Search

Abstract COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus’s variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework’s reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings.

Introduction: Coronavirus disease 2019 (COVID-19) is a highly contagious severe and acute respiratory syndrome caused by the SARS-CoV-2 virus. A variety of factors can increase a patient's risk of death, including coagulopathy characterized by increased D-dimer levels. Brixia scores could be one of the determinants of COVID-19 severity, as assessed by chest radiographs. This study aimed to analyze chest radiographic severity based on the Brixia score at the degree of coagulation based on D-dimer in mortality of COVID-19 patients who were hospitalized. Methods: This cohort retrospective study was conducted at Dr. Saiful Anwar General Hospital, Malang, using an observational cross-sectional design. The study included 300 medical records of COVID-19 patients who passed away while hospitalized. The data were analyzed using the Wilcoxon test, and the results were also tested for Spearman correlation to determine the relationship between variables. Results: Significance results of median D-dimer were found by age and severity of COVID-19 (p-values 0.015 and 0.002), and median Brixia scores by age, gender, severity of COVID-19, and length of treatment (p-values 0.001, 0.001, 0.001, and 0.005). The results were also compared with normal values, which were significant (p = 0.000). Spearman correlation test results between the final D-dimer and the initial Brixia score (p = 0.005). Conclusion: The research results display a retrospective study of the correlation between D-dimer and Brixia score values "‹"‹and outcomes in COVID-19 patients. Higher D-dimer values"‹ "‹and Brixia scores on admission were shown to be associated with mortality.

Human adenoviruses (HAdVs) are known to be highly contagious pathogens. They are commonly associated with mild respiratory infections in young children but can also cause severe life-threatening infections. Human adenovirus types 4 and 7 have frequently been reported to cause pneumonia in immunocompetent youths and adults. In this retrospective study, we analyzed the clinical, laboratory, radiological, and microbiological features, as well as the treatment and outcomes of an adenovirus outbreak in 185 patients who were admitted to the Emergency Unit of the Departments of Infectious Diseases and Pediatrics, University Hospital of Split, Croatia, between October 2022 and April 2023. An unusual increase in the frequency of adenovirus pneumonia was observed, especially in adults, followed by respiratory failure and complications such as pulmonary embolism. The most common chest X-ray findings were unilateral patchy opacity and unilateral reticulations (11.6%), followed by unilateral lobar pneumonia (7.1%). The predominant CT presentation was unilateral lobar pneumonia with multiple patchy ground glass opacities (23.5%) or lobar pneumonia with mixed opacities (17.6%). We found a low correlation between Brixia score and C-reactive protein in adults and no correlation in children. Adenovirus type 7 was almost exclusively isolated from patients with pneumonia. Most of our patients with severe or critical adenovirus pneumonia were immunocompetent adults without any medical history. So far, only a few studies have presented the radiological features of HAdV pneumonia, which generally did not reveal lobar pneumonia in a substantial percentage. Our research also demonstrated an unusual presentation of adenovirus infection complicated with pulmonary embolism, which has rarely been reported in previous studies. The aforementioned HAdV outbreak indicates the necessity for further research, especially in the context of effective antiviral therapy and infection prevention.

Barotrauma occurs in a significant number of patients with COVID-19 interstitial pneumonia undergoing mechanical ventilation. The aim of the current study was to investigate whether the Brixia score (BS) calculated on chest-X-rays acquired at the Emergency Room was associated with barotrauma. We retrospectively evaluated 117 SARS-CoV-2 patients presented to the Emergency Department (ED) and then admitted to the intensive care unit (ICU) for mechanical ventilation between February and April 2020. Subjects were divided into two groups according to the occurrence of barotrauma during their hospitalization. CXRs performed at ED admittance were assessed using the Brixia score. Distribution of barotrauma (pneumomediastinum, pneumothorax, subcutaneous emphysema) was identified in chest CT scans. Thirty-eight subjects (32.5%) developed barotrauma (25 pneumomediastinum, 24 pneumothorax, 24 subcutaneous emphysema). In the barotrauma group we observed higher Brixia score values compared to the non-barotrauma group (mean value 12.18 vs. 9.28), and logistic regression analysis confirmed that Brixia score is associated with the risk of barotrauma. In this work, we also evaluated the relationship between barotrauma and clinical and ventilatory parameters: SOFA score calculated at ICU admittance and number of days of non-invasive ventilation (NIV) prior to intubation emerged as other potential predictors of barotrauma.

The COVID-19 pandemic has put intense pressure on the healthcare systems. As the lung complication of COVID-19, pneumonia can be assessed by chest radiography which can be used to predict the severity of patient deterioration using Brixia and RALE scores. This research aims to assess the Radiologists' agreement on diagnosing pneumonia COVID-19 by RT-PCR in CXR using the Brixia and RALE score at Dr. Sardjito Central General Hospital from May 2020-January 2021. Two separate radiologists scored initial chest radiographs for RALE and Brixia independently. The analysis assessed included a descriptive analysis of demographic data, and Bland-Altman plots were used to visualize intra-observer agreement. A total of 332 samples were 162 men (48.8%) and 170 women (51.2%), with a mean age of 42.37. The ICC of Brixia score (0.855, CI:0.794-0.895) and RALE score (0.756, CI:0.662-0.812). Bland–Altman analysis revealed a bias of 5.08 ± 6.04 (95% limits of agreement of -6.760 and 16.929) for Brixia and RALE scores and significantly correlated (r=0.886 (p0.05)). The average score of Brixia (6.29±4.430) and RALE (11.56±9.997) in men was higher than in women. The agreement of Radiologists in diagnosing pneumonia COVID-19 using Brixia and RALE scores with the Bland Altman curve was significant or reliable.

Background: Critical COVID-19 patients account for 1.7 to 13% of all pregnant COVID-19 patients. Methods: Patients admitted to the COVID-19 intensive care unit of Elena Doamna Obstetrics and Gynecology University Hospital in Iasi between 1 January and 1 December 2021, with critical forms of the disease, were included and retrospectively studied. The patients’ age range was 25–44 years in the Alpha group (n = 12) and 27–52 years in the Delta group (n = 9). Results: Most critically ill pregnant COVID-19 patients in the Alpha group delivered when admitted to the intensive care unit, while less than half of those in the Delta group delivered when admitted; the rest were released home and continued their pregnancy normally. There was a significant difference regarding the number of patients released to home care and the number of days after admission when delivery occurred (p = 0.02 and 0.022, respectively). Conclusions: There was no significant difference in maternal and fetal outcomes between the two groups, except for the number of patients released to home care and the number of days after admission when delivery occurred. There was no correlation between any Brixia scores (H, L, A, E) and any maternal or fetal outcomes in both groups.

Rosy Setiawati,1 Anita Widyoningroem,1 Triwulan Handarini,1 Fierly Hayati,1 Agnes Triana Basja,1 Atrikha Rahma Dyana Surya Putri,1 Merlin Guntur Jaya,2 Jessica Andriani,2 Melina Rosita Tanadi,2 Imran Harsam Kamal2 1Department of Radiology, Faculty of Medicine, Universitas Airlangga - Dr. Soetomo General Hospital Surabaya, Surabaya, Indonesia; 2Faculty of Medicine Universitas Airlangga, Surabaya, IndonesiaCorrespondence: Rosy Setiawati 60286 Tel +62 878 5330 0019Email rosy-s@fk.unair.ac.idIntroduction: The management of COVID-19 patients requires efficiency and accuracy in methods of detection, identification, monitoring, and treatment feasible in every hospital. Aside from clinical presentations and laboratory markers, chest x-ray imaging could also detect pneumonia caused by COVID-19. It is also a fast, simple, cheap, and safe modality used for the management of COVID-19 patients. Established scoring systems of COVID-19 chest x-ray imaging include Radiographic Assessment of Lung Edema (RALE) and Brixia classification. A modified scoring system has been adopted from BRIXIA and RALE scoring systems and has been made to adjust the scoring system needs at Dr. Soetomo General Hospital, Indonesia. This study aims to determine the value of scoring systems through chest x-ray imaging in evaluating the severity of COVID-19.Methods: Data were collected from May to June of 2020 who underwent chest x-ray evaluation. Each image is then scored using three types of classifications: modified score, RALE score, and Brixia score. The scores are then analyzed and compared with the clinical conditions and laboratory markers to determine their value in evaluating the severity of COVID-19 infection in patients.Results: A total of 115 patients were males (51.1%) and 110 were females (48.9%). All three scoring systems are significantly correlated with the clinical severity of the disease, with the strengths of correlation in order from the strongest to weakest as Brixia score (p< 0.01, correlation coefficient 0.232), RALE score (p< 0.01, correlation coefficient 0.209), and Dr. Soetomo General Hospital score (p< 0.01, correlation coefficient 0.194). All three scoring systems correlate significantly with each other. Dr. Soetomo General Hospital score correlates more towards Brixia score (p< 0.01, correlation coefficient 0.865) than RALE score (p< 0.01, correlation coefficient 0.855). Brixia to RALE score correlates with a coefficient of 0.857 (p< 0.01).Conclusion: The modified scoring system can help determine the severity of the disease progression in COVID-19 patients especially in areas with shortages of facilities and specialists.Keywords: Brixia score, chest radiographs, COVID-19, modified score, RALE score

Background: Diabetes mellitus is a chronic hyperglycemic condition that can affect the body's immune response to SARS-CoV-2 This study aimed to determine the relationship between diabetes mellitus and lung severity in COVID-19 patients. Methods: A cross-sectional design was conducted at Hasan Sadikin General Hospital during the January–May 2021 period. Data were based on medical records of patients aged 18 years and over with COVID-19. The chi-square test was performed to assess the relationship between diabetes mellitus and lung severity based on the BRIXIA score. Results: This study included 538 subjects, mostly aged

On March 11, 2020, the World Health Organization declared the COVID-19 pandemic. This disease damages the lung and resulting mild to severe pneumonia. This study aimed to determine the value of the Brixia score for predicting mortality and length of stay of COVID-19 confirmed patients. The study design was case-control with secondary data from digital medical records of COVID-19 confirmed patients (December 2020 to February 2021). All patients' chest x-rays (CXR) were scored using the Brixia score. Logistic regression and the Spearman rank correlation test were used to identify mortality and length of stay predictors. There were 636 subjects included in this study, with the proportion of deceased patients (case group) being 20.3% (95% CI=17.33, 23.59%). Most CXR findings had signs of pneumonia (95.1%), including ground-glass opacities (GGOs) mixed with consolidation. The distribution of GGOs and consolidation were most frequent in the peripheral of survived patients (83.9%), while the deceased group had peripheral involvements mixed with medial (45.0%) and bilateral (22.2%). The mean Brixia score in the group of decease patients was significantly higher than the group of survived patients (11.95 vs 6.73, p=0.00). Brixia score had an OR of 1.14, 95% CI=1.07, 1.21 after adjusting by age, SpO2 level, and comorbid. The chance of dying was higher than 50% if the Brixia score reached to score of 15 (probability=49%, 95% CI=41, 56%). However, the Brixia score has no significant correlation with length of stay (rho=0.05, p=0.24). In conclusion, the CXR Brixia score can predict mortality, but it can not predict the length of stay of hospitalized COVID-19 confirmed patients.