What question did this study set out to answer?

To develop a radiomics model that predicts breast cancer subtypes using DCE-MRI kinetic data.

February 24, 2026Open Access

Dynamic Contrast-Enhanced MRI Kinetic Curve-Driven Parametric Radiomics for Predicting Breast Cancer Molecular Subtypes: A Multicenter and Interpretable Study

View Full Paper

Ask AI

Bookmark

To develop a radiomics model that predicts breast cancer subtypes using DCE-MRI kinetic data.
Retrospective analysis of 935 female patients with confirmed breast cancer and DCE-MRI scans.
Utilized wash-in rate and area under time-intensity curve for imaging analyses.
Extracted radiomics features and applied low variance filtering and regression techniques for model building.
Employed categorical boosting algorithms to enhance prediction accuracy and interpretability.
The TIC-Combined model had an internal validation average AUC of 0.79 and external validation AUC of 0.77.
The highest AUC for triple-negative breast cancer was 0.81 in internal validation.
The model demonstrated strong calibration and clear insights into feature importance.

No takes yet. Share an insight, caveat, or question.

Multicenter study develops a model to predict breast cancer molecular subtypes using DCE-MRI, suggesting non-invasive insights.

Wang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark