Journal of Translational Medicine (Sep 2024)

CT-based radiomics nomogram to predict proliferative hepatocellular carcinoma and explore the tumor microenvironment

  • Gongzheng Wang,
  • Feier Ding,
  • Kaige Chen,
  • Zhuoshuai Liang,
  • Pengxi Han,
  • Linxiang Wang,
  • Fengyun Cui,
  • Qiang Zhu,
  • Zhaoping Cheng,
  • Xingzhi Chen,
  • Chencui Huang,
  • Hongxia Cheng,
  • Ximing Wang,
  • Xinya Zhao

DOI
https://doi.org/10.1186/s12967-024-05393-3
Journal volume & issue
Vol. 22, no. 1
pp. 1 – 16

Abstract

Read online

Abstract Background Proliferative hepatocellular carcinomas (HCCs) is a class of aggressive tumors with poor prognosis. We aimed to construct a computed tomography (CT)-based radiomics nomogram to predict proliferative HCC, stratify clinical outcomes and explore the tumor microenvironment. Methods Patients with pathologically diagnosed HCC following a hepatectomy were retrospectively collected from two medical centers. A CT-based radiomics nomogram incorporating radiomics model and clinicoradiological features to predict proliferative HCC was constructed using the training cohort (n = 184), and validated using an internal test cohort (n = 80) and an external test cohort (n = 89). The predictive performance of the nomogram for clinical outcomes was evaluated for HCC patients who underwent surgery (n = 201) or received transarterial chemoembolization (TACE, n = 104). RNA sequencing data and histological tissue slides from The Cancer Imaging Archive database were used to perform transcriptomics and pathomics analysis. Results The areas under the receiver operating characteristic curve of the radiomics nomogram to predict proliferative HCC were 0.84, 0.87, and 0.85 in the training, internal test, and external test cohorts, respectively. The radiomics nomogram could stratify early recurrence-free survivals in the surgery outcome cohort (hazard ratio [HR] = 2.25; P < 0.001) and progression-free survivals in the TACE outcome cohort (HR = 2.21; P = 0.03). Transcriptomics and pathomics analysis indicated that the radiomics nomogram was associated with carbon metabolism, immune cells infiltration, TP53 mutation, and heterogeneity of tumor cells. Conclusion The CT-based radiomics nomogram could predict proliferative HCC, stratify clinical outcomes, and measure a pro-tumor microenvironment.

Keywords