Skip to main content

Table 2 Metrics for the proposed model on different data sets

From: A comparative study between deep learning and radiomics models in grading liver tumors using hepatobiliary phase contrast-enhanced MR images

Model

Data set

Accuracy

Precision

Recall

F1-score

AUC (95% CI)

Radiomics

Training

0.798

0.757

0.805

0.781

0.857 (0.816–0.888)

Test

0.759

0.717

0.884

0.792

0.879 (0.779–0.935)

Deep

Training

0.770

0.775

0.815

0.794

0.838 (0.799–0.871)

Test

0.659

0.617

0.690

0.652

0.717 (0.601–0.814)

  1. AUC area under the curve, CI confidence interval
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us