Related Experiment Video
Updated: Aug 7, 2026
10:27
Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts
Published on: July 25, 2020
Radiomics Model Predicts Efficacy of First-Line CDK4/6 Inhibitor Combined with Endocrine Therapy in HR+/HER2-
Ying Wei1, Guang Lin2, Peiwei Cao3
1Department of Radiology, Zhejiang Cancer Hospital, Hangzhou, Zhejiang 310022, China (Y.W., X.W., L.S., H.C.).
Academic Radiology
|August 5, 2026
Summary
Radiomics models show promise in predicting treatment efficacy for advanced HR+/HER2- breast cancer patients receiving CDK4/6 inhibitors and endocrine therapy. These models may help personalize treatment selection for better outcomes.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- Advanced HR+/HER2- breast cancer is typically treated with CDK4/6 inhibitors and endocrine therapy.
- Tumor heterogeneity can limit treatment benefit for some patients.
- Predicting treatment efficacy is crucial for optimizing patient outcomes.
Purpose of the Study:
- To develop and validate a radiomics-based model for predicting the efficacy of first-line treatment in advanced HR+/HER2- breast cancer.
- To assess the model's ability to predict progression-free survival (PFS) and treatment response.
Main Methods:
- Retrospective analysis of 102 patients with advanced HR+/HER2- breast cancer.
- Extraction of radiomic features from baseline contrast-enhanced CT images.
- Development of prediction models using LASSO, recursive feature elimination, Cox proportional-hazards, and XGBoost algorithms.
- Evaluation of model performance using concordance index (C-index), area under the curve (AUC), and decision curve analysis (DCA).
Main Results:
- The combined radiomics-clinical model achieved high C-index values for PFS prediction (0.85 in training, 0.76 in testing), outperforming clinical-only and radiomics-only models.
- Time-dependent AUC values in the test set reached up to 0.938 at 6 months for PFS prediction.
- Response prediction models showed AUCs of 0.80 for overall response and 0.70 for early treatment response.
Conclusions:
- Radiomics models demonstrate preliminary potential in predicting treatment efficacy for CDK4/6 inhibitor plus endocrine therapy in advanced breast cancer.
- These findings require validation in larger, multicenter, independent cohorts for clinical implementation.
