MRI radiomics-clinical model predicts radiotherapy tumor shrinkage in cervical cancer

MRI radiomics-clinical fusion model predicted radiotherapy response in cervical cancer: random survival forest had AUC 0.863, accuracy 0.920, sensitivity 0.937, specificity 0.833 (internal validation).

• Fusion models combining radiomics from multisequence MRI and clinical data outperformed all single-sequence models (AUC range 0.824-0.863 vs 0.681-0.827).
• The random survival forest model achieved the highest performance with accuracy 0.920, sensitivity 0.937, and specificity 0.833 for predicting post-radiotherapy tumor shrinkage.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.