COVID-19 Lung Research Articles

COVID-19 Lung Ultrasound Scores and Lessons from the Pandemic: A Narrative Review.

The WHO recently declared that COVID-19 no longer constitutes a public health emergency of international concern; however, lessons learned through the pandemic should not be left behind. Lung ultrasound was largely utilized as a diagnostic tool thanks to its feasibility, easy application, and the possibility to reduce the source of infection for health personnel. Lung ultrasound scores consist of grading systems used to guide diagnosis and medical decisions, owning a good prognostic value. In the emergency context of the pandemic, several lung ultrasound scores emerged either as new scores or as modifications of pre-existing ones. Our aim is to clarify the key aspects of lung ultrasound and lung ultrasound scores to standardize their clinical use in a non-pandemic context. The authors searched on PubMed for articles related to "COVID-19", "ultrasound", and "Score" until 5 May 2023; other keywords were "thoracic", "lung", "echography", and "diaphragm". A narrative summary of the results was made. Lung ultrasound scores are demonstrated to be an important tool for triage, prediction of severity, and aid in medical decisions. Ultimately, the existence of numerous scores leads to a lack of clarity, confusion, and an absence of standardization.

Fighting against COVID‐19: Innovations and applications

Fighting against <scp>COVID</scp>‐19: Innovations and applications

Comparison of artificial intelligence versus real-time physician assessment of pulmonary edema with lung ultrasound

BackgroundLung ultrasound can evaluate for pulmonary edema, but data suggest moderate inter-rater reliability among users. Artificial intelligence (AI) has been proposed as a model to increase the accuracy of B line interpretation. Early data suggest a benefit among more novice users, but data are limited among average residency-trained physicians. The objective of this study was to compare the accuracy of AI versus real-time physician assessment for B lines. MethodsThis was a prospective, observational study of adult Emergency Department patients presenting with suspected pulmonary edema. We excluded patients with active COVID-19 or interstitial lung disease. A physician performed thoracic ultrasound using the 12-zone technique. The physician recorded a video clip in each zone and provided an interpretation of positive (≥3 B lines or a wide, dense B line) or negative (<3 B lines and the absence of a wide, dense B line) for pulmonary edema based upon the real-time assessment. A research assistant then utilized the AI program to analyze the same saved clip to determine if it was positive versus negative for pulmonary edema. The physician sonographer was blinded to this assessment. The video clips were then reviewed independently by two expert physician sonographers (ultrasound leaders with >10,000 prior ultrasound image reviews) who were blinded to the AI and initial determinations. The experts reviewed all discordant values and reached consensus on whether the field (i.e., the area of lung between two adjacent ribs) was positive or negative using the same criteria as defined above, which served as the gold standard. Results71 patients were included in the study (56.3% female; mean BMI: 33.4 [95% CI 30.6–36.2]), with 88.3% (752/852) of lung fields being of adequate quality for assessment. Overall, 36.1% of lung fields were positive for pulmonary edema. The physician was 96.7% (95% CI 93.8%–98.5%) sensitive and 79.1% (95% CI 75.1%–82.6%) specific. The AI software was 95.6% (95% CI 92.4%–97.7%) sensitive and 64.1% (95% CI 59.8%–68.5%) specific. ConclusionBoth the physician and AI software were highly sensitive, though the physician was more specific. Future research should identify which factors are associated with increased diagnostic accuracy.

Marked elevations in lung and plasma ceramide in COVID-19 linked to microvascular injury.

The pathogenesis of the marked pulmonary microvasculature injury, a distinguishing feature of COVID-19 acute respiratory distress syndrome (COVID-ARDS), remains unclear. Implicated in the pathophysiology of diverse diseases characterized by endothelial damage, including ARDS and ischemic cardiovascular disease, ceramide and in particular palmitoyl ceramide (C16:0-ceramide) may be involved in the microvascular injury in COVID-19. Using deidentified plasma and lung samples from COVID-19 patients, ceramide profiling by mass spectrometry was performed. Compared with healthy individuals, a specific 3-fold C16:0-ceramide elevation in COVID-19 patient plasma was identified. Compared with age-matched controls, autopsied lungs of individuals succumbing to COVID-ARDS displayed a massive 9-fold C16:0-ceramide elevation and exhibited a previously unrecognized microvascular ceramide-staining pattern and markedly enhanced apoptosis. In COVID-19 plasma and lungs, the C16-ceramide/C24-ceramide ratios were increased and reversed, respectively, consistent with increased risk of vascular injury. Indeed, exposure of primary human lung microvascular endothelial cell monolayers to C16:0-ceramide-rich plasma lipid extracts from COVID-19, but not healthy, individuals led to a significant decrease in endothelial barrier function. This effect was phenocopied by spiking healthy plasma lipid extracts with synthetic C16:0-ceramide and was inhibited by treatment with ceramide-neutralizing monoclonal antibody or single-chain variable fragment. These results indicate that C16:0-ceramide may be implicated in the vascular injury associated with COVID-19.

An Improved COVID-19 Lung X-Ray Image Classification Algorithm Based on ConvNeXt Network

Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.

MCSC-Net: COVID-19 detection using deep-Q-neural network classification with RFNN-based hybrid whale optimization.

COVID-19 is the most dangerous virus, and its accurate diagnosis saves lives and slows its spread. However, COVID-19 diagnosis takes time and requires trained professionals. Therefore, developing a deep learning (DL) model on low-radiated imaging modalities like chest X-rays (CXRs) is needed. The existing DL models failed to diagnose COVID-19 and other lung diseases accurately. This study implements a multi-class CXR segmentation and classification network (MCSC-Net) to detect COVID-19 using CXR images. Initially, a hybrid median bilateral filter (HMBF) is applied to CXR images to reduce image noise and enhance the COVID-19 infected regions. Then, a skip connection-based residual network-50 (SC-ResNet50) is used to segment (localize) COVID-19 regions. The features from CXRs are further extracted using a robust feature neural network (RFNN). Since the initial features contain joint COVID-19, normal, pneumonia bacterial, and viral properties, the conventional methods fail to separate the class of each disease-based feature. To extract the distinct features of each class, RFNN includes a disease-specific feature separate attention mechanism (DSFSAM). Furthermore, the hunting nature of the Hybrid whale optimization algorithm (HWOA) is used to select the best features in each class. Finally, the deep-Q-neural network (DQNN) classifies CXRs into multiple disease classes. The proposed MCSC-Net shows the enhanced accuracy of 99.09% for 2-class, 99.16% for 3-class, and 99.25% for 4-class classification of CXR images compared to other state-of-art approaches. The proposed MCSC-Net enables to conduct multi-class segmentation and classification tasks applying to CXR images with high accuracy. Thus, together with gold-standard clinical and laboratory tests, this new method is promising to be used in future clinical practice to evaluate patients.

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning.

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

Amniotic fluid derived extracellular vesicles as novel anti-inflammatory therapeutics against SARS-CoV-2 infection

Abstract The ongoing Covid-19 pandemic caused by SARS-CoV-2 is associated with acute respiratory distress syndrome (ARDS) and fatal pneumonia. Excessive inflammation caused by SARS-CoV-2 is the key driver of ARDS and lethal disease. Despite strong evidence for the role of virus induced inflammation in severe COVID19, no effective anti-inflammatory drug is available to control robust inflammation. Although corticosteroids are in clinical use to suppress excessive inflammation, global immunosuppressive effects of these drugs have limited their clinical success. Moreover, cytotoxicity caused by several chemically derived drugs is a cause of concern. Therefore, there is an urgent need to identify biologically derived immunomodulators that suppress inflammation without affecting antiviral immunity. In this study, we evaluated human amniotic fluid derived extracellular vesicles (hAF-EVs) as a potential safe biologic for immunomodulation during Covid-19. Our results showed that hAF-EVs significantly reduced inflammatory cytokine production in TLR2/4/7 and CoV structural protein stimulated mouse macrophages, in-vitro. Importantly, we also found that intraperitoneal administration of hAF-EVs in mice infected with a mouse-adapted SARS-CoV-2 reduced morbidity and mortality. A detailed examination of infected lungs showed that the increased protection in hAF-EV-treated mice was associated with reduced myeloid cell accumulation and inflammatory cytokine production. Collectively, we identify a novel biologic that has potential to suppress excessive inflammation and promote survival following SARS-CoV-2 infection, highlighting the translational potential of hAF-EVs against Covid-19 and other viral lung infections. This study was supported in part by institutional research funds from Oklahoma State University—Stillwater and NIGMS 5P20GM103648-10.

Multi-omic spatial profiling in COVID-19 lung revels temporal evolution of the disease and novel collagen VI biomarker for outcome

Abstract Whilst the peripheral immune response to COVID-19 infection is well characterised, less is known about the tissue response in the lungs of affected patients. We conducted a multi-omic investigation in post-mortem lung tissue from fatal COVID-19 infection comprising bulk Quantseq RNA sequencing, spatial transcriptomic profiling on the Nanostring GeoMX, multiplex immunohistochemistry on the Lunaphore COMET and in-situ transcriptomcics with RNAscope. We found the SARS-CoV-2 virus was progressively cleared in more temporally advanced disease. Furthermore, collagen VI was found to be transcriptionally up-regulated by bulk sequencing and within the interstitium on spatial transcriptomics. These findings were supported by multiplex immunohistochemistry at a proteomic level which showed fibrillar deposition of collagen VI in the interstitum. To validate these findings clinically, we looked at blood markers for collagen VI synthesis and degradation by ELISA in a cohort of severe and mildly infected COVID-19 patients. Blood markers of collagen VI synthesis (PRO-C6) was significantly predictive for mortality in hospitalised (p = 0.0065) and intensive care (p = 0.028) COVID-19 patients. Overall, blood PRO-C6 levels, based on increase interstitial lung deposition, could help identify high-risk of patients enabling better treatment stratification. The study also demonstrates the power of post-mortem investigation and spatial profiling in elucidating clinically relevant insights into complex disease phenomena.

An Effective COVID-19 CT Image Denoising Method Based on a Deep Convolutional Neural Network

Background: Faced with the global threat posed by SARS-CoV-2 (COVID-19), lowdose computed tomography (LDCT), as the primary diagnostic tool, is often accompanied by high levels of noise. This can easily interfere with the radiologist's assessment. Convolutional neural networks (CNN), as a method of deep learning, have been shown to have excellent effects in image denoising. Objective: The objective of the study was to use modified convolutional neural network algorithm to train the denoising model. The purpose was to make the model extract the highlighted features of the lesion region better and ensure its effectiveness in removing noise from COVID-19 lung CT images, preserving more important detail information of the images and reducing the adverse effects of denoising. Methods: We propose a CNN-based deformable convolutional denoising neural network (DCDNet). By combining deformable convolution methods with residual learning on the basis of CNN structure, more image detail features are retained in CT image denoising. Result: According to the noise reduction evaluation index of PSNR, SSIM and RMSE, DCDNet shows excellent denoising performance for COVID-19 CT images. From the visual effect of denoising, DCDNet can effectively remove image noise and preserve more detailed features of lung lesions. Conclusion: The experimental results indicate that the DCDNet-trained model is more suitable for image denoising of COVID-19 than traditional image denoising algorithms under the same training set.

Abstract 628: Molecular Mechanisms of Covid-19 in the Lungs and Heart: Insights from Spatial Transcriptomics

Introduction: Spatial transcriptomics has become a powerful tool for interrogating a disease-specific transcriptome within the context of tissue architecture. In this study, we used spatial transcriptomics to investigate the molecular mechanisms underlying COVID-19 in the lungs and heart. Methods: We performed sequencing-based spatial transcriptomics (ST), using 10X Genomics’ Visium, on 6 paired fatal COVID-19 lung and heart tissue samples and 2 control samples per organ. With the gene by spot matrix, we performed dimensional reduction, clustering (Louvain), differential expression (Wilcoxon Rank sum test), and pathway analysis (GSEA). spacexr was used to estimate the cell type composition of ST spots. Results: By histology and ST, COVID-19 tissue was defined by a loss in parenchymal cells and increased inflammation ( fig. 1E ). In both the heart and lung, we found a cluster of ST spots specific to fatal COVID-19 ( fig. 1A, B ; P&lt;0.001). Between the two organs, these clusters shared genes and pathways relating to tissue remodeling, B cell action, and complement pathway activation ( fig. 1C, D ). Response to wounding and blood vessel endothelial cell migration pathways were distinct to the heart cluster, also explaining the increased capillary cell weight in the COVID-19 heart compared to the control ( fig. 1D, E ; P=0.0167). Conclusion: Our results suggest that there is a shared spatial niche between the heart and lungs in COVID-19 infection and highlight the importance of studying multiple organs in understanding the disease. These findings provide new insights into the molecular basis of COVID-19 and have the potential to inform the development of novel therapies for this disease. Figure 1 (A) UMAP colored by (left) clusters and (right) disease. (B) Cluster proportions between COVID-19 and control tissue (C) Scatter plot of shared differentially expressed genes. (D) GSEA pathway score. (E) Spatial mapping of clusters and cell-type deconvolution.

AUTOMATED SEVERITY SCORING OF COVID-19 CT SEQUENCES USING SPACE-TIME TRANSFORMERS

Automatic diagnosis of Covid-19 lung complications from Computerized Tomography (CT) scans is an increasingly important research topic. In this rapidly developing area of Covid detection from medical image sequences, it is noted that most prior literature has focused on binary classification to detect diseased versus healthy cases from single X-ray or CT image. In this paper, we advance a step further by presenting a comprehensive framework for automated classification of the severity of lung infection (mild, moderate and severe) from CT sequences of confirmed Covid cases. We consider the sequence information for automation because in practice, the medical experts look at the CT sequence to score the severity of infection. We have collected a new lung CT sequence dataset at various stages of Covid infection from Indian patients. This dataset has been scored in terms of the severity of each lung lobe by experts in the field. We present a novel application of space-time transformers for CT sequences and achieve 93.3% accuracy for sequence level and 99% accuracy for patient-level, for multi- class classification of severity classes.

SARS-CoV-2 infection dysregulates the expression of clinically relevant drug metabolizing enzymes in Vero E6 cells and membrane transporters in human lung tissues.

SARS-CoV-2-mediated interactions with drug metabolizing enzymes and membrane transporters (DMETs) in different tissues, especially lung, the main affected organ may limit the clinical efficacy and safety profile of promising COVID-19 drugs. Herein, we investigated whether SARS-CoV-2 infection could dysregulate the expression of 25 clinically relevant DMETs in Vero E6 cells and postmortem lung tissues from COVID-19 patients. Also, we assessed the role of 2 inflammatory and 4 regulatory proteins in modulating the dysregulation of DMETs in human lung tissues. We showed for the first time that SARS-CoV-2 infection dysregulates CYP3A4 and UGT1A1 at the mRNA level, as well as P-gp and MRP1 at the protein level, in Vero E6 cells and postmortem human lung tissues, respectively. We observed that at the cellular level, DMETs could potentially be dysregulated by SARS-CoV-2-associated inflammatory response and lung injury. We uncovered the pulmonary cellular localization of CYP1A2, CYP2C8, CYP2C9, and CYP2D6, as well as ENT1 and ENT2 in human lung tissues, and observed that the presence of inflammatory cells is the major driving force for the discrepancy in the localization of DMETs between COVID-19 and control human lung tissues. Because alveolar epithelial cells and lymphocytes are both sites of SARS-CoV-2 infection and localization of DMETs, we recommend further investigation of the pulmonary pharmacokinetic profile of current COVID-19 drug dosing regimen to improve clinical outcomes.

Pulmonary circulation abnormalities in post-acute COVID-19 syndrome: dual-energy CT angiographic findings in 79 patients.

To evaluate the frequency and pattern of pulmonary vascular abnormalities in the year following COVID-19. The study population included 79 patients remaining symptomatic more than 6months after hospitalization for SARS-CoV-2 pneumonia who had been evaluated with dual-energy CT angiography. Morphologic images showed CT features of (a) acute (2/79; 2.5%) and focal chronic (4/79; 5%) PE; and (b) residual post COVID-19 lung infiltration (67/79; 85%). Lung perfusion was abnormal in 69 patients (87.4%). Perfusion abnormalities included (a) perfusion defects of 3 types: patchy defects (n = 60; 76%); areas of non-systematized hypoperfusion (n = 27; 34.2%); and/or PE-type defects (n = 14; 17.7%) seen with (2/14) and without (12/14) endoluminal filling defects; and (b) areas of increased perfusion in 59 patients (74.9%), superimposed on ground-glass opacities (58/59) and vascular tree-in-bud (5/59). PFTs were available in 10 patients with normal perfusion and in 55 patients with abnormal perfusion. The mean values of functional variables did not differ between the two subgroups with a trend toward lower DLCO in patients with abnormal perfusion (74.8 ± 16.7% vs 85.0 ± 8.1). Delayed follow-up showed CT features of acute and chronic PE but also two types of perfusion abnormalities suggestive of persistent hypercoagulability as well as unresolved/sequelae of microangiopathy. Despite dramatic resolution of lung abnormalities seen during the acute phase of the disease, acute pulmonary embolism and alterations at the level of lung microcirculation can be identified in patients remaining symptomatic in the year following COVID-19. • This study demonstrates newly developed proximal acute PE/thrombosis in the year following SARS-CoV-2 pneumonia. • Dual-energy CT lung perfusion identified perfusion defects and areas of increased iodine uptake abnormalities, suggestive of unresolved damage to lung microcirculation. • This study suggests a complementarity between HRCT and spectral imaging for proper understanding of post COVID-19 lung sequelae.

ADU-Net: An Attention Dense U-Net based deep supervised DNN for automated lesion segmentation of COVID-19 from chest CT images

An automatic method for qualitative and quantitative evaluation of chest Computed Tomography (CT) images is essential for diagnosing COVID-19 patients. We aim to develop an automated COVID-19 prediction framework using deep learning.We put forth a novel Deep Neural Network (DNN) composed of an attention-based dense U-Net with deep supervision for COVID-19 lung lesion segmentation from chest CT images. We incorporate dense U-Net where convolution kernel size 5×5 is used instead of 3×3. The dense and transition blocks are introduced to implement a densely connected network on each encoder level. Also, the attention mechanism is applied between the encoder, skip connection, and decoder. These are used to keep both the high and low-level features efficiently. The deep supervision mechanism creates secondary segmentation maps from the features. Deep supervision combines secondary supervision maps from various resolution levels and produces a better final segmentation map. The trained artificial DNN model takes the test data at its input and generates a prediction output for COVID-19 lesion segmentation. The proposed model has been applied to the MedSeg COVID-19 chest CT segmentation dataset. Data pre-processing methods help the training process and improve performance.We compare the performance of the proposed DNN model with state-of-the-art models by computing the well-known metrics: dice coefficient, Jaccard coefficient, accuracy, specificity, sensitivity, and precision. As a result, the proposed model outperforms the state-of-the-art models.This new model may be considered an efficient automated screening system for COVID-19 diagnosis and can potentially improve patient health care and management system.

Low-dose computed tomography in COVID-19: systematic review

BACKGROUND: The increased number of computed tomography scans during the COVID-19 pandemic has emphasized the task of decreasing radiation exposure of patients, since it is known to be associated with an elevated risk of cancer development. The ALARA (as low as reasonably achievable) principle, proposed by the International Commission on Radiation Protection, should be adhered to in the operation of radiation diagnostics departments, even during the pandemic.&#x0D; AIM: To systematize data on the appropriateness and effectiveness of low-dose computed tomography in the diagnosis of lung lesions in COVID-19.&#x0D; MATERIALS AND METHODS: Relevant national and foreign literature in scientific libraries PubMed and eLIBRARY, using English and Russian queries low-dose computed tomography and COVID-19, published between 2020 and 2022 were analyzed. Publications were evaluated after assessing the relevance to the review topic by title and abstract analysis. The references were further analyzed to identify articles omitted during the search that may meet the inclusion criteria.&#x0D; RESULTS: Published studies summarized the current data on the imaging of COVID-19 lung lesions and the use of computed tomography scans and identified possible options for reducing the effective dose.&#x0D; CONCLUSION: We present techniques to reduce radiation exposure during chest computed tomography and preserve high-quality diagnostic images potentially sufficient for reliable detection of COVID-19 signs. Reducing radiation dose is a valid approach to obtain relevant diagnostic information, preserving opportunities for the introduction of advanced computational analysis technologies in clinical practice.

Mitochondria and cytochrome components released into the plasma of severe COVID-19 and ICU acute respiratory distress syndrome patients

IntroductionProteomic analysis of human plasma by LC–ESI–MS/MS has discovered a limited number of new cellular protein biomarkers that may be confirmed by independent biochemical methods. Analysis of COVID-19 plasma has indicated the re-purposing of known biomarkers that might be used as prognostic markers of COVID-19 infection. However, multiple molecular approaches have previously indicated that the SARS-COV2 infection cycle is linked to the biology of mitochondria and that the response to infections may involve the action of heme containing oxidative enzymes.MethodsHuman plasma from COVID-19 and ICU-ARDS was analyzed by classical analytical biochemistry techniques and classical frequency-based statistical approaches to look for prognostic markers of severe COVID-19 lung damage. Plasma proteins from COVID-19 and ICU-ARDS were identified and enumerated versus the controls of normal human plasma (NHP) by LC–ESI–MS/MS. The observation frequency of proteins detected in COVID-19 and ICU-ARDS patients were compared to normal human plasma, alongside random and noise MS/MS spectra controls, using the Chi Square (χ2) distribution.ResultsPCR showed the presence of MT-ND1 DNA in the plasma of COVID-19, ICU-ARDS, as well as normal human plasma. Mitochondrial proteins such as MRPL, L2HGDH, ATP, CYB, CYTB, CYP, NDUF and others, were increased in COVID-19 and ICU-ARDS plasma. The apparent activity of the cytochrome components were tested alongside NHP by dot blotting on PVDF against a purified cytochrome c standard preparation for H2O2 dependent reaction with luminol as measured by enhanced chemiluminescence (ECL) that showed increased activity in COVID-19 and ICU-ARDS patients.DiscussionThe results from PCR, LC–ESI–MS/MS of tryptic peptides, and cytochrome ECL assays confirmed that mitochondrial components were present in the plasma, in agreement with the established central role of the mitochondria in SARS-COV-2 biology. The cytochrome activity assay showed that there was the equivalent of at least nanogram amounts of cytochrome(s) in the plasma sample that should be clearly detectable by LC–ESI–MS/MS. The release of the luminol oxidase activity from cells into plasma forms the basis of a simple and rapid test for the severity of cell damage and lung injury in COVID-19 infection and ICU-ARDS.Graphical

GSAL: Geometric structure adversarial learning for robust medical image segmentation

Automatic medical image segmentation plays a crucial role in clinical diagnosis and treatment. However, it is still a challenging task due to the complex interior characteristics (e.g., inconsistent intensity, low contrast, texture heterogeneity) and ambiguous external boundary structures. In this paper, we introduce a novel geometric structure learning mechanism (GSLM) to overcome the limitations of existing segmentation models that lack learning ”focus, path, and difficulty.” The geometric structure in this mechanism is jointly characterized by the skeleton-like structure extracted by the mask distance transform (MDT) and the boundary structure extracted by the mask distance inverse transform (MDIT). Among them, the skeleton-like and boundary pay attention to the trend of interior characteristics consistency and external structure continuity, respectively. With this idea, we design GSAL, a novel end-to-end geometric structure adversarial learning for robust medical image segmentation. GSAL has four components: a geometric structure generator, which yields the geometric structure to learn the most discriminative features that preserve interior characteristics consistency and external boundary structure continuity, skeleton-like and boundary structure discriminators, which enhance and correct the characterization of internal and external geometry to mutually promote the capture of global contextual dependencies, and a geometric structure fusion sub-network, which fuses the two complementary and refined skeleton-like and boundary structures to generate the high-quality segmentation results. The proposed approach has been successfully applied to three different challenging medical image segmentation tasks, including polyp segmentation, COVID-19 lung infection segmentation, and lung nodule segmentation. Extensive experimental results demonstrate that the proposed GSAL achieves favorably against most state-of-the-art methods under different evaluation metrics. The code is available at: https://github.com/DLWK/GSAL.

Detecting Covid-19 and Other Lung Diseases with Deep Learning

Since December 2019, Covid-19, also known as severe acute respiratory syndrome (SARSCOV-2), has infected about 531 million individuals worldwide causing devastating consequences. Scientists, health professionals, and radiologists have all invested huge amounts of time, effort and resources in developing faster and accurate methods for detecting the virus as it spreads all over the world. The current gold standards for detecting covid-19 such as RT-PCR, POC, Droplet-based digital PCR (dPCR) and Immunoassays are not only expensive for low-income countries but also require substantial human expert knowledge which in turn makes them time-consuming and susceptible to manipulation. The study presented in this paper aims to address these issues by proposing a model to automatically detect COVID-19 in chest X-rays using Deep Learning techniques. Specifically, the model uses convolutional neural networks (CNNs), a deep learning technique, which has been shown to produced very good results when applied to medical image diagnosis problems. Our proposed model will therefore not only provide a cheaper, faster and accurate method of detecting COVID-19 but will also provide an easy to use web and mobile platform for non-experts. While current detection techniques such the RT-PCR are still considered as the most effective, our CNN-based model was also able to produce good results when applied to the COVID-19 radiography dataset. For instance, the model was able to detect COVID-19 from X-ray images with an accuracy rate of 90 percent. Furthermore, the model was also able to automatically detect other respiratory diseases such as viral pneumonia and lung opacity with an accuracy rate of over 90 percent. Given the potential of the automated detection of COVID-19 established in this study, future work will extend this work by incorporating automated search techniques such as genetic algorithms in the fine tuning of the model’s parameters in order to obtain an even higher accuracy rate.

Post COVID lung fibrosis (PCLF) or post COVID lung sequelae (PCLS): Which one is the right choice?

Lung is the primary target organ in COVID-19 disease with diverse clinical and radiological presentations and outcome. It has caused minimal to moderate lung disease in some patients and in some cases caused deadly acute respiratory distress syndrome (ARDS). COVID-19 disease caused lung damage by direct virus induced alveolar damage, cytokine induced alveolar and vascular damage and microvascular thrombosis resulting into acute hypoxic respiratory failure. COVID-19 pneumonia evolved over period of three weeks in cases with ARDS as natural course of illness. Usually, ARDS resolves by fibrosis or resolution as final outcome. Similarly, in COVID-19 recovered cases of advanced disease or those suffering from ARDS are having post COVID lung disease. Lung fibrosis is final radiological outcome of COVID-19 pneumonia documented in proportionately majority of cases. Post COVID lung fibrosis is considered as worrisome radiological complication observed during early phase of pandemic. Time trends of final radiological outcome has evolved over months with or without treatment with antifibrotics and steroids. Importantly, Post COVID lung fibrosis resolved more than fifty percent cases in six months and nearly in all cases after one year. Post COVID lung fibrosis is considered as ‘health issue of great concern’ initially in post pandemic phase of first wave, and due to its resolving nature over time period; now considered as ‘sigh with relief’ due to its reversible pathophysiology. Post COVID sequel is minimal residual effects of COVID-19 lung disease irrespective of disease severity in past. We recommend to use term post COVID sequel over post COVID lung fibrosis.