Table 4 Performance comparison of various machine learning models using radiomic features extracted via univariate (Uni) and combined univariate plus multivariate (Multi) techniques.

From: Integrating radiomic texture analysis and deep learning for automated myocardial infarction detection in cine-MRI

Model

AUC (Uni)

Accuracy (Uni)

F1 Score (Uni)

AUC (Multi)

Accuracy (Multi)

Precision (Multi)

Recall (Multi)

F1 Score (Multi)

RF

0.58

0.60

0.52

0.96 ± 0.04

0.88 ± 0.05

0.88 ± 0.04

0.95 ± 0.03

0.90 ± 0.05

ET

0.54

0.58

0.49

0.96 ± 0.03

0.96 ± 0.02

0.96 ± 0.03

0.92 ± 0.05

0.90 ± 0.04

LR

0.44

0.50

0.42

0.90 ± 0.03

0.73 ± 0.08

0.77 ± 0.06

0.75 ± 0.10

0.72 ± 0.06

LDA

0.44

0.50

0.42

0.78 ± 0.08

0.85 ± 0.04

0.81 ± 0.04

0.94 ± 0.05

0.88 ± 0.07

QDA

0.57

0.60

0.59

0.90 ± 0.05

0.84 ± 0.03

0.87 ± 0.03

0.87 ± 0.04

0.88 ± 0.02

AB

0.47

0.48

0.34

0.96 ± 0.04

0.92 ± 0.05

0.95 ± 0.05

0.96 ± 0.04

0.96 ± 0.04

KNN

0.42

0.40

0.40

0.89 ± 0.04

0.95 ± 0.03

0.95 ± 0.05

0.86 ± 0.03

0.90 ± 0.04

NB

0.48

0.47

0.38

0.69 ± 0.08

0.68 ± 0.12

0.95 ± 0.05

0.48 ± 0.15

0.61 ± 0.11

SVM

0.52

0.50

0.40

0.92 ± 0.05

0.88 ± 0.06

0.94 ± 0.06

0.86 ± 0.05

0.87 ± 0.07

MLP

0.54

0.58

0.55

0.91 ± 0.05

0.91 ± 0.02

0.89 ± 0.03

0.97 ± 0.02

0.91 ± 0.03

Back to article page