The role of chest radiography in confirming covid-19 pneumonia

Clinical and ultrasound characteristics in patients with sars-cov-2 pneumonia, associated with hospitalization prognosis. e-covid project

BACKGROUND

During the COVID-19 pandemia, the imaging test of choice to diagnose COVID-19 pneumonia as chest computed tomography (CT). However, access was limited in the hospital setting and patients treated in Primary Care (PC) could only access the chest x-ray as an imaging test. Several scientific articles that demonstrated the sensitivity of lung ultrasound, being superior to chest x-ray [Cleverley J et al., BMJ 370, 202013] and comparable to CT scan [Tung-Chen Y et al., Ultrasound Med Biol 46:2918-2926, 2020], promoted the incorporation of this technique in the assessment of COVID-19 patients in PC. [Pérez J et al., Arch. Bronconeumol 56:27-30, 2020; Gargani L et al., Eur Heart J Cardiovasc Imaging 21:941-8, 2020, Soldati G et al., J Ultrasound Med 39:1459, 2020] A prior study in our territory (Lleida, Spain) was designed to predict complications (hospital admission) of COVID-19 pneumonia in PC patients, being different patterns of Lung ultrasounds (LUS) risk factors for hospital admission. [Martínez Redondo J et al., Int J Environ Res Public Health 18:3481, 2021] The rationale for conducting this study lies in the urgent need to understand the determinants of severity and prognosis in COVID-19 patients with interstitial pneumonia, according to its lung ultrasound patterns. This research is crucial to provide a deeper understanding of how these pre-existing ultrasound patterns related to disease progression influence the medical treatment.

METHODS

The objective of the study is to generate predictive models of lung ultrasound patterns for the prediction of lung areas characteristics associated with hospitalizations and admissions to the Intensive Care Unit (ICU) associated with COVID-19 disease, using ultrasound, sociodemographic and medical data obtained through the computerized medical history.

RESULTS

A single relevant variable has been found for the prediction of hospitalization (number of total regions with potentially pathological presence of B lines) and one for the prediction of ICU admission (number of regions of the right lung with potentially pathological presence of B lines). In both cases it has been determined that the optimal point for classification was 2 or more lung affected areas. Those areas under the curve have been obtained with good predictive capacity and consistency in both cohorts.

CONCLUSIONS

The results of this study will contribute to the determination of the ultrasound prognostic value based on the number of lung areas affected, the presence of pulmonary condensation or the irregularity of pleural effusion patterns in COVID-19 patients, being able to be extended to other lung viral infections with similar patterns.

Psittacosis Pneumonia Features, Distinguishing Characteristics, and Outcomes: A Retrospective Study

Purpose

Psittacosis is an often-neglected cause of community acquired pneumonia (CAP). The limited diagnostic methods for psittacosis pneumonia invariably result in an unfavourable prognosis. Consequently, the early detection of psittacosis pneumonia is crucial. This study aimed to analyse the characteristics, clinical features and treatments of the patients to improve early diagnosis and outcomes.

Patients and Methods

We retrospectively analyzed the clinical features and outcomes of 52 cases of psittacosis pneumonia diagnosed with next-generation sequencing (NGS) from January 2022 to August 2024 in a local tertiary hospital in China.

Results

Of the 52 patients, 18 had a clear exposure to poultry or birds. The main clinical manifestations included fever (100%, 52/52), cough (75.0%, 39/52), fatigue (57.7%, 30/352), and dyspnea (36.5%, 19/52). Significant elevations in neutrophil counts (NEUT), C-reactive protein (CRP), alanine aminotransferase (ALT), aspartate aminotransferase (AST), D-dimer, lactate dehydrogenase (LDH), creatine kinase (CK), interleukin-6 (IL-6) and interferon-γ (IFN-γ), as well as reductions in lymphocyte (LY) and albumin (ALB) were observed. The main chest computed tomography (CT) features were consolidated. Eight patients diagnosed with severe CAP (SCAP) exhibited higher NEUT, CRP, procalcitonin (PCT), blood urea nitrogen (BUN), creatinine, D-Dimer and IL-6 levels, as well as lower oxygen index. The interval between the onset of symptoms and diagnosis was 6-34 days. C. psittaci infection was identified by metagenomic NGS (mNGS) or targeted NGS (tNGS) in all cases, and the average length of hospital stay for these patients was 9.4 days. Following the identification of the aetiology, all patients were promptly initiated on tetracycline- or fluoroquinolone-based therapy, with complete recovery observed in all cases.

Conclusion

Patients exposed to poultry should be alert to Chlamydia psittaci pneumonia. The application of NGS has improved the diagnostic accuracy of C. psittaci pneumonia, reduced unnecessary use of antibiotics, and shortened the course of disease. Patients who received tetracycline-based therapy showed a good prognosis.

Distribution-based detection of radiographic changes in pneumonia patterns: A COVID-19 case study

Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population-based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVID-negative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.

Evaluating Acute Pulmonary Changes of Coronavirus 2019: Comparative Analysis of the Pertinent Modalities

This review explores imaging's crucial role in acute Coronavirus Disease 2019 (COVID-19) assessment. High Resolution Computer Tomography is especially effective in detection of lung abnormalities. Chest radiography has limited utility in the initial stages of COVID-19 infection. Lung Ultrasound has emerged as a valuable, radiation-free tool in critical care, and Magnetic Resonance Imaging shows promise as a Computed Tomography alternative. Typical and atypical findings of COVID-19 by each of these modalities are discussed with emphasis on their prognostic value. Considerations for pediatric and immunocompromised cases are outlined. A comprehensive diagnostic approach is recommended, as radiological diagnosis remains challenging in the acute phase.

Introducing SPINE: A Holistic Approach to Synthetic Pulmonary Imaging Evaluation Through End-to-End Data and Model Management

In the evolving field of medical imaging and machine learning (ML), this paper introduces a novel framework for evaluating synthetic pulmonary imaging aiming to assess synthetic data quality and applicability. Our study concentrates on synthetic X-ray chest images, crucial for diagnosing respiratory diseases. We employ SPINE (Synthetic Pulmonary Imaging Evaluation) framework, a threefold synthetic images evaluation method including expert domain assessment, statistical data analysis and adversarial evaluation. In order to replicate and validate our methodology, we followed an End-to-End data and model management process which begins with a dataset of Normal and Pneumonia chest X-rays, generating synthetic images using Generative Adversarial Networks (GANs) and training a baseline classifier, essential in the adversarial evaluation axis, testing synthetic images against real data assessing their predictive value. The critical outcome of our approach is the post-market analysis of synthetic images. This innovative method evaluates synthetic images using clinical, statistical, and scientific criteria independently from traditional generation performance metrics. This independent evaluation provides deep insights into the clinical and research effectiveness of the synthetic data. By ensuring these images mirror real data's statistical properties and maintain clinical accuracy, our framework establishes a new standard for the ethical and reliable use of synthetic data in medical imaging and research.

COVID-19 detection and analysis from lung CT images using novel channel boosted CNNs

In December 2019, the global pandemic COVID-19 in Wuhan, China, affected human life and the worldwide economy. Therefore, an efficient diagnostic system is required to control its spread. However, the automatic diagnostic system poses challenges with a limited amount of labeled data, minor contrast variation, and high structural similarity between infection and background. In this regard, a new two-phase deep convolutional neural network (CNN) based diagnostic system is proposed to detect minute irregularities and analyze COVID-19 infection. In the first phase, a novel SB-STM-BRNet CNN is developed, incorporating a new channel Squeezed and Boosted (SB) and dilated convolutional-based Split-Transform-Merge (STM) block to detect COVID-19 infected lung CT images. The new STM blocks performed multi-path region-smoothing and boundary operations, which helped to learn minor contrast variation and global COVID-19 specific patterns. Furthermore, the diverse boosted channels are achieved using the SB and Transfer Learning concepts in STM blocks to learn texture variation between COVID-19-specific and healthy images. In the second phase, COVID-19 infected images are provided to the novel COVID-CB-RESeg segmentation CNN to identify and analyze COVID-19 infectious regions. The proposed COVID-CB-RESeg methodically employed region-homogeneity and heterogeneity operations in each encoder-decoder block and boosted-decoder using auxiliary channels to simultaneously learn the low illumination and boundaries of the COVID-19 infected region. The proposed diagnostic system yields good performance in terms of accuracy: 98.21 %, F-score: 98.24%, Dice Similarity: 96.40 %, and IOU: 98.85 % for the COVID-19 infected region. The proposed diagnostic system would reduce the burden and strengthen the radiologist's decision for a fast and accurate COVID-19 diagnosis.

American Society of Echocardiography COVID-19 Statement Update: Lessons Learned and Preparation for Future Pandemics

The COVID-19 pandemic has evolved since the publication of the initial American Society of Echocardiography (ASE) statements providing guidance to echocardiography laboratories. In light of new developments, the ASE convened a diverse, expert writing group to address the current state of the COVID-19 pandemic and to apply lessons learned to echocardiography laboratory operations in future pandemics. This statement addresses important areas specifically impacted by the current and future pandemics: (1) indications for echocardiography, (2) application of echocardiographic services in a pandemic, (3) infection/transmission mitigation strategies, (4) role of cardiac point-of-care ultrasound/critical care echocardiography, and (5) training in echocardiography.

MultiCOVID: a multi modal deep learning approach for COVID-19 diagnosis

The rapid spread of the severe acute respiratory syndrome coronavirus 2 led to a global overextension of healthcare. Both Chest X-rays (CXR) and blood test have been demonstrated to have predictive value on Coronavirus Disease 2019 (COVID-19) diagnosis on different prevalence scenarios. With the objective of improving and accelerating the diagnosis of COVID-19, a multi modal prediction algorithm (MultiCOVID) based on CXR and blood test was developed, to discriminate between COVID-19, Heart Failure and Non-COVID Pneumonia and healthy (Control) patients. This retrospective single-center study includes CXR and blood test obtained between January 2017 and May 2020. Multi modal prediction models were generated using opensource DL algorithms. Performance of the MultiCOVID algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar-Bowker test. A total of 8578 samples from 6123 patients (mean age 66 ± 18 years of standard deviation, 3523 men) were evaluated across datasets. For the entire test set, the overall accuracy of MultiCOVID was 84%, with a mean AUC of 0.92 (0.89-0.94). For 300 random test images, overall accuracy of MultiCOVID was significantly higher (69.6%) compared with individual radiologists (range, 43.7-58.7%) and the consensus of all five radiologists (59.3%, P < .001). Overall, we have developed a multimodal deep learning algorithm, MultiCOVID, that discriminates among COVID-19, heart failure, non-COVID pneumonia and healthy patients using both CXR and blood test with a significantly better performance than experienced thoracic radiologists.

Role of cardiac and lung ultrasound in the COVID-19 era

INTRODUCTION

The primary diagnostic method of Coronavirus disease 2019 is reverse transcription polymerase chain reaction of the nucleic acid of severe acute respiratory syndrome coronavirus 2 in nasopharyngeal swabs. There is growing evidence regarding the 2019 coronavirus disease imaging results on chest X-rays and computed tomography but the accessibility to standard diagnostic methods may be limited during the pandemic.

EVIDENCE ACQUISITION

Databases used for the search were MEDLINE (PubMed), Scopus Search, and Cochrane Library. The research took into consideration studies published in English until March 2022 and was conducted using the following research query: ((((sars cov [MeSH Terms])) OR (COVID-19)) OR (Sars-Cov2)) OR (Coronavirus)) AND (((((2d echocardiography [MeSH Terms]) OR (doppler ultrasound imaging [MeSH Terms]))) OR (echography [MeSH Terms])) OR (LUS)) OR ("LUNG ULTRASOUND")).

EVIDENCE SYNTHESIS

Pulmonary and cardiac ultrasound are cost-effective, widely available, and provide information that can influence management.

CONCLUSIONS

Point-of-care ultrasonography is a method that can provide relevant clinical and therapeutic information in patients with COVID-19 where other diagnostic methods may not be easily accessible.

POLCOVID: a multicenter multiclass chest X-ray database (Poland, 2020-2021)

The outbreak of the SARS-CoV-2 pandemic has put healthcare systems worldwide to their limits, resulting in increased waiting time for diagnosis and required medical assistance. With chest radiographs (CXR) being one of the most common COVID-19 diagnosis methods, many artificial intelligence tools for image-based COVID-19 detection have been developed, often trained on a small number of images from COVID-19-positive patients. Thus, the need for high-quality and well-annotated CXR image databases increased. This paper introduces POLCOVID dataset, containing chest X-ray (CXR) images of patients with COVID-19 or other-type pneumonia, and healthy individuals gathered from 15 Polish hospitals. The original radiographs are accompanied by the preprocessed images limited to the lung area and the corresponding lung masks obtained with the segmentation model. Moreover, the manually created lung masks are provided for a part of POLCOVID dataset and the other four publicly available CXR image collections. POLCOVID dataset can help in pneumonia or COVID-19 diagnosis, while the set of matched images and lung masks may serve for the development of lung segmentation solutions.

Artificial intelligence innovation in healthcare: Relevance of reporting guidelines for clinical translation from bench to bedside

Artificial intelligence (AI) and digital innovation are transforming healthcare. Technologies such as machine learning in image analysis, natural language processing in medical chatbots and electronic medical record extraction have the potential to improve screening, diagnostics and prognostication, leading to precision medicine and preventive health. However, it is crucial to ensure that AI research is conducted with scientific rigour to facilitate clinical implementation. Therefore, reporting guidelines have been developed to standardise and streamline the development and validation of AI technologies in health. This commentary proposes a structured approach to utilise these reporting guidelines for the translation of promising AI techniques from research and development into clinical translation, and eventual widespread implementation from bench to bedside.

Automatic Identification of Lung Opacities Due to COVID-19 from Chest X-ray Images-Focussing Attention on the Lungs

Due to the primary affection of the respiratory system, COVID-19 leaves traces that are visible in plain chest X-ray images. This is why this imaging technique is typically used in the clinic for an initial evaluation of the patient's degree of affection. However, individually studying every patient's radiograph is time-consuming and requires highly skilled personnel. This is why automatic decision support systems capable of identifying those lesions due to COVID-19 are of practical interest, not only for alleviating the workload in the clinic environment but also for potentially detecting non-evident lung lesions. This article proposes an alternative approach to identify lung lesions associated with COVID-19 from plain chest X-ray images using deep learning techniques. The novelty of the method is based on an alternative pre-processing of the images that focuses attention on a certain region of interest by cropping the original image to the area of the lungs. The process simplifies training by removing irrelevant information, improving model precision, and making the decision more understandable. Using the FISABIO-RSNA COVID-19 Detection open data set, results report that the opacities due to COVID-19 can be detected with a Mean Average Precision with an IoU > 0.5 (mAP@50) of 0.59 following a semi-supervised training procedure and an ensemble of two architectures: RetinaNet and Cascade R-CNN. The results also suggest that cropping to the rectangular area occupied by the lungs improves the detection of existing lesions. A main methodological conclusion is also presented, suggesting the need to resize the available bounding boxes used to delineate the opacities. This process removes inaccuracies during the labelling procedure, leading to more accurate results. This procedure can be easily performed automatically after the cropping stage.

Portable Chest Radiograph: A Boon for Critically Ill Patients With COVID-19 Pneumonia

OBJECTIVE

In the present study, we evaluated the role of portable chest radiographs in critically ill patients with COVID-19 pneumonia in whom computed tomography (CT) of the chest was not feasible.

METHODS

A retrospective chest X-ray study of patients under investigation for COVID-19 was performed in our dedicated COVID hospital (DCH) during the exponential growth phase of the COVID-19 outbreak (August-October, 2020). A total of 562 on-bed chest radiographs were examined comprising 289 patients (critically ill who couldn't be mobilized for CT) along with positive reverse transcription-polymerase chain reaction (RT-PCR) tests. We categorized each chest radiograph as progressive, with changes, or improvement in appearance for COVID-19, utilizing well-documented COVID-19 imaging patterns.

RESULTS

 In our study, portable radiographs provided optimum image quality for diagnosing pneumonia, in critically ill patients. Although less informative than CT, nevertheless radiographs detected serious complications like pneumothorax or lung cavitation and estimated the evolution of pneumonia.

CONCLUSION

A portable chest X-ray is a simple but reliable alternative for critically ill SARS-CoV-2 patients who could not undergo chest CT. With the help of portable chest radiographs, we could monitor the severity of the disease as well as different complications with minimal radiation exposure which would help in identifying the prognosis of the patient and thus help in medical management.

Multisystem Imaging Recommendations/Guidelines: In the Pursuit of Precision Oncology

With an increasing rate of cancers in almost all age groups and advanced screening techniques leading to an early diagnosis and longer longevity of patients with cancers, it is of utmost importance that radiologists assigned with cancer imaging should be prepared to deal with specific expected and unexpected circumstances that may arise during the lifetime of these patients. Tailored integration of preventive and curative interventions with current health plans and global escalation of efforts for timely diagnosis of cancers will pave the path for a cancer-free world. The commonly encountered circumstances in the current era, complicating cancer imaging, include coronavirus disease 2019 infection, pregnancy and lactation, immunocompromised states, bone marrow transplant, and screening of cancers in the relevant population. In this article, we discuss the imaging recommendations pertaining to cancer screening and diagnosis in the aforementioned clinical circumstances.

COVID-19 diagnostics: Molecular biology to nanomaterials

The SARS-CoV-2 pandemic has claimed around 6.4 million lives worldwide. The disease symptoms range from mild flu-like infection to life-threatening complications. The widespread infection demands rapid, simple, and accurate diagnosis. Currently used methods include molecular biology-based approaches that consist of conventional amplification by RT-PCR, isothermal amplification-based techniques such as RT-LAMP, and gene editing tools like CRISPR-Cas. Other methods include immunological detection including ELISA, lateral flow immunoassay, chemiluminescence, etc. Radiological-based approaches are also being used. Despite good analytical performance of these current methods, there is an unmet need for less costly and simpler tests that may be performed at point of care. Accordingly, nanomaterial-based testing has been extensively pursued. In this review, we discuss the currently used diagnostic techniques for SARS-CoV-2, their usefulness, and limitations. In addition, nanoparticle-based approaches have been highlighted as another potential means of detection. The review provides a deep insight into the current diagnostic methods and future trends to combat this deadly menace.

Clinical outcomes in patients with COVID-19 and gynecologic cancer: A society of gynecologic oncology COVID-19 and gynecologic cancer registry study

OBJECTIVES

Patients with gynecologic malignancies may have varied responses to COVID-19 infection. We aimed to describe clinical courses, treatment changes, and short-term clinical outcomes for gynecologic oncology patients with concurrent COVID-19 in the United States.

METHODS

The Society of Gynecologic Oncology COVID-19 and Gynecologic Cancer Registry was created to capture clinical courses of gynecologic oncology patients with COVID-19. Logistic regression models were employed to evaluate factors for an association with hospitalization and death, respectively, within 30 days of COVID-19 diagnosis.

RESULTS

Data were available for 348 patients across 7 institutions. At COVID-19 diagnosis, 125 patients (36%) had active malignancy. Delay (n = 88) or discontinuation (n = 10) of treatment due to COVID-19 infection occurred in 28% with those on chemotherapy (53/88) or recently receiving surgery (32/88) most frequently delayed. In addition to age, performance status, diabetes, and specific COVID symptoms, both non-White race (adjusted odds ratio (aOR) = 3.93, 95% CI 2.06-7.50) and active malignancy (aOR = 2.34, 95% CI 1.30-4.20) were associated with an increased odds of hospitalization. Eight percent of hospitalized patients (8/101) died of COVID-19 complications and 5% (17/348) of the entire cohort died within 30 days after diagnosis.

CONCLUSIONS

Gynecologic oncology patients diagnosed with COVID-19 are at risk for hospitalization, delay of anti-cancer treatments, and death. One in 20 gynecologic oncology patients with COVID-19 died within 30 days after diagnosis. Racial disparities exist in patient hospitalizations for COVID-19, a surrogate of disease severity. Additional studies are needed to determine long-term outcomes and the impact of race.

Radiological Findings in SARS-CoV-2 Viral Pneumonia Compared to Other Viral Pneumonias: A Single-Centre Study

BACKGROUND

Thorax computed tomography (CT) imaging is widely used as a diagnostic method in the diagnosis of coronavirus disease 2019 (COVID-19)-related pneumonia. Radiological differential diagnosis and isolation of other viral agents causing pneumonia in patients have gained importance, particularly during the pandemic.

AIMS

We aimed to investigate whether there is a difference between CT images from patients with COVID-19-associated pneumonia compared to CT images of patients with pneumonia due to other viral agents and which finding may be more effective in diagnosis. Study Design. The study included 249 adult patients with pneumonia identified by thorax CT examination and with a positive COVID-19 RT-PCR test compared to 94 patients diagnosed with non-COVID-19 pneumonia (viral PCR positive but no bacterial or fungal agents detected in other cultures) between 2015 and 2019. CT images were retrospectively analyzed using the PACS system. CT findings were evaluated by two radiologists with 5 and 20 years of experience, in a blinded fashion, and the outcome was decided by consensus.

METHODS

Demographic data (age, gender, and known chronic disease) and CT imaging findings (percentage of involvement, number of lesions, distribution preference, dominant pattern, ground-glass opacity distribution pattern, nodule, tree in bud sign, interstitial changes, crazy paving sign, reversed halo sign, vacuolar sign, halo sign, vascular enlargement, linear opacities, traction bronchiectasis, peribronchial wall thickness, air trapping, pleural retraction, pleural effusion, pericardial effusion, cavitation, mediastinal/hilar lymphadenopathy, dominant lesion size, consolidation, subpleural curvilinear opacities, air bronchogram, and pleural thickening) of the patients were evaluated. CT findings were also evaluated with the RSNA consensus guideline and the CORADS scoring system. Data were divided into two main groups-non-COVID-19 and COVID-19 pneumonia-and compared statistically with chi-squared tests and multiple regression analysis of independent variables.

RESULTS

RSNA and CORADS classifications of CT scan images were able to successfully differentiate between positive and negative COVID-19 pneumonia patients. Statistically significant differences were found between the two patient groups in various categories including the percentage of involvement, number of lesions, distribution preference, dominant pattern, nodule, tree in bud, interstitial changes, crazy paving, reverse halo vascular enlargement, peribronchial wall thickness, air trapping, pleural retraction, pleural/pericardial effusion, cavitation, and mediastinal/hilar lymphadenopathy (p < 0.01). Multiple linear regression analysis of independent variables found a significant effect in reverse halo sign (β = 0.097, p < 0.05) and pleural effusion (β = 10.631, p < 0.05) on COVID-19 pneumonia patients.

CONCLUSION

The presence of reverse halo and absence of pleural effusion was found to be characteristic of COVID-19 pneumonia and therefore a reliable diagnostic tool to differentiate it from non-COVID-19 pneumonia.

Point-of-care contrast enhanced lung ultrasound and COVID-19

OBJECTIVES

Bedside lung ultrasound has been indispensable during the coronavirus disease 2019 (COVID-19) pandemic, allowing us to rapidly assess critically unwell patients. We demonstrate the unique application of contrast-enhanced ultrasound with the aim of further understanding this disease.

METHODS

Patient demographics were recorded alongside recent cross-sectional imaging and inflammatory markers. Ultrasound was conducted by experienced operators in a portable setting. Conventional six-point lung ultrasound method was used to evaluate B-lines, small (subpleural) consolidation and the pleura. Areas of small consolidation were targeted after intravenous administration of ultrasound contrast.

RESULTS

The areas of small consolidations, a potential sign of pneumonia on B-mode lung ultrasound, usually enhance on contrast-enhanced ultrasound. Our study revealed these areas to be avascular, indicating an underlying thrombotic/infarction process. Findings were present in 100% of the patients we examined. We have also shown that the degree of infarction correlates with CT severity (r = 0.4) and inflammatory markers, and that these areas improve as patients recover.

CONCLUSIONS

We confirmed the theory of immune thrombus by identifying the presence of microthrombi in the lungs of 100% of our patients, despite 79% having had a recent negative CT pulmonary angiogram study. contrast-enhanced ultrasound can be utilised to add confidence to an uncertain COVID-19 diagnosis and for prognosticating and monitoring progress in confirmed COVID-19 patients. Contrast-enhanced ultrasound is clearly very different to CT, the gold standard, and while there are specific pathologies that can only be detected on CT, contrast-enhanced ultrasound has many advantages, most notability the ability to pick up microthrombi at the periphery of the lungs.

A comparison of Covid-19 early detection between convolutional neural networks and radiologists

Background

The role of chest radiography in COVID-19 disease has changed since the beginning of the pandemic from a diagnostic tool when microbiological resources were scarce to a different one focused on detecting and monitoring COVID-19 lung involvement. Using chest radiographs, early detection of the disease is still helpful in resource-poor environments. However, the sensitivity of a chest radiograph for diagnosing COVID-19 is modest, even for expert radiologists. In this paper, the performance of a deep learning algorithm on the first clinical encounter is evaluated and compared with a group of radiologists with different years of experience.

Methods

The algorithm uses an ensemble of four deep convolutional networks, Ensemble4Covid, trained to detect COVID-19 on frontal chest radiographs. The algorithm was tested using images from the first clinical encounter of positive and negative cases. Its performance was compared with five radiologists on a smaller test subset of patients. The algorithm's performance was also validated using the public dataset COVIDx.

Results

Compared to the consensus of five radiologists, the Ensemble4Covid model achieved an AUC of 0.85, whereas the radiologists achieved an AUC of 0.71. Compared with other state-of-the-art models, the performance of a single model of our ensemble achieved nonsignificant differences in the public dataset COVIDx.

Conclusion

The results show that the use of images from the first clinical encounter significantly drops the detection performance of COVID-19. The performance of our Ensemble4Covid under these challenging conditions is considerably higher compared to a consensus of five radiologists. Artificial intelligence can be used for the fast diagnosis of COVID-19.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01250-3.

Automated diagnosis and prognosis of COVID-19 pneumonia from initial ER chest X-rays using deep learning

Background

Airspace disease as seen on chest X-rays is an important point in triage for patients initially presenting to the emergency department with suspected COVID-19 infection. The purpose of this study is to evaluate a previously trained interpretable deep learning algorithm for the diagnosis and prognosis of COVID-19 pneumonia from chest X-rays obtained in the ED.

Methods

This retrospective study included 2456 (50% RT-PCR positive for COVID-19) adult patients who received both a chest X-ray and SARS-CoV-2 RT-PCR test from January 2020 to March of 2021 in the emergency department at a single U.S. institution. A total of 2000 patients were included as an additional training cohort and 456 patients in the randomized internal holdout testing cohort for a previously trained Siemens AI-Radiology Companion deep learning convolutional neural network algorithm. Three cardiothoracic fellowship-trained radiologists systematically evaluated each chest X-ray and generated an airspace disease area-based severity score which was compared against the same score produced by artificial intelligence. The interobserver agreement, diagnostic accuracy, and predictive capability for inpatient outcomes were assessed. Principal statistical tests used in this study include both univariate and multivariate logistic regression.

Results

Overall ICC was 0.820 (95% CI 0.790–0.840). The diagnostic AUC for SARS-CoV-2 RT-PCR positivity was 0.890 (95% CI 0.861–0.920) for the neural network and 0.936 (95% CI 0.918–0.960) for radiologists. Airspace opacities score by AI alone predicted ICU admission (AUC = 0.870) and mortality (0.829) in all patients. Addition of age and BMI into a multivariate log model improved mortality prediction (AUC = 0.906).

Conclusion

The deep learning algorithm provides an accurate and interpretable assessment of the disease burden in COVID-19 pneumonia on chest radiographs. The reported severity scores correlate with expert assessment and accurately predicts important clinical outcomes. The algorithm contributes additional prognostic information not currently incorporated into patient management.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07617-7.

Chest Radiograph Severity Scores, Comorbidity Prevalence, and Outcomes of Patients with Coronavirus Disease Treated at the King Abdullah University Hospital in Jordan: A Retrospective Study

Introduction

Hospitalized patients with coronavirus disease (COVID-19) often undergo chest x-ray (CXR). Utilizing CXR findings could reduce the cost of COVID-19 treatment and the resultant pressure on the Jordanian healthcare system.

Methods

We evaluated the association between the CXR severity score, based on the Radiographic Assessment of Lung Edema (RALE) scoring system, and outcomes of patients with COVID-19. The main objective of this work is to assess the role of the RALE scoring system in predicting in-hospital mortality and clinical outcomes of patients with COVID-19. Adults with a positive severe acute respiratory syndrome COVID-19 two reverse-transcription polymerase chain reaction test results and a baseline CXR image, obtained in November 2020, were included. The RALE severity scores were calculated by expert radiologists and categorized as normal, mild, moderate, and severe. Chi-square tests and multivariable logistic regression were used to assess the association between the severity category and admission location and clinical characteristics.

Results

Based on the multivariable regression analysis, it has been found that male sex, hypertension, and the RALE severity score were significantly associated with in-hospital mortality. The baseline RALE severity score was associated with the need for critical care (P<0.001), in-hospital mortality (P<0.001), and the admission location (P=0.002).

Discussion

The utilization of RALE severity scores helps to predict clinical outcomes and promote prudent use of resources during the COVID-19 pandemic.

Imaging related to underlying immunological and pathological processes in COVID-19

The introduction of coronavirus disease-2019 (COVID-19) as a global pandemic has contributed to overall morbidity and mortality. With a focus on understanding the immunology and pathophysiology of the disease, these features can be linked with the respective findings of imaging studies. Thus, the constellation between clinical presentation, histological, laboratory, immunological, and imaging results is crucial for the proper management of patients. The purpose of this article is to examine the role of imaging during the particular stages of severe acute respiratory syndrome coronavirus 2 infection – asymptomatic stage, typical and atypical COVID-19 pneumonia, acute respiratory distress syndrome, multiorgan failure, and thrombosis. The use of imaging methods to assess the severity and duration of changes is crucial in patients with COVID-19. Radiography and computed tomography are among the methods that allow accurate characterization of changes.

Immune and epithelial determinants of age-related risk and alveolar injury in fatal COVID-19

Respiratory failure in COVID-19 is characterized by widespread disruption of the lung’s alveolar gas exchange interface. To elucidate determinants of alveolar lung damage, we performed epithelial and immune cell profiling in lungs from 24 COVID-19 autopsies and 43 uninfected organ donors ages 18–92 years. We found marked loss of type 2 alveolar epithelial (T2AE) cells and increased perialveolar lymphocyte cytotoxicity in all fatal COVID-19 cases, even at early stages before typical patterns of acute lung injury are histologically apparent. In lungs from uninfected organ donors, there was also progressive loss of T2AE cells with increasing age, which may increase susceptibility to COVID-19–mediated lung damage in older individuals. In the fatal COVID-19 cases, macrophage infiltration differed according to the histopathological pattern of lung injury. In cases with acute lung injury, we found accumulation of CD4⁺ macrophages that expressed distinctly high levels of T cell activation and costimulation genes and strongly correlated with increased extent of alveolar epithelial cell depletion and CD8⁺ T cell cytotoxicity. Together, our results show that T2AE cell deficiency may underlie age-related COVID-19 risk and initiate alveolar dysfunction shortly after infection, and we define immune cell mediators that may contribute to alveolar injury in distinct pathological stages of fatal COVID-19.

Assessing clinical applicability of COVID-19 detection in chest radiography with deep learning

The coronavirus disease 2019 (COVID-19) pandemic has impacted healthcare systems across the world. Chest radiography (CXR) can be used as a complementary method for diagnosing/following COVID-19 patients. However, experience level and workload of technicians and radiologists may affect the decision process. Recent studies suggest that deep learning can be used to assess CXRs, providing an important second opinion for radiologists and technicians in the decision process, and super-human performance in detection of COVID-19 has been reported in multiple studies. In this study, the clinical applicability of deep learning systems for COVID-19 screening was assessed by testing the performance of deep learning systems for the detection of COVID-19. Specifically, four datasets were used: (1) a collection of multiple public datasets (284.793 CXRs); (2) BIMCV dataset (16.631 CXRs); (3) COVIDGR (852 CXRs) and 4) a private dataset (6.361 CXRs). All datasets were collected retrospectively and consist of only frontal CXR views. A ResNet-18 was trained on each of the datasets for the detection of COVID-19. It is shown that a high dataset bias was present, leading to high performance in intradataset train-test scenarios (area under the curve 0.55–0.84 on the collection of public datasets). Significantly lower performances were obtained in interdataset train-test scenarios however (area under the curve > 0.98). A subset of the data was then assessed by radiologists for comparison to the automatic systems. Finetuning with radiologist annotations significantly increased performance across datasets (area under the curve 0.61–0.88) and improved the attention on clinical findings in positive COVID-19 CXRs. Nevertheless, tests on CXRs from different hospital services indicate that the screening performance of CXR and automatic systems is limited (area under the curve < 0.6 on emergency service CXRs). However, COVID-19 manifestations can be accurately detected when present, motivating the use of these tools for evaluating disease progression on mild to severe COVID-19 patients.

Role of a Chest X-ray Severity Score in a Multivariable Predictive Model for Mortality in Patients with COVID-19: A Single-Center, Retrospective Study

Predicting the mortality risk of patients with Coronavirus Disease 2019 (COVID-19) can be valuable in allocating limited medical resources in the setting of outbreaks. This study assessed the role of a chest X-ray (CXR) scoring system in a multivariable model in predicting the mortality of COVID-19 patients by performing a single-center, retrospective, observational study including consecutive patients admitted with a confirmed diagnosis of COVID-19 and an initial CXR. The CXR severity score was calculated by three radiologists with 12 to 15 years of experience in thoracic imaging, based on the extent of lung involvement and density of lung opacities. Logistic regression analysis was used to identify independent predictive factors for mortality to create a predictive model. A validation dataset was used to calculate its predictive value as the AUROC. A total of 628 patients (58.1% male) were included in this study. Age (p < 0.001), sepsis (p < 0.001), S/F ratio (p < 0.001), need for mechanical ventilation (p < 0.001), and the CXR severity score (p = 0.005) were found to be independent predictive factors for mortality. We used these variables to develop a predictive model with an AUROC of 0.926 (0.891, 0.962), which was significantly higher than that of the WHO COVID severity classification, 0.853 (0.798, 0.909) (one-tailed p-value = 0.028), showing that our model can accurately predict mortality of hospitalized COVID-19 patients.

Artificial Intelligence for COVID-19 Detection in Medical Imaging-Diagnostic Measures and Wasting-A Systematic Umbrella Review

The COVID-19 pandemic has sparked a barrage of primary research and reviews. We investigated the publishing process, time and resource wasting, and assessed the methodological quality of the reviews on artificial intelligence techniques to diagnose COVID-19 in medical images. We searched nine databases from inception until 1 September 2020. Two independent reviewers did all steps of identification, extraction, and methodological credibility assessment of records. Out of 725 records, 22 reviews analysing 165 primary studies met the inclusion criteria. This review covers 174,277 participants in total, including 19,170 diagnosed with COVID-19. The methodological credibility of all eligible studies was rated as critically low: 95% of papers had significant flaws in reporting quality. On average, 7.24 (range: 0-45) new papers were included in each subsequent review, and 14% of studies did not include any new paper into consideration. Almost three-quarters of the studies included less than 10% of available studies. More than half of the reviews did not comment on the previously published reviews at all. Much wasting time and resources could be avoided if referring to previous reviews and following methodological guidelines. Such information chaos is alarming. It is high time to draw conclusions from what we experienced and prepare for future pandemics.

Deep Learning and Medical Image Analysis for COVID-19 Diagnosis and Prediction

The coronavirus disease 2019 (COVID-19) pandemic has imposed dramatic challenges to health-care organizations worldwide. To combat the global crisis, the use of thoracic imaging has played a major role in diagnosis, prediction, and management for COVID-19 patients with moderate to severe symptoms or with evidence of worsening respiratory status. In response, the medical image analysis community acted quickly to develop and disseminate deep learning models and tools to meet the urgent need of managing and interpreting large amounts of COVID-19 imaging data. This review aims to not only summarize existing deep learning and medical image analysis methods but also offer in-depth discussions and recommendations for future investigations. We believe that the wide availability of high-quality, curated, and benchmarked COVID-19 imaging data sets offers the great promise of a transformative test bed to develop, validate, and disseminate novel deep learning methods in the frontiers of data science and artificial intelligence. Expected final online publication date for the Annual Review of Biomedical Engineering, Volume 24 is June 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

COVID-19 pandemic and the effect of increased utilisation of mobile X-ray examinations on radiation dose to radiographers

Introduction

The use of ionising radiation results in occupational exposure to medical imaging professionals, requiring routine monitoring. This study aims to assess the effect of increased utilisation of mobile X‐ray units, mobile imaging of non‐routine body regions and radiographer work practice changes for impact on staff radiation dose during the early stages of the COVID‐19 pandemic.

Methods

A retrospective analysis of general radiology departments across two metropolitan hospitals was performed. Personal radiation monitor exposure reports between January 2019 and December 2020 were analysed. Statistical analysis was conducted using a Mann–Whitney U test when comparing each quarter, from 2019 to 2020. Categorical data were compared using a Chi‐squared test.

Results

Mobile X‐ray use during the pandemic increased approximately 1.7‐fold, with the peak usage observed in September 2020. The mobile imaging rate per month of non‐routine body regions increased from approximately 6.0–7.8%. Reported doses marginally increased during Q2, Q3 and Q4 of 2020 (in comparison to 2019 data), though was not statistically significant (Q2: P = 0.13; Q3: P = 0.31 and Q4 P = 0.32). In Q1, doses marginally decreased and were not statistically significant (P = 0.22).

Conclusion

Increased utilisation and work practice changes had no significant effect on reported staff radiation dose. The average reported dose remained significantly lower than the occupational dose limits for radiation workers of 20 mSv.

Severe Acute Respiratory Syndrome Coronavirus 2 Diagnostic Tests for Border Screening During the Very Early Phase of Coronavirus Disease 2019 Pandemic: A Systematic Review and Meta-Analysis

Diagnosis of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) during border screening among returning residents and prioritized travelers during the early phase of a pandemic can reduce the risk of importation and transmission in the community. This study aimed to compare the accuracy of various SARS-CoV-2 diagnostics and assess their potential utility as border screening for infection and immunity. Systematic literature searches were conducted in six electronic databases for studies reporting SARS-CoV-2 diagnostics (up to April 30, 2020). Meta-analysis and methodological assessment were conducted for all included studies. The performance of the diagnostic tests was evaluated with pooled sensitivity, specificity, and their respective 95% confidence intervals. A total of 5,416 unique studies were identified and 95 studies (at least 29,785 patients/samples) were included. Nucleic acid amplification tests (NAAT) consistently outperformed all other diagnostic methods regardless of the selected viral genes with a pooled sensitivity of 98% and a pooled specificity of 99%. Point-of-care (POC) serology tests had moderately high pooled sensitivity (69%), albeit lower than laboratory-based serology tests (89%), but both had high pooled specificity (96-98%). Serology tests were more sensitive for sampling collected at ≥ 7 days than ≤ 7 days from the disease symptoms onset. POC NAAT and POC serology tests are suitable for detecting infection and immunity against the virus, respectively as border screening. Independent validation in each country is highly encouraged with the preferred choice of diagnostic tool/s.

Automatic coronavirus disease 2019 diagnosis based on chest radiography and deep learning - Success story or dataset bias?

PURPOSE

Over the last 2 years, the artificial intelligence (AI) community has presented several automatic screening tools for coronavirus disease 2019 (COVID-19) based on chest radiography (CXR), with reported accuracies often well over 90%. However, it has been noted that many of these studies have likely suffered from dataset bias, leading to overly optimistic results. The purpose of this study was to thoroughly investigate to what extent biases have influenced the performance of a range of previously proposed and promising convolutional neural networks (CNNs), and to determine what performance can be expected with current CNNs on a realistic and unbiased dataset.

METHODS

Five CNNs for COVID-19 positive/negative classification were implemented for evaluation, namely VGG19, ResNet50, InceptionV3, DenseNet201, and COVID-Net. To perform both internal and cross-dataset evaluations, four datasets were created. The first dataset Valencian Region Medical Image Bank (BIMCV) followed strict reverse transcriptase-polymerase chain reaction (RT-PCR) test criteria and was created from a single reliable open access databank, while the second dataset (COVIDxB8) was created through a combination of six online CXR repositories. The third and fourth datasets were created by combining the opposing classes from the BIMCV and COVIDxB8 datasets. To decrease inter-dataset variability, a pre-processing workflow of resizing, normalization, and histogram equalization were applied to all datasets. Classification performance was evaluated on unseen test sets using precision and recall. A qualitative sanity check was performed by evaluating saliency maps displaying the top 5%, 10%, and 20% most salient segments in the input CXRs, to evaluate whether the CNNs were using relevant information for decision making. In an additional experiment and to further investigate the origin of potential dataset bias, all pixel values outside the lungs were set to zero through automatic lung segmentation before training and testing.

RESULTS

When trained and evaluated on the single online source dataset (BIMCV), the performance of all CNNs is relatively low (precision: 0.65-0.72, recall: 0.59-0.71), but remains relatively consistent during external evaluation (precision: 0.58-0.82, recall: 0.57-0.72). On the contrary, when trained and internally evaluated on the combinatory datasets, all CNNs performed well across all metrics (precision: 0.94-1.00, recall: 0.77-1.00). However, when subsequently evaluated cross-dataset, results dropped substantially (precision: 0.10-0.61, recall: 0.04-0.80). For all datasets, saliency maps revealed the CNNs rarely focus on areas inside the lungs for their decision-making. However, even when setting all pixel values outside the lungs to zero, classification performance does not change and dataset bias remains.

CONCLUSIONS

Results in this study confirm that when trained on a combinatory dataset, CNNs tend to learn the origin of the CXRs rather than the presence or absence of disease, a behavior known as short-cut learning. The bias is shown to originate from differences in overall pixel values rather than embedded text or symbols, despite consistent image pre-processing. When trained on a reliable, and realistic single-source dataset in which non-lung pixels have been masked, CNNs currently show limited sensitivity (<70%) for COVID-19 infection in CXR, questioning their use as a reliable automatic screening tool.

Chest radiological finding of COVID-19 in patients with and without diabetes mellitus: Differences in imaging finding

The pandemic of novel coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Diabetes mellitus is a risk factor for developing severe illness and a leading cause of death in patients with COVID-19. Diabetes can precipitate hyperglycaemic emergencies and cause prolonged hospital admissions. Insulin resistance is thought to cause endothelial dysfunction, alveolar capillary micro-angiopathy and interstitial lung fibrosis through pro-inflammatory pathways. Autopsy studies have also demonstrated the presence of microvascular thrombi in affected sections of lung, which may be associated with diabetes. Chest imaging using x-ray (CXR) and computed tomography (CT) of chest is used to diagnose, assess disease progression and severity in COVID-19. This article reviews current literature regarding chest imaging findings in patients with diabetes affected by COVID-19. A literature search was performed on PubMed. Patients with diabetes infected with SARS-CoV-2 are likely to have more severe infective changes on CXR and CT chest imaging. Severity of airspace consolidation on CXR is associated with higher mortality, particularly in the presence of co-morbidities such as ischaemic heart disease. Poorly controlled diabetes is associated with more severe acute lung injury on CT. However, no association has been identified between poorly-controlled diabetes and the incidence of pulmonary thromboembolism in patients with COVID-19.

Incidental radiological findings suggestive of COVID-19 in asymptomatic patients

Despite routine screening of patients for coronavirus disease 2019 (COVID-19) symptoms and signs at hospital entrances, patients may slip between the cracks and be incidentally discovered to have lung findings that could indicate COVID-19 infection on imaging obtained for other reasons. Multiple case reports and case series have been published to identify the pattern of this highly infectious disease. This article addresses the radiographic findings in different imaging modalities that may be incidentally seen in asymptomatic patients who carry COVID-19. In general, findings of COVID-19 infection may appear in computed tomography (CT), magnetic resonance imaging, positron emission tomography-CT, ultrasound, or plain X-rays that show lung or only apical or basal cuts. The identification of these characteristics by radiologists and clinicians is crucial because this would help in the early recognition of cases so that a rapid treatment protocol can be established, the immediate isolation to reduce community transmission, and the organization of close monitoring. Thus, it is important to both the patient and the physician that these findings are highlighted and reported.

COVID-19 detection from chest x-ray using MobileNet and residual separable convolution block

A newly emerged coronavirus disease affects the social and economical life of the world. This virus mainly infects the respiratory system and spreads with airborne communication. Several countries witness the serious consequences of the COVID-19 pandemic. Early detection of COVID-19 infection is the critical step to survive a patient from death. The chest radiography examination is the fast and cost-effective way for COVID-19 detection. Several researchers have been motivated to automate COVID-19 detection and diagnosis process using chest x-ray images. However, existing models employ deep networks and are suffering from high training time. This work presents transfer learning and residual separable convolution block for COVID-19 detection. The proposed model utilizes pre-trained MobileNet for binary image classification. The proposed residual separable convolution block has improved the performance of basic MobileNet. Two publicly available datasets COVID5K, and COVIDRD have considered for the evaluation of the proposed model. Our proposed model exhibits superior performance than existing state-of-art and pre-trained models with 99% accuracy on both datasets. We have achieved similar performance on noisy datasets. Moreover, the proposed model outperforms existing pre-trained models with less training time and competitive performance than basic MobileNet. Further, our model is suitable for mobile applications as it uses fewer parameters and lesser training time.

Diagnostic Performance of a Deep Learning Model Deployed at a National COVID-19 Screening Facility for Detection of Pneumonia on Frontal Chest Radiographs

(1) Background: Chest radiographs are the mainstay of initial radiological investigation in this COVID-19 pandemic. A reliable and readily deployable artificial intelligence (AI) algorithm that detects pneumonia in COVID-19 suspects can be useful for screening or triage in a hospital setting. This study has a few objectives: first, to develop a model that accurately detects pneumonia in COVID-19 suspects; second, to assess its performance in a real-world clinical setting; and third, by integrating the model with the daily clinical workflow, to measure its impact on report turn-around time. (2) Methods: The model was developed from the NIH Chest-14 open-source dataset and fine-tuned using an internal dataset comprising more than 4000 CXRs acquired in our institution. Input from two senior radiologists provided the reference standard. The model was integrated into daily clinical workflow, prioritising abnormal CXRs for expedited reporting. Area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity were calculated to characterise diagnostic performance. The average time taken by radiologists in reporting the CXRs was compared against the mean baseline time taken prior to implementation of the AI model. (3) Results: 9431 unique CXRs were included in the datasets, of which 1232 were ground truth-labelled positive for pneumonia. On the “live” dataset, the model achieved an AUC of 0.95 (95% confidence interval (CI): 0.92, 0.96) corresponding to a specificity of 97% (95% CI: 0.97, 0.98) and sensitivity of 79% (95% CI: 0.72, 0.84). No statistically significant degradation of diagnostic performance was encountered during clinical deployment, and report turn-around time was reduced by 22%. (4) Conclusion: In real-world clinical deployment, our model expedites reporting of pneumonia in COVID-19 suspects while preserving diagnostic performance without significant model drift.

A review of explainable and interpretable AI with applications in COVID-19 imaging

The development of medical imaging artificial intelligence (AI) systems for evaluating COVID-19 patients has demonstrated potential for improving clinical decision making and assessing patient outcomes during the recent COVID-19 pandemic. These have been applied to many medical imaging tasks, including disease diagnosis and patient prognosis, as well as augmented other clinical measurements to better inform treatment decisions. Because these systems are used in life-or-death decisions, clinical implementation relies on user trust in the AI output. This has caused many developers to utilize explainability techniques in an attempt to help a user understand when an AI algorithm is likely to succeed as well as which cases may be problematic for automatic assessment, thus increasing the potential for rapid clinical translation. AI application to COVID-19 has been marred with controversy recently. This review discusses several aspects of explainable and interpretable AI as it pertains to the evaluation of COVID-19 disease and it can restore trust in AI application to this disease. This includes the identification of common tasks that are relevant to explainable medical imaging AI, an overview of several modern approaches for producing explainable output as appropriate for a given imaging scenario, a discussion of how to evaluate explainable AI, and recommendations for best practices in explainable/interpretable AI implementation. This review will allow developers of AI systems for COVID-19 to quickly understand the basics of several explainable AI techniques and assist in the selection of an approach that is both appropriate and effective for a given scenario.

COVID-19 Prognostic Models: A Pro-con Debate for Machine Learning vs. Traditional Statistics

The SARS-CoV-2 virus, which causes the COVID-19 pandemic, has had an unprecedented impact on healthcare requiring multidisciplinary innovation and novel thinking to minimize impact and improve outcomes. Wide-ranging disciplines have collaborated including diverse clinicians (radiology, microbiology, and critical care), who are working increasingly closely with data-science. This has been leveraged through the democratization of data-science with the increasing availability of easy to access open datasets, tutorials, programming languages, and hardware which makes it significantly easier to create mathematical models. To address the COVID-19 pandemic, such data-science has enabled modeling of the impact of the virus on the population and individuals for diagnostic, prognostic, and epidemiological ends. This has led to two large systematic reviews on this topic that have highlighted the two different ways in which this feat has been attempted: one using classical statistics and the other using more novel machine learning techniques. In this review, we debate the relative strengths and weaknesses of each method toward the specific task of predicting COVID-19 outcomes.

Public Covid-19 X-ray datasets and their impact on model bias - A systematic review of a significant problem

Computer-aided-diagnosis and stratification of COVID-19 based on chest X-ray suffers from weak bias assessment and limited quality-control. Undetected bias induced by inappropriate use of datasets, and improper consideration of confounders prevents the translation of prediction models into clinical practice. By adopting established tools for model evaluation to the task of evaluating datasets, this study provides a systematic appraisal of publicly available COVID-19 chest X-ray datasets, determining their potential use and evaluating potential sources of bias. Only 9 out of more than a hundred identified datasets met at least the criteria for proper assessment of risk of bias and could be analysed in detail. Remarkably most of the datasets utilised in 201 papers published in peer-reviewed journals, are not among these 9 datasets, thus leading to models with high risk of bias. This raises concerns about the suitability of such models for clinical use. This systematic review highlights the limited description of datasets employed for modelling and aids researchers to select the most suitable datasets for their task.

Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence

Artificial intelligence provides a promising solution for streamlining COVID-19 diagnoses; however, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalized model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the artificial intelligence (AI) model can be distributedly trained and independently executed at each host institution under a federated learning framework without data sharing. Here we show that our federated learning framework model considerably outperformed all of the local models (with a test sensitivity/specificity of 0.973/0.951 in China and 0.730/0.942 in the United Kingdom), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals without the federated learning framework) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans from 3,336 patients collected from 23 hospitals located in China and the United Kingdom. Collectively, our work advanced the prospects of utilizing federated learning for privacy-preserving AI in digital health.

Effectiveness of fever tent setup in Covid-19 pandemic – from radiology's perspective

Introduction

This paper describes our experience in setting up a dedicated imaging facility within a temporary fever tentage in an acute tertiary hospital in Singapore during the coronavirus disease 2019 (COVID-19) pandemic. We review the effectiveness of the setup and its role from the radiological perspective in detail.

Methods

The dedicated imaging facility within the temporary fever tentage was equipped with a computer-on-wheels (COWs) to access patients’ medical records and a portable x-ray machine to allow for a smooth workflow. Radiation dose measurements were acquired around the imaging facility using phantoms and dosimeters to ensure radiation safety.

Results

Due to its rapid nature and availability as a screening tool, chest x-ray (CXR) is the most widely used imaging modality during the COVID-19 pandemic. Our dedicated fever tent setup minimizes possible in-hospital transmission between both patients and staff and provides a more streamlined workflow to tackle the high workload. It allowed us to reduce the time required for each radiograph, providing timely imaging services and radiological reports for expedient clinical screening.

Discussion

The close collaboration between Radiology and Emergency Departments in setting up the fever tentage is a crucial tool in managing the COVID-19 pandemic. The fever tentage imaging facility is a highly effective tool, providing the means to handle the increased patient load in a streamlined and safe manner during a pandemic.

Conclusion

This paper provides insights and guidelines in setting up a dedicated imaging service within the fever tent for future infectious disease outbreak contingency plans.

An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis

BACKGROUND

The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage.

FINDINGS

The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage.

CONCLUSION

The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.

Dentists deployed: an insider's perspective of life on the NHS front line

The COVID-19 pandemic has stretched and overburdened healthcare services within the UK. This national crisis has led to the widespread redeployment of healthcare workers and reorganization of services throughout the NHS in the UK. The flexible and altruistic nature of healthcare workers has been inspiring, and central in the UK's response to the COVID-19 pandemic. This article describes the 'first-hand' experience of a secondary care dentist, highlighting the redeployment journey to the emergency department (ED) of a major trauma hospital in the North-West of England during the first wave of the COVID-19 pandemic.

AANet: Adaptive Attention Network for COVID-19 Detection From Chest X-Ray Images

Accurate and rapid diagnosis of COVID-19 using chest X-ray (CXR) plays an important role in large-scale screening and epidemic prevention. Unfortunately, identifying COVID-19 from the CXR images is challenging as its radiographic features have a variety of complex appearances, such as widespread ground-glass opacities and diffuse reticular-nodular opacities. To solve this problem, we propose an adaptive attention network (AANet), which can adaptively extract the characteristic radiographic findings of COVID-19 from the infected regions with various scales and appearances. It contains two main components: an adaptive deformable ResNet and an attention-based encoder. First, the adaptive deformable ResNet, which adaptively adjusts the receptive fields to learn feature representations according to the shape and scale of infected regions, is designed to handle the diversity of COVID-19 radiographic features. Then, the attention-based encoder is developed to model nonlocal interactions by self-attention mechanism, which learns rich context information to detect the lesion regions with complex shapes. Extensive experiments on several public datasets show that the proposed AANet outperforms state-of-the-art methods.

Experiences of diagnostic radiographers through the Covid-19 pandemic

Introduction

Diagnostic Radiography plays a major role in the diagnosis and management of patients with Covid-19. This has seen an increase in the demand for imaging services, putting pressure on the workforce. Diagnostic radiographers, as with many other healthcare professions, have been on the frontline, dealing with an unprecedented situation. This research aimed to explore the experience of diagnostic radiographers working clinically during the Covid-19 pandemic.

Methods

Influenced by interpretative phenomenology, this study explored the experiences of diagnostic radiographers using virtual focus group interviews as a method of data collection.

Results

Data were analysed independently by four researchers and five themes emerged from the data. Adapting to new ways of working, feelings and emotions, support mechanisms, self-protection and resilience, and professional recognition.

Conclusion

The adaptability of radiographers came across strongly in this study. Anxieties attributed to the provision of personal protective equipment (PPE), fear of contracting the virus and spreading it to family members were evident. The resilience of radiographers working throughout this pandemic came across strongly throughout this study. A significant factor for coping has been peer support from colleagues within the workplace. The study highlighted the lack of understanding of the role of the radiographer and how the profession is perceived by other health care professionals.

Implications for practice

This study highlights the importance of interprofessional working and that further work is required in the promotion of the profession.

One year of COVID-19 pandemic: what we Radiologists have learned about imaging

BACKGROUND

 Since its outbreak in December 2019, Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has infected more than 151 million people worldwide. More than 3.1 million have died from Coronavirus Disease 2019 (COVID-19), the illness caused by SARS-CoV-2. The virus affects mainly the upper respiratory tract and the lungs causing pneumonias of varying severity. Moreover, via direct and indirect pathogenetic mechanisms, SARS-CoV-2 may lead to a variety of extrapulmonary as well as vascular manifestations.

METHODS

 Based on a systematic literature search via PubMed, original research articles, meta-analyses, reviews, and case reports representing the current scientific knowledge regarding diagnostic imaging of COVID-19 were selected. Focusing on the imaging appearance of pulmonary and extrapulmonary manifestations as well as indications for imaging, these data were summarized in the present review article and correlated with basic pathophysiologic mechanisms.

RESULTS AND CONCLUSION

 Typical signs of COVID-19 pneumonia are multifocal, mostly bilateral, rounded, polycyclic or geographic ground-glass opacities and/or consolidations with mainly peripheral distribution. In severe cases, peribronchovascular lung zones are affected as well. Other typical signs are the "crazy paving" pattern and the halo and reversed halo (the latter two being less common). Venous thromboembolism (and pulmonary embolism in particular) is the most frequent vascular complication of COVID-19. However, arterial thromboembolic events like ischemic strokes, myocardial infarctions, and systemic arterial emboli also occur at higher rates. The most frequent extrapulmonary organ manifestations of COVID-19 affect the central nervous system, the heart, the hepatobiliary system, and the gastrointestinal tract. Usually, they can be visualized in imaging studies as well. The most important imaging modality for COVID-19 is chest CT. Its main purpose is not to make the primary diagnosis, but to differentiate COVID-19 from other (pulmonary) pathologies, to estimate disease severity, and to detect concomitant diseases and complications.

KEY POINTS

  · Typical signs of COVID-19 pneumonia are multifocal, mostly peripheral ground-glass opacities/consolidations.. · Imaging facilitates differential diagnosis, estimation of disease severity, and detection of complications.. · Venous thromboembolism (especially pulmonary embolism) is the predominant vascular complication of COVID-19.. · Arterial thromboembolism (e. g., ischemic strokes, myocardial infarctions) occurs more frequently as well.. · The most common extrapulmonary manifestations affect the brain, heart, hepatobiliary system, and gastrointestinal system..

CITATION FORMAT

· Gross A, Albrecht T. One year of COVID-19 pandemic: what we Radiologists have learned about imaging. Fortschr Röntgenstr 2021; DOI: 10.1055/a-1522-3155.

Development and prospective validation of COVID-19 chest X-ray screening model for patients attending emergency departments

Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation. In this work we develop an AI algorithm, CovIx, to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid.

Role of Chest X-Ray in Coronavirus Disease and Correlation of Radiological Features with Clinical Outcomes in Indian Patients

Recent literature has reported that radiological features of coronavirus disease (COVID-19) patients are influenced by computed tomography. This study aimed to assess the characteristic chest X-ray features of COVID-19 and correlate them with clinical outcomes of patients. This retrospective study included 120 COVID-19 patients. Baseline chest X-rays and serial chest X-rays were reviewed. A severity index in the form of maximum radiological assessment of lung edema (RALE) score was calculated for each lung, and scores of both the lungs were summed to obtain a final score. The mean ± standard deviation (SD) and frequency (%) were determined, and an unpaired t test, Spearman's rank correlation coefficient, and logistic regression analyses were performed for statistical analyses. Among 120 COVID-19 patients, 74 (61.67%) and 46 (38.33%) were males and females, respectively; 64 patients (53.33%) had ground-glass opacities (GGO), 55 (45.83%) had consolidation, and 38 (31.67%) had reticular-nodular opacities, with lower zone distribution (50%) and peripheral distribution (41.67%). Baseline chest X-ray showed a sensitivity of 63.3% in diagnosing typical findings of SARS-CoV-2 pneumonia. The maximum RALE score was 2.13 ± 1.9 in hospitalized patients and 0.57 ± 0.77 in discharged patients (p value <0.0001). Spearman's rank correlation coefficient between maximum RALE score and clinical outcome parameters was as follows: age, 0.721 (p value <0.00001); >10 days of hospital stay, 0.5478 (p value <0.05); ≤10 days of hospital stay, 0.5384 (p value <0.0001); discharged patients, 0.5433 (p value <0.0001); and death, 0.6182 (p value = 0.0568). The logistic regression analysis revealed that maximum RALE scores (0.0932 [0.024-0.367]), (10.730 [2.727-42.206]), (1.258 [0.990-1.598]), and (0.794 [0.625-1.009]) predicted discharge, death, >10 days of hospital stay, and ≤10 days of hospital stay, respectively. The study findings suggested that the RALE score can quantify the extent of COVID-19 and can predict the prognosis of patients.

Covid-19 detection via deep neural network and occlusion sensitivity maps

Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue, we propose a deep learning architecture called CovidNet which requires a relatively smaller number of parameters. CovidNet accepts grayscale images as inputs and is suitable for training with limited training dataset. Experimental results show that CovidNet outperforms other state-of-the-art deep learning models for Covid-19 detection.