Background: One of the most challenging aspects related to Covid-19 is to establish the presence of infection in an early phase of the disease. Texture analysis might be an additional tool for the evaluation of Chest X-ray in patients with clinical suspicion of Covid-19 related pneumonia.

Objective: To evaluate the diagnostic performance of texture analysis and machine learning models for the diagnosis of Covid-19 interstitial pneumonia in Chest X-ray images.

Methods: Chest X-ray images were accessed from a publicly available repository(https://www.kaggle. com/tawsifurrahman/covid19-radiography-database). Lung areas were manually segmented using a polygonal region of interest covering both lung areas, using MaZda, a freely available software for texture analysis. A total of 308 features per ROI was extracted. One hundred-ten Covid-19 Chest X-ray images were selected for the final analysis.

Results: Six models, namely NB, GLM, DL, GBT, ANN, and PLS-DA were selected and ensembled. According to Youden's index, the Covid-19 Ensemble Machine Learning Score showing the highest area under the curve (0.971±0.015) was 132.57. Assuming this cut-off the Ensemble model performance was estimated by evaluating both true and false positive/negative, resulting in 91.8% accuracy with 93% sensitivity and 90% specificity. Moving the cut-off value to -100, although the accuracy resulted lower (90.6%), the Ensemble Machine Learning showed 100% sensitivity, with 80% specificity.

Conclusion: Texture analysis of Chest X-ray images and machine learning algorithms may help in differentiating patients with Covid-19 pneumonia. Despite several limitations, this study can lay the ground for future research works in this field and help to develop more rapid and accurate screening tools for these patients.

Download full-text PDF

Source
http://dx.doi.org/10.2174/1573405617999210112195450DOI Listing

Publication Analysis

Top Keywords

chest x-ray
24
texture analysis
20
x-ray images
16
machine learning
16
covid-19 pneumonia
8
pneumonia chest
8
lung areas
8
ensemble machine
8
covid-19
7
chest
6

Similar Publications

Lung cancers associated with cystic airspaces (LCCAs) are a rare and relatively novel concept analyzed in various case reports and retrospective studies. In this review, it was our aim to investigate the morphologic, imaging, and clinicopathologic characteristics of this entity, as well as its natural course in light of the current literature. Literature search including the years 2000-2022 was conducted in PubMed.

View Article and Find Full Text PDF

Tracheal schwannomas are exceedingly rare, accounting for a minute fraction of primary tracheal tumors. They are classified into intraluminal and mixed types, with treatment strategies varying significantly between these subtypes. While thorax tomography is usually sufficient to distinguish intraluminal and mixed type, endobronchial ultrasonography (EBUS) can also be used in cases where the distinction cannot be made clearly with tomography.

View Article and Find Full Text PDF

Introduction: Pneumonia is a common symptom of coronavirus disease-2019 (COVID-19), and this study aimed to determine how analyzing initial thoracic computerized-tomography (CT) scans using semi-quantitative methods could be used to predict the outcomes for hospitalized patients.

Materials And Methods: This study looked at previously collected data from adult patients who were hospitalized with a positive test for severe acute respiratory syndrome coronavirus-2 and had CT scans of their thorax at the time of presentation. The CT scans were evaluated for the extent of lung involvement using a semi-quantitative scoring system ranging from 0 to 72.

View Article and Find Full Text PDF

Introduction: This study aimed to evaluate the imaging findings of the chest flat panel detector computed tomography (FDCT) among coronavirus disease-2019 (COVID-19) positive patients during urgent/emergent interventional neuroradiologic procedures.

Materials And Methods: Chest FDCT examinations were performed using a C-arm mounted FDCT within the interventional radiology (IR) suite if the reverse transcription polymerase chain reaction (RT-PCR) results were pending in patients with clinical findings suggestive of COVID-19. In those who already had positive RT-PCR results, FDCT was performed for acute evaluation only if an acute unexpected cardiopulmonary event occurred during the procedure.

View Article and Find Full Text PDF

Assessing chest radiographic quality and the influence of COVID-19 pathology: the Australian experience.

J Med Radiat Sci

January 2025

Discipline of Medical Imaging Sciences, Faculty of Medicine and Health, University of Sydney, Camperdown, New South Wales, Australia.

Introduction: Quality assurance (QA) in medical imaging ensures consistently high-quality images at acceptable radiation doses. However, the applicability of the chest X-ray (CXR) QA tool in images with pathology, particularly infectious diseases like COVID-19, has not been explored. This study examines the utility of the European Guidelines for image quality in QA of CXRs with varying severity and types of infectious disease.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!