Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content

Table 3 Predictive performance of the deep learning models for the training and validation cohorts

From: Predicting the efficacy of microwave ablation of benign thyroid nodules from ultrasound images using deep convolutional neural networks

 

ACC

AUC

SEN

SPEC

PPV

NPV

Training cohort

ResNet 50

0.73

0.84

0.89

0.53

0.72

0.78

Inception v3

0.65

0.75

0.79

0.46

0.66

0.62

VGG19

0.71

0.77

0.86

0.51

0.70

0.73

EfficientNetB0

0.78

0.89

0.86

0.67

0.78

0.78

EfficientNetB1

0.78

0.87

0.90

0.62

0.76

0.83

EfficientNetB1*

0.85

0.93

0.93

0.75

0.83

0.89

Validation cohort

Resnet 50

0.63

0.76

0.80

0.40

0.63

0.61

InceptionV3

0.54

0.59

0.69

0.34

0.57

0.46

VGG19

0.73

0.81

0.78

0.66

0.74

0.70

EfficientNetB0

0.74

0.86

0.84

0.60

0.73

0.75

EfficientNetB1

0.79

0.84

0.87

0.67

0.78

0.80

EfficientNetB1*

0.79

0.85

0.82

0.74

0.80

0.76

  1. AUC, area under the curve; ACC, accuracy; SEN, sensitivity; SPEC, specificity; NPV, negative predictive value; PPV, positive predictive value; * fine-tuned
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us