Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation

N B Prakash; M Murugappan; G R Hemalakshmi; M Jayalakshmi; Mufti Mahmud

doi:10.1016/j.scs.2021.103252

Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation

Sustain Cities Soc. 2021 Dec:75:103252. doi: 10.1016/j.scs.2021.103252. Epub 2021 Aug 16.

Authors

N B Prakash¹, M Murugappan², G R Hemalakshmi³, M Jayalakshmi³, Mufti Mahmud^{4

5

6}

Affiliations

¹ Department of Electrical and Electronics Engineering, National Engineering College, Tamil Nadu, India.
² Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Kuwait.
³ Department of Computer Science and Engineering, National Engineering College, Tamil Nadu, India.
⁴ Department of Computer Science, Nottingham Trent University, Clifton, Nottingham NG11 8NS, UK.
⁵ Medical Technologies Innovation Facility, Nottingham Trent University, Clifton, Nottingham NG11 8NS, UK.
⁶ Computing and Informatics Research Centre, Nottingham Trent University, Clifton, Nottingham NG11 8NS, UK.

Abstract

The evolution the novel corona virus disease (COVID-19) as a pandemic has inflicted several thousand deaths per day endangering the lives of millions of people across the globe. In addition to thermal scanning mechanisms, chest imaging examinations provide valuable insights to the detection of this virus, diagnosis and prognosis of the infections. Though Chest CT and Chest X-ray imaging are common in the clinical protocols of COVID-19 management, the latter is highly preferred, attributed to its simple image acquisition procedure and mobility of the imaging mechanism. However, Chest X-ray images are found to be less sensitive compared to Chest CT images in detecting infections in the early stages. In this paper, we propose a deep learning based framework to enhance the diagnostic values of these images for improved clinical outcomes. It is realized as a variant of the conventional SqueezeNet classifier with segmentation capabilities, which is trained with deep features extracted from the Chest X-ray images of a standard dataset for binary and multi class classification. The binary classifier achieves an accuracy of 99.53% in the discrimination of COVID-19 and Non COVID-19 images. Similarly, the multi class classifier performs classification of COVID-19, Viral Pneumonia and Normal cases with an accuracy of 99.79%. This model called the COVID-19 Super pixel SqueezNet (COVID-SSNet) performs super pixel segmentation of the activation maps to extract the regions of interest which carry perceptual image features and constructs an overlay of the Chest X-ray images with these regions. The proposed classifier model adds significant value to the Chest X-rays for an integral examination of the image features and the image regions influencing the classifier decisions to expedite the COVID-19 treatment regimen.

Keywords: COVID-19; Chest X-Ray; GMM; SqueezeNet; Super pixel.