search button
Open Access

Model‑based three‑dimensional texture analysis of contrast‑enhanced magnetic resonance imaging as a potential tool for preoperative prediction of microvascular invasion in hepatocellular carcinoma

  • Authors:
    • Yong‑Jian Zhu
    • Bing Feng
    • Shuang Wang
    • Li‑Ming Wang
    • Jiang‑Fen Wu
    • Xiao‑Hong Ma
    • Xin‑Ming Zhao

  • View Affiliations

  • Published online on: May 20, 2019     https://doi.org/10.3892/ol.2019.10378
  • Pages: 720-732

  • Copyright: © Zhu et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )
Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )


Abstract

The purpose of the present study was to investigate the value of contrast‑enhanced magnetic resonance imaging (CE‑MRI) texture analysis for preoperatively predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC). Accordingly, a retrospective study of 142 patients with pathologically confirmed HCC was performed. The patients were divided into two cohorts: The training cohort (n=99) and the validation cohort (n=43), including the MVI‑positive group (n=53) and MVI‑negative group (n=89). On the basis of three‑dimensional texture analysis, 58 features were extracted from the preoperative CE‑MR images of arterial‑phase (AP) and portal‑venous‑phase (PP). The t‑test or Kruskal‑Wallis test, univariate logistic regression analysis and Pearson correlation were applied for feature reduction. Clinical‑radiological features were also analyzed. Multivariate logistic regression analysis was used to build the texture model and combined model with clinical‑radiological features. The MVI‑predictive performance of the models was evaluated using receiver operating characteristic (ROC) analysis and presented using nomogram. Among the clinical features, a significant difference was found in maximum tumor diameter (P=0.002), tumor differentiation (P=0.026) and α‑fetoprotein level (P=0.025) between the two groups in the training cohort. Four MR texture features in AP and five in PP images were identified through feature reduction. On ROC analysis, the AP texture model showed better diagnostic performance than did the PP model in the validation cohort, with an area under the curve (AUC) of 0.773 vs. 0.623, sensitivity of 0.750 vs. 0.500, and specificity of 0.815 vs. 0.926. Together with the clinical features, the combined model of AP improved the AUC, sensitivity and specificity to 0.810, 0.811 and 0.790, respectively, which was demonstrated in nomogram. To conclude, model‑based texture analysis of CE‑MRI could predict MVI in HCC preoperatively and noninvasively, and the AP image shows better predictive efficiency than PP image. The combined model of AP with clinical‑radiological features could improve MVI prediction ability.
View Figures
View References

Related Articles

Journal Cover

July-2019
Volume 18 Issue 1

Print ISSN: 1792-1074
Online ISSN:1792-1082

Sign up for eToc alerts

Recommend to Library

  • Journal Metrics
  • Impact Factor: 2.9
  • Ranked Oncology
    (total number of cites)
  • CiteScore: 6.3
  • CiteScore Rank: Q2: #119/366 Oncology
  • Source Normalized Impact per Paper (SNIP): 0.725
  • SCImago Journal Rank (SJR): 0.639
International Symposium on Molecular Medicine Conference Banner
The Cancer Story
World Congress on Advances in Oncology and International Symposium on Molecular Medicine Conference Banner
World Academy Of Sciences Banner
Heyday Road Banner

0

Copy and paste a formatted citation
x
Spandidos Publications style
Zhu YJ, Feng B, Wang S, Wang LM, Wu JF, Ma XH and Zhao XM: Model‑based three‑dimensional texture analysis of contrast‑enhanced magnetic resonance imaging as a potential tool for preoperative prediction of microvascular invasion in hepatocellular carcinoma. Oncol Lett 18: 720-732, 2019
APA
Zhu, Y., Feng, B., Wang, S., Wang, L., Wu, J., Ma, X., & Zhao, X. (2019). Model‑based three‑dimensional texture analysis of contrast‑enhanced magnetic resonance imaging as a potential tool for preoperative prediction of microvascular invasion in hepatocellular carcinoma. Oncology Letters, 18, 720-732. https://doi.org/10.3892/ol.2019.10378
MLA
Zhu, Y., Feng, B., Wang, S., Wang, L., Wu, J., Ma, X., Zhao, X."Model‑based three‑dimensional texture analysis of contrast‑enhanced magnetic resonance imaging as a potential tool for preoperative prediction of microvascular invasion in hepatocellular carcinoma". Oncology Letters 18.1 (2019): 720-732.
Chicago
Zhu, Y., Feng, B., Wang, S., Wang, L., Wu, J., Ma, X., Zhao, X."Model‑based three‑dimensional texture analysis of contrast‑enhanced magnetic resonance imaging as a potential tool for preoperative prediction of microvascular invasion in hepatocellular carcinoma". Oncology Letters 18, no. 1 (2019): 720-732. https://doi.org/10.3892/ol.2019.10378