Fig. 2: ROC curves for the C and CT and MBR and CMBR and CTMBR models. | British Journal of Cancer

Fig. 2: ROC curves for the C and CT and MBR and CMBR and CTMBR models.

From: MRI radiomics independent of clinical baseline characteristics and neoadjuvant treatment modalities predicts response to neoadjuvant therapy in rectal cancer

Fig. 2

a ROC curve for the C model in the validation set, showing a mean AUC of 0.6103(95% CI, 0.5983–0.6286). b ROC curve for the CT model in the validation set, showing a mean AUC of 0.6294 (95% CI, 0.6036–0.6552). c ROC curve for the MBR model in the validation set, showing a mean AUC of 0.7835 (95% CI, 0.6984–0.8686). d ROC curve for the CMBR model in the validation set, showing a mean AUC of 0.7871 (95% CI, 0.7057–0.8686). e ROC curve for the CTMBR model in the validation set, showing a mean AUC of 0.7916 (95% CI, 0.7570–0.8263). Receiver-operating characteristic, ROC; clinical baseline characteristics, C; clinical baseline characteristics and neoadjuvant treatment modalities, CT; MRI-based radiomics, MBR; MBR signatures combined with clinical baseline characteristics, CMBR; MRI-based radiomics signatures combined with clinical baseline characteristics and neoadjuvant treatment modalities, CTMBR.

Back to article page