Skip to main content

Table 7 Results of additional validation using the EfficientNet B4

From: Distinguishing nontuberculous mycobacterial lung disease and Mycobacterium tuberculosis lung disease on X-ray images using deep transfer learning

Class

Model

Precision

Recall

F1 score

AUROC

Accuracy

NTM-LD

(NP = 40,

NI = 40)

EfficientNet B4

0.82

0.78

0.79

0.80

0.78

Ensemble 2

0.84

0.78

0.81

0.81

0.78

MTB-LD

(NP = 40,

NI = 40)

EfficientNet B4

0.79

0.82

0.80

0.80

0.83

Ensemble 2

0.79

0.85

0.82

0.81

0.85

  1. Bold text means the highest performance, NP: Number of Patients, NI: Number of Images.
Back to article page

BMC Infectious Diseases

ISSN: 1471-2334

Contact us