PUBLICATIONS

Abstract

Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-Rays.


Rajaraman S, Siegelman J, Alderson PO, Folio LS, Folio LR, Antani SK

IEEE Access, vol. 8, pp. 115041-115050, 2020, doi: 10.1109/ACCESS.2020.3003810

Abstract:

We demonstrate use of iteratively pruned deep learning model ensembles for detecting pulmonary manifestations of COVID-19 with chest X-rays. This disease is caused by the novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus, also known as the novel Coronavirus (2019-nCoV). A custom convolutional neural network and a selection of ImageNet pretrained models are trained and evaluated at patient-level on publicly available CXR collections to learn modality-specific feature representations. The learned knowledge is transferred and fine-tuned to improve performance and generalization in the related task of classifying CXRs as normal, showing bacterial pneumonia, or COVID-19-viralabnormalities.Thebestperformingmodelsareiterativelyprunedtoreducecomplexityand improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that theweightedaverageofthebest-performingprunedmodelssignificantlyimprovesperformanceresultingin an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resultedinimprovedpredictions.WeexpectthatthismodelcanbequicklyadoptedforCOVID-19screening using chest radiographs.


Rajaraman S, Siegelman J, Alderson PO, Folio LS, Folio LR, Antani SK Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-Rays. 
IEEE Access, vol. 8, pp. 115041-115050, 2020, doi: 10.1109/ACCESS.2020.3003810

PDF