Skip to main content

Table 2 Areas under the curve (AUC) for radiomics, clinical imaging, and comprehensive (nomogram) models

From: Establishment of a predictive nomogram for breast cancer lympho-vascular invasion based on radiomics obtained from digital breast tomography and clinical imaging features

Model

AUC (95% confidence interval [CI])

Training set

Testing set

External validation set

Radiomics

0.858 (0.787–0.930)

0.849 (0.733–0.965)

0.844 (0.697–0.991)

Clinical imaging

0.743 (0.649–0.836)

0.759 (0.605–0.914)

0.732 (0.546–0.918)

Comprehensive

0.881 (0.811–0.952)

0.908 (0.825–0.991)

0.862 (0.718–1.000)

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us