Related Experiment Video
Updated: Jul 3, 2025
10:35
An Orthotopic Model of Serous Ovarian Cancer in Immunocompetent Mice for in vivo Tumor Imaging and Monitoring of Tumor Immune Responses
Published on: November 28, 2010
18.3K
MRI-based radiomics model to preoperatively predict mesenchymal transition subtype in high-grade serous ovarian
1Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai 200032, China; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China; Department of Radiology, Jinshan Hospital, Fudan University, Shanghai 201508, China.
Clinical Radiology
|February 11, 2024
Summary
A new magnetic resonance imaging (MRI) radiomics model accurately identifies mesenchymal transition (MT) subtypes in high-grade serous ovarian cancer (HGSOC), aiding personalized treatment strategies.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- High-grade serous ovarian cancer (HGSOC) is a heterogeneous disease.
- Mesenchymal transition (MT) is a key process in HGSOC progression and treatment resistance.
- Accurate preoperative identification of MT subtype is crucial for personalized management.
Purpose of the Study:
- To develop and validate a magnetic resonance imaging (MRI)-based radiomics model.
- To enable preoperative identification of the mesenchymal transition (MT) subtype in high-grade serous ovarian cancer (HGSOC).
Main Methods:
- Retrospective analysis of 189 HGSOC patients.
- Extraction of 204 radiomic features from T2-weighted imaging (T2WI) and contrast-enhanced (CE)-T1WI.
- Feature selection using Mann-Whitney U test, Spearman correlation, and Boruta algorithm.
- Development of radiomics models using logistic regression (LR), support vector machine (SVM), and random forest (RF) classifiers.
Main Results:
- Seven radiomic features were selected to build the models.
- The random forest (RF) model demonstrated superior performance.
- Achieved AUCs of 0.866 (training) and 0.852 (testing) for MT subtype prediction.
- RF model showed good calibration and favorable clinical utility via decision curve analysis (DCA).
Conclusions:
- The developed RF-based radiomics model accurately differentiates MT from non-MT subtypes in HGSOC.
- This model holds potential for facilitating personalized management strategies in HGSOC patients.
- MRI-based radiomics offers a promising non-invasive approach for HGSOC subtyping.
