Automatic Detection of COVID-19 Using a Stacked Denoising Convolutional Autoencoder

Abstract

The exponential increase in new coronavirus disease 2019 cases and deaths has made COVID-19 the leading cause of death in many countries. Thus, in this study, we propose an efficient technique for the automatic detection of COVID-19 and pneumonia based on X-ray images. A stacked denoising convolutional autoencoder (SDCA) model was proposed to classify X-ray images into three classes: normal, pneumonia, and COVID-19. The SDCA model was used to obtain a good representation of the input data and extract the relevant features from noisy images. The proposed model's architecture mainly composed of eight autoencoders, which were fed to two dense layers and SoftMax classifiers. The proposed model was evaluated with 6356 images from the datasets from different sources. The experiments and evaluation of the proposed model were applied to an 80/20 training/validation split and for five cross-validation data splitting, respectively. The metrics used for the SDCA model were the classification accuracy, precision, sensitivity, and specificity for both schemes. Our results demonstrated the superiority of the proposed model in classifying X-ray images with high accuracy of 96.8%. Therefore, this model can help physicians accelerate COVID-19 diagnosis.

Study of Different Deep Learning Methods for Coronavirus (COVID-19) Pandemic: Taxonomy, Survey and Insights

“…Thus, DL techniques are regularly utilized to automatically extract features to classify cases infected with COVID-19. Components of these systems are built using a pre-trained model that incorporates transfer learning [26][27][28], and a few are introduced through personalized networks [29][30][31].…”

EVAE-Net: An Ensemble Variational Autoencoder Deep Learning Network for COVID-19 Classification Based on Chest X-ray Images

“…Similarly, Abdulkareem et al [ 81 ] proposed a model that used stacked autoencoders instead of sparse autoencoders. Other works have also explored stacked autoencoders [ 82 , 83 , 84 ]. To deal with anomaly localization and lack of pixel annotation in CT images, Zhou et al [ 78 ] proposed a “Weak Variational Autoencoder for Localisation and Enhancement (WAVLE)” framework with two parts: the localization part, which generates attention maps by combining a context-encoding variational autoencoder with a gradient-based technique; and an enhancement part that localizes the infected regions in the CT images, combining the attention maps generated in the first part.…”

Multi-lingual Handwriting Recovery Framework based on Convolutional Denoising Autoencoder with Attention model

“…In general, the autoencoder contains two encoder parts, which project the input image onto a low dimension space. The authors in [26] proved the effectiveness of adding noise to the input image, which improved the generalization of the input data. The distorted image is represented by ln ∈ R (m×n) , and its corresponding image without noise is noticed by l ∈ R (m×n) .…”

“…The distorted image is represented by ln ∈ R (m×n) , and its corresponding image without noise is noticed by l ∈ R (m×n) . The image with noise can be defined as [26]:…”