Detection of COVID-19 Patients from CT Scan and Chest X-ray Data Using Modified MobileNetV2 and LIME

Md Manjurul Ahsan; Redwan Nazim; Zahed Siddique; Pedro Huebner

doi:10.3390/healthcare9091099

Detection of COVID-19 Patients from CT Scan and Chest X-ray Data Using Modified MobileNetV2 and LIME

Healthcare (Basel). 2021 Aug 25;9(9):1099. doi: 10.3390/healthcare9091099.

Authors

Md Manjurul Ahsan¹, Redwan Nazim², Zahed Siddique³, Pedro Huebner¹

Affiliations

¹ Industrial and Systems Engineering, University of Oklahoma, Norman, OK 73019, USA.
² Chemical, Biological & Materials Engineering, University of Oklahoma, Norman, OK 73019, USA.
³ School of Aerospace and Mechanical Engineering, University of Oklahoma, Norman, OK 73019, USA.

Abstract

The COVID-19 global pandemic caused by the widespread transmission of the novel coronavirus (SARS-CoV-2) has become one of modern history's most challenging issues from a healthcare perspective. At its dawn, still without a vaccine, contagion containment strategies remained most effective in preventing the disease's spread. Patient isolation has been primarily driven by the results of polymerase chain reaction (PCR) testing, but its initial reach was challenged by low availability and high cost, especially in developing countries. As a means of taking advantage of a preexisting infrastructure for respiratory disease diagnosis, researchers have proposed COVID-19 patient screening based on the results of Chest Computerized Tomography (CT) and Chest Radiographs (X-ray). When paired with artificial-intelligence- and deep-learning-based approaches for analysis, early studies have achieved a comparatively high accuracy in diagnosing the disease. Considering the opportunity to further explore these methods, we implement six different Deep Convolutional Neural Networks (Deep CNN) models-VGG16, MobileNetV2, InceptionResNetV2, ResNet50, ResNet101, and VGG19-and use a mixed dataset of CT and X-ray images to classify COVID-19 patients. Preliminary results showed that a modified MobileNetV2 model performs best with an accuracy of 95 ± 1.12% (AUC = 0.816). Notably, a high performance was also observed for the VGG16 model, outperforming several previously proposed models with an accuracy of 98.5 ± 1.19% on the X-ray dataset. Our findings are supported by recent works in the academic literature, which also uphold the higher performance of MobileNetV2 when X-ray, CT, and their mixed datasets are considered. Lastly, we further explain the process of feature extraction using Local Interpretable Model-Agnostic Explanations (LIME), which contributes to a better understanding of what features in CT/X-ray images characterize the onset of COVID-19.

Keywords: COVID-19; CT scan; SARS-CoV-2; chest X-ray; coronavirus; deep learning; explainable AI; imbalanced data; mixed-data; small data.