Collective intelligent strategy for improved segmentation of COVID-19 from CT

Abstract

We propose a novel non-invasive tool, using deep learning and imaging, for delineating COVID-19 infection in lungs. The Ensembling of selective Focus-based Multi-resolution Convolution network (EFMC), employing Leave-One-Patient-Out (LOPO) training, exhibits high sensitivity and precision in outlining infected regions along with assessment of severity. The selective focus mechanism combines contextual with local information, at multiple resolutions, for accurate segmentation. Ensemble learning integrates heterogeneity of decision through different base classifiers. The superiority of EFMC, even with severe class imbalance, is established through comparison with existing state-of-the-art learning models over four publicly-available COVID-19 datasets. The results are suggestive of the relevance of deep learning in providing assistive intelligence to medical practitioners, when they are overburdened with patients as in pandemics.