Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays

Abstract

Covid-19 first occurred in Wuhan, China in December 2019. Subsequently, the virus spread throughout the world and as of June 2020 the total number of confirmed cases are above 4.7 million with over 315,000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is to conduct a critical analysis to investigate the applicability of convolutional neural networks (CNNs) for the purpose of COVID-19 detection in chest X-ray images and highlight the issues of using CNN directly on the whole image. To accomplish this task, we use 12-off-the-shelf CNN architectures in transfer learning mode on 3 publicly available chest X-ray databases together with proposing a shallow CNN architecture in which we train it from scratch. Chest X-ray images are fed into CNN models without any preprocessing to replicate researches used chest X-rays in this manner. Then a qualitative investigation performed to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed to the decision of CNNs back to the original image to visualize the most discriminating region(s) on the input image. We conclude that CNN decisions should not be taken into consideration, despite their high classification accuracy, until clinicians can visually inspect and approve the region(s) of the input image used by CNNs that lead to its prediction.

Pre-trained deep learning models in automatic COVID-19 diagnosis

“…On two datasets, this method has 96% and 97% test accuracy, respectively. These performances are superior in comparison to other works like 89.60% test accuracy achieved by Khan et al [28], 95% test accuracy achieved by Waheed [29] and 87.02% test accuracy achieved by Majeed et al [2].…”

“…Majeed et al [2] have provided an analysis of 12 regular convolutional neural network models to help radiologists discriminate against COVID-19 based on chest X-rays, and also have introduced a CNN model that could give efficient final prediction results. The proposed model has been designed to perform reliable diagnostics for COVID vs. Normal classification and COVID vs. Normal vs.…”

AI-based diagnosis of COVID-19 patients using X-ray scans with stochastic ensemble of CNNs

“…DeTraC used class decomposition mechanism to deal with class boundaries leading to an accuracy of 0.931 and sensitivity of 1. A work by Taban et al on chest X-ray images used the 12-off-the-shelf CNN architectures in transfer learning [ 16 ]. GANs have also been used in the process of COVID-19 disease analysis by Mohamed et al [ 17 ].…”

CovFrameNet: An Enhanced Deep Learning Framework for COVID-19 Detection

“…The CNN architecture proposed in the study was found to outperform 7 out of 12 established CNN architectures: AlexNet, GoogleNet, Vgg16, Vgg19, ResNet18, ResNet50, ResNet101, InceptionV3, InceptionResNetv2, SqueezeNet, Densenet201 and Xception. In another study, Ouyang et al [35] proposed an online attention module with 3D CNN to diagnose COVID-19 from CT scan images, and an accuracy of 87.5% was achieved.…”