Rethinking Densely Connected Convolutional Networks for Diagnosing Infectious Diseases

Due to its high transmissibility, the COVID-19 pandemic has placed an unprecedented burden on healthcare systems worldwide. X-ray imaging of the chest has emerged as a valuable and cost-effective tool for detecting and diagnosing COVID-19 patients. In this study, we developed a deep learning model using transfer learning with optimized DenseNet-169 and DenseNet-201 models for three-class classification, utilizing the Nadam optimizer. We modified the traditional DenseNet architecture and tuned the hyperparameters to improve the model's performance. The model was evaluated on a novel dataset of 3312 X-ray images from publicly available datasets, using metrics such as accuracy, recall, precision, F1-score, and the area under the receiver operating characteristics curve. Our results showed impressive detection rate accuracy and recall for COVID-19 patients, with 95.98% and 96% achieved using DenseNet-169 and 96.18% and 99% using DenseNet-201. Unique layer configurations and the Nadam optimization algorithm enabled our deep learning model to achieve high rates of accuracy not only for detecting COVID-19 patients but also for identifying normal and pneumonia-affected patients. The model's ability to detect lung problems early on, as well as its low false-positive and false-negative rates, suggest that it has the potential to serve as a reliable diagnostic tool for a variety of lung diseases.

Rethinking the Transfer Learning Architecture for Respiratory Diseases and COVID-19 Diagnosis

The emergence of COVID-19 has caused a disastrous scenario worldwide, becoming one of the most acute and deadly diseases in the last century wreaking havoc on the health and lives of countless people. The prevalence rate of COVID-19 is growing significantly every day across the world. One critical step in combating COVID-19 is the capacity to identify infected individuals and place them in special care as soon as possible. Detecting this condition via radiography and radiology images is one of the quickest ways to diagnose patients. Early study has found specific abnormalities in the chest radiographs of infected individuals with COVID-19. Inspired by prior research, we examine the application of transfer learning models to detect COVID-19 patients in X-rays. In this study, an X-ray image collection from patients with common bacterial pneumonia, viral pneumonia, proven COVÍD-19 disease, and normal occurrences was used to diagnose coronavirus disease automatically. A dataset has been used in this experiment comprising 76 image samples showing verified COVID-19 illness, 2786 images showing bacterial pneumonia, 1504 images showing viral pneumonia, and 1583 images showing normal circumstances. The information was gathered from publicly accessible X-ray images. Data augmentation technique is applied to the trained image dataset. Two transfer learning models, namely, VGG 16 and Xception, have been modified in this paper after applying additional layers with the base model. Modified Xception model provides an overall accuracy of 84.82% for Adam optimizer and 78.40% for RMSprop optimizer. Modified VGG 16 model provides an overall accuracy of 84.98% for Adam optimizer and 83.88% for RMSprop optimizer. In addition to accuracy, we show each model’s receiver operating characteristic (ROC) curve, precision, recall, F1-score, and AUC. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Medical Imaging with Deep Learning for COVID- 19 Diagnosis: A Comprehensive Review

The outbreak of novel coronavirus disease (COVID-19) has claimed millions of lives and has affected all aspects of human life. This paper focuses on the application of deep learning (DL) models to medical imaging and drug discovery for managing COVID-19 disease. In this article, we detail various medical imaging-based studies such as X-rays and computed tomography (CT) images along with DL methods for classifying COVID-19 affected versus pneumonia. The applications of DL techniques to medical images are further described in terms of image localization, segmentation, registration, and classification leading to COVID-19 detection. The reviews of recent papers indicate that the highest classification accuracy of 99.80% is obtained when InstaCovNet-19 DL method is applied to an X-ray dataset of 361 COVID-19 patients, 362 pneumonia patients and 365 normal people. Furthermore, it can be seen that the best classification accuracy of 99.054% can be achieved when EDL_COVID DL method is applied to a CT image dataset of 7500 samples where COVID-19 patients, lung tumor patients and normal people are equal in number. Moreover, we illustrate the potential DL techniques in drug or vaccine discovery in combating the coronavirus. Finally, we address a number of problems, concerns and future research directions relevant to DL applications for COVID-19. © 2021 MIR Labs. All Rights Reserved.

Machine Learning to Predict COVID-19 and ICU Requirement

This paper focuses on the application of machine learning (ML) algorithms to manage novel coronavirus disease (COVID-19). For this, different ML classifiers are used for two cases, one for the prediction of COVID-19 patients, and another for the prediction of the intensive care unit (ICU) requirement. A dataset of 5644 samples and 111 attributes collected at Hospital Israelita Albert Einstein, Brazil is considered in this paper. After necessary preprocessing 57 attributes are used for COVID-19 detection, while 67 attributes are considered for ICU requirement prediction. Using scikit-learn library of Python programming language, the most important features for both cases are found out. A number of base as well as ensemble classifiers are applied to the resultant datasets for the two cases. Results show that COVID-19 detection can be predicted with an accuracy of 94.39% and recall of 92% using stacking ensemble with random forest (RF), XGBoost (XGB) and logistic regression (LR). Results also show that ICU requirement can be predicted with an accuracy of 98.13% and recall of 99% using stacking ensemble with RF, extra trees and LR.

Forecasting the Spread of COVID-19 and ICU Requirements

Since December 2019, the world is fighting against coronavirus disease (COVID-19). This disease is caused by a novel coronavirus termed as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This work focuses on the applications of machine learning algorithms in the context of COVID-19. Firstly, regression analysis is performed to model the number of confirmed cases and death cases. Our experiments show that autoregressive integrated moving average (ARIMA) can reliably model the increase in the number of confirmed cases and can predict future cases. Secondly, a number of classifiers are used to predict whether a COVID-19 patient needs to be admitted to an intensive care unit (ICU) or semi-ICU. For this, classification algorithms are applied to a dataset having 5644 samples. Using this dataset, the most significant attributes are selected using features selection by ExtraTrees classifier, and Proteina C reativa (mg/dL) is found to be the highest-ranked feature. In our experiments, random forest, logistic regression, support vector machine, XGBoost, stacking and voting classifiers are applied to the top 10 selected attributes of the dataset. Results show that random forest and hard voting classifiers achieve the highest classification accuracy values near 98%, and the highest recall value of 98% in predicting the need for admission into ICU / semi-ICU units.