Detection of Covid-19 from the Chest X-Ray Images: A Comparison Study between CNN and Resnet-50

SARS-CoV-2-virus, or COVID-19, is an infectious disease that makes people's lives turn inside out. The disease spread drastically worldwide, affecting the world's socioeconomic balance. Currently, most parts of the world rely on antigen tests or RT PCR tests for diagnosing patients with symptoms of Covid-19. However, in an outbreak where a large group of people gets the symptoms, it will be challenging to conduct the tests for all in a short period;therefore, finding alternates as a backup plan is essential. Many studies were conducted to simplify and automate disease identification using CXR images for that specific purpose. The proposed system aims to compare a ResNet-50 based Covid detection model with a deep CNN model to analyze the difference in terms of performance and efficiency of the models. Both models are trained and tested on the same dataset for better comparison. In this study, both CNN and ResNet-50 model achieved an accuracy of 96 percent, whereas ResNet-50 performed slightly better on the test dataset. © 2022 IEEE.

Comparison of Chest X-rays findings in COVID-19 suspected and confirmed cases at a university teaching hospital: A retrospective comparative study

Objectives: To compare Chest X-rays findings in COVID-19 suspected and confirmed patients on RT-PCR, presented at corona filtration center, Benazir Bhutto hospital Rawalpindi. Methods: In this study, Chest radiographs of 100 COVID-19 RT-PCR positive confirmed patients were compared with 100 RT-PCR negative suspected COVID-19 patients screened at corona filtration center, Benazir Bhutto Hospital Rawalpindi from November 2020 to December 2020. Data on demographics, presenting complaints, co-morbid, lesion characteristic, distribution and attenuation, lobar involvement, pleural effusion and lymphadenopathy were collected. Associations between imaging characteristics and COVID-19 pneumonia were analyzed with univariate and multivariate logistic regression modals. Results: Chest X-rays findings revealed bilateral lung consolidation with peripheral and diffuse distribution, involving middle and lower lobe to be statistically significant (p<0.05) between RT-PCR positives and negative patients. Peripheral distribution was associated with an 11.08-fold risk in COVID-19 positive patients than diffuse distribution. Middle lobe involvement had four folds risk and lower lobe involvement had 11.04 folds risk in COVID-19 cases as compared to upper lobe involvement. Consolidation had 2.6 folds risk in COVID-19 positive cases. Conclusions: Bilateral, peripheral distribution of middle and lower lobes ground glass haze or consolidation with no pleural effusion is significantly related to COVID-19 pneumonia. Overlapping imaging features of the infectious and non-infectious COVID mimickers can be further excluded by detailed clinical evaluation and further radiological workup.

COVID-CBR: A Deep Learning Architecture Featuring Case-Based Reasoning for Classification of COVID-19 from Chest X-Ray Images

Background and Objectives: This study aims to assist rapid accurate diagnosis of COVID-19 based on chest x-ray (CXR) images to provide supplementary information, leading to screening program for early detection of COVID-19 based on CXR images by developing an interpretable, robust and performant AI system. Methods: A case-based reasoning approach built upon autoencoder deep learning architecture is applied to classify COVID-19 from other non-COVID-19 as well as normal subjects from chest x-ray images. The system integrates the interpretation and decision-making together by producing a set of profiles that in appearance resemble the training samples and hence explain the outcome of classifications. Three classes are studied, which are COVID-19 (n=250), other non-COVID-19 diseases (NCD) (n=384), including TB and ARDS, and normal (n=327). Results: This COVID-CBR system sustains the average sensitivity and specificity of 93.1±3.58% and 96.1±4.10% respectively for classification of these three classes. In comparison with the current state of the art, including COVID-Net, VGG-16 and other explainable AI systems, the developed COVID-CBR system appears to perform similar or better when classifying multi-class categories. Conclusion: This paper presents a case-based reasoning deep learning system for detection of COVID19 from chest x-ray images. Comparison with several state of the art systems is conducted. Although the improvement tends to be marginal, especially for VGG-16, the novelty of this work manifests its interpretable feature building upon case-based reasoning, leading to revealing this viral insight and hence ascertaining more effective treatment and drugs while maintaining being transparent. Furthermore, different from several other current explainable networks that highlight key regions or the points of an input that activate the network, i.e. heat maps, this work is constructed upon whole training images, i.e. case-based, whereby each training image belongs to one of the case clusters. © 2021 IEEE.

Chest X-rays findings in COVID 19 patients at a University Teaching Hospital - A descriptive study.

OBJECTIVE: To analyze Chest X-ray findings in COVID 19 positive patients, presented at corona filtration center, Benazir Bhutto Hospital Rawalpindi, based on CXR classification of British Society of Thoracic Imaging (BSTI). METHODS: In this study, all RT-PCR COVID-19 positive patients screened at corona filtration center, Benazir Bhutto hospital Rawalpindi from 20th March 2020 to 10th April 2020 were included. Mean age of the cohort with age range was calculated. Presenting complaints & Co-morbid were analyzed and tabulated in frequencies and percentages. Portable CXR findings were classified according to BSTI classification and documented in frequencies and percentages. RESULTS: Mean age of the patients was 44 years. Presenting complaints were cough 20 (67%), fever 18 (60%), shortness of breath 11 (37%), sore throat six (20%), loss of sense of taste and smell four(13%). Main co-morbid was hypertension six (20%). Two (7%) patients had normal and seven (23%) had classical COVID CXRs. 21 (70%) patients were in indeterminate group with only one (3%) having unilateral lung disease. Three (10%) patients had diffuse lung involvement and 18(60%) had peripheral lung involvement. Majority of patients 19 (63%), had bilateral middle and lower zonal involvement. CONCLUSIONS: In this study, COVID-19 CXRs generally manifested a spectrum of pure ground glass, mixed ground glass opacities to consolidation in bilateral peripheral middle and lower lung zones. BSTI CXR reporting classification of COVID-19 is valid in our patients with addition of middle zonal involvement in classical COVID-19 criteria as opposed to just lower zone involvement.

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

COVID-19 has evolved into one of the most severe and acute illnesses. The number of deaths continues to climb despite the development of vaccines and new strains of the virus have appeared. The early and precise recognition of COVID-19 are key in viably treating patients and containing the pandemic on the whole. Deep learning technology has been shown to be a significant tool in diagnosing COVID-19 and in assisting radiologists to detect anomalies and numerous diseases during this epidemic. This research seeks to provide an overview of novel deep learning-based applications for medical imaging modalities, computer tomography (CT) and chest X-rays (CXR), for the detection and classification COVID-19. First, we give an overview of the taxonomy of medical imaging and present a summary of types of deep learning (DL) methods. Then, utilizing deep learning techniques, we present an overview of systems created for COVID-19 detection and classification. We also give a rundown of the most well-known databases used to train these networks. Finally, we explore the challenges of using deep learning algorithms to detect COVID-19, as well as future research prospects in this field.