Neural Network based Lungs Infection Detection System

Authors: Saranyavaishalini V G, Raghavan P

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: The corona virus disease 2019 (COVID-19) has become a global pandemic since the beginning of December 2019. The World Health Organization (WHO) and the end of November 2020 have regarded the disease as a Public Health Emergency of International Concern (PHEIC). Automated detection of lung infections from Computed Tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel lungs infection segmented system on SqueezeNet and a Convolutional Neural Network (CNN) is proposed to automatically identify infected regions from chest CT slices. In CNN, a parallel partial decoder is used to aggregate the high-level features and generate a global map.

Keywords: CNN, SqueezeNet, CT Scan, Neural Network, Lungs Infection Detection

Paper Id: 1261

Published On: 2021-10-13

Published In: Volume 9, Issue 5, September-October 2021

Share this