Delta radiomics from multiparametric MRI plus clinical features predicts pCR after neoadjuvant breast cancer therapy

In a retrospective study of 254 patients, an integrated model combining intratumoral and peritumoral delta radiomics from multiparametric MRI with clinical data outperformed radiomics or clinical models alone for predicting pathologic complete response to neoadjuvant breast canc…

• Retrospective, two-center study of 254 breast cancer patients; delta radiomics features were derived from baseline and post-cycle-2 MRI.
• The ExtraTrees algorithm yielded the best performance among six machine learning algorithms tested.
• No external validation was performed; the model is limited to the two hospitals and retrospective design.

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