English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Background and Objective:Currently, the whole world is facing a pandemicdisease, novel Coronavirus also known as COVID-19, which spread in more than200 countries with around 3.3 million active cases and 4.4 lakh deathsapproximately. Due to rapid increase in number of cases and limited supply oftesting kits, availability of alternative diagnostic method is necessary forcontaining the spread of COVID-19 cases at an early stage and reducing thedeath count. For making available an alternative diagnostic method, we proposeda deep neural network based diagnostic method which can be easily integratedwith mobile devices for detection of COVID-19 and viral pneumonia using ChestX-rays (CXR) images. Methods:In this study, we have proposed a method namedCOVIDLite, which is a combination of white balance followed by Contrast LimitedAdaptive Histogram Equalization (CLAHE) and depth-wise separable convolutionalneural network (DSCNN). In this method, white balance followed by CLAHE is usedas an image preprocessing step for enhancing the visibility of CXR images andDSCNN trained using sparse cross entropy is used for image classification withlesser parameters and significantly lighter in size, i.e., 8.4 MB withoutquantization. Results:The proposed COVIDLite method resulted in improvedperformance in comparison to vanilla DSCNN with no pre-processing. The proposedmethod achieved higher accuracy of 99.58% for binary classification, whereas96.43% for multiclass classification and out-performed various state-of-the-artmethods. Conclusion:Our proposed method, COVIDLite achieved exceptional resultson various performance metrics. With detailed model interpretations, COVIDLitecan assist radiologists in detecting COVID-19 patients from CXR images and canreduce the diagnosis time significantly.

COVIDLite: A depth-wise separable deep neural network with white balance and CLAHE for detection of COVID-19