Chest CT Airway and Vascular Measurements in Females with COPD or Long-COVID.

Chest CT provides a way to quantify pulmonary airway and vascular tree measurements. In patients with COPD, CT airway measurement differences in females are concomitant with worse quality-of-life and other outcomes. CT total airway count (TAC), airway lumen area (LA), and wall thickness (WT) also differ in females with long-COVID. Our objective was to evaluate CT airway and pulmonary vascular and quality-of-life measurements in females with COPD as compared to ex-smokers and patients with long-COVID. Chest CT was acquired 3-months post-COVID-19 infection in females with long-COVID for comparison with the same inspiratory CT in female ex-smokers and COPD patients. TAC, LA, WT, and pulmonary vascular measurements were quantified. Linear regression models were adjusted for confounders including age, height, body-mass-index, lung volume, pack-years and asthma diagnosis. Twenty-one females (53 ± 14 years) with long-COVID, 17 female ex-smokers (69 ± 9 years) and 13 female COPD (67 ± 6 years) patients were evaluated. In the absence of differences in quality-of-life scores, females with long-COVID reported significantly different LA (p = 0.006) compared to ex-smokers but not COPD (p = 0.7); WT% was also different compared to COPD (p = 0.009) but not ex-smokers (p = 0.5). In addition, there was significantly greater pulmonary small vessel volume (BV5) in long-COVID as compared to female ex-smokers (p = 0.045) and COPD (p = 0.003) patients and different large (BV10) vessel volume as compared to COPD (p = 0.03). In females with long-COVID and highly abnormal quality-of-life scores, there was CT evidence of airway remodelling, similar to ex-smokers and patients with COPD, but there was no evidence of pulmonary vascular remodelling.Clinical Trial Registration: www.clinicaltrials.gov NCT05014516 and NCT02279329.

Patients recovering from COVID-19 who presented with anosmia during their acute episode have behavioral, functional, and structural brain alterations.

Patients recovering from COVID-19 commonly exhibit cognitive and brain alterations, yet the specific neuropathological mechanisms and risk factors underlying these alterations remain elusive. Given the significant global incidence of COVID-19, identifying factors that can distinguish individuals at risk of developing brain alterations is crucial for prioritizing follow-up care. Here, we report findings from a sample of patients consisting of 73 adults with a mild to moderate SARS-CoV-2 infection without signs of respiratory failure and 27 with infections attributed to other agents and no history of COVID-19. The participants underwent cognitive screening, a decision-making task, and MRI evaluations. We assessed for the presence of anosmia and the requirement for hospitalization. Groups did not differ in age or cognitive performance. Patients who presented with anosmia exhibited more impulsive alternative changes after a shift in probabilities (r = - 0.26, p = 0.001), while patients who required hospitalization showed more perseverative choices (r = 0.25, p = 0.003). Anosmia correlated with brain measures, including decreased functional activity during the decision-making task, thinning of cortical thickness in parietal regions, and loss of white matter integrity. Hence, anosmia could be a factor to be considered when identifying at-risk populations for follow-up.

Adaptive Mish activation and ranger optimizer-based SEA-ResNet50 model with explainable AI for multiclass classification of COVID-19 chest X-ray images.

A recent global health crisis, COVID-19 is a significant global health crisis that has profoundly affected lifestyles. The detection of such diseases from similar thoracic anomalies using medical images is a challenging task. Thus, the requirement of an end-to-end automated system is vastly necessary in clinical treatments. In this way, the work proposes a Squeeze-and-Excitation Attention-based ResNet50 (SEA-ResNet50) model for detecting COVID-19 utilizing chest X-ray data. Here, the idea lies in improving the residual units of ResNet50 using the squeeze-and-excitation attention mechanism. For further enhancement, the Ranger optimizer and adaptive Mish activation function are employed to improve the feature learning of the SEA-ResNet50 model. For evaluation, two publicly available COVID-19 radiographic datasets are utilized. The chest X-ray input images are augmented during experimentation for robust evaluation against four output classes namely normal, pneumonia, lung opacity, and COVID-19. Then a comparative study is done for the SEA-ResNet50 model against VGG-16, Xception, ResNet18, ResNet50, and DenseNet121 architectures. The proposed framework of SEA-ResNet50 together with the Ranger optimizer and adaptive Mish activation provided maximum classification accuracies of 98.38% (multiclass) and 99.29% (binary classification) as compared with the existing CNN architectures. The proposed method achieved the highest Kappa validation scores of 0.975 (multiclass) and 0.98 (binary classification) over others. Furthermore, the visualization of the saliency maps of the abnormal regions is represented using the explainable artificial intelligence (XAI) model, thereby enhancing interpretability in disease diagnosis.

COVID-19 pneumonia incidentally discovered on [18F]F-PSMA-1007 PET/CT scan.

A 75-year-old man underwent a positron emission tomography/computed tomography (PET/CT) scan with fluorine-18-prostate specific membrane antigen ([¹8F]F-PSMA-1007) for initial staging of prostate adenocarcinoma. The scan showed lung infiltrates predominantly in both lower lobes with moderate uptake, in addition to a bilateral pulmonary hilar lymph node uptake. CT images revealed ground-glass opacities and a reticular pattern, suggesting COVID-19 pneumonia, which was confirmed by reverse transcription polymerase chain reaction (RT-PCR). Similar incidental findings have been reported in patients undergoing PET/CT scans with other radiotracers. In this case, the probable lung angiogenesis linked to COVID-19 infection can be potencially demonstrated by [¹8F]F-PSMA-1007, which helps ensure timely diagnosis and appropriate care for cancer patients.

Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung CT-scan.

BACKGROUND: Automated analysis of lung computed tomography (CT) scans may help characterize subphenotypes of acute respiratory illness. We integrated lung CT features measured via deep learning with clinical and laboratory data in spontaneously breathing subjects to enhance the identification of COVID-19 subphenotypes. METHODS: This is a multicenter observational cohort study in spontaneously breathing patients with COVID-19 respiratory failure exposed to early lung CT within 7 days of admission. We explored lung CT images using deep learning approaches to quantitative and qualitative analyses; latent class analysis (LCA) by using clinical, laboratory and lung CT variables; regional differences between subphenotypes following 3D spatial trajectories. RESULTS: Complete datasets were available in 559 patients. LCA identified two subphenotypes (subphenotype 1 and 2). As compared with subphenotype 2 (n = 403), subphenotype 1 patients (n = 156) were older, had higher inflammatory biomarkers, and were more hypoxemic. Lungs in subphenotype 1 had a higher density gravitational gradient with a greater proportion of consolidated lungs as compared with subphenotype 2. In contrast, subphenotype 2 had a higher density submantellar-hilar gradient with a greater proportion of ground glass opacities as compared with subphenotype 1. Subphenotype 1 showed higher prevalence of comorbidities associated with endothelial dysfunction and higher 90-day mortality than subphenotype 2, even after adjustment for clinically meaningful variables. CONCLUSIONS: Integrating lung-CT data in a LCA allowed us to identify two subphenotypes of COVID-19, with different clinical trajectories. These exploratory findings suggest a role of automated imaging characterization guided by machine learning in subphenotyping patients with respiratory failure. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT04395482. Registration date: 19/05/2020.

COVID-19's Radiologic, Functional, and Serologic Consequences at 6-Month and 18-Month Follow-up: A Prospective Cohort Study.

BACKGROUND: We evaluated the radiologic, pulmonary functional, and antibody statuses of coronavirus disease 2019 (COVID-19) patients 6 and 18 months after discharge, comparing changes in status and focusing on risk factors for residual computed tomography (CT) abnormalities. METHODS: This prospective cohort study was conducted on COVID-19 patients discharged between April 2020 and January 2021. Chest CT, pulmonary function testing (PFT), and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) immunoglobulin G (IgG) measurements were performed 6 and 18 months after discharge. We evaluated factors associated with residual CT abnormalities and the correlation between lesion volume in CT (lesionvolume), PFT, and IgG levels. RESULTS: This study included 68 and 42 participants evaluated 6 and 18 months, respectively, after hospitalizations for COVID-19. CT abnormalities were noted in 22 participants (32.4%) at 6 months and 13 participants (31.0%) at 18 months. Lesionvolume was significantly lower at 18 months than 6 months (P < 0.001). Patients with CT abnormalities at 6 months showed lower forced expiratory volume in 1 second (FEV1) and FEV1/forced vital capacity (FVC), and patients with CT abnormalities at 18 months exhibited lower FVC. FVC significantly improved between 6 and 18 months of follow-up (all P < 0.0001). SARS-CoV-2 IgG levels were significantly higher in patients with CT abnormalities at 6 and 18 months (P < 0.001). At 18-month follow-up assessments, age was associated with CT abnormalities (odds ratio, 1.17; 95% confidence interval, 1.03-1.32; P = 0.01), and lesionvolume showed a positive correlation with IgG level (r = 0.643, P < 0.001). CONCLUSION: At 18-month follow-up assessments, 31.0% of participants exhibited residual CT abnormalities. Age and higher SARS-CoV-2 IgG levels were significant predictors, and FVC was related to abnormal CT findings at 18 months. Lesionvolume and FVC improved between 6 and 18 months. TRIAL REGISTRATION: Clinical Research Information Service Identifier: KCT0008573.

FMD-UNet: fine-grained feature squeeze and multiscale cascade dilated semantic aggregation dual-decoder UNet for COVID-19 lung infection segmentation from CT images.

With the advancement of computer-aided diagnosis, the automatic segmentation of COVID-19 infection areas holds great promise for assisting in the timely diagnosis and recovery of patients in clinical practice. Currently, methods relying on U-Net face challenges in effectively utilizing fine-grained semantic information from input images and bridging the semantic gap between the encoder and decoder. To address these issues, we propose an FMD-UNet dual-decoder U-Net network for COVID-19 infection segmentation, which integrates a Fine-grained Feature Squeezing (FGFS) decoder and a Multi-scale Dilated Semantic Aggregation (MDSA) decoder. The FGFS decoder produces fine feature maps through the compression of fine-grained features and a weighted attention mechanism, guiding the model to capture detailed semantic information. The MDSA decoder consists of three hierarchical MDSA modules designed for different stages of input information. These modules progressively fuse different scales of dilated convolutions to process the shallow and deep semantic information from the encoder, and use the extracted feature information to bridge the semantic gaps at various stages, this design captures extensive contextual information while decoding and predicting segmentation, thereby suppressing the increase in model parameters. To better validate the robustness and generalizability of the FMD-UNet, we conducted comprehensive performance evaluations and ablation experiments on three public datasets, and achieved leading Dice Similarity Coefficient (DSC) scores of 84.76, 78.56 and 61.99% in COVID-19 infection segmentation, respectively. Compared to previous methods, the FMD-UNet has fewer parameters and shorter inference time, which also demonstrates its competitiveness.

COVID-19 severity detection using chest X-ray segmentation and deep learning.

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.

Novel Deep CNNs Explore Regions, Boundaries, and Residual Learning for COVID-19 Infection Analysis in Lung CT.

COVID-19 poses a global health crisis, necessitating precise diagnostic methods for timely containment. However, accurately delineating COVID-19-affected regions in lung CT scans is challenging due to contrast variations and significant texture diversity. In this regard, this study introduces a novel two-stage classification and segmentation CNN approach for COVID-19 lung radiological pattern analysis. A novel Residual-BRNet is developed to integrate boundary and regional operations with residual learning, capturing key COVID-19 radiological homogeneous regions, texture variations, and structural contrast patterns in the classification stage. Subsequently, infectious CT images undergo lesion segmentation using the newly proposed RESeg segmentation CNN in the second stage. The RESeg leverages both average and max-pooling implementations to simultaneously learn region homogeneity and boundary-related patterns. Furthermore, novel pixel attention (PA) blocks are integrated into RESeg to effectively address mildly COVID-19-infected regions. The evaluation of the proposed Residual-BRNet CNN in the classification stage demonstrates promising performance metrics, achieving an accuracy of 97.97%, F1-score of 98.01%, sensitivity of 98.42%, and MCC of 96.81%. Meanwhile, PA-RESeg in the segmentation phase achieves an optimal segmentation performance with an IoU score of 98.43% and a dice similarity score of 95.96% of the lesion region. The framework's effectiveness in detecting and segmenting COVID-19 lesions highlights its potential for clinical applications.

An Overview of Cone-Beam Computed Tomography and Dental Panoramic Radiography in Dentistry in the Community.

This study reviews the two most important and frequently used systems of tomography used in dentistry today. These are the dental panoramic radiograph (DPR) and cone-beam computed tomography (CBCT). The importance of the DPR has been accentuated by the recent COVID-19 pandemic, as it does not produce an aerosol. Its clinical importance is derived from its panoramic display of the jaws and associated structures and should be examined for incidental findings that may portend a potentially serious outcome. An important recent spin-off of the DPR is the extra-oral bitewing, which can replace its traditional, uncomfortable and aerosol-generating intra-oral counterpart. Although much has been written about them, this paper reviews their essential attributes and limitations in clinical dentistry. Although attempts have been made to reproduce some of the attributes of CT in CBCT such as Hounsfield Units (HU) and improve the contrast resolution of the soft tissues, these remain elusive. Nevertheless, CBCT's dataset should be appropriately reconstructed to fully display the clinical feature prompting its prescription. In certain cases, more than one mode of reconstruction is required.

Deep Learning-Based System Combining Chest X-Ray and Computerized Tomography Images for COVID-19 Diagnosis.

Aims/Background: The coronavirus disease 2019 (COVID-19) pandemic has highlighted the need for accurate and efficient diagnostic methods. This study aims to improve COVID-19 detection by integrating chest X-ray (CXR) and computerized tomography (CT) images using deep learning techniques, further improving diagnostic accuracy by using a combined imaging approach. Methods: The study used two publicly accessible databases, COVID-19 Questionnaires for Understanding the Exposure (COVID-QU-Ex) and Integrated Clinical and Translational Cancer Foundation (iCTCF), containing CXR and CT images, respectively. The proposed system employed convolutional neural networks (CNNs) for classification, specifically EfficientNet and ResNet architectures. The data underwent preprocessing steps, including image resizing, Gaussian noise addition, and data augmentation. The dataset was divided into training, validation, and test sets. Gradient-weighted Class Activation Mapping (Grad-CAM) was used for model interpretability. Results: The EfficientNet-based models outperformed the ResNet-based models across all metrics. The highest accuracy achieved was 99.44% for CXR images and 99.81% for CT images with EfficientNetB5. The models also demonstrated high precision, recall, and F1 scores. For statistical significance, the p-values were less than 0.05, indicating that the results are significant. Conclusion: Integrating CXR and CT images using deep learning significantly improves the accuracy of COVID-19 diagnosis. The EfficientNet-based models, with their superior feature extraction capabilities, show better performance than ResNet models. Grad-CAM Visualizations provide insights into the model's decision-making process, potentially reducing diagnostic errors and accelerating diagnosis processes. This approach can improve patient care and support healthcare systems in managing the pandemic more effectively.

Predictors of the presence of radiological abnormalities 6 months after severe COVID-19 pneumonia.

BACKGROUND: SARS-CoV-2 pneumonia can cause significant long-term radiological changes, even resembling pulmonary fibrosis. However, the risk factors for these long-term effects are unknown. This study aims to assess radiological abnormalities and their possible risk factors six months after hospital discharge due to COVID-19 pneumonia. MATERIAL AND METHODS: This cross-sectional study in a tertiary hospital included adults admitted for COVID-19 pneumonia from March 2020 to February 2021, who underwent high-resolution computed tomography (HRCT) scans of the chest six months after hospital discharge. The primary outcome was radiological abnormalities on HRCT, while the main explanatory variables were drawn from the patient's medical history along with the disease course, analytical indicators, and the treatment received during admission. RESULTS: The 189 included patients had a mean age of 61.5 years; 70.9% were male, and hypertension was the main comorbidity (45%). About two-thirds (67.2%) presented acute respiratory distress syndrome (ARDS). Most (97.9%) received systemic corticosteroid therapy, and 81% presented pathological findings on HRCT, most commonly ground glass (63.5%), followed by bronchial dilatation (36%) and subpleural bands (25.4%). The multivariable analysis showed that age was the main risk factor, associated with most radiological changes. Other factors were the duration of corticosteroid therapy for ground glass (adjusted odds ratio [aOR] 1.020) as well as a longer stay in the intensive care unit (ICU) (aOR 1.290) and high levels of IL-6 for bronchial dilation (aOR 1.002). CONCLUSION: Radiological involvement of the lungs six months after COVID-19 pneumonia is frequent, especially ground glass. Elderly patients with prolonged ICU admission and a significant inflammatory response measured by IL-6 are more likely to present worse radiological evolution and are candidates for radiological follow-up after COVID-19 pneumonia.

Lung Ultrasound Efficacy in Monitoring Post-SARS-CoV-2 Pneumonia and Inflammatory Biomarkers in Pediatric Patients.

Background and Objectives: Recognizing the crucial gaps in our understanding of pediatric pneumonia post-SARS-CoV-2 infection, this study aimed to assess the relationship between Pediatric Pneumonia Ultrasound Scores (PedPne) and inflammatory biomarkers. The primary objective of this study is to evaluate the predictive value of PedPne in comparison with inflammatory biomarkers (IL-6 and dNLR) for the development of pneumonia in pediatric patients following SARS-CoV-2 infection. Materials and Methods: This longitudinal observational study collected data from pediatric patients diagnosed with pneumonia after an acute SARS-CoV2 infection. The study focused on analyzing changes in PedPne scores and inflammatory markers such as IL-6 and dNLR from initial admission to follow-up at 7 days. Statistical analysis involved calculating the sensitivity, specificity, and Area Under the Curve (AUC) for each biomarker, alongside regression analysis to determine their hazard ratios for predicting pneumonia development. Results: The analysis identified significant cutoff values for dNLR at 1.88 (sensitivity 77.0%, specificity 85.7%, AUC 0.802, p < 0.001), IL-6 at 6.1 pg/mL (sensitivity 70.3%, specificity 92.9%, AUC 0.869, p < 0.001), and PedPne score at 3.3 (sensitivity 75.7%, specificity 78.6%, AUC 0.794, p < 0.001). Conversely, NLR showed lower diagnostic performance (AUC 0.485, p = 0.327). Regression analysis further highlighted the strong predictive power of these markers, with IL-6 showing a fourfold increase in pneumonia risk (HR = 4.25, CI: 2.07-9.53, p < 0.001), dNLR indicating more than a twofold increase (HR = 2.53, CI: 1.19-6.97, p = 0.006), and PedPne score associated with more than a doubling of the risk (HR = 2.60, CI: 1.33-5.18, p < 0.001). Conclusions: The study conclusively demonstrated that both PedPne ultrasound scores and specific inflammatory biomarkers such as dNLR and IL-6 are significant predictors of pneumonia development in pediatric patients post-COVID-19 infection. These findings advocate for the integration of these biomarkers in routine clinical assessments to enhance the diagnostic accuracy and management of pneumonia in children following SARS-CoV-2 infection.

Exploring bone density analysis on routine CT scans as a tool for opportunistic osteoporosis screening.

The primary aim of this study was to evaluate computed tomography (CT)-based bone density analysis at the level of thoracic vertebra 12 (Th12) as a screening method for decreased bone density in patients admitted to the intensive care unit (ICU). Interobserver variability was analyzed. Secondary aims were to assess the prevalence of CT-based low bone density upon ICU admission in a cohort of COVID-19 patients and to assess the potential effect of long-term ICU stay on bone density in these patients. Retrospective single-center cohort study. ICU of the Leiden University Medical Center (LUMC), the Netherlands. Patients admitted to the ICU of the LUMC between March 1st, 2020 and February 1st, 2022 with a diagnosis of COVID-19, and a length of ICU stay of ≥ 21 days. In the included patients both baseline chest CT scans (obtained upon ICU admission) and follow-up chest CT scans (obtained ≥ 21 days after ICU admission) were available for analysis. A total of 118 CT scans in 38 patients were analyzed. There was a good interobserver variability, with an overall mean absolute difference (between measurements of three observers) of 9.7 Hounsfield Units (HU) and an intraclass correlation coefficient (ICC) of 0.93 (95% CI 0.88-0.96). The effect of intravenous contrast administration on bone density measurements was small (+ 7.5 HU (95% CI 3.4-11.5 HU)) higher in contrast enhanced CT images compared to non contrast enhanced CT images). Thirty-seven percent of patients had a bone density < 140 HU, suggestive of osteoporosis. No significant difference was found between bone density upon ICU admission and bone density at follow-up (≥ 21 days after ICU admission). Vertebral CT-based bone density analysis using routine CT scans is an easily applicable method to identify ICU patients with decreased bone density, which could enable enrollment in osteoporosis prevention programs. A high prevalence of low bone density was found in our cohort of ICU patients. There were no changes observed in bone density between baseline and follow-up measurements.

A deep convolutional neural network approach using medical image classification.

The epidemic diseases such as COVID-19 are rapidly spreading all around the world. The diagnosis of epidemic at initial stage is of high importance to provide medical care to and recovery of infected people as well as protecting the uninfected population. In this paper, an automatic COVID-19 detection model using respiratory sound and medical image based on internet of health things (IoHT) is proposed. In this model, primarily to screen those people having suspected Coronavirus disease, the sound of coughing used to detect healthy people and those suffering from COVID-19, which finally obtained an accuracy of 94.999%. This approach not only expedites diagnosis and enhances accuracy but also facilitates swift screening in public places using simple equipment. Then, in the second step, in order to help radiologists to interpret medical images as best as possible, we use three pre-trained convolutional neural network models InceptionResNetV2, InceptionV3 and EfficientNetB4 and two data sets of chest radiology medical images, and CT Scan in a three-class classification. Utilizing transfer learning and pre-existing knowledge in these models leads to notable improvements in disease diagnosis and identification compared to traditional techniques. Finally, the best result obtained for CT-Scan images belonging to InceptionResNetV2 architecture with 99.414% accuracy and for radiology images related to InceptionV3 and EfficientNetB4 architectures with the accuracy is 96.943%. Therefore, the proposed model can help radiology specialists to confirm the initial assessments of the COVID-19 disease.

High-resolution Computed Tomography Thorax Volumetric Assessment in Coronavirus Disease 2019 Patients and Correlation with Pulmonary Function Tests.

INTRODUCTION: Years after SARS coronavirus disease 2019 (COVID-19) recovery, residual pulmonary abnormalities may still exist. This brings on the question of whether or not COVID-19 could have comparable late consequences. Structural changes in the lungs after recovery can be better visualized using computed tomography (CT) thorax. Computed Tomography Lung Parenchymal changes during hospitalization by COVID-19 and after 4 months of follow-up to correlate with the volumetric high-resolution computed tomography thorax indices, Pulmonary function tests (PFTs) indices, SpO2, and 6 min Walking Test (6MWT). MATERIALS AND METHODS: This is a Hospital based cross-sectional study, with a follow-up among 100 Patients from 2020 to 2022. Each patient's different CT parameters and HRCT volumetric indices Normal Lung (NL), Normal Lung Percentage (NL%), Whole Lung (WL) were correlated with the PFT indices (Forced expiratory volume in 1s [FEV1], forced vital capacity [FVC], FEV1/FVC), Oxygen Saturation (SpO2) and 6-Minute Walking Test (6MWT). RESULTS: The mean NL (L) and NL% during COVID were significantly lower than the mean values 4 months post-COVID. Architectural distortion, bronchiolar dilatation, interstitial thickening, and parenchymal bands were reduced considerably after 4 months post-COVID, compared to during COVID. PFTs results, such as PFT indices, were not significantly different after 4 months post-COVID, compared to during COVID. SpO2 (%) and 6 MWT (m) were significantly increased. During COVID and post-COVID, the values of NL (L) and NL (%) had a significant positive correlation with PFT indices, SpO2, and 6MWT (m). CONCLUSION: Hence, the different CT indices (NL and NL%) can be used as a surrogate for functional recovery of COVID patients since it correlates with the PFT indices (FEV1 and FEV1/FVC), SpO2, and 6MWT post-COVID.

Résumé Introduction:Des années après la guérison du SRAS Covid-19, des anomalies pulmonaires résiduelles peuvent encore exister. Cela amène à se demander si le Covid-19 pourrait ou non avoir des conséquences tardives comparables. Les changements structurels dans les poumons après la récupération peuvent être mieux visualisés à l'aide de CT-Thorax. Étudier les changements CT post-Covid pendant l'hospitalisation et après quatre mois de suivi de l'infection, et corréler les indices volumétriques du thorax HRCT avec les indices des tests de la fonction pulmonaire (PFT), la SpO2 et le test de marche de 6 min (6MWT).Matériels et méthodes:Il s'agit d'une étude transversale en milieu hospitalier, avec un suivi de 100 patients de 2020 à 2022. Les différents paramètres CT et indices volumétriques HRCT de chaque patient Poumon normal (NL), Pourcentage pulmonaire normal (NL%), Les poumons entiers (WL) étaient corrélés avec les indices PFT (volume expiratoire forcé en 1 s [FEV1], capacité vitale forcée [FVC], FEV1/FVC), saturation en oxygène (SpO2) et test de marche de 6 minutes (6MWT).Résultats:Les moyennes NL (L) et NL% pendant le Covid étaient significativement inférieures aux valeurs moyennes 4 mois post-covid. La distorsion architecturale, la dilatation bronchiolaire, l'épaississement interstitiel et les bandes parenchymateuses ont été considérablement réduits après 4 mois post-covid, par rapport à pendant Covid. Les résultats des tests de la fonction pulmonaire, tels que les indices PFT, n'étaient pas significativement différents après 4 mois post-covid, par rapport à pendant Covid. SpO2 (%) et 6 MWT (m) ont été significativement augmentés. Pendant Covid et post-covid, les valeurs de NL (L) et NL (%) avaient une corrélation positive significative avec les indices PFT, SpO2 et 6 MWT (m).Conclusion:Ainsi, les différents indices CT (NL, NL %) peuvent être utilisés comme substitut de la récupération fonctionnelle des patients Covid car ils sont corrélés aux indices PFT (FEV1, FEV1/FVC), SpO2, 6-MWT post-covid.

Laboratory data and broncho-alveolar lavage on Covid-19 patients with no intensive care unit admission: Correlation with chest CT features and clinical outcomes.

Broncho-alveolar lavage (BAL) is indicated in cases of uncertain diagnosis but high suspicion of Sars-Cov-2 infection allowing to collect material for microbiological culture to define the presence of coinfection or super-infection. This prospective study investigated the correlation between chest computed tomography (CT) findings, Covid-19 Reporting and Data System score, and clinical outcomes in Coronavirus disease 2019 (Covid-19) patients who underwent BAL with the aim of predicting outcomes such as lung coinfection, respiratory failure, and hospitalization length based on chest CT abnormalities. Study population included 34 patients (range 38-90 years old; 20 males, 14 females) with a positive nucleic acid amplification test for Covid-19 infection, suitable BAL examination, and good quality chest CT scan in the absence of lung cancer history. Pulmonary coinfections were found in 20.6% of patients, predominantly caused by bacteria. Specific correlations were found between right middle lobe involvement and pulmonary co-infections. Severe lung injury (PaO2/FiO2 ratio of 100-200) was associated with substantial involvement of right middle, right upper, and left lower lobes. No significant correlation was found between chest CT findings and inflammatory markers (C-reactive protein, procalcitonin) or hospitalization length of stay. Specific chest CT patterns, especially in right middle lobe, could serve as indicators for the presence of co-infections and disease severity in noncritically ill Covid-19 patients, aiding clinicians in timely interventions and personalized treatment strategies.

Technical Principles and Clinical Applications of Electrical Impedance Tomography in Pulmonary Monitoring.

Pulmonary monitoring is crucial for the diagnosis and management of respiratory conditions, especially after the epidemic of coronavirus disease. Electrical impedance tomography (EIT) is an alternative non-radioactive tomographic imaging tool for monitoring pulmonary conditions. This review proffers the current EIT technical principles and applications on pulmonary monitoring, which gives a comprehensive summary of EIT applied on the chest and encourages its extensive usage to clinical physicians. The technical principles involving EIT instrumentations and image reconstruction algorithms are explained in detail, and the conditional selection is recommended based on clinical application scenarios. For applications, specifically, the monitoring of ventilation/perfusion (V/Q) is one of the most developed EIT applications. The matching correlation of V/Q could indicate many pulmonary diseases, e.g., the acute respiratory distress syndrome, pneumothorax, pulmonary embolism, and pulmonary edema. Several recently emerging applications like lung transplantation are also briefly introduced as supplementary applications that have potential and are about to be developed in the future. In addition, the limitations, disadvantages, and developing trends of EIT are discussed, indicating that EIT will still be in a long-term development stage before large-scale clinical applications.

COVID-19 and Pneumonia detection and web deployment from CT scan and X-ray images using deep learning.

During the COVID-19 pandemic, pneumonia was the leading cause of respiratory failure and death. In addition to SARS-COV-2, it can be caused by several other bacterial and viral agents. Even today, variants of SARS-COV-2 are endemic and COVID-19 cases are common in many places. The symptoms of COVID-19 are highly diverse and robust, ranging from invisible to severe respiratory failure. Current detection methods for the disease are time-consuming and expensive with low accuracy and precision. To address such situations, we have designed a framework for COVID-19 and Pneumonia detection using multiple deep learning algorithms further accompanied by a deployment scheme. In this study, we have utilized four prominent deep learning models, which are VGG-19, ResNet-50, Inception V3 and Xception, on two separate datasets of CT scan and X-ray images (COVID/Non-COVID) to identify the best models for the detection of COVID-19. We achieved accuracies ranging from 86% to 99% depending on the model and dataset. To further validate our findings, we have applied the four distinct models on two more supplementary datasets of X-ray images of bacterial pneumonia and viral pneumonia. Additionally, we have implemented a flask app to visualize the outcome of our framework to show the identified COVID and Non-COVID images. The findings of this study will be helpful to develop an AI-driven automated tool for the cost effective and faster detection and better management of COVID-19 patients.

Optimization of vision transformer-based detection of lung diseases from chest X-ray images.

BACKGROUND: Recent advances in Vision Transformer (ViT)-based deep learning have significantly improved the accuracy of lung disease prediction from chest X-ray images. However, limited research exists on comparing the effectiveness of different optimizers for lung disease prediction within ViT models. This study aims to systematically evaluate and compare the performance of various optimization methods for ViT-based models in predicting lung diseases from chest X-ray images. METHODS: This study utilized a chest X-ray image dataset comprising 19,003 images containing both normal cases and six lung diseases: COVID-19, Viral Pneumonia, Bacterial Pneumonia, Middle East Respiratory Syndrome (MERS), Severe Acute Respiratory Syndrome (SARS), and Tuberculosis. Each ViT model (ViT, FastViT, and CrossViT) was individually trained with each optimization method (Adam, AdamW, NAdam, RAdam, SGDW, and Momentum) to assess their performance in lung disease prediction. RESULTS: When tested with ViT on the dataset with balanced-sample sized classes, RAdam demonstrated superior accuracy compared to other optimizers, achieving 95.87%. In the dataset with imbalanced sample size, FastViT with NAdam achieved the best performance with an accuracy of 97.63%. CONCLUSIONS: We provide comprehensive optimization strategies for developing ViT-based model architectures, which can enhance the performance of these models for lung disease prediction from chest X-ray images.