Radiomics-based gradient boosting model on contrast-enhanced MRI for non-invasive prediction of epidermal growth factor receptor expression and therapeutic response to EGFR-targeted antibody-drug conjugates in high-grade glioma organoid models

Key Points

• This research aims to develop a gradient boosting model using radiomics on MRI to predict EGFR expression and therapeutic response in high-grade glioma organoid models.
• Utilized radiomics features extracted from contrast-enhanced MRI images.
• Implemented gradient boosting to create a predictive model.
• Evaluated model performance and implications for EGFR-targeted antibody-drug conjugates.
• Model shows promise for non-invasive prediction of EGFR expression.
• EGFR-targeted antibody-drug conjugates exhibited partial efficacy in glioma.
• Found associations between EGFR expression and unfavorable outcomes in high-grade glioma.