Skip to main content

Table 6 Classification performance of both DL models on test sets

From: Automated assessment of cardiac pathologies on cardiac MRI using T1-mapping and late gadolinium phase sensitive inversion recovery sequences with deep learning

Dataset images

Accuracy (%)

Sensitivity (%)

Specificity (%)

FPR (%)

FNG (%)

AUC

PSIR

88

100

38

63

0

0.75

T1 mapping

70

78

54

46

11

0.69

  1. Note. — Dataset refers to the training and evaluation of the two separate DL models on PSIR against on T1 mapping images. FPR stands for false positive rate. FNR stands for false negative rate.
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us