Skip to main content

Table 6 Results of classification modelling for the scanner related target variables. All classifications used only the calculated radiomic features, as passed to the models of Table 5 and there was no direct access by the models to either the raw pixel matrices or the DICOM header information

From: “Real-world” radiomics from multi-vendor MRI: an original retrospective study on the prediction of nodal status and disease survival in breast cancer, as an exemplar to promote discussion of the wider issues

Classification target

AUC

Siemens Avanto 1.5 T vs. Rest

0.91

Siemens Aera 1.5 T vs. Rest

0.96

Philips Achieva 3 T vs. Rest

0.97

Philips Achieva or Intera 1.5 T vs. Rest

0.99

Siemens Skyra 3 T vs. Rest

0.97

1.5 T vs. 3 T

0.95

Siemens vs. Philips

1.00