Skip to main content

Table 3 Predictive Performances for Recurrence Using Clinicopathological Variables Only and Combinations of Clinicopathological Variables and MRI Metrics

From: Quantitative DCE-MRI prediction of breast cancer recurrence following neoadjuvant chemotherapy: a preliminary study

Model

Wald test p-

value

ROC AUC

95% CI

cv ROC AUC

Clinicopathological variables

RCB + Age

N/A

 

0.900

[0.762, 1]

0.797

Clinicopathological variables and individual MRI metrics

LD_V1

0.807

 

0.892

[0.747, 1]

0.744

LD_V4

0.537

 

0.900

[0.760, 1]

0.769

LD_V4_1%

0.647

 

0.900

[0.778, 1]

0.730

Ktrans_V1

0.116

 

0.946

[0.878, 1]

0.798

ve_V1

0.659

 

0.907

[0.795, 1]

0.777

kep_V1

0.137

 

0.942

[0.872, 1]

0.755

Ï„i_V1

0.486

 

0.911

[0.797, 1]

0.754

Ktrans_V4

0.081

 

0.965

[0.916, 1]

0.814

ve_V4

0.441

 

0.919

[0.808, 1]

0.814

kep_V4

0.071

 

0.961

[0.908, 1]

0.845

Ï„i_V4

0.367

 

0.911

[0.812, 1]

0.725

Ktrans_V4_1%

0.296

 

0.938

[0.862, 1]

0.781

ve_V4_1%

0.289

 

0.927

[0.824, 1]

0.843

kep_V4_1%

0.582

 

0.911

[0.799, 1]

0.782

Ï„i_V4_1%

0.668

 

0.892

[0.770, 1]

0.720

Clinicopathological variables and Principal Components of all MRI metrics

PC1

0.071

 

0.961

[0.910, 1]

0.837

  1. ROC AUC - area under the receiver operating characteristic curve, 95% CI – 95% confidence interval for ROC AUC, cv – cross validated, N/A – not applicable, LD – Longest diameter, V1 – Visit 1 (pre-NACT MRI), V4 – Visit 4 (post NACT, pre-surgery MRI), V4_1% - corresponding percent changes (V4 relative to V1), PC1 – first principal components of all MRI metrics
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us