JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Development and Validation of a Nomogram Based on DCE-MRI Radiomics for Predicting Hypoxia-Inducible Factor 1α Expression in Locally Advanced Rectal Cancer

  • 0Department of Radiology, Shaoxing People's Hospital, Shaoxing, China.
Academic Radiology +

|

May 30, 2024

|

May 30, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a nomogram using MRI radiomics and clinical data to predict hypoxia-inducible factor 1 alpha (HIF-1α) expression in locally advanced rectal cancer patients. The nomogram demonstrated high accuracy, aiding in treatment response prediction.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Hypoxia-inducible factor 1 alpha (HIF-1α) expression is a key marker for treatment response in locally advanced rectal cancer (LARC).
  • Accurate prediction of HIF-1α expression is crucial for tailoring treatment strategies in LARC patients.

Purpose Of The Study

  • To develop and validate a predictive nomogram for HIF-1α expression in LARC patients.
  • To integrate dynamic contrast-enhanced MRI (DCE-MRI) radiomics with clinical features for enhanced prediction.
  • To assess the clinical utility and accuracy of the developed nomogram.

Main Methods

  • A cohort of 102 LARC patients was divided into training and validation sets.
  • DCE-MRI radiomics features were extracted and selected using ICC, mRMR, and LASSO methods.
  • A nomogram was constructed incorporating selected radiomics features (radiomics score) and clinical factors (CEA, Ki-67).
  • Model performance was evaluated using ROC curves, DCA, and calibration curves.

Main Results

  • A radiomics signature was built using seven DCE-MRI features.
  • The nomogram, including CEA, Ki-67, and radiomics score, achieved high predictive accuracy (AUC: 0.918 in training, 0.920 in validation).
  • The nomogram demonstrated superior clinical utility compared to the clinical model and radiomics signature alone.
  • Calibration curves confirmed good agreement between predicted and observed HIF-1α expression.

Conclusions

  • The developed nomogram effectively predicts HIF-1α expression in LARC patients.
  • This DCE-MRI radiomics and clinical feature-based nomogram shows promise for preoperative discrimination of HIF-1α levels.
  • The findings suggest potential for improved treatment stratification and personalized therapy in LARC.

Keywords: