Ground-glass opacity (GGO): a review of the differential diagnosis in the era of COVID-19

Radiology of fibrosis. Part I: Thoracic organs

Sustained injury from factors such as hypoxia, infection, or physical damage may provoke improper tissue repair and the anomalous deposition of connective tissue that causes fibrosis. This phenomenon may take place in any organ, ultimately leading to their dysfunction and eventual failure. Tissue fibrosis has also been found to be central in both the process of carcinogenesis and cancer progression. Thus, its prompt diagnosis and regular monitoring is necessary for implementing effective disease-modifying interventions aiming to reduce mortality and improve overall quality of life. While significant research has been conducted on these subjects, a comprehensive understanding of how their relationship manifests through modern imaging techniques remains to be established. This work intends to provide a comprehensive overview of imaging technologies relevant to the detection of fibrosis affecting thoracic organs as well as to explore potential future advancements in this field.

Lung Involvement in Pulmonary Vasculitis: A Radiological Review

Pulmonary vasculitis identifies a heterogeneous group of diseases characterized by inflammation, damage and necrosis of the wall of pulmonary vessels. The most common approach to classify vasculitis is according to etiology, therefore dividing them into primary and secondary, with a further sub-classification of primary vasculitis based on the size of the affected vessels (large, medium, and small). Pulmonary involvement is frequently observed in patients with systemic vasculitis and radiological presentation is not pathognomonic, but may vary between diseases. The main findings using high-resolution computed tomography (HRCT) include small vessel wall thickening, nodular lesions, cavitary lesions, reticular opacities, ground-glass opacities (GGO), consolidations, interlobular septal thickening, tracheobronchial stenosis, and aneurysmal dilatation of pulmonary arteries, with or without pleural effusion. Radiological diagnosis alone is difficult since signs and symptoms of lung vessel involvement are often non-specific and might overlap with other conditions such as infections, connective tissue diseases and neoplasms. Therefore, the aim of this review is to describe the most common radiological features of lung involvement in pulmonary vasculitis so that, alongside detailed clinical history and laboratory tests, a prompt diagnosis can be performed.

COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography

Background and novelty

When RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections.

Methodology

Annotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland-Altman, and (iv) Correlation plots.

Results

Among the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann-Whitney, Paired t-Test, Wilcoxon test, and Friedman test all of which had a p < 0.001.

Conclusion

Full-scale skip connections of UNet3+ with VGG and ResNet in HDL framework proved the hypothesis showing powerful results improving the detection accuracy of COVID-19.

A Literature Review on the Relative Diagnostic Accuracy of Chest CT Scans versus RT-PCR Testing for COVID-19 Diagnosis

BACKGROUND

Reverse transcription polymerase chain reaction (RT-PCR) is the main technique used to identify COVID-19 from respiratory samples. It has been suggested in several articles that chest CTs could offer a possible alternate diagnostic tool for COVID-19; however, no professional medical body recommends using chest CTs as an early COVID-19 detection modality. This literature review examines the use of CT scans as a diagnostic tool for COVID-19.

METHOD

A comprehensive search of research works published in peer-reviewed journals was carried out utilizing precisely stated criteria. The search was limited to English-language publications, and studies of COVID-19-positive patients diagnosed using both chest CT scans and RT-PCR tests were sought. For this review, four databases were consulted: these were the Cochrane and ScienceDirect catalogs, and the CINAHL and Medline databases made available by EBSCOhost.

FINDINGS

In total, 285 possibly pertinent studies were found during an initial search. After applying inclusion and exclusion criteria, six studies remained for analysis. According to the included studies, chest CT scans were shown to have a 44 to 98% sensitivity and 25 to 96% specificity in terms of COVID-19 diagnosis. However, methodological limitations were identified in all studies included in this review.

CONCLUSION

RT-PCR is still the suggested first-line diagnostic technique for COVID-19; while chest CT is adequate for use in symptomatic patients, it is not a sufficiently robust diagnostic tool for the primary screening of COVID-19.

Investigating the trend of demographic changes, mortality, clinical and paraclinical findings of patients hospitalized in the Corona ward, before and after the start of general vaccination of COVID-19

BACKGROUND

Prioritizing prevention over treatment has been a longstanding principle in the world health system. This study aims to compare the demographic changes, mortality, clinical, and paraclinical findings of patients hospitalized in the Corona ward before and after the start of general vaccination.

METHODS

This cross-sectional study utilized the simple random sampling method in 2022, analyzing 300 medical records of patients admitted to the Corona ward at 22 Bahman Khaf Hospital. Data were collected using a checklist with the help of the Medical Care Monitoring System and analyzed using SPSS-22 statistical software and Chi-square statistical test at a significance level of p < 0.05.

RESULTS

Before the start of general vaccination for COVID-19, the majority of patients were hospitalized in the Corona Intensive Care Unit (59.3%), aged between 51 and 65 years (47.3%), hospitalized for more than 3 days (54%), required intubation (49.3%), had SPO2 < 93% (60.7%), and exhibited common symptoms such as cough, shortness of breath, and loss of consciousness. Paraclinical findings included positive CRP, decreased lymphocytes, and ground glass opacity (GGO). After the start of general vaccination for COVID-19, most patients were hospitalized in the general care department of Corona (68%), aged between 36 and 50 years (47.3%), hospitalized for less than three days (66%), required intubation (20%), had SPO2 ≥ 93% (77.3%), and exhibited common symptoms such as weakness, headache, and body pain. Paraclinical findings were within the normal range.

CONCLUSIONS

General vaccination for COVID-19 has significantly reduced patient mortality and morbidity. Health policymakers should prioritize general vaccination to achieve herd immunity and improve public health.

Comparing Visual and Software-Based Quantitative Assessment Scores of Lungs' Parenchymal Involvement Quantification in COVID-19 Patients

(1) Background: Computed tomography (CT) plays a paramount role in the characterization and follow-up of COVID-19. Several score systems have been implemented to properly assess the lung parenchyma involved in patients suffering from SARS-CoV-2 infection, such as the visual quantitative assessment score (VQAS) and software-based quantitative assessment score (SBQAS) to help in managing patients with SARS-CoV-2 infection. This study aims to investigate and compare the diagnostic accuracy of the VQAS and SBQAS with two different types of software based on artificial intelligence (AI) in patients affected by SARS-CoV-2. (2) Methods: This is a retrospective study; a total of 90 patients were enrolled with the following criteria: patients' age more than 18 years old, positive test for COVID-19 and unenhanced chest CT scan obtained between March and June 2021. The VQAS was independently assessed, and the SBQAS was performed with two different artificial intelligence-driven software programs (Icolung and CT-COPD). The Intraclass Correlation Coefficient (ICC) statistical index and Bland-Altman Plot were employed. (3) Results: The agreement scores between radiologists (R1 and R2) for the VQAS of the lung parenchyma involved in the CT images were good (ICC = 0.871). The agreement score between the two software types for the SBQAS was moderate (ICC = 0.584). The accordance between Icolung and the median of the visual evaluations (Median R1-R2) was good (ICC = 0.885). The correspondence between CT-COPD and the median of the VQAS (Median R1-R2) was moderate (ICC = 0.622). (4) Conclusions: This study showed moderate and good agreement upon the VQAS and the SBQAS; enhancing this approach as a valuable tool to manage COVID-19 patients and the combination of AI tools with physician expertise can lead to the most accurate diagnosis and treatment plans for patients.

Incidence, management and prognosis of new-onset sarcoidosis post COVID-19 infection

BACKGROUND AND AIM

SARS-CoV-2 infection has been linked to hyperinflammation in multiple organs with a potential mechanistic link with resulting autoimmunity. There have been reports of many inflammatory complications following COVID-19, including sarcoidosis. A literature review on new-onset sarcoidosis following COVID-19 is lacking. We evaluated potential associations between COVID-19 and development of new-onset sarcoidosis.

METHODS

Articles discussing biopsy-proven sarcoidosis after confirmed COVID-19 infection, published 1956 until April 2023, were included. All article types were deemed eligible except opinion and review articles.

RESULTS

A pooled total of 15 patients with new-onset diagnosis of sarcoidosis after COVID-19 infection were included, 45.5% female, mean age 46.1 years (standard deviation 14.7) at onset of sarcoidosis. Patients were from: Europe (n=11); North America (n=2); South America (n=1); Asia (n=1). The mean time between COVID-19 infection and diagnosis of sarcoidosis was 56.3 days, although this ranged from 10 to 140 days. Organ systems predominantly affected by sarcoidosis were: pulmonary (n=11); cutaneous (n=3); cardiac (n=2); ocular (n=1); systemic (n=1) (with overlapping features in certain patients). Sarcoidosis was treated as follows: glucocorticoids (n=8); azathioprine (n=1); cardiac re-synchronisation therapy (n=1); heart transplant (n=1). All patients were reported to have survived, with one requiring intensive care admission.

CONCLUSIONS

Our result suggests there is a potential link between COVID-19 and new-onset sarcoidosis. The potential mechanism for this is through cytokine mediated immune modulation in COVID-19 infection. Obtaining a tissue sample remains key in confirming the diagnosis of sarcoidosis and this may be delayed during active COVID-19 infection.

Parenchymal Cavitations in Pulmonary Tuberculosis: Comparison between Lung Ultrasound, Chest X-ray and Computed Tomography

This article aims to detect lung cavitations using lung ultrasound (LUS) in a cohort of patients with pulmonary tuberculosis (TB) and correlate the findings with chest computed tomography (CT) and chest X-ray (CXR) to obtain LUS diagnostic sensitivity. Patients with suspected TB were enrolled after being evaluated with CXR and chest CT. A blinded radiologist performed LUS within 3 days after admission at the Infectious Diseases Department. Finally, 82 patients were enrolled in this study. Bronchoalveolar lavage (BAL) confirmed TB in 58/82 (71%). Chest CT showed pulmonary cavitations in 38/82 (43.6%; 32 TB patients and 6 non-TB ones), LUS in 15/82 (18.3%; 11 TB patients and 4 non-TB ones) and CXR in 27/82 (33%; 23 TB patients and 4 non-TB ones). Twelve patients with multiple cavitations were detected with CT and only one with LUS. LUS sensitivity was 39.5%, specificity 100%, PPV 100% and NPV 65.7%. CXR sensitivity was 68.4% and specificity 97.8%. No false positive cases were found. LUS sensitivity was rather low, as many cavitated consolidations did not reach the pleural surface. Aerated cavitations could be detected with LUS with relative confidence, highlighting a thin air crescent sign towards the pleural surface within a hypoechoic area of consolidation, easily distinguishable from a dynamic or static air bronchogram.

Performance of chest X-ray scoring in predicting disease severity and outcomes of patients hospitalised with COVID-19 in Bangladesh

Introduction

Evaluation of potential outcomes of COVID-19-affected pneumonia patients using computed tomography scans may not be conceivable in low-resource settings. Thus, we aimed to evaluate the performance of chest X-ray scoring in predicting the disease severity and outcomes of adults hospitalised with COVID-19.

Methods

This was a retrospective chart analysis consuming data from COVID-19-positive adults who had chest X-ray availability and were admitted to a temporary COVID unit, in Bangladesh from 23rd April 2020 to 15th November 2021. At least one clinical intensivist and one radiologist combinedly reviewed each admission chest X-ray for the different lung findings. Chest X-ray scoring varied from 0 to 8, depending on the area of lung involvement with 0 indicating no involvement and 8 indicating ⩾75% involvement of both lungs. The receiver operating characteristic curve was used to determine the optimum chest X-ray cut-off score for predicting the fatal outcomes.

Result

A total of 218 (82.9%) out of 263 COVID-19-affected adults were included in the study. The receiver operating characteristic curve demonstrated the optimum cut-off as ⩾3 and ⩾5 for disease severity and death, respectively. In multivariate logistic regression analysis, a chest X-ray score of ⩾3 was found to be independently associated with disease severity (aOR: 8.70; 95% CI: 3.82, 19.58, p < 0.001) and a score of ⩾5 with death (aOR: 16.53; 95% CI: 4.74, 57.60, p < 0.001) after adjusting age, sex, antibiotic usage before admission, history of fever, cough, diabetes mellitus, hypertension, total leukocytes count and C-reactive protein.

Conclusion

Using chest X-ray scoring derived cut-off at admission might help to identify the COVID-19-affected adults who are at risk of severe disease and mortality. This may help to initiate early and aggressive management of such patients, thereby reducing their fatal outcomes.

Fairness of artificial intelligence in healthcare: review and recommendations

In this review, we address the issue of fairness in the clinical integration of artificial intelligence (AI) in the medical field. As the clinical adoption of deep learning algorithms, a subfield of AI, progresses, concerns have arisen regarding the impact of AI biases and discrimination on patient health. This review aims to provide a comprehensive overview of concerns associated with AI fairness; discuss strategies to mitigate AI biases; and emphasize the need for cooperation among physicians, AI researchers, AI developers, policymakers, and patients to ensure equitable AI integration. First, we define and introduce the concept of fairness in AI applications in healthcare and radiology, emphasizing the benefits and challenges of incorporating AI into clinical practice. Next, we delve into concerns regarding fairness in healthcare, addressing the various causes of biases in AI and potential concerns such as misdiagnosis, unequal access to treatment, and ethical considerations. We then outline strategies for addressing fairness, such as the importance of diverse and representative data and algorithm audits. Additionally, we discuss ethical and legal considerations such as data privacy, responsibility, accountability, transparency, and explainability in AI. Finally, we present the Fairness of Artificial Intelligence Recommendations in healthcare (FAIR) statement to offer best practices. Through these efforts, we aim to provide a foundation for discussing the responsible and equitable implementation and deployment of AI in healthcare.

Trimethoprim-sulfamethoxazole-induced lung injury: a case report

Background

Trimethoprim-sulfamethoxazole (TMP-SMX) is a commonly used antibiotic. While cutaneous adverse drug reactions associated with TMP-SMX are commonly recognized, lung toxicity induced by TMP-SMX is an unusual condition, with scattered reports of hypersensitivity pneumonitis, acute fibrinous organizing pneumonia, interstitial lung disease and acute respiratory distress syndrome. Reports of TMP-SMX-associated drug-induced lung injury (DLI) are rare in the pediatric population and its pathogenesis is not well understood. Diagnosis of DLI remains a challenge, given the wide range of clinical presentations that overlap with other conditions and the lack of diagnostic tests. In this report, we describe a case of TMP-SMX-induced lung injury in an eight-year-old child.

Case Description

An eight-year-old girl presented in respiratory failure with acute symptoms of shortness of breath, fever, maculopapular rash and vomiting. This was associated with pneumonitis, pneumothorax, pneumomediastinum and subcutaneous emphysema on imaging. She had been on 25 days of TMP-SMX for treatment of Group D Salmonella bacteremia and osteomyelitis that was diagnosed prior to this current presentation. TMP-SMX was discontinued on admission due to concerns of possible drug reaction. Extensive infective, autoimmune and immunologic workup did not reveal the cause of the respiratory failure. Considering the absence of an alternative explanation for her clinical presentation and similarities in clinical courses to other reported cases, she was eventually diagnosed with TMP-SMX-associated DLI. She received a course of corticosteroids with subsequent clinical improvement and was weaned off home oxygen therapy a few months after her discharge from the hospital.

Conclusions

Diagnosis of DLI can be challenging. The early identification of DLI and discontinuation of culprit drug is essential in its management. Further understanding of the underlying pathophysiology and risk factors for TMP-SMX-associated DLI is required.

New trend in artificial intelligence-based assistive technology for thoracic imaging

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

Usefulness and performance evaluation of serum KL-6 and SP-A assays in healthy individuals and patients with interstitial lung disease

BACKGROUND

Interstitial lung abnormalities (ILAs) are associated with the risk of progression to interstitial lung diseases (ILDs). Krebs von den Lungen 6 (KL-6) and surfactant protein (SP)-A have been used as biomarkers of ILDs. In this study, we evaluated the levels of these biomarkers and identified their clinical correlations in healthy individuals to assess their usefulness in the diagnosis of ILAs.

METHODS

The patient samples were categorized into three groups: healthy, disease, and ILD groups. We used the automated immunoassay HISCL KL-6 and SP-A assay kits. The analytical performance evaluation involved precision, linearity, comparison, establishment of reference intervals, and determination of the cutoff points. We also analyzed the correlations between presence of abnormalities on chest radiography and computed tomography (CT) or pulmonary function test (PFT) and serum levels in the healthy group.

RESULTS

KL-6 and SP-A assays showed good analytical performance. The KL-6 and SP-A cutoff values were 304 U/mL and 43.5 ng/mL between the ILD and healthy groups, respectively, which were lower than the values recommended by the manufacturer. In the clinical correlations with radiological findings, SP-A values in subjects with lung abnormalities on CT scans were significantly higher than those in normal scans. There was no significant difference in KL-6 and SP-A levels among PFT patterns; however, both serum levels in the mixed pattern showed higher values than those in the other patterns.

CONCLUSIONS

The results revealed a positive association between increased serum levels of SP-A and KL-6 and clinical characteristics as incidental findings on chest imaging and reduced lung function.

A Novel Approach for Prediction of Lung Disease Using Chest X-ray Images Based on DenseNet and MobileNet

Covid19 corona virus has caused widespread disruption across the world, in terms of the health, economy, and society problems. X-ray images of the chest can be helpful in making an accurate diagnosis because the corona virus typically first manifests its symptoms in patients' lungs. In this study, a classification method based on deep learning is proposed as a means of identifying lung disease from chest X-ray images. In the proposed study, the detection of covid19 corona virus disease from chest X-ray images was made with MobileNet and Densenet models, which are deep learning methods. Several different use cases can be built with the help of MobileNet model and case modelling approach is utilized to achieve 96% accuracy and an Area Under Curve (AUC) value of 94%. According to the result, the proposed method may be able to more accurately identify the signs of an impurity from dataset of chest X-ray images. This research also compares various performance parameters such as precision, recall and F1-Score.

Comparison of Computed Tomography Scoring Systems in Patients with COVID-19 and Hematological Malignancies

BACKGROUND

Numerous computed tomography (CT) scales have been proposed to assess lung involvement in COVID-19 pneumonia as well as correlate radiological findings with patient outcomes.

OBJECTIVE

Comparison of different CT scoring systems in terms of time consumption and diagnostic performance in patients with hematological malignancies and COVID-19 infection.

MATERIALS AND METHODS

Retrospective analysis included hematological patients with COVID-19 and CT performed within 10 days of diagnosis of infection. CT scans were analyzed in three different semi-quantitative scoring systems, Chest CT Severity Score (CT-SS), Chest CT Score(CT-S), amd Total Severity Score (TSS), as well as qualitative modified Total Severity Score (m-TSS). Time consumption and diagnostic performance were analyzed.

RESULTS

Fifty hematological patients were included. Based on the ICC values, excellent inter-observer reliability was found among the three semi-quantitative methods with ICC > 0.9 (p < 0.001). The inter-observer concordance was at the level of perfect agreement (kappa value = 1) for the mTSS method (p < 0.001). The three-receiver operating characteristic (ROC) curves revealed excellent and very good diagnostic accuracy for the three quantitative scoring systems. The AUC values were excellent (0.902), very good (0.899), and very good (0.881) in the CT-SS, CT-S and TSS scoring systems, respectively. Sensitivity showed high levels at 72.7%, 75%, and 65.9%, respectively, and specificity was recorded at 98.2%, 100%, 94.6% for the CT-SS, CT-S, and TSS scoring systems, respectively. Time consumption was the same for Chest CT Severity Score and TSS and was longer for Chest CT Score (p < 0.001).

CONCLUSIONS

Chest CT score and chest CT severity score have very high sensitivity and specificity in terms of diagnostic accuracy. The highest AUC values and the shortest median time of analysis in chest CT severity score indicate this method as preferred for semi-quantitative assessment of chest CT in hematological patients with COVID-19.

EffViT-COVID: A dual-path network for COVID-19 percentage estimation

The first case of novel Coronavirus (COVID-19) was reported in December 2019 in Wuhan City, China and led to an international outbreak. This virus causes serious respiratory illness and affects several other organs of the body differently for different patient. Worldwide, several waves of this infection have been reported, and researchers/doctors are working hard to develop novel solutions for the COVID diagnosis. Imaging and vision-based techniques are widely explored for the prediction of COVID-19; however, COVID infection percentage estimation is under explored. In this work, we propose a novel framework for the estimation of COVID-19 infection percentage based on deep learning techniques. The proposed network utilizes the features from vision transformers and CNN (Convolutional Neural Networks), specifically EfficientNet-B7. The features of both are fused together for preparing an information-rich feature vector that contributes to a more precise estimation of infection percentage. We evaluate our model on the Per-COVID-19 dataset (Bougourzi et al., 2021b) which comprises labeled CT data of COVID-19 patients. For the evaluation of the model on this dataset, we employ the most widely-used slice-level metrics, i.e., Pearson correlation coefficient (PC), Mean absolute error (MAE), and Root mean square error (RMSE). The network outperforms the other state-of-the-art methods and achieves 0 . 9886 ± 0 . 009 , 1 . 23 ± 0 . 378 , and 3 . 12 ± 1 . 56 , PC, MAE, and RMSE, respectively, using a 5-fold cross-validation technique. In addition, the overall average difference in the actual and predicted infection percentage is observed to be < 2 % . In conclusion, the detailed experimental results reveal the robustness and efficiency of the proposed network.

Imaging of metabolic and overload disorders in tissues and organs

Metabolic and overload disorders are a heterogeneous group of relatively uncommon but important diseases. While imaging plays a key role in the early detection and accurate diagnosis in specific organs with a pivotal role in several metabolic pathways, most of these diseases affect different tissues as part of a systemic syndromes. Moreover, since the symptoms are often vague and phenotypes similar, imaging alterations can present as incidental findings, which must be recognized and interpreted in the light of further biochemical and histological investigations. Among imaging modalities, MRI allows, thanks to its multiparametric properties, to obtain numerous information on tissue composition, but many metabolic and accumulation alterations require a multimodal evaluation, possibly using advanced imaging techniques and sequences, not only for the detection but also for accurate characterization and quantification. The purpose of this review is to describe the different alterations resulting from metabolic and overload pathologies in organs and tissues throughout the body, with particular reference to imaging findings.

Diagnosis of Legionnaires' Disease Assisted by Next-Generation Sequencing in a Patient with COVID-19

Coinfection in COVID-19 patients is associated with worsening outcome. Among patients with COVID-19, Legionella pneumophila, a common cause of pneumonia, has been reported as a co-occurring respiratory infection. A nonspecific clinical presentation, however, makes an early diagnosis difficult. Bronchoalveolar lavage fluid was collected from a patient suffering from COVID-19 and presenting with pneumonia and sent for metagenomic analysis. Differential abundance analysis was carried out by comparing each taxon reads per million between the bronchoalveolar lavage fluid sample and the negative control. Two replicates of metagenomic sequencing were conducted on bronchoalveolar lavage fluid samples. Within each replicated sequencing, one negative control was sequenced for comparison of taxon abundance in the BALF sample. In both replicates, Legionella pneumophila was the only taxon with significantly higher abundance when compared with the negative control. PCR of the bronchoalveolar further confirmed the presence of L. pneumophila. Several studies have estimated that the incidence of Legionnaires' disease co-infection in patients with COVID-19 infection is approximately 0% to 1.5%. There are some common characteristics of COVID-19 and co-infection with Legionnaires' disease, making it difficult to diagnose bacterial infection early. The diagnosis of these cases is important due to the different treatments used. Current diagnostic tests for Legionnaires' disease include conventional culture, urinary antigen for L. pneumophila serogroup 1, polymerase chain reaction, direct fluorescent antibody stain, and paired serology. The current study demonstrated that metagenomics is a promising approach that facilitated the diagnosis of Legionnaires' disease.

Quality of Thorax CT Scan Images among Covid-19 Cases using Variations of Filter

A typical image of the Thorax CT Scan as a sign of the early stages and development of Covid-19 is the finding of Ground Glass Opacities (GGO). GGO is an insignificant increase in the density of the lungs without occlusion of blood vessels and bronchi. In mild cases, GGO tends to be difficult to identify and requires high-resolution CT scanning. In this study, we intend to improve the resolution of the Thorax CT Scan image through filter settings, to analyze the difference in the variations of filters B50s, B70s, and B90s towards the quality of the CT Scan image and obtain the optimal use of filter in the Thorax CT Scan examination among Covid-19 cases. This was a quantitative analytical study conducted at one of the Regional General Hospital in Jakarta on March-April 2022. The samples were secondary data derived from 10 patients by using MSCT Siemens Somatom Perspective 128 slices. Data were collected through observation and experiment. The images collected were further analyzed using Image j software to find values of Signal to Noise Ratio (SNR) and Contrast to Noise Ratio (CNR). Furthermore, the values were compared by assessing the anatomical image information through various filters. The results of this study indicated that there were differences in the SNR and CNR values of the three filters. The higher resolution of the filter used, the more capable it was to sharper and more detailed the image but the noise level was also higher. Thorax CT Scan examination should be carried out using the B70s very sharp filter that was able to produce images with the optimal information and fairly low noise level. A very thin GGO image in the early stage of the manifestation of Covid-19 could be identified in the Thorax CT Scan examinations for diagnosis of Covid-19 case.

GROUND GLASS OPACITIES: SIGN OF CAUTION IN TYPICAL INTERSTITIAL PNEUMONIA

Typical interstitial pneumonia (IP) is mainly the fibrotic form of interstitial lung disease. In some cases with typical IP, a certain amount of ground-glass opacity (GGO) can be detected on high-resolution computed tomography, however, some important issues, such as the co-existence of GGO and typical IP, still require further investigation by biopsy. After the diagnosis of typical IP, anti-fibrosis treatment is usually considered. Here, we hypothesized that GGO in typical IP could be a manifestation of an acute inflammatory attack requiring immunosuppressive therapy or an indicator of ongoing contact with trigger factors that initiate pathological reactions in typical IP.

Vascular Implications of COVID-19: Role of Radiological Imaging, Artificial Intelligence, and Tissue Characterization: A Special Report

The SARS-CoV-2 virus has caused a pandemic, infecting nearly 80 million people worldwide, with mortality exceeding six million. The average survival span is just 14 days from the time the symptoms become aggressive. The present study delineates the deep-driven vascular damage in the pulmonary, renal, coronary, and carotid vessels due to SARS-CoV-2. This special report addresses an important gap in the literature in understanding (i) the pathophysiology of vascular damage and the role of medical imaging in the visualization of the damage caused by SARS-CoV-2, and (ii) further understanding the severity of COVID-19 using artificial intelligence (AI)-based tissue characterization (TC). PRISMA was used to select 296 studies for AI-based TC. Radiological imaging techniques such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound were selected for imaging of the vasculature infected by COVID-19. Four kinds of hypotheses are presented for showing the vascular damage in radiological images due to COVID-19. Three kinds of AI models, namely, machine learning, deep learning, and transfer learning, are used for TC. Further, the study presents recommendations for improving AI-based architectures for vascular studies. We conclude that the process of vascular damage due to COVID-19 has similarities across vessel types, even though it results in multi-organ dysfunction. Although the mortality rate is ~2% of those infected, the long-term effect of COVID-19 needs monitoring to avoid deaths. AI seems to be penetrating the health care industry at warp speed, and we expect to see an emerging role in patient care, reduce the mortality and morbidity rate.

The comparison of chest X-ray and CT visibility according to size and lesion types in the patients with COVID-19

Introduction: Chest X-ray (CXR) is one of the routinely used radiological examinations in COVID-19. However, the lesion detectability level of CXR is low. To date, to the best of our knowledge, the visualization quality of X-ray in COVID-19 has not been specifically evaluated in different lesions. Our study aims to determine the visualization quality of CXR in COVID-19 patients according to elementary lesions. Material and Method: 52 COVID-positive patients (26 Males and 26 Females); 69,6346±15,14250 (32-89) years [mean±SD age (range)] were included in the study. 98 different elementary lesions of lung detected on CT were evaluated in six different groups (consolidation, indeterminate ground-glass opacity (IGGO), dense GGO (DGGO), reversed halo, parenchymal band and curvilinear band). Lesions were compared with CXR taken on the same day. The detectability rates of the lesions on CXR were evaluated. Results: The mean sizes of CXR negative and CXR positive lesions for every group (consolidations, IGGO, DGGO, reversed halo sign, parenchymal band, curvilinear band) were respectively 1.36 cm -5.75 cm, 3.44 cm -5.50 cm, 2.25 cm -5.06 cm, 2.5cm -4.09 cm, N/A -3.14 cm and 1 cm -4.5 cm. According to Mann-Whitney U analysis, p values were found as (respectively in consolidations, IGGO, DGGO, reversed halo sign, and curvilinear band) 0.0001p, 0.145, 0.0001 p, 0.143 and 0.286. Given consolidation and DGGO groups, there was a statistically significant difference between non-visualized and visualized groups. According to ROC analysis, cut-off values were respectively 3 cm and 3.5 cm for consolidation and DGGO. Conclusion: Our study showed that consolidations smaller than 3 cm and DGGO smaller than 3.5 cm are difficult to visualize with CXR. Although there is no definite cut-off value in other elementary lesions, the visualization ratio of parenchymal bands and curvilinear bants on chest X-rays is quite high. IGGOs may not be detected even at higher dimensions. Reversed halos less than 3 cm can rarely be detected on CXR.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson’s Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson’s disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

COVLIAS 1.0Lesion vs. MedSeg: An Artificial Intelligence Framework for Automated Lesion Segmentation in COVID-19 Lung Computed Tomography Scans

Background: COVID-19 is a disease with multiple variants, and is quickly spreading throughout the world. It is crucial to identify patients who are suspected of having COVID-19 early, because the vaccine is not readily available in certain parts of the world. Methodology: Lung computed tomography (CT) imaging can be used to diagnose COVID-19 as an alternative to the RT-PCR test in some cases. The occurrence of ground-glass opacities in the lung region is a characteristic of COVID-19 in chest CT scans, and these are daunting to locate and segment manually. The proposed study consists of a combination of solo deep learning (DL) and hybrid DL (HDL) models to tackle the lesion location and segmentation more quickly. One DL and four HDL models—namely, PSPNet, VGG-SegNet, ResNet-SegNet, VGG-UNet, and ResNet-UNet—were trained by an expert radiologist. The training scheme adopted a fivefold cross-validation strategy on a cohort of 3000 images selected from a set of 40 COVID-19-positive individuals. Results: The proposed variability study uses tracings from two trained radiologists as part of the validation. Five artificial intelligence (AI) models were benchmarked against MedSeg. The best AI model, ResNet-UNet, was superior to MedSeg by 9% and 15% for Dice and Jaccard, respectively, when compared against MD 1, and by 4% and 8%, respectively, when compared against MD 2. Statistical tests—namely, the Mann−Whitney test, paired t-test, and Wilcoxon test—demonstrated its stability and reliability, with p < 0.0001. The online system for each slice was <1 s. Conclusions: The AI models reliably located and segmented COVID-19 lesions in CT scans. The COVLIAS 1.0Lesion lesion locator passed the intervariability test.

Protocolo diagnóstico de los infiltrados pulmonares febriles durante la pandemia de la COVID-19

La radiografía de tórax y la tomografía computarizada (TC) son pilares importantes para el diagnóstico de la afectación pulmonar en la COVID-19, con una imagen radiológica caracterizada típicamente por opacidades en vidrio deslustrado (OVD) periféricas, bilaterales y localizadas principalmente en lóbulos inferiores. La sensibilidad y la especificidad limitada de estas técnicas de imagen y las posibles presentaciones morfológicas o topográficas atípicas obligan a descartar siempre otras patologías tanto infecciosas como no infecciosas, para lo que es fundamental considerar los datos clínicos y analíticos del paciente y las circunstancias epidemiológicas.

Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model

The coronavirus (COVID-19) pandemic has had a terrible impact on human lives globally, with far-reaching consequences for the health and well-being of many people around the world. Statistically, 305.9 million people worldwide tested positive for COVID-19, and 5.48 million people died due to COVID-19 up to 10 January 2022. CT scans can be used as an alternative to time-consuming RT-PCR testing for COVID-19. This research work proposes a segmentation approach to identifying ground glass opacity or ROI in CT images developed by coronavirus, with a modified structure of the Unet model having been used to classify the region of interest at the pixel level. The problem with segmentation is that the GGO often appears indistinguishable from a healthy lung in the initial stages of COVID-19, and so, to cope with this, the increased set of weights in contracting and expanding the Unet path and an improved convolutional module is added in order to establish the connection between the encoder and decoder pipeline. This has a major capacity to segment the GGO in the case of COVID-19, with the proposed model being referred to as “convUnet.” The experiment was performed on the Medseg1 dataset, and the addition of a set of weights at each layer of the model and modification in the connected module in Unet led to an improvement in overall segmentation results. The quantitative results obtained using accuracy, recall, precision, dice-coefficient, F1score, and IOU were 93.29%, 93.01%, 93.67%, 92.46%, 93.34%, 86.96%, respectively, which is better than that obtained using Unet and other state-of-the-art models. Therefore, this segmentation approach proved to be more accurate, fast, and reliable in helping doctors to diagnose COVID-19 quickly and efficiently.

National Research Institute of Tuberculosis and Lung Disease (NRITLD) Protocol for the Treatment of Patients with COVID-19

: More than a year after the onset of the coronavirus disease pandemic in 2019, the disease remains a major global health issue. During this time, health organizations worldwide have tried to provide integrated treatment guidelines to control coronavirus disease 2019 (COVID-19) at different levels. However, due to the novel nature of the disease and the emergence of new variants, medical teams' updating medical information and drug prescribing guidelines should be given special attention. This version is an updated instruction of the National Research Institute of Tuberculosis and Lung Disease (NRITLD) in collaboration with a group of specialists from Masih Daneshvari Hospital in Tehran, Iran, which is provided to update the information of caring clinicians for the treatment and care of COVID-19 hospitalized patients.

A central role for amyloid fibrin microclots in long COVID/PASC: origins and therapeutic implications

Post-acute sequelae of COVID (PASC), usually referred to as 'Long COVID' (a phenotype of COVID-19), is a relatively frequent consequence of SARS-CoV-2 infection, in which symptoms such as breathlessness, fatigue, 'brain fog', tissue damage, inflammation, and coagulopathies (dysfunctions of the blood coagulation system) persist long after the initial infection. It bears similarities to other post-viral syndromes, and to myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). Many regulatory health bodies still do not recognize this syndrome as a separate disease entity, and refer to it under the broad terminology of 'COVID', although its demographics are quite different from those of acute COVID-19. A few years ago, we discovered that fibrinogen in blood can clot into an anomalous 'amyloid' form of fibrin that (like other β-rich amyloids and prions) is relatively resistant to proteolysis (fibrinolysis). The result, as is strongly manifested in platelet-poor plasma (PPP) of individuals with Long COVID, is extensive fibrin amyloid microclots that can persist, can entrap other proteins, and that may lead to the production of various autoantibodies. These microclots are more-or-less easily measured in PPP with the stain thioflavin T and a simple fluorescence microscope. Although the symptoms of Long COVID are multifarious, we here argue that the ability of these fibrin amyloid microclots (fibrinaloids) to block up capillaries, and thus to limit the passage of red blood cells and hence O2 exchange, can actually underpin the majority of these symptoms. Consistent with this, in a preliminary report, it has been shown that suitable and closely monitored 'triple' anticoagulant therapy that leads to the removal of the microclots also removes the other symptoms. Fibrin amyloid microclots represent a novel and potentially important target for both the understanding and treatment of Long COVID and related disorders.

Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images

BACKGROUND

In the field of biomedical imaging, radiomics is a promising approach that aims to provide quantitative features from images. It is highly dependent on accurate identification and delineation of the volume of interest to avoid mistakes in the implementation of the texture-based prediction model. In this context, we present a customized deep learning approach aimed at addressing the real-time, and fully automated identification and segmentation of COVID-19 infected regions in computed tomography images.

METHODS

In a previous study, we adopted ENET, originally used for image segmentation tasks in self-driving cars, for whole parenchyma segmentation in patients with idiopathic pulmonary fibrosis which has several similarities to COVID-19 disease. To automatically identify and segment COVID-19 infected areas, a customized ENET, namely C-ENET, was implemented and its performance compared to the original ENET and some state-of-the-art deep learning architectures.

RESULTS

The experimental results demonstrate the effectiveness of our approach. Considering the performance obtained in terms of similarity of the result of the segmentation to the gold standard (dice similarity coefficient ~75%), our proposed methodology can be used for the identification and delineation of COVID-19 infected areas without any supervision of a radiologist, in order to obtain a volume of interest independent from the user.

CONCLUSIONS

We demonstrated that the proposed customized deep learning model can be applied to rapidly identify, and segment COVID-19 infected regions to subsequently extract useful information for assessing disease severity through radiomics analyses.

Sodium Toxicity in the Nutritional Epidemiology and Nutritional Immunology of COVID-19

Dietary factors in the etiology of COVID-19 are understudied. High dietary sodium intake leading to sodium toxicity is associated with comorbid conditions of COVID-19 such as hypertension, kidney disease, stroke, pneumonia, obesity, diabetes, hepatic disease, cardiac arrhythmias, thrombosis, migraine, tinnitus, Bell's palsy, multiple sclerosis, systemic sclerosis, and polycystic ovary syndrome. This article synthesizes evidence from epidemiology, pathophysiology, immunology, and virology literature linking sodium toxicological mechanisms to COVID-19 and SARS-CoV-2 infection. Sodium toxicity is a modifiable disease determinant that impairs the mucociliary clearance of virion aggregates in nasal sinuses of the mucosal immune system, which may lead to SARS-CoV-2 infection and viral sepsis. In addition, sodium toxicity causes pulmonary edema associated with severe acute respiratory syndrome, as well as inflammatory immune responses and other symptoms of COVID-19 such as fever and nasal sinus congestion. Consequently, sodium toxicity potentially mediates the association of COVID-19 pathophysiology with SARS-CoV-2 infection. Sodium dietary intake also increases in the winter, when sodium losses through sweating are reduced, correlating with influenza-like illness outbreaks. Increased SARS-CoV-2 infections in lower socioeconomic classes and among people in government institutions are linked to the consumption of foods highly processed with sodium. Interventions to reduce COVID-19 morbidity and mortality through reduced-sodium diets should be explored further.