Skip to main content
Fig. 4 | Radiation Oncology

Fig. 4

From: Multiphase and multiparameter MRI-based radiomics for prediction of tumor response to neoadjuvant therapy in locally advanced rectal cancer

Fig. 4

Radscore, calibration curves, and decision curves to evaluate pCR. a Radscore for each patient in the training cohort (n = 292), internal testing (n = 74), cohort and external validation cohort (n = 110). b Calibration curves for Model_pCR in the training cohort, internal testing cohort, and external validation cohort. The dotted reference line indicates perfect calibration. c Decision curves for Model_pCR in the training cohort, internal testing cohort, and external validation cohort. The y-axis represents the net benefit. The x-axis represents the threshold probability. The red line represents Model_pCR. The gray line represents the assumption that all patients achieved pCR. The black line represents the hypothesis that no patients achieved pCR. The threshold probability is where the expected benefit of treatment is equal to the expected benefit of avoiding treatment. Model_pCR, multiple phase and multiple parameter MRI-based radiomics model. pCR, pathological complete response

Back to article page