Lung Diseases Detection Using Various Deep Learning Algorithms

Table 1

Comparison of our model with existing works related to pneumonia.

Related work	Dataset	Techniques	F1score	Accuracy	Recall	Precision	Specificity
Sourab and Kabir [19]	Mendeley datav2 (5856 images)	CNN	96	94.55	94	99	85
Gayathri [20]	GitHub (783 images)	CNN	95.63	95.78	—	95.63	95
Vrbančič and Podgorelec [21]	ImageNet	Ensemble	95.01	91.98	93.8	96.38	90
Fernandes et al. [22]	CXR dataset (3883 images)	CNN	93.2	95.7	91.2	95.1	97.5
Hasija et al. [23]	—	CNN	98.52	98.38	—	—	99.81
Our proposed model	Chest X-ray (1000 images)	CNN-sequential model	98.55	98.4375%	96.33%	99%	99.89%