Title
: Fast identification of probable Covid-19 patients from easily available X-ray images using deep learning model
Description
: The quick identification and isolation of the affected persons is the key to fight against the highly infectious COVID-19. We are proposing a deep learning-based architecture that doctors can use to quickly identify probable COVID-19 positive patients and take necessary measures. A website will take chest X-ray images as input and generate probabilities of the presence of COVID-19 or pneumonia and a heatmap highlighting the probable infected areas. Moreover, our proposed model will enhance performance over time using users' input images. We achieved state-of-the-art accuracy on the COVIDx dataset containing 13,800 X-ray images across 13,725 patients. To check the robustness of our model, we performed k-fold and patient-wise cross-validation and observed consistent performance.
