eduzhai > Applied Sciences > Engineering >

Improving performance of CNN to predict likelihood of COVID-19 using chest X-ray images with preprocessing algorithms

  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: As the rapid spread of coronavirus disease (COVID-19) worldwide, chest X-rayradiography has also been used to detect COVID-19 infected pneumonia and assessits severity or monitor its prognosis in the hospitals due to its low cost, lowradiation dose, and wide accessibility. However, how to more accurately andefficiently detect COVID-19 infected pneumonia and distinguish it from othercommunity-acquired pneumonia remains a challenge. In order to address thischallenge, we in this study develop and test a new computer-aided diagnosis(CAD) scheme. It includes several image pre-processing algorithms to removediaphragms, normalize image contrast-to-noise ratio, and generate three inputimages, then links to a transfer learning based convolutional neural network (aVGG16 based CNN model) to classify chest X-ray images into three classes ofCOVID-19 infected pneumonia, other community-acquired pneumonia and normal(non-pneumonia) cases. To this purpose, a publicly available dataset of 8,474chest X-ray images is used, which includes 415 confirmed COVID-19 infectedpneumonia, 5,179 community-acquired pneumonia, and 2,880 non-pneumonia cases.The dataset is divided into two subsets with 90 and 10 of images in eachsubset to train and test the CNN-based CAD scheme. The testing results achieve94.0 of overall accuracy in classifying three classes and 98.6 accuracy indetecting Covid-19 infected cases. Thus, the study demonstrates the feasibilityof developing a CAD scheme of chest X-ray images and providing radiologistsuseful decision-making supporting tools in detecting and diagnosis of COVID-19infected pneumonia.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×