Skip to main content

Table 3 The performance of the radiomic models in the training cohort and validation cohort

From: A delta-radiomic lymph node model using dynamic contrast enhanced MRI for the early prediction of axillary response after neoadjuvant chemotherapy in breast cancer patients

Models

Training cohort

Validation cohort

SEN

SPE

ACC

AUC (95% CI)

SEN

SPE

ACC

AUC (95% CI)

Pre-radiomic

0.703

0.702

0.702

0.734 (0.628–0.841)

0.500

0.950

0.750

0.683 (0.486–0.876)

1st-radiomic

0.648

0.829

0.750

0.790 (0.693–0.886)

0.937

0.450

0.666

0.718 (0.548–0.888)

Delta-radiomic

0.757

0.809

0.786

0.851 (0.770–0.932)

0.875

0.650

0.750

0.822 (0.685–0.958)

Clinical

0.648

0.702

0.678

0.742 (0.637–0.846)

0.562

0.900

0.750

0.723 (0.550–0.896)

Pre-radiomic +Clinical

0.837

0.702

0.761

0.829 (0.734–0.915)

0.625

0.900

0.778

0.734 (0.549–0.918)

1st-radiomic+ Clinical

0.703

0.936

0.833

0.831 (0.739–0.922)

0.750

0.800

0.778

0.809 (0.667–0.951)

Delta-radiomic + Clinical

0.865

0.894

0.881

0.932 (0.882–0.983)

0.750

0.850

0.806

0.859 (0.733–0.985)

  1. AUC Area under the ROC, 95%CI 95% confidence interval, SEN Sensitivity, SPE Specificity, ACC Accuracy
Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us