A Novel COVID-19 Diagnosis Support System Using the Stacking Approach and Transfer Learning Technique on Chest X-Ray Images

Table 2

Dataset sources used to generate a combined dataset containing four classes.

Dataset source	COVID-19	Normal	Viral pneumonia	Tuberculosis
COVID-19 Radiography Database (https://www.kaggle.com/tawsifurrahman/covid19-radiography-database/data?select=COVID-19+Radiography+Database)	1200	1341	1345	—
COVID-19 Detection X-Ray Dataset (https://www.kaggle.com/darshan1504/covid19-detection-xray-dataset)	60	880	412	—
COVID-19 Patients Lungs X-Ray Images (https://www.kaggle.com/nabeelsajid917/covid-19-x-ray-10000-images?select=dataset)	70	28	—	—
COVID-19 X-Rays (https://www.kaggle.com/andrewmvd/convid19-x-rays?select=X+rays)	70	—	—	—
Pneumonia Virus vs Pneumonia Bacteria (https://www.kaggle.com/muhammadmasdar/pneumonia-virus-vs-pneumonia-bacteria)	—	—	1493	—
Tuberculosis (TB) Chest X-Ray Database (https://www.kaggle.com/tawsifurrahman/tuberculosis-tb-chest-xray-dataset)	—	—	—	3500
Generated dataset	1400	2249	3250	3500