A deep learning approach for classification of COVID and pneumonia using DenseNet-201

摘要

In the present paper, our model consists of deep learning approach: Dense-Net201 for detection of COVID and Pneumonia using the Chest X-ray Images.The model is a framework consisting of the modeling software which assists inHealth Insurance Portability and Accountability Act Compliance which protectsand secures the Protected Health Information . The need of the proposedframework in medical facilities shall give the feedback to the radiologist fordetecting COVID and pneumonia though the transfer learning methods. AGraphical User Interface tool allows the technician to upload the chest X-rayImage. The software then uploads chest X-ray radiograph (CXR) to the developeddetection model for the detection. Once the radiographs are processed,the radiologist shall receive the Classification of the disease which further aidsthem to verify the similar CXR Images and draw the conclusion. Our modelconsists of the dataset from Kaggle and if we observe the results, we get anaccuracy of 99.1%, sensitivity of 98.5%, and specificity of 98.95%. The proposedBio-Medical Innovation is a user-ready framework which assists the medicalproviders in providing the patients with the best-suited medication regimen bylooking into the previous CXR Images and confirming the results. There is amotivation to design more such applications for Medical Image Analysis in thefuture to serve the community and improve the patient care.