DSSAE: Deep Stacked Sparse Autoencoder Analytical Model for COVID-19 Diagnosis by Fractional Fourier Entropy

( Aim ) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. ( Methods ) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom deep stacked sparse autoencoder (DSSAE) model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. ( Results ) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). ( Conclusion ) Our method outperforms 10 state-of-the-art approaches.

SECONDARY PULMONARY TUBERCULOSIS RECOGNITION BY ROTATION ANGLE VECTOR GRID-BASED FRACTIONAL FOURIER ENTROPY

Aim: Tuberculosis is an infectious disease caused by Mycobacterium tuberculosis bacteria. This study plans to build a novel deep learning-based model for the accurate recognition of tuberculosis. Methods: We propose a novel model — rotation angle vector grid-based fractional Fourier entropy and deep stacked sparse autoencoder (RAVG-FrFE–DSSAE) — which uses RAVG-FrFE as a feature extractor and harnesses DSSAE as the classifier. Moreover, an 18-way MDA is introduced on the training set to avoid overfitting. Results: Experimental results of 10 runs of 10-fold CV showcase that this proposed RAVG-FrFE–DSSAE algorithm yields a reasonable performance including of 93.68[Formula: see text]±[Formula: see text]1.11% sensitivity, 94.38[Formula: see text]±[Formula: see text]1.11% specificity, 94.35[Formula: see text]±[Formula: see text]1.04% precision, 94.03[Formula: see text]±[Formula: see text]0.69% accuracy, 94.01[Formula: see text]±[Formula: see text]0.70% [Formula: see text]-score, 88.07[Formula: see text]±[Formula: see text]1.38% MCC, 94.01[Formula: see text]±[Formula: see text]0.70% FMI, and 0.9725 AUC, respectively. Conclusions: Our result outperforms the eight state-of-the-art approaches. Besides, the result shows the effectiveness of the 18-way MDA.

Deep learning based on stacked sparse autoencoder applied to viral genome classification of SARS-CoV-2 virus

Since December 2019, the world has been intensely affected by the COVID-19 pandemic, caused by the SARS-CoV-2 virus, first identified in Wuhan, China. In the case of a novel virus identification, the early elucidation of taxonomic classification and origin of the virus genomic sequence is essential for strategic planning, containment, and treatments. Deep learning techniques have been successfully used in many viral classification problems associated with viral infections diagnosis, metagenomics, phylogenetic, and analysis. This work proposes to generate an efficient viral genome classifier for the SARS-CoV-2 virus using the deep neural network (DNN) based on the stacked sparse autoencoder (SSAE) technique. We performed four different experiments to provide different levels of taxonomic classification of the SARS-CoV-2 virus. The confusion matrix presented the validation and test sets and the ROC curve for the validation set. In all experiments, the SSAE technique provided great performance results. In this work, we explored the utilization of image representations of the complete genome sequences as the SSAE input to provide a viral classification of the SARS-CoV-2. For that, a dataset based on k-mers image representation, with k=6, was applied. The results indicated the applicability of using this deep learning technique in genome classification problems.