JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Radiomics analysis based on contrast-enhanced MRI for predicting short-term efficacy of drug-eluting beads transarterial chemoembolization in hepatocellular carcinoma

  • 0Department of Radiology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China. 13931382378@163.com.
Abdominal Radiology (new York) +

|

July 19, 2024

|

July 19, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

A new clinical-radiomics model accurately predicts treatment effectiveness for hepatocellular carcinoma (HCC) before drug-eluting beads transarterial chemoembolization (D-TACE). This tool aids in patient selection and improves outcomes.

Area Of Science

  • Radiology
  • Oncology
  • Medical Imaging

Background

  • Hepatocellular carcinoma (HCC) is a common primary liver cancer.
  • Drug-eluting beads transarterial chemoembolization (D-TACE) is a standard treatment for intermediate and advanced HCC.
  • Predicting treatment response before D-TACE is crucial for optimizing patient management.

Purpose Of The Study

  • To develop and validate a clinical-radiomics model for predicting the short-term efficacy of initial D-TACE in HCC patients.
  • To assess the predictive performance of the model using various statistical measures.
  • To evaluate the clinical utility and prognostic implications of the model.

Main Methods

  • Retrospective cohort study of 113 HCC patients.
  • Extraction of 5343 radiomic features from contrast-enhanced MRI (arterial phase, diffusion-weighted, T2-weighted images).
  • Feature selection using minimum redundancy maximum correlation and LASSO regression; model construction via multifactor logistic regression.

Main Results

  • A clinical-radiomics model incorporating 34 radiomic features demonstrated high predictive performance (AUC=0.902 training, 0.845 testing).
  • Arterial phase radiomics score and microsphere type were significant predictors of short-term efficacy.
  • The model's predictions correlated with progression-free survival (PFS), indicating prognostic value.

Conclusions

  • The developed clinical-radiomics model is effective for predicting short-term D-TACE efficacy in HCC.
  • This predictive tool can guide treatment decisions and potentially lead to better clinical and economic outcomes for patients.
  • The model's ability to predict PFS highlights its prognostic significance.

Keywords: