Research ArticleRadiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma
Graphical abstract
Introduction
Hepatocellular carcinoma (HCC) is one of the most common primary hepatic malignant tumors and its incidence is increasing worldwide.1 It is the second leading cause of cancer-specific mortality in the Asia-Pacific regions, and especially in China.2 Surgical resection and liver transplantation (LT) are potentially curative for patients with HCC,3 but recurrence after surgical treatment is common. Some studies maintained that approximately 70% of patients would suffer from recurrence within 5 years after surgical resection, and 35% after LT.[4], [5], [6], [7], [8]
Microvascular invasion (MVI) is one of the most important prognostic factors for HCC after surgical treatment.[9], [10], [11] Contrary to macrovascular invasion, which can be detected with diagnostic imaging, MVI is a histologic finding that can only be postoperatively diagnosed with a surgical specimen.12 Preoperative prediction of MVI is still challenging. A variety of imaging findings have been described, with variable diagnostic utility. Previous studies found that imaging features such as tumor size, multinodular tumor morphology, tumor margins, and peritumoral enhancement were associated with MVI.[13], [14], [15] In addition, Renzulli et al. showed that a 2-trait predictor of venous invasion can be a useful preoperative predictor of MVI.14 Banerjee et al. showed that a radio-genomic venous invasion (RVI) predictor, based on the association between imaging features and gene expression, achieves high accuracy in predicting MVI in HCC.8 However, these criteria for a preoperative imaging diagnosis of MVI in HCC have not yet been widely recognized.
Radiomics is a newly emerging form of imaging analysis using a series of data-mining algorithms or statistical analysis tools on high-throughput imaging features to obtain predictive or prognostic information. By building appropriate models with refined features, it achieved successful assessment and prediction abilities in various challenging clinical tasks.[16], [17], [18], [19] A landmark study in colorectal cancer revealed clear associations between CT radiomics and lymph node metastases, and a combination of radiomic and clinico-radiologic factors could achieve significant clinical benefits.20 However, despite its potential, the use of radiomics as a clinical biomarker still necessitates amelioration and standardization.21 Greater integration between radiomics and other sources of data is required for clinicians to fully and confidently accept its role in patient management. To the best of our knowledge, only one study to date has assessed the prognostic aspect of radiomics for MVI in a group of 304 patients with HCC.22 However, stronger evidence is needed in support of the implications for tumor progression and the reliability of the methodology. Additionally, MVI concerns tumor edges, while in previous studies radiomic features were only extracted inside the tumor, where by definition there is no microvascular involvement. A more effective evaluation should focus on the radiomic features at the tumor periphery.
The purpose of this study was to investigate whether a computational approach integrating large-scale clinical and imaging modalities, especially radiomic features extracted from contrast-enhanced CT (CECT), could be useful to predict MVI and the long-term clinical outcomes in patients with HCC. Additionally, the added value provided by radiomics to evidence-based clinico-radiologic factors was investigated.
Section snippets
Patients
This retrospective study involved standard care performed at a single medical institution. Ethics committee approval was granted by the local institutional ethics review board, and the requirement for written informed consent was waived. All procedures involving human participants were performed in accordance with the 1975 Helsinki declaration and its later amendments.
We queried our institution’s medical records to derive all surgically confirmed cases of HCC between January 2009 and August
Basic clinico-radiologic characteristics
Out of 495 patients included, histologic MVI was diagnosed in explanted tissue of 149 patients (30.1%). Patients with MVI were younger, and had higher ALT, AST, PLT, INR and AFP levels than those without MVI. The 2 groups were similar in their distribution of sex, hepatic virus infection, cirrhosis, Child-Pugh stage, TB, CB, ALB, PT and Scr test. Risk coefficient estimated by univariate analysis is summarized in Table 1. HCCs with and without MVI demonstrated significantly different imaging
Discussion
The aim of this study was to investigate the prognostic aspects of computational-assisted models derived from large-scale clinical and imaging data, especially radiomic features from CECT, for preoperative prediction of histologic MVI status and clinical outcomes in a cohort of 495 patients with HCC. We concluded that CT tumor radiomic features, converted into quantitative R-scores, can be independent predictors of MVI, but less relevant than radiologist scores. A risk model integrating
Financial support
This work was supported by China Postdoctoral Fund (grant number 2015M580453, Z.Y.) and a Key Social Development Program for the Ministry of Science and Technology of Jiangsu Province (grant number BE2017756, Z.Y.).
Conflict of interest
The authors declare no conflicts of interest that pertain to this work.
Authors' contributions
Conception and design: Yu-Dong Zhang, Xi-Sheng Liu. Development of methodology: Xun Xu, Hai-Long Zhang, Qiu-Ping Liu, Shu-Wen Sun, Fei-Peng Zhu, Jing Zhang, Xu Yan, Guang Yang, Yu-Dong Zhang, Xi-Sheng Liu. Acquisition of data (acquired and managed patients, provided facilities, etc.): Xun Xu, Hai-Long Zhang, Qiu-Ping Liu, Shu-Wen Sun, Fei-Peng Zhu, Jing Zhang, Xu Yan, Guang Yang, Yu-Dong Zhang, Xi-Sheng Liu. Analysis and interpretation of data (e.g., statistical analysis, biostatistics,
Acknowledgement
We thank the Department of Pathology of the First Affiliated Hospital of Nanjing Medical University for assistance with histopathology.
References (31)
- et al.
Modern diagnosis and management of hepatocellular carcinoma
Clin Liver Dis
(2009) - et al.
Hepatocellular carcinoma recurrence and death following living and deceased donor liver transplantation
Am J Transplant
(2007) - et al.
Tumour lymphocytic infiltrate and recurrence of hepatocellular carcinoma following liver transplantation
J Hepatol
(2006) - et al.
Portal vein invasion and intrahepatic micrometastasis in small hepatocellular carcinoma by gross type
Hepatol Res
(2003) - et al.
Recurrence after liver resection for hepatocellular carcinoma: risk factors, treatment, and outcomes
Surgery
(2007) - et al.
Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology
Ann Oncol
(2017) - et al.
A support vector machine-recursive feature elimination feature selection method based on artificial contrast variables and mutual information
J Chromatogr B: Anal Technol Biomed Life Sci
(2012) - et al.
Predicting prognosis of resected hepatocellular carcinoma by radiomics analysis with random survival forest
Diagn Interventional Imaging
(2018) - et al.
Development and validation of a novel predictive scoring model for microvascular invasion in patients with hepatocellular carcinoma
Eur J Radiol
(2017) - et al.
Asia-Pacific clinical practice guidelines on the management of hepatocellular carcinoma: a 2017 update
Hep Intl
(2017)
Potentially curative treatment in patients with hepatocellular cancer–results from the liver cancer research network
Aliment Pharmacol Ther
Tumor recurrence following liver transplantation for hepatocellular carcinoma: role of tumor proliferation status
Liver Transplant
Recurrence of hepatocellular carcinoma following liver transplantation: a review of preoperative and postoperative prognostic indicators
Arch Surg
A computed tomography radiogenomic biomarker predicts microvascular invasion and clinical outcomes in hepatocellular carcinoma
Hepatology
Predicting recurrence after liver transplantation in patients with hepatocellular carcinoma exceeding the up-to-seven criteria
Liver Transplant
Cited by (427)
Prediction of microvascular invasion and pathological differentiation of hepatocellular carcinoma based on a deep learning model
2024, European Journal of Radiology