JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Radiomics and quantitative multi-parametric MRI for predicting uterine fibroid growth

  • 0University of Chicago, Department of Radiology, Chicago, Illinois, United States.
Journal of Medical Imaging +

|

September 16, 2024

|

September 16, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

A new model predicts uterine fibroid (UF) growth using MRI data. This tool helps identify fast-growing UFs, potentially improving patient management and reducing morbidity.

Area Of Science

  • Medical imaging
  • Radiology
  • Oncology

Background

  • Uterine fibroids (UFs) are common benign tumors in women.
  • Their unpredictable growth and morbidity pose significant health risks.
  • Current management is limited by the inability to forecast UF progression.

Purpose Of The Study

  • To develop a predictive model for identifying uterine fibroids with accelerated growth rates.
  • To assess the model's ability to predict resultant morbidity.
  • To improve clinical management strategies for uterine fibroids.

Main Methods

  • Retrospective analysis of 44 uterine fibroids from 20 patients using multi-parametric MRI.
  • Extraction of quantitative MRI, morphological, and radiomics features.
  • Dimensionality reduction using Principal Component Analysis (PCA) and classification with Linear Discriminant Analysis (LDA).

Main Results

  • A predictive model using the first three principal components achieved an AUC of 0.80.
  • The model effectively distinguished between faster and slower-growing UFs.
  • Time-to-event analysis showed a hazard ratio of 0.33, indicating clinical utility.

Conclusions

  • A promising predictive model for UF growth was developed using quantitative MRI and PCA.
  • The model demonstrates potential for clinical utility in personalized UF management.
  • Further validation on a larger cohort is recommended.

Keywords: