Radiomics model based on dual-energy CT venous phase parameters to predict Ki-67 levels in gastrointestinal stromal tumors
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study developed a combined model using Dual-Energy CT (DECT) radiomics and clinical features to accurately predict Ki-67 expression in gastrointestinal stromal tumors (GISTs). The model shows high accuracy for preoperative prediction, aiding in GIST management.
Area Of Science
- Radiology
- Oncology
- Medical Imaging
Background
- Gastrointestinal stromal tumors (GISTs) require accurate assessment of proliferation markers like Ki-67.
- Current methods for predicting Ki-67 expression in GISTs may have limitations.
Purpose Of The Study
- To develop and validate a radiomics model using Dual-Energy CT (DECT) features to predict Ki-67 expression levels in GISTs.
- To integrate DECT-derived radiomics with clinical features for enhanced predictive accuracy.
Main Methods
- Retrospective analysis of 91 GIST patients.
- Construction of clinical, radiomics (iodine density, effective atomic number maps), and combined models.
- Validation using discrimination, calibration, and decision curve analysis.
Main Results
- The combined model demonstrated superior predictive performance with an AUC of 0.982.
- Excellent calibration was observed (Hosmer-Lemeshow P=0.99).
- The model showed significant clinical utility across a broad probability threshold.
Conclusions
- A nomogram integrating clinical and DECT radiomics features accurately predicts preoperative Ki-67 expression in GISTs.
- This approach offers a non-invasive method for assessing GIST proliferation.
- The combined model enhances preoperative prediction accuracy for GIST management.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.