Comparative Analysis of Deep Learning Models for Pneumonia Detection in Chest X-Ray Images DOI Open Access

Williams O. Falana,

Oluwafunsho P. Falana,

Ayodeji Falana

et al.

International Journal of Innovative Science and Research Technology (IJISRT), Journal Year: 2024, Volume and Issue: unknown, P. 2483 - 2488

Published: July 13, 2024

This paper focused on Comparative Analysis of Deep Learning Models for Pneumonia Detection in Chest X-ray Image. is one the illnesses which are associated with lung’s region, can lead to a severe condition when not diagnose or detected at early stages. The ability disease restrict flow oxygen getting into bloodstream makes more dangerous as result existence virus, bacteria Fungi lung. Hence leads untimely death. Experimental AlexNet ANN, ResNet50 ANN and DenseNet 121 algorithms were distinguish detect pneumonia from non-pneumonia patients using medical images total number 1877 both non- used train alexnet algorithm 805 testing, dataset contained balanced combination images. following results gotten experiments respectively: accuracy was 0.877, Sensitivity 0.834, specificity 0.917, f1Score 0.866 AUC 0.93; 0.817, 0.720, 0.910, 0.793 0.88 0.915, 0.837, 0.990, 0.906 0.98 Accuracy, Sensitivity, values. three Scenarios Architecture observed. It found that all models able accurately no significant error.

Language: Английский

Comparative Analysis of Deep Learning Models for Pneumonia Detection in Chest X-Ray Images DOI Open Access

Williams O. Falana,

Oluwafunsho P. Falana,

Ayodeji Falana

et al.

International Journal of Innovative Science and Research Technology (IJISRT), Journal Year: 2024, Volume and Issue: unknown, P. 2483 - 2488

Published: July 13, 2024

This paper focused on Comparative Analysis of Deep Learning Models for Pneumonia Detection in Chest X-ray Image. is one the illnesses which are associated with lung’s region, can lead to a severe condition when not diagnose or detected at early stages. The ability disease restrict flow oxygen getting into bloodstream makes more dangerous as result existence virus, bacteria Fungi lung. Hence leads untimely death. Experimental AlexNet ANN, ResNet50 ANN and DenseNet 121 algorithms were distinguish detect pneumonia from non-pneumonia patients using medical images total number 1877 both non- used train alexnet algorithm 805 testing, dataset contained balanced combination images. following results gotten experiments respectively: accuracy was 0.877, Sensitivity 0.834, specificity 0.917, f1Score 0.866 AUC 0.93; 0.817, 0.720, 0.910, 0.793 0.88 0.915, 0.837, 0.990, 0.906 0.98 Accuracy, Sensitivity, values. three Scenarios Architecture observed. It found that all models able accurately no significant error.

Language: Английский

Citations

1