scholarly journals Diagnosis of COVID-19 Infected Lungs from Chest X-Ray Images

2021 ◽  
Vol 20 (1) ◽  
pp. 33-40
Author(s):  
Ta-Seen Reaz Niloy ◽  
Md. Abdur Rahman

Severe Acute Respiratory Symptom Coronavirus 2 (SARS-CoV-2) was newly discovered as a beta coronavirus. The virus-induced unexplained etiological pneumonia and is referred to as the 2019 Coronavirus Disease (COVID-19). Though the disease has appeared in a new way, there is no medication for transited patients. So, for diagnosing the COVID-19 infected lungs from X-Ray images, an automated technique has been suggested in this manuscript. In this study, Convolutional neural network (CNN) and VGG19 were used and found accuracy scores of 97% and 67%, respectively. The comparative analysis shows that the proposed method performs better than the solution that exists. Eventually, Precision, Recall, and F1-Score have been extracted and interpreted the model's loss functions in the research. This research has carried out by focusing on essential aspects in terms of COVID-19. Therefore, for the diagnosis of coronavirus infection, the technique can be used effectively.

Tuberculosis is one of the single infectious diseases which is one among the top ten causes of deaths. Eradication is only possible by timely diagnosis of disease and treatment at its early stage. But unfortunately, timely detection is lagging due to many reasons. In this angle we present a novel scheme for automatic detection of tuberculosis from chest X-ray images. The proposed method accurately detects the malady by performing graph cut segmentation followed by classification using convolutional neural network. The classifier facilitates the chest X-rays to be classified as normal or abnormal. Simulation results show that the accuracy of 94%, sensitivity of 96% and specificity of 84% obtained from the proposed system are comparable and even better than the existing reported methods.


2021 ◽  
Vol 232 ◽  
pp. 107494
Author(s):  
Junding Sun ◽  
Xiang Li ◽  
Chaosheng Tang ◽  
Shui-Hua Wang ◽  
Yu-Dong Zhang

Sign in / Sign up

Export Citation Format

Share Document