JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Radiomics-Based Prediction Model for Outcome of Radioembolization in Metastatic Colorectal Cancer

  • 0Department of Nuclear Medicine, University Hospital Münster, Münster, Germany.
Cardiovascular and Interventional Radiology +

|

February 28, 2024

|

February 28, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

A computed tomography (CT) radiomics model effectively predicts treatment response and survival in patients with colorectal liver metastases undergoing transarterial Yttrium-90 radioembolization (TARE). The model quantifies tumor heterogeneity, identifying high-risk patients for poorer outcomes.

Area Of Science

  • Radiology
  • Oncology
  • Medical Imaging Analysis

Background

  • Colorectal liver metastases are a common clinical challenge.
  • Transarterial Yttrium-90 radioembolization (TARE) is a treatment option for these metastases.
  • Predicting treatment response and survival is crucial for optimizing patient management.

Purpose Of The Study

  • To evaluate a contrast-enhanced computed tomography (CT) radiomics-based model.
  • To predict treatment response and survival in patients with colorectal liver metastases receiving TARE.
  • To assess the benefit of radiomics in this specific patient population.

Main Methods

  • Retrospective study of 51 patients undergoing TARE.
  • Radiomic features (RF) extracted from pre-TARE CT scans.
  • A radiomics model developed using logistic regression to classify response (RECIST 1.1).
  • Kaplan-Meier analysis to compare survival between risk groups.

Main Results

  • Two RFs (Energy, Maximal Correlation Coefficient) reflected tumor heterogeneity and predicted TARE non-response.
  • The radiomics model achieved an AUC of 0.75 for predicting treatment response.
  • High-risk patients identified by the model had significantly shorter overall survival (3.4 vs. 6.4 months).

Conclusions

  • CT radiomics can predict response and survival in TARE-treated colorectal liver metastases.
  • Quantifying tumor heterogeneity using radiomics is key to predicting outcomes.
  • This model offers potential for improved patient stratification and treatment planning.

Keywords: