular carcinoma after curative resection. Hepatobiliary Pancreat Dis Int 9:33–37PubMedGoogle Scholar
  5. 5.
    Roayaie S, Blume IN, Thung SN et al (2009) A system of classifying microvascular invasion to predict outcome after resection in patients with hepatocellular carcinoma. Gastroenterology 137:850–855CrossRefGoogle Scholar
  6. 6.
    Mazzaferro V, Llovet JM, Miceli R et al (2009) Predicting survival after liver transplantation in patients with hepatocellular carcinoma beyond the Milan criteria: a retrospective, exploratory analysis. Lancet Oncol 10:35–43CrossRefGoogle Scholar
  7. 7.
    Iwatsuki S, Dvorchik I, Marsh JW et al (2000) Liver transplantation for hepatocellular carcinoma: a proposal of a prognostic scoring system. J Am Coll Surg 191:389–394CrossRefGoogle Scholar
  8. 8.
    Shi M, Guo RP, Lin XJ et al (2007) Partial hepatectomy with wide versus narrow resection margin for solitary hepatocellular carcinoma: a prospective randomized trial. Ann Surg 245:36–43CrossRefGoogle Scholar
  9. 9.
    Sun JJ, Wang K, Zhang CZ et al (2016) Postoperative adjuvant transcatheter arterial chemoembolization after R0 hepatectomy improves outcomes of patients who have hepatocellular carcinoma with microvascular invasion. Ann Surg Oncol 23:1344–1351CrossRefGoogle Scholar
  10. 10.
    Cucchetti A, Piscaglia F, Grigioni AD et al (2010) Preoperative prediction of hepatocellular carcinoma tumour grade and micro-vascular invasion by means of artificial neural network: a pilot study. J Hepatol 52:880–888CrossRefGoogle Scholar
  11. 11.
    Lee S, Kim SH, Lee JE, Sinn DH, Park CK (2017) Preoperative gadoxetic acid-enhanced MRI for predicting microvascular invasion in patients with single hepatocellular carcinoma. J Hepatol 67:526–534CrossRefGoogle Scholar
  12. 12.
    Banerjee S, Wang DS, Kim HJ et al (2015) A computed tomography radiogenomic biomarker predicts microvascular invasion and clinical outcomes in hepatocellular carcinoma. Hepatology 62:792–800CrossRefGoogle Scholar
  13. 13.
    Huang M, Liao B, Xu et al (2018) Prediction of microvascular invasion in hepatocellular carcinoma: preoperative Gd-EOB-DTPA-dynamic enhanced MRI and histopathological correlation. Contrast Media Mol Imaging 2018:9674565PubMedPubMedCentralGoogle Scholar
  14. 14.
    Kumar V, Gu Y, Basu S et al (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234–1248CrossRefGoogle Scholar
  15. 15.
    Li Y, Liu X, Xu K et al (2018) MRI features can predict EGFR expression in lower grade gliomas: a voxel-based radiomic analysis. Eur Radiol 28:356–362CrossRefGoogle Scholar
  16. 16.
    Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118CrossRefGoogle Scholar
  17. 17.
    Braman NM, Etesami M, Prasanna P et al (2017) Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res 19:57CrossRefGoogle Scholar
  18. 18.
    Yushkevich PA, Piven J, Hazlett HC et al (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31:1116–1128CrossRefGoogle Scholar
  19. 19.
    Leijenaar RT, Carvalho S, Velazquez ER et al (2013) Stability of FDG-PET radiomics features: an integrated analysis of test-retest and inter-observer variability. Acta Oncol 52:1391–1397CrossRefGoogle Scholar
  20. 20.
    Le TN, Bao PT, Huynh HT (2016) Liver tumor segmentation from MR images using 3D fast marching algorithm and single hidden layer feedforward neural network. Biomed Res Int 2016:3219068PubMedPubMedCentralGoogle Scholar
  21. 21.
    Clément O, Mühler A, Vexler V, Berthezène Y, Brasch RC (1992) Gadolinium-ethoxybenzyl-DTPA, a new liver-specific magnetic resonance contrast agent. Kinetic and enhancement patterns in normal and cholestatic rats. Invest Radiol 27:612–619CrossRefGoogle Scholar
  22. 22.
    Hamm B, Staks T, Mühler A et al (1995) Phase I clinical evaluation of Gd-EOB-DTPA as a hepatobiliary MR contrast agent: safety, pharmacokinetics, and MR imaging. Radiology 195:785–792CrossRefGoogle Scholar
  23. 23.
    Joo I, Lee JM (2016) Recent advances in the imaging diagnosis of hepatocellular carcinoma: value of gadoxetic acid-enhanced MRI. Liver Cancer 5:67–87CrossRefGoogle Scholar
  24. 24.
    Choi JW, Lee JM, Kim SJ et al (2013) Hepatocellular carcinoma: imaging patterns on gadoxetic acid-enhanced MR images and their value as an imaging biomarker. Radiology 267:776–786CrossRefGoogle Scholar
  25. 25.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefGoogle Scholar
  26. 26.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006CrossRefGoogle Scholar
  27. 27.
    Lundsgaard Hansen M, Fallentin E, Axelsen T et al (2016) Interobserver and intraobserver reproducibility with volume dynamic contrast enhanced computed tomography (DCE-CT) in gastroesophageal junction cancer. Diagnostics (Basel).  https://doi.org/10.3390/diagnostics6010008
  28. 28.
    Grossmann P, Stringfield O, El-Hachem N et al (2017) Defining the biological basis of radiomic phenotypes in lung cancer. Elife.  https://doi.org/10.7554/eLife.23421
  29. 29.
    Fox MJ, Gibbs P, Pickles MD (2016) Minkowski functionals: an MRI texture analysis tool for determination of the aggressiveness of breast cancer. J Magn Reson Imaging 43:903–910CrossRefGoogle Scholar
  30. 30.
    Hayano K, Tian F, Kambadakone AR et al (2015) Texture analysis of non-contrast-enhanced computed tomography for assessing angiogenesis and survival of soft tissue sarcoma. J Comput Assist Tomogr 39:607–612CrossRefGoogle Scholar
  31. 31.
    Ganeshan B, Goh V, Mandeville HC, Ng QS, Hoskin PJ, Miles KA (2013) Non-small cell lung cancer: histopathologic correlates for texture parameters at CT. Radiology 266:326–336CrossRefGoogle Scholar
  32. 32.
    Segal E, Sirlin CB, Ooi C et al (2007) Decoding global gene expression programs in liver cancer by noninvasive imaging. Nat Biotechnol 25:675–680CrossRefGoogle Scholar
  33. 33.
    Zhou W, Zhang L, Wang K et al (2017) Malignancy characterization of hepatocellular carcinomas based on texture analysis of contrast-enhanced MR images. J Magn Reson Imaging 45:1476–1484CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  • Shi-Ting Feng
    • 1
  • Yingmei Jia
    • 1
  • Bing Liao
    • 2
  • Bingsheng Huang
    • 3
  • Qian Zhou
    • 4
  • Xin Li
    • 5
  • Kaikai Wei
    • 1
  • Lili Chen
    • 2
  • Bin Li
    • 4
  • Wei Wang
    • 6
  • Shuling Chen
    • 6
  • Xiaofang He
    • 7
  • Haibo Wang
    • 4
  • Sui Peng
    • 4
    • 8
  • Ze-Bin Chen
    • 9
  • Mimi Tang
    • 8
  • Zhihang Chen
    • 9
  • Yang Hou
    • 10
  • Zhenwei Peng
    • 11
    Email author
  • Ming Kuang
    • 6
    • 9
    Email author
  1. 1.Department of RadiologyThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  2. 2.Department of PathologyThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  3. 3.National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science CenterShenzhen UniversityShenzhenChina
  4. 4.Clinical Trials UnitThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  5. 5.GE HealthcareShanghaiChina
  6. 6.Department of Medical Ultrasonics, Division of Interventional UltrasoundThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  7. 7.Department of Radiation OncologyThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  8. 8.Department of Gastroenterology and HepatologyThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  9. 9.Department of Liver SurgeryThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  10. 10.Jinan UniversityGuangzhouChina
  11. 11.Department of OncologyThe First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina

Personalised recommendations