Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jul;8(14):870.
doi: 10.21037/atm-20-3041.

Gadoxetic acid-enhanced MRI radiomics signature: prediction of clinical outcome in hepatocellular carcinoma after surgical resection

Zhen Zhang  1 , Jie Chen  1 , Hanyu Jiang  1 , Yi Wei  1 , Xin Zhang  2 , Likun Cao  3 , Ting Duan  1 , Zheng Ye  1 , Shan Yao  1 , Xuelin Pan  1 , Bin Song  1
Affiliations

Gadoxetic acid-enhanced MRI radiomics signature: prediction of clinical outcome in hepatocellular carcinoma after surgical resection

Zhen Zhang et al. Ann Transl Med. 2020 Jul.

Abstract

Background: This study aimed to evaluate the efficiency of gadoxetic acid-enhanced MRI-based radiomics features for prediction of overall survival (OS) in hepatocellular carcinoma (HCC) patients after surgical resection.

Methods: This prospective study approved by the Institutional Review Board enrolled 120 patients with pathologically confirmed HCC. Radiomics signatures (rad-scores) were built from radiomics features in 3 different regions of interest (ROIs) with the least absolute shrinkage and selection operator (LASSO) cox regression analysis. Preoperative clinical characteristics and semantic imaging features potentially associated with patient survival were evaluated to develop a clinic-radiological model. The radiomics features and clinic-radiological predictors were integrated into a joint model using multivariable Cox regression analysis. Kaplan-Meier analysis and log-rank tests were performed to compare the discriminative performance and evaluated on the validation cohort.

Results: The radiomics signatures showed a significant association with patient survival in both cohorts (all P<0.001). The BCLC (Barcelona clinic liver cancer) stage, non-smooth tumor margin, and the combined rad-score were independently associated with OS. Moreover, the combined model incorporating with clinic-radiological and radiomics features showed an improved predictive performance with C-index of 0.92 [95% confidence interval (CI): 0.87-0.97], compared to the clinic-radiological model (C-index, 0.86, 95% CI: 0.79-0.94; P=0.039) or the combined rad-score (C-index, 0.88, 95% CI: 0.81-0.95; P=0.016).

Conclusions: Radiomics features along with clinic-radiological predictors can efficiently aid in preoperative HCC prognosis prediction after surgical resection and enable a step forward precise medicine.

Keywords: Hepatocellular carcinoma (HCC); gadoxetic acid-enhanced MRI; overall survival (OS); radiomics.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: All authors have completed the ICJME uniform disclosure form (available at http://dx.doi.org/10.21037/atm-20-3041). The authors have no conflicts of interest to declare.

Figures

Figure 1
Figure 1
Diagram shows the workflow of the radiomics study. Image segmentation reveals a representative example of ROIs segmentation. First, radiologists manually draw a region on the largest cross-sectional area of the tumor as an ROI tumor (yellow), and the computer automatically extended the contour of the lesion, with a 1 cm-wide radius surrounding the tumor boundary (ROI penumbra) obtained automatically (red). On the bases of ROI penumbra, a region of liver parenchyma excluding intratumoral and peritumoral region were manually segmented (ROI liver) (green). ROI, regions of interest.
Figure 2
Figure 2
Patient recruitment process. HCC, hepatocellular carcinoma; ROI, region of interest.
Figure 3
Figure 3
Development of nomogram and calibration curves of the combined model for overall survival of patients in both primary and validation cohorts. A nomogram was set up based on the primary cohort, with radiomics signature, BCLC stage, and non-smooth tumor margin incorporated, and scaled by the proportional regression coefficient of each predictor (A). Calibration curves for the combined model in predicting the overall survival of patients at 1, 2, or 3 years after surgery in the primary cohort (B) and the validation cohort (C).
Figure 4
Figure 4
The results of Kaplan-Meier survival analysis for predicting the overall survival of the combined model for patients in the primary cohort (A) and validation cohort (B).
See this image and copyright information in PMC

References

    1. Omata M, Cheng AL, Kokudo N, et al. Asia-Pacific clinical practice guidelines on the management of hepatocellular carcinoma: a 2017 update. Hepatol Int 2017;11:317-70. 10.1007/s12072-017-9799-9 - DOI - PMC - PubMed
    1. Imamura H, Matsuyama Y, Tanaka E, et al. Risk factors contributing to early and late phase intrahepatic recurrence of hepatocellular carcinoma after hepatectomy. J Hepatol 2003;38:200-07. 10.1016/S0168-8278(02)00360-4 - DOI - PubMed
    1. Chawla A, Ferrone C. Hepatocellular carcinoma surgical therapy: perspectives on the current limits to resection. Chin Clin Oncol 2018;7:48. 10.21037/cco.2018.08.12 - DOI - PubMed
    1. Poon RT, Fan ST, Ng IOL, et al. Different risk factors and prognosis for early and late intrahepatic recurrence after resection of hepatocellular carcinoma. Cancer 2000;89:500-07. 10.1002/1097-0142(20000801)89:3<500::AID-CNCR4>3.0.CO;2-O - DOI - PubMed
    1. Ye L, Liang R, Zhang J, et al. Postoperative albumin-bilirubin grade and albumin-bilirubin change predict the outcomes of hepatocellular carcinoma after hepatectomy. Ann Transl Med 2019;7:367. 10.21037/atm.2019.06.01 - DOI - PMC - PubMed