The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society

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.

Radio-Histological Correlation of Lung Features in Severe COVID-19 Through CT-Scan and Lung Ultrasound Evaluation

Background

Patients with coronavirus disease 2019 (COVID-19) can develop severe bilateral pneumonia leading to respiratory failure. Lung histological samples were scarce due to the high risk of contamination during autopsies. We aimed to correlate histological COVID-19 features with radiological findings through lung ultrasound (LU)-guided postmortem core needle biopsies (CNBs) and computerized tomography (CT) scans.

Methodology

We performed an observational prospective study, including 30 consecutive patients with severe COVID-19. The thorax was divided into 12 explorations regions to correlate LU and CT-scan features. Histological findings were also related to radiological features through CNBs.

Results

Mean age was 62.56 ± 13.27 years old, with 96.7% male patients. Postmortem LU-guided CNBs were performed in 13 patients. Thirty patients were evaluated with both thoracic LU and chest CT scan, representing a total of 279 thoracic regions explored. The most frequent LU finding was B2-lines (49.1%). The most CT-scan finding was ground-glass opacity (GGO, 29%). Pathological CT-scan findings were commonly observed when B2-lines or C-lines were identified through LU (positive predictive value, PPV, 87.1%). Twenty-five postmortem echo-guided histological samples were obtained from 12 patients. Histological samples showed diffuse alveolar damage (DAD) (75%) and chronic interstitial inflammation (25%). The observed DAD was heterogeneous, showing multiple evolving patterns of damage, including exudative (33.3%), fibrotic (33.3%), and organizing (8.3%) phases. In those patients with acute or exudative pattern, two lesions were distinguished: classic hyaline membrane; fibrin "plug" in alveolar space (acute fibrinous organizing pneumonia, AFOP). C-profile was described in 33.3% and presented histological signs of DAD and lung fibrosis. The predominant findings were collagen deposition (50%) and AFOP (50%). B2-lines were identified in 66.7%; the presence of hyaline membrane was the predominant finding (37.5%), then organizing pneumonia (12.5%) and fibrosis (37.5%). No A-lines or B1-lines were observed in these patients.

Conclusion

LU B2-lines and C-profile are predominantly identified in patients with severe COVID-19 with respiratory worsening, which correspond to different CT patterns and histological findings of DAD and lung fibrosis.

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.

Mortality Prediction of COVID-19 Patients Using Radiomic and Neural Network Features Extracted from a Wide Chest X-ray Sample Size: A Robust Approach for Different Medical Imbalanced Scenarios

Aim: The aim of this study was to develop robust prognostic models for mortality prediction of COVID-19 patients, applicable to different sets of real scenarios, using radiomic and neural network features extracted from chest X-rays (CXRs) with a certified and commercially available software. Methods: 1816 patients from 5 different hospitals in the Province of Reggio Emilia were included in the study. Overall, 201 radiomic features and 16 neural network features were extracted from each COVID-19 patient’s radiography. The initial dataset was balanced to train the classifiers with the same number of dead and survived patients, randomly selected. The pipeline had three main parts: balancing procedure; three-step feature selection; and mortality prediction with radiomic features through three machine learning (ML) classification models: AdaBoost (ADA), Quadratic Discriminant Analysis (QDA) and Random Forest (RF). Five evaluation metrics were computed on the test samples. The performance for death prediction was validated on both a balanced dataset (Case 1) and an imbalanced dataset (Case 2). Results: accuracy (ACC), area under the ROC-curve (AUC) and sensitivity (SENS) for the best classifier were, respectively, 0.72 ± 0.01, 0.82 ± 0.02 and 0.84 ± 0.04 for Case 1 and 0.70 ± 0.04, 0.79 ± 0.03 and 0.76 ± 0.06 for Case 2. These results show that the prediction of COVID-19 mortality is robust in a different set of scenarios. Conclusions: Our large and varied dataset made it possible to train ML algorithms to predict COVID-19 mortality using radiomic and neural network features of CXRs.

TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design for Detection of Tuberculosis Cases From Chest X-Ray Images

Tuberculosis (TB) remains a global health problem, and is the leading cause of death from an infectious disease. A crucial step in the treatment of tuberculosis is screening high risk populations and the early detection of the disease, with chest x-ray (CXR) imaging being the most widely-used imaging modality. As such, there has been significant recent interest in artificial intelligence-based TB screening solutions for use in resource-limited scenarios where there is a lack of trained healthcare workers with expertise in CXR interpretation. Motivated by this pressing need and the recent recommendation by the World Health Organization (WHO) for the use of computer-aided diagnosis of TB in place of a human reader, we introduce TB-Net, a self-attention deep convolutional neural network tailored for TB case screening. We used CXR data from a multi-national patient cohort to train and test our models. A machine-driven design exploration approach leveraging generative synthesis was used to build a highly customized deep neural network architecture with attention condensers. We conducted an explainability-driven performance validation process to validate TB-Net's decision-making behavior. Experiments on CXR data from a multi-national patient cohort showed that the proposed TB-Net is able to achieve accuracy/sensitivity/specificity of 99.86/100.0/99.71%. Radiologist validation was conducted on select cases by two board-certified radiologists with over 10 and 19 years of experience, respectively, and showed consistency between radiologist interpretation and critical factors leveraged by TB-Net for TB case detection for the case where radiologists identified anomalies. The proposed TB-Net not only achieves high tuberculosis case detection performance in terms of sensitivity and specificity, but also leverages clinically relevant critical factors in its decision making process. While not a production-ready solution, we hope that the open-source release of TB-Net as part of the COVID-Net initiative will support researchers, clinicians, and citizen data scientists in advancing this field in the fight against this global public health crisis.

Deep Learning Applied to Chest Radiograph Classification—A COVID-19 Pneumonia Experience

Due to the recent COVID-19 pandemic, a large number of reports present deep learning algorithms that support the detection of pneumonia caused by COVID-19 in chest radiographs. Few studies have provided the complete source code, limiting testing and reproducibility on different datasets. This work presents Cimatec_XCOV19, a novel deep learning system inspired by the Inception-V3 architecture that is able to (i) support the identification of abnormal chest radiographs and (ii) classify the abnormal radiographs as suggestive of COVID-19. The training dataset has 44,031 images with 2917 COVID-19 cases, one of the largest datasets in recent literature. We organized and published an external validation dataset of 1158 chest radiographs from a Brazilian hospital. Two experienced radiologists independently evaluated the radiographs. The Cimatec_XCOV19 algorithm obtained a sensitivity of 0.85, specificity of 0.82, and AUC ROC of 0.93. We compared the AUC ROC of our algorithm with a well-known public solution and did not find a statistically relevant difference between both performances. We provide full access to the code and the test dataset, enabling this work to be used as a tool for supporting the fast screening of COVID-19 on chest X-ray exams, serving as a reference for educators, and supporting further algorithm enhancements.

COVID-CXNet: Detecting COVID-19 in frontal chest X-ray images using deep learning

One of the primary clinical observations for screening the novel coronavirus is capturing a chest x-ray image. In most patients, a chest x-ray contains abnormalities, such as consolidation, resulting from COVID-19 viral pneumonia. In this study, research is conducted on efficiently detecting imaging features of this type of pneumonia using deep convolutional neural networks in a large dataset. It is demonstrated that simple models, alongside the majority of pretrained networks in the literature, focus on irrelevant features for decision-making. In this paper, numerous chest x-ray images from several sources are collected, and one of the largest publicly accessible datasets is prepared. Finally, using the transfer learning paradigm, the well-known CheXNet model is utilized to develop COVID-CXNet. This powerful model is capable of detecting the novel coronavirus pneumonia based on relevant and meaningful features with precise localization. COVID-CXNet is a step towards a fully automated and robust COVID-19 detection system.

Detecting COVID-19 from chest computed tomography scans using AI-driven android application

The COVID-19 (coronavirus disease 2019) pandemic affected more than 186 million people with over 4 million deaths worldwide by June 2021. The magnitude of which has strained global healthcare systems. Chest Computed Tomography (CT) scans have a potential role in the diagnosis and prognostication of COVID-19. Designing a diagnostic system, which is cost-efficient and convenient to operate on resource-constrained devices like mobile phones would enhance the clinical usage of chest CT scans and provide swift, mobile, and accessible diagnostic capabilities. This work proposes developing a novel Android application that detects COVID-19 infection from chest CT scans using a highly efficient and accurate deep learning algorithm. It further creates an attention heatmap, augmented on the segmented lung parenchyma region in the chest CT scans which shows the regions of infection in the lungs through an algorithm developed as a part of this work, and verified through radiologists. We propose a novel selection approach combined with multi-threading for a faster generation of heatmaps on a Mobile Device, which reduces the processing time by about 93%. The neural network trained to detect COVID-19 in this work is tested with a F1 score and accuracy, both of 99.58% and sensitivity of 99.69%, which is better than most of the results in the domain of COVID diagnosis from CT scans. This work will be beneficial in high-volume practices and help doctors triage patients for the early diagnosis of COVID-19 quickly and efficiently.

AI-driven quantification of ground glass opacities in lungs of COVID-19 patients using 3D computed tomography imaging

Objectives

Ground-glass opacity (GGO)—a hazy, gray appearing density on computed tomography (CT) of lungs—is one of the hallmark features of SARS-CoV-2 in COVID-19 patients. This AI-driven study is focused on segmentation, morphology, and distribution patterns of GGOs.

Method

We use an AI-driven unsupervised machine learning approach called PointNet++ to detect and quantify GGOs in CT scans of COVID-19 patients and to assess the severity of the disease. We have conducted our study on the “MosMedData”, which contains CT lung scans of 1110 patients with or without COVID-19 infections. We quantify the morphologies of GGOs using Minkowski tensors and compute the abnormality score of individual regions of segmented lung and GGOs.

Results

PointNet++ detects GGOs with the highest evaluation accuracy (98%), average class accuracy (95%), and intersection over union (92%) using only a fraction of 3D data. On average, the shapes of GGOs in the COVID-19 datasets deviate from sphericity by 15% and anisotropies in GGOs are dominated by dipole and hexapole components. These anisotropies may help to quantitatively delineate GGOs of COVID-19 from other lung diseases.

Conclusion

The PointNet++ and the Minkowski tensor based morphological approach together with abnormality analysis will provide radiologists and clinicians with a valuable set of tools when interpreting CT lung scans of COVID-19 patients. Implementation would be particularly useful in countries severely devastated by COVID-19 such as India, where the number of cases has outstripped available resources creating delays or even breakdowns in patient care. This AI-driven approach synthesizes both the unique GGO distribution pattern and severity of the disease to allow for more efficient diagnosis, triaging and conservation of limited resources.

Post-acute COVID-19 syndrome

Infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is responsible for the coronavirus disease 2019 (COVID-19) pandemic that has resulted in millions of deaths and a major strain on health systems worldwide. Medical treatments for COVID-19 (anticoagulants, corticosteroids, anti-inflammatory drugs, oxygenation therapy and ventilation) and vaccination have improved patient outcomes. The majority of patients will recover spontaneously or after acute-phase management, but clinicians are now faced with long-term complications of COVID-19 including a large variety of symptoms, defined as "post-acute COVID-19 syndrome". Most studies have focused on patients hospitalised for severe COVID-19, but acute COVID-19 syndrome is not restricted to these patients and exists in outpatients. Given the diversity of symptoms and the high prevalence of persistent symptoms, the management of these patients requires a multidisciplinary team approach, which will result in the consumption of large amounts of health resources in the coming months. In this review, we discuss the presentation, prevalence, pathophysiology and evolution of respiratory complications and other organ-related injuries associated with post-acute COVID-19 syndrome.

Spectrum of Typical and Atypical Pulmonary CT Imaging Findings of COVID-19 Infection: A Retrospective Study

Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The first known case was identified in Wuhan, China, in December 2019. It was declared a public health emergency by WHO in January 2020. The definitive diagnostic test for COVID-19 is a real time polymerase chain reaction test (RT-PCR) which is highly specific, but sensitivity is variable. COVID-19 typically presents clinically with respiratory and systemic symptoms. The majority of the infected patients are asymptomatic during the course of the disease, which we have not included in our study. Imaging findings on high-resolution computed tomography (HRCT) chest are important to diagnose the disease in early stage, for treatment planning and to predict the patient prognosis. The purpose of our study was to characterize typical and atypical pulmonary and extra-pulmonary HRCT findings in patients with COVID-19 infection and to help in the management of patients. 

In this retrospective study, we have included 70 patients who had undergone HRCT examination of the chest in the Radiodiagnosis Department, Maharishi Markandeshwar Medical College, Kumarhatti, Solan, Himachal Pradesh, India. The HRCT findings of the chest of these patients in the study will be evaluated and data will be statistically analyzed.

Chest imaging in pregnant patients with COVID-19: Recommendations, justification, and optimization

Evaluation of COVID-19 related complication is challenging in pregnancy, due to concerns about ionizing radiation risk to mother and the fetus. Although there are instances when diagnostic imaging is clinically warranted for COVID-19 evaluation despite the minimal risks of radiation exposure, often there are concerns raised by the patients and sometimes by the attending physicians. This article reviews the current recommendations on indications of chest imaging in pregnant patients with COVID-19, the dose optimization strategies, and the risks related to imaging exposure during pregnancy. In clinical practice, these imaging strategies are key in addressing the complex obstetrical complications associated with COVID-19 pneumonia.

Cumulative Radiation Exposure in Covid-19 Patients Admitted to the Intensive Care Unit

Medical imaging plays a major role in coronavirus disease-2019 (COVID-19) patient diagnosis and management. However, the radiation dose received from medical procedures by these patients has been poorly investigated. We aimed to estimate the cumulative effective dose (CED) related to medical exposure in COVID-19 patients admitted to the intensive care unit (ICU) in comparison to the usual critically ill patients. We designed a descriptive cohort study including 90 successive ICU COVID-19 patients admitted between March and May 2020 and 90 successive non-COVID-19 patients admitted between March and May 2019. In this study, the CED resulting from all radiological examinations was calculated and clinical characteristics predictive of higher exposure risk identified. The number of radiological examinations was 12.0 (5.0–26.0) [median (interquartile range) in COVID-19 vs.4.0 (2.0–8.0) in non-COVID-19 patient (P &lt; 0.001)]. The CED during a four-month period was 4.2 mSv (1.9–11.2) in the COVID-19 vs. 1.2 mSv (0.13–6.19) in the non-COVID-19 patients (P &lt; 0.001). In the survivors, the CED in COVID-19 vs. non-COVID-19 patients was ≥100 mSv in 3% vs. 0%, 10–100 mSv in 23% vs. 15%, 1–10 mSv in 56% vs. 30% and &lt;1 mSv in 18% vs. 55%. The CED (P &lt; 0.001) and CED per ICU hospitalization day (P = 0.004) were significantly higher in COVID-19 than non-COVID-19 patients. The CED correlated significantly with the hospitalization duration (r = 0.45, P &lt; 0.001) and the number of conventional radiological examinations (r = 0.8, P &lt; 0.001). To conclude, more radiological examinations were performed in critically ill COVID-19 patients than non-COVID-19 patients resulting in higher CED. In COVID-19 patients, contribution of strategies to limit CED should be investigated in the future.

Radiological findings in low-dose CT for COVID-19 pneumonia in 182 patients: Correlation of signs and severity with patient outcome

To characterize computed tomography (CT) findings of coronavirus disease 2019 (COVID-19) pneumonia and their value in outcome prediction.Chest CTs of 182 patients with a confirmed diagnosis of COVID-19 infection by real-time reverse transcription polymerase chain reaction were evaluated for the presence of CT-abnormalities and their frequency. Regarding the patient outcome each patient was categorized in 5 progressive stages and the duration of hospitalization was determined. Regression analysis was performed to find which CT findings are predictive for patient outcome and to assess prognostic factors for the hospitalization duration.Multivariate statistical analysis confirmed a higher age (OR = 1.023, P  =  .025), a higher total visual severity score (OR = 1.038, P  =  .002) and the presence of crazy paving (OR = 2.160, P  =  .034) as predictive parameters for patient outcome. A higher total visual severity score (+0.134 days; P  =  .012) and the presence of pleural effusion (+13.985 days, P  =  0.005) were predictive parameters for a longer hospitalization duration. Moreover, a higher sensitivity of chest CT (false negatives 10.4%; true positives 78.6%) in comparison to real-time reverse transcription polymerase chain reaction was obtained.An increasing percentage of lung opacity as well as the presence of crazy paving and a higher age are associated with a worse patient outcome. The presence of a higher total visual severity score and pleural effusion are significant predictors for a longer hospitalization duration. These results are underscoring the value of chest CT as a diagnostic and prognostic tool in the pandemic outbreak of COVID-19, to facilitate fast detection and to preserve the limited (intensive) care capacity only for the most vulnerable patients.

Relationship of Computed Tomography Severity Score With Patient Characteristics and Survival in Hypoxemic COVID-19 Patients

Background

Computed tomography (CT) scans and CT severity scores (CTSS) are widely used to assess the severity and prognosis in coronavirus disease 2019 (COVID-19). CTSS has performed well as a predictor in differentiating severe from non-severe cases. However, it is not known if CTSS performs similarly in hospitalized severe cases with hypoxia at admission.

Methods

We conducted a retrospective comparative study at a COVID-care center from Western India between 25th April and 31st May 2021, enrolling all consecutive severe COVID-19 patients with hypoxemia (peripheral oxygen saturation < 94%). Neutrophil-lymphocyte ratio (NLR), C-reactive protein (CRP), interleukin-6 (IL-6), lactate dehydrogenase (LDH), D-dimer, ferritin, and CT thorax were done within 24h of admission before being initiated on any anti-COVID-19 therapy. CTSS was calculated by visual assessment and categorized into three severity categories and was correlated with laboratory markers and overall survival (OS). Statistical analysis was done using John's Macintosh Project (JMP) 15.0.0 ver. 3.0.0 (Cary, North Carolina).

Results

The median age of the study population (n-298) was 59 years (24-95) with a male preponderance (61.41%, n=183). The 15 and 30-day survivals were 67.64% and 59.90%, respectively. CTSS did not correlate with age, gender, time from vaccination, symptoms, or comorbidities but had a significant though weak correlation with LDH (p=0.009), D-dimer (p=0.006), and NLR (p=0.019). Comparing demographic and laboratory aspects using CT severity categories, only NLR (p=0.0146) and D-dimer (p=0.0006) had significant differences. The 15d-OS of mild, moderate, and severe CT categories were 88.62%, 70.39%, and 52.62%, respectively, while 30d-OS of three categories were 59.08%, 63.96%, and 49.12%, respectively.

Conclusion

Among hospitalized severe COVID-19 patients with hypoxemia at admission, CT severity categories correlate well with outcomes but not inflammatory markers at admission.

[Korean Clinical Imaging Guidelines for Justification of Diagnostic Imaging Study for COVID-19]

To develop Korean coronavirus disease (COVID-19) chest imaging justification guidelines, eight key questions were selected and the following recommendations were made with the evidence-based clinical imaging guideline adaptation methodology. It is appropriate not to use chest imaging tests (chest radiograph or CT) for the diagnosis of COVID-19 in asymptomatic patients. If reverse transcription-polymerase chain reaction testing is not available or if results are delayed or are initially negative in the presence of symptoms suggestive of COVID-19, chest imaging tests may be considered. In addition to clinical evaluations and laboratory tests, chest imaging may be contemplated to determine hospital admission for asymptomatic or mildly symptomatic unhospitalized patients with confirmed COVID-19. In hospitalized patients with confirmed COVID-19, chest imaging may be advised to determine or modify treatment alternatives. CT angiography may be considered if hemoptysis or pulmonary embolism is clinically suspected in a patient with confirmed COVID-19. For COVID-19 patients with improved symptoms, chest imaging is not recommended to make decisions regarding hospital discharge. For patients with functional impairment after recovery from COVID-19, chest imaging may be considered to distinguish a potentially treatable disease.

COVID-19 Radiology Preparedness, Challenges & Opportunities: Responses From 18 Countries

PURPOSE

Radiology departments around the world have been faced with the challenge to adapt, and recover to the COVID-19 pandemic. This study is part of a worldwide survey of radiologists' responses to COVID-19 in 18 different countries in Africa, Asia, Europe, and Latin America. The purpose of this study is to analyze the changes made in international radiology departments and practices in response to the pandemic.

METHODS

The 18-item survey was sent via email from April to May 2020 to radiologists in Africa, Asia, Europe, and Latin America to assess their response to COVID-19. Our survey included questions regarding imaging, workforce adjustments, testing availability, staff and patient safety, research and education, and infrastructure availability.

RESULTS

Twenty-eight survey responses were reviewed. Of the 28 respondents, 42.9% have shortages of infrastructure and 78.6% responded that COVID-19 testing was available. Regarding the use of Chest CT in COVID-19 patients, 28.6% respondents used Chest CT as screening for COVID-19. For staff safety, interventions included encouraging use of masks in patient encounters, social distancing and PPE training. To cope with their education and research mission, radiology departments are doing online lectures, reducing the number of residents in rotations, and postponing any non-urgent activities.

CONCLUSION

In conclusion, there are disparities in infrastructure, research, and educational initiatives during COVID-19 which also provides opportunity for the global radiology community to work together on these issues.

Automated COVID-19 diagnosis and prognosis with medical imaging and who is publishing: a systematic review

OBJECTIVES

 To conduct a systematic survey of published techniques for automated diagnosis and prognosis of COVID-19 diseases using medical imaging, assessing the validity of reported performance and investigating the proposed clinical use-case. To conduct a scoping review into the authors publishing such work.

METHODS

 The Scopus database was queried and studies were screened for article type, and minimum source normalized impact per paper and citations, before manual relevance assessment and a bias assessment derived from a subset of the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). The number of failures of the full CLAIM was adopted as a surrogate for risk-of-bias. Methodological and performance measurements were collected from each technique. Each study was assessed by one author. Comparisons were evaluated for significance with a two-sided independent t-test.

FINDINGS

 Of 1002 studies identified, 390 remained after screening and 81 after relevance and bias exclusion. The ratio of exclusion for bias was 71%, indicative of a high level of bias in the field. The mean number of CLAIM failures per study was 8.3 ± 3.9 [1,17] (mean ± standard deviation [min,max]). 58% of methods performed diagnosis versus 31% prognosis. Of the diagnostic methods, 38% differentiated COVID-19 from healthy controls. For diagnostic techniques, area under the receiver operating curve (AUC) = 0.924 ± 0.074 [0.810,0.991] and accuracy = 91.7% ± 6.4 [79.0,99.0]. For prognostic techniques, AUC = 0.836 ± 0.126 [0.605,0.980] and accuracy = 78.4% ± 9.4 [62.5,98.0]. CLAIM failures did not correlate with performance, providing confidence that the highest results were not driven by biased papers. Deep learning techniques reported higher AUC (p < 0.05) and accuracy (p < 0.05), but no difference in CLAIM failures was identified.

INTERPRETATION

 A majority of papers focus on the less clinically impactful diagnosis task, contrasted with prognosis, with a significant portion performing a clinically unnecessary task of differentiating COVID-19 from healthy. Authors should consider the clinical scenario in which their work would be deployed when developing techniques. Nevertheless, studies report superb performance in a potentially impactful application. Future work is warranted in translating techniques into clinical tools.

COVID-19 pneumonia detected by [18F]FDG PET/MRI: a case with negative antigen test and chest X-ray results

Since the outbreak of pneumonia caused by a novel coronavirus (SARS-CoV-2) named Coronavirus disease 2019 (COVID-19) in China, researchers have reported the fluorodeoxyglucose positron emission tomography/CT (FDG PET/CT) manifestations of COVID-19 infection. We present a 37-year-old female with early-stage cervical cancer and fever without a focus who had negative SARS-CoV-2 antigen test and chest X-ray results. FDG PET/MRI performed for preoperative evaluation incidentally detected pneumonia showing high FDG uptake and diffusion-weighted imaging signals in right lung base. She retested positive for SARS-CoV-2 and was diagnosed as having COVID-19 pneumonia. Whole-body PET/MRI can provide multi functional images and could be useful for evaluating the pathophysiology of COVID-19.

Investigating of the role of CT scan for cancer patients during the first wave of COVID-19 pandemic

Introduction

Amidst this current COVID-19 pandemic, we undertook this systematic review to determine the role of medical imaging, with a special emphasis on computed tomography (CT), on guiding the care and management of oncologic patients.

Material and Methods

Study selection focused on articles from 01/02/2020 to 04/23/2020. After removal of irrelevant articles, all systematic or non-systematic reviews, comments, correspondence, editorials, guidelines and meta-analysis and case reports with less than 5 patients were also excluded. Full-text articles of eligible publications were reviewed to select all imaging-based publications, and the existence or not of an oncologic population was reported for each publication. Two independent reviewers collected the following information: ( 1) General publication data; (2) Study design characteristics; (3) Demographic, clinical and pathological variables with percentage of cancer patients if available; (4) Imaging performances. The sensitivity and specificity of chest CT (C-CT) were pooled separately using a random-effects model. The positive predictive value (PPV) and negative predictive value (NPV) of C-CT as a test was estimated for a wide range of disease prevalence rates.

Results

A total of 106 publications were fully reviewed. Among them, 96 were identified to have extractable data for a two-by-two contingency table for CT performance. At the end, 53 studies (including 6 that used two different populations) were included in diagnosis accuracy analysis (N = 59). We identified 53 studies totaling 11,352 patients for whom the sensitivity (95CI) was 0.886 (0.880; 0.894), while specificity remained low: in 93% of cases (55/59), specificity was ≤ 0.5. Among all the 106 reviewed studies, only 7 studies included oncologic patients and were included in the final analysis for C-CT performances. The percentage of patients with cancer in these studies was 0.3% (34/11352 patients), lower than the global prevalence of cancer. Among all these studies, only 1 (0.9%, 1/106) reported performance specifically in a cohort of cancer patients, but it however only reported true positives.

Discussion

There is a concerning lack of COVID-19 studies involving oncologic patients, showing there is a real need for further investigation and evaluation of the performance of the different medical imaging modalities in this specific patient population.

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 Pneumonia and Lung Cancer: A Challenge for the Radiological Review of the Main Radiological Features, Differential Diagnosis and Overlapping Pathologies

The COVID-19 pneumonia pandemic represents the most severe health emergency of the 21st century and has been monopolizing health systems’ economic and human resources world-wide. Cancer patients have been suffering from the health systems’ COVID-19 priority management with evidence of late diagnosis leading to patients’ poor prognosis and late medical treatment. The radiologist plays a pivotal role as CT represents a non-invasive radiological technique which may help to identify possible overlap and differential diagnosis between COVID-19 pneumonia and lung cancer, which represents the most frequent cancer histology in COVID-19 patients. Our aims are: to present the main CT features of COVID-19 pneumonia; to provide the main differential diagnosis with lung cancer, chemotherapy-, immunotherapy-, and radiotherapy-induced lung disease; and to suggest practical tips and key radiological elements to identify possible overlap between COVID-19 pneumonia and lung cancer. Despite similarities or overlapping findings, the combination of clinics and some specific radiological findings, which are also identified by comparison with previous and follow-up CT scans, may guide differential diagnosis. It is crucial to search for typical COVID-19 pneumonia phase progression and typical radiological features on HRTC. The evidence of atypical findings such as lymphadenopathies and mediastinal and vessel invasion, as well as the absence of response to therapy, should arouse the suspicion of lung cancer and require contrast administration. Ground-glass areas and/or consolidations bound to radiotherapy fields or pneumonitis arising during and after oncological therapy should always arouse the suspicion of radiation-induced lung disease and chemo/immunotherapy-induced lung disease. The radiological elements we suggest for COVID-19 and lung cancer differential diagnosis may be used to develop AI protocols to guarantee an early and proper diagnosis and treatment to improve patients’ quality of life and life expectancy.

Lung Ultrasound Signs and Their Correlation With Clinical Symptoms in COVID-19 Pregnant Women: The "PINK-CO" Observational Study

Objective

To analyze the application of lung ultrasound (LUS) diagnostic approach in obstetric patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and compare LUS score and symptoms of the patients.

Design

A single-center observational retrospective study from October 31, 2020 to March 31, 2021.

Setting

Department of Ob/Gyn at the University-Hospital of Udine, Italy.

Participants

Pregnant women with SARS-CoV-2 diagnosed with reverse transcription-PCR (RT-PCR) swab test were subdivided as symptomatic and asymptomatic patients with COVID-19.

Exposure

Lung ultrasound evaluation both through initial evaluation upon admission and through serial evaluations.

Main Outcome

Reporting LUS findings and LUS score characteristics.

Results

Symptomatic patients with COVID-19 showed a higher LUS (median 3.5 vs. 0, p < 0.001). LUS was significantly correlated with COVID-19 biomarkers as C-reactive protein (CPR; p = 0.011), interleukin-6 (p = 0.013), and pro-adrenomedullin (p = 0.02), and inversely related to arterial oxygen saturation (p = 0.004). The most frequent ultrasound findings were focal B lines (14 vs. 2) and the light beam (9 vs. 0).

Conclusion

Lung ultrasound can help to manage pregnant women with SARS-CoV-2 infection during a pandemic surge.

Study Registration

ClinicalTrials.gov, NCT04823234. Registered on March 29, 2021.

Semantic segmentation of COVID-19 lesions with a multiscale dilated convolutional network

Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment. The remaining challenges are the obvious scale difference between different types of COVID-19 lesions and the similarity between the lesions and normal tissues. This work aims to segment lesions of different scales and lesion boundaries correctly by utilizing multiscale and multilevel features. A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features for better segmentation of lesions at different scales. Furthermore, a multilevel feature aggregate (MLFA) module is proposed to reduce the information loss in the downsampling process. Experiments on the publicly available COVID-19 CT Segmentation dataset demonstrate that the proposed MSDC-Net is superior to other existing methods in segmenting lesion boundaries and large, medium, and small lesions, and achieves the best results in Dice similarity coefficient, sensitivity and mean intersection-over-union (mIoU) scores of 82.4%, 81.1% and 78.2%, respectively. Compared with other methods, the proposed model has an average improvement of 10.6% and 11.8% on Dice and mIoU. Compared with the existing methods, our network achieves more accurate segmentation of lesions at various scales and lesion boundaries, which will facilitate further clinical analysis. In the future, we consider integrating the automatic detection and segmentation of COVID-19, and conduct research on the automatic diagnosis system of COVID-19.

Quantitative determination of pulmonary emphysema in follow-up LD-CTs of patients with COVID-19 infection

Purpose

To evaluate the association between the coronavirus disease 2019 (COVID-19) and post-inflammatory emphysematous lung alterations on follow-up low-dose CT scans.

Methods

Consecutive patients with proven COVID-19 infection and a follow-up CT were retrospectively reviewed. The severity of pulmonary involvement was classified as mild, moderate and severe. Total lung volume, emphysema volume and the ratio of emphysema/-to-lung volume were quantified semi-automatically and compared inter-individually between initial and follow-up CT and to a control group of healthy, age- and sex-matched patients. Lung density was further assessed by drawing circular regions of interest (ROIs) into non-affected regions of the upper lobes.

Results

A total of 32 individuals (mean age: 64 ± 13 years, 12 females) with at least one follow-up CT (mean: 52 ± 66 days, range: 5–259) were included. In the overall cohort, total lung volume, emphysema volume and the ratio of lung-to-emphysema volume did not differ significantly between the initial and follow-up scans. In the subgroup of COVID-19 patients with > 30 days of follow-up, the emphysema volume was significantly larger as compared to the subgroup with a follow-up < 30 days (p = 0.045). Manually measured single ROIs generally yielded lower attenuation values prior to COVID-19 pneumonia, but the difference was not significant between groups (all p > 0.05).

Conclusion

COVID-19 patients with a follow-up CT >30 days showed significant emphysematous lung alterations. These findings may help to explain the long-term effect of COVID-19 on pulmonary function and warrant validation by further studies.

Medical imaging of pulmonary disease in SARS-CoV-2-exposed non-human primates

Chest X-ray (CXR), computed tomography (CT), and positron emission tomography-computed tomography (PET-CT) are noninvasive imaging techniques widely used in human and veterinary pulmonary research and medicine. These techniques have recently been applied in studies of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-exposed non-human primates (NHPs) to complement virological assessments with meaningful translational readouts of lung disease. Our review of the literature indicates that medical imaging of SARS-CoV-2-exposed NHPs enables high-resolution qualitative and quantitative characterization of disease otherwise clinically invisible and potentially provides user-independent and unbiased evaluation of medical countermeasures (MCMs). However, we also found high variability in image acquisition and analysis protocols among studies. These findings uncover an urgent need to improve standardization and ensure direct comparability across studies.

Evaluating the Association Between Comorbidities and COVID-19 Severity Scoring on Chest CT Examinations Between the Two Waves of COVID-19: An Imaging Study Using Artificial Intelligence

Background

Coronavirus disease 2019 (COVID-19) has accounted for over 352 million cases and five million deaths globally. Although it affects populations across all nations, developing or transitional, of all genders and ages, the extent of the specific involvement is not very well known. This study aimed to analyze and determine how different were the first and second waves of the COVID-19 pandemic by assessing computed tomography severity scores (CT-SS).

Methodology

This was a retrospective, cross-sectional, observational study performed at a tertiary care Institution. We included 301 patients who underwent CT of the chest between June and October 2020 and 1,001 patients who underwent CT of the chest between February and April 2021. All included patients were symptomatic and were confirmed to be COVID-19 positive. We compared the CT-SS between the two datasets. In addition, we analyzed the distribution of CT-SS concerning age, comorbidities, and gender, as well as their differences between the two waves of COVID-19. Analysis was performed using the SPSS version 22 (IBM Corp., Armonk, NY, USA). The artificial intelligence platform U-net architecture with Xception encoder was used in the analysis.

Results

The study data revealed that while the mean CT-SS did not differ statistically between the two waves of COVID-19, the age group most affected in the second wave was almost a decade younger. While overall the disease had a predilection toward affecting males, our findings showed that females were more afflicted in the second wave of COVID-19 compared to the first wave. In particular, the disease had an increased severity in cases with comorbidities such as hypertension, diabetes mellitus, bronchial asthma, and tuberculosis.

Conclusions

This assessment demonstrated no significant difference in radiological severity score between the two waves of COVID-19. The secondary objective revealed that the two waves showed demographical differences. Hence, we iterate that no demographical subset of the population should be considered low risk as the disease manifestation was heterogeneous.

Chest X-ray versus chest computed tomography for outcome prediction in hospitalized patients with COVID-19

The purpose of this study was to compare the prognostic value of chest X-ray (CXR) and chest computed tomography (CT) in a group of hospitalized patients with COVID-19. For this study, we retrospectively selected a cohort of 106 hospitalized patients with COVID-19 who underwent both CXR and chest CT at admission. For each patient, the pulmonary involvement was ranked by applying the Brixia score for CXR and the percentage of well-aerated lung (WAL) for CT. The Brixia score was assigned at admission (A-Brixia score) and during hospitalization. During hospitalization, only the highest score (H-Brixia score) was considered. At admission, the percentage of WAL (A-CT%WAL) was quantified using a dedicated software. On logistic regression analyses, H-Brixia score was the most effective radiological marker for predicting in-hospital mortality and invasive mechanical ventilation. Additionally, A-CT%WAL did not provide substantial advantages in the risk stratification of hospitalized patients with COVID-19 compared to A-Brixia score.

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.

Lung Ultrasound as a First-Line Test in the Evaluation of Post-COVID-19 Pulmonary Sequelae

Background: Interstitial lung sequelae are increasingly being reported in survivors of COVID-19 pneumonia. An early detection of these lesions may help prevent the development of irreversible lung fibrosis. Lung ultrasound (LUS) has shown high diagnostic accuracy in interstitial lung disease (ILD) and could likely be used as a first-line test for post-COVID-19 lung sequelae. Methods: Single-center observational prospective study. Follow-up assessments of consecutive patients hospitalized for COVID-19 pneumonia were conducted 2-5 months after the hospitalization. All patients underwent pulmonary function tests (PFTs), high-resolution computed tomography (HRCT), and LUS. Radiological alterations in HRCT were quantified using the Warrick score. The LUS score was obtained by evaluating the presence of pathological B-lines in 12 thoracic areas (range, 0-12). The correlation between the LUS and Warrick scores was analyzed. Results: Three hundred and fifty-two patients who recovered from COVID-19 pneumonia were recruited between July and September 2020. At follow-up, dyspnea was the most frequent symptom (69.3%). FVC and DLCO alterations were present in 79 (22.4%) and 234 (66.5%) patients, respectively. HRCT showed relevant interstitial lung sequelae (RILS) in 154 (43.8%) patients (Warrick score ≥ 7). The LUS score was strongly correlated with the HRCT Warrick score (r = 0.77) and showed a moderate inverse correlation with DLCO (r = -0.55). The ROC curve analysis revealed that a LUS score ≥ 3 indicated an excellent ability to discriminate patients with RILS (sensitivity, 94.2%; specificity, 81.8%; negative predictive value, 94.7%). Conclusions: LUS could be implemented as a first-line procedure in the evaluation of Post-COVID-19 interstitial lung sequelae. A normal LUS examination rules out the presence of these sequelae in COVID-19 survivors, avoiding the need for additional diagnostic tests such as HRCT.

The Deep Learning-Based Framework for Automated Predicting COVID-19 Severity Score

With the COVID-19 pandemic sweeping the globe, an increasing number of people are working on pandemic research, but there is less effort on predicting its severity. Diagnostic chest imaging is thought to be a quick and reliable way to identify the severity of COVID-19. We describe a deep learning method to automatically predict the severity score of patients by analyzing chest X-rays, with the goal of collaborating with doctors to create corresponding treatment measures for patients and can also be used to track disease change. Our model consists of a feature extraction phase and an outcome prediction phase. The feature extraction phase uses a DenseNet backbone network to extract 18 features related to lung diseases from CXRs; the outcome prediction phase, which employs the MLP regression model, selects several important features for prediction from the features extracted in the previous phase and demonstrates the effectiveness of our model by comparing it with several commonly used regression models. On a dataset of 2373 CXRs, our model predicts the geographic extent score with 1.02 MAE and the lung opacity score with 0.85 MAE.

Still a role for the chest radiograph - humble but helpful!

-

Emergency room comprehensive assessment of demographic, radiological, laboratory and clinical data of patients with COVID-19: determination of its prognostic value for in-hospital mortality

Mortality risk in COVID-19 patients is determined by several factors. The aim of our study was to adopt an integrated approach based on clinical, laboratory and chest x-ray (CXR) findings collected at the patient's admission to Emergency Room (ER) to identify prognostic factors. Retrospective study on 346 consecutive patients admitted to the ER of two North-Western Italy hospitals between March 9 and April 10, 2020 with clinical suspicion of COVID-19 confirmed by reverse transcriptase-polymerase reaction chain test (RT-PCR), CXR performed within 24 h (analyzed with two different scores) and recorded prognosis. Clinical and laboratory data were collected. Statistical analysis on the features of 83 in-hospital dead vs 263 recovered patients was performed with univariate (uBLR), multivariate binary logistic regression (mBLR) and ROC curve analysis. uBLR identified significant differences for several variables, most of them intertwined by multiple correlations. mBLR recognized as significant independent predictors for in-hospital mortality age > 75 years, C-reactive protein (CRP) > 60 mg/L, PaO₂/FiO₂ ratio (P/F) < 250 and CXR "Brixia score" > 7. Among the patients with at least two predictors, the in-hospital mortality rate was 58% against 6% for others [p < 0.0001; RR = 7.6 (4.4-13)]. Patients over 75 years had three other predictors in 35% cases against 10% for others [p < 0.0001, RR = 3.5 (1.9-6.4)]. The greatest risk of death from COVID-19 was age above 75 years, worsened by elevated CRP and CXR score and reduced P/F. Prompt determination of these data at admission to the emergency department could improve COVID-19 pretreatment risk stratification.

Evaluation of AI-Based Segmentation Tools for COVID-19 Lung Lesions on Conventional and Ultra-low Dose CT Scans

A reliable diagnosis and accurate monitoring are pivotal steps for treatment and prevention of COVID-19. Chest computed tomography (CT) has been considered a crucial diagnostic imaging technique for the injury assessment of the viral pneumonia. Furthermore, the automatization of the segmentation methods for lung alterations helps to speed up the diagnosis and lighten radiologists' workload. Considering the assiduous pathology monitoring, ultra-low dose (ULD) chest CT protocols have been implemented to drastically reduce the radiation burden. Unfortunately, the available AI technologies have not been trained on ULD-CT data and validated and their applicability deserves careful evaluation. Therefore, this work aims to compare the results of available AI tools (BCUnet, CORADS AI, NVIDIA CLARA Train SDK and CT Pneumonia Analysis) on a dataset of 73 CT examinations acquired both with conventional dose (CD) and ULD protocols. COVID-19 volume percentage, resulting from each tool, was statistically compared. This study demonstrated high comparability of the results on CD-CT and ULD-CT data among the four AI tools, with high correlation between the results obtained on both protocols (R > .68, P < .001, for all AI tools).

30 s sit-to-stand power is positively associated with chest muscle thickness in COVID-19 survivors

Introduction

After hospitalization, early detection of musculoskeletal sequelae might help healthcare professionals to improve and individualize treatment, accelerating recovery after COVID-19. The objective was to determine the association between the 30s sit-to-stand muscle power (30s-STS) and cross-sectional area of the chest muscles (pectoralis) in COVID-19 survivors.

Method

This cross-sectional study collected routine data from COVID-19 survivors one month after hospitalization: 1) a chest computed tomography (CT) scan and 2) a functional capacity test (30s-STS). The pectoralis muscle area (PMA) was measured from axial CT images. For each gender, patients were categorized into tertiles based on PMA. The 30s-STS was performed to determine the leg extension power. The allometric and relative STS power were calculated as absolute 30s-STS power normalized to height squared and body mass. The two-way ANOVA was used to compare the gender-stratified tertiles of 30s-STS power variants.

Results

Fifty-eight COVID-19 survivors were included (mean age 61.2 ± 12.9 years, 30/28 (51.7%/48.3%) men/women). The two-way ANOVA showed significant differences between the PMA tertiles in absolute STS power (p = .002) and allometric STS power (p = .001). There were no significant gender x PMA tertile interactions (all variables p > .05). The high tertile of PMA showed a higher allometric STS power compared to the low and middle tertile, p = .002 and p = .004, respectively. Absolute STS power and allometric STS power had a moderate correlation with the PMA, r = 0.519 (p < .001) and r = 0.458 (p < .001) respectively.

Conclusion

The 30s-STS power is associated with pectoralis muscle thickness in both male and female COVID-19 survivors. Thus, this test may indicate global muscle-wasting and may be used as a screening tool for lower extremity functional capacity in the early stages of rehabilitation planning in COVID-19 survivors.

Impact of COVID-19 pandemic on 2-[18F]FDG PET/CT imaging work-flow in a single medical institution: comparison among the three Italian waves

PURPOSE

To compare the impact of COVID-19 pandemic on 2-[18F]FDG PET/CT imaging work-flow during the three waves in a medical institution of southern of Italy.

METHODS

We retrospectively reviewed the numbers and results of 2-[18F]FDG PET/CT studies acquired during the following three periods of the COVID-19 waves: 1) February 3-April 30, 2020; 2) October 15, 2020-January 15, 2021; and 3) January 18-April 16, 2021.

RESULTS

A total of 861 PET/CT studies in 725 patients (388 men, mean age 64 ± 4 years) was acquired during the three waves of COVID-19 pandemic. The majority (94%) was performed for diagnosis/staging (n = 300) or follow-up (n = 512) of neoplastic diseases. The remaining 49 studies (6%) were acquired for non-oncological patients. The distribution of number and type of clinical indications for PET/CT studies in the three waves were comparable (p = 0.06). Conversely, the occurrence of patients positive for COVID-19 infection progressively increased (p < 0.0001) from the first to third wave; in particular, patients with COVID-19 had active infection before PET/CT study as confirmed by molecular oro/nasopharyngeal swab.

CONCLUSION

Despite the restrictive medical measures for the emergency, the number of 2-[18F]FDG PET/CT studies was unchanged during the three waves guaranteeing the diagnostic performance of PET/CT imaging for oncological patients.

Using artificial intelligence to risk stratify COVID-19 patients based on chest X-ray findings

BACKGROUND

Deep learning-based radiological image analysis could facilitate use of chest x-rays as a triaging tool for COVID-19 diagnosis in resource-limited settings. This study sought to determine whether a modified commercially available deep learning algorithm (M-qXR) could risk stratify patients with suspected COVID-19 infections.

METHODS

A dual track clinical validation study was designed to assess the clinical accuracy of M-qXR. The algorithm evaluated all Chest-X-rays (CXRs) performed during the study period for abnormal findings and assigned a COVID-19 risk score. Four independent radiologists served as radiological ground truth. The M-qXR algorithm output was compared against radiological ground truth and summary statistics for prediction accuracy were calculated. In addition, patients who underwent both PCR testing and CXR for suspected COVID-19 infection were included in a co-occurrence matrix to assess the sensitivity and specificity of the M-qXR algorithm.

RESULTS

625 CXRs were included in the clinical validation study. 98% of total interpretations made by M-qXR agreed with ground truth (p = 0.25). M-qXR correctly identified the presence or absence of pulmonary opacities in 94% of CXR interpretations. M-qXR's sensitivity, specificity, PPV, and NPV for detecting pulmonary opacities were 94%, 95%, 99%, and 88% respectively. M-qXR correctly identified the presence or absence of pulmonary consolidation in 88% of CXR interpretations (p = 0.48). M-qXR's sensitivity, specificity, PPV, and NPV for detecting pulmonary consolidation were 91%, 84%, 89%, and 86% respectively. Furthermore, 113 PCR-confirmed COVID-19 cases were used to create a co-occurrence matrix between M-qXR's COVID-19 risk score and COVID-19 PCR test results. The PPV and NPV of a medium to high COVID-19 risk score assigned by M-qXR yielding a positive COVID-19 PCR test result was estimated to be 89.7% and 80.4% respectively.

CONCLUSION

M-qXR was found to have comparable accuracy to radiological ground truth in detecting radiographic abnormalities on CXR suggestive of COVID-19.

Imaging of COVID-19

The novel coronavirus disease 2019 (COVID-19) emerged as the source of a global pandemic in late 2019 and early 2020 and quickly spread throughout the world becoming one of the worst pandemics in recent history. This chapter reviews the most up to date radiological literature and outlines the utility of thoracic imaging in COVID-19, defining both the common and the less typical imaging appearances during the acute and subacute phases of COVID-19. The short term complications and the long term sequela will also be discussed in the context of radiology, including pulmonary emboli, acute respiratory distress syndrome, superimposed infections, barotrauma, cardiac manifestations, pulmonary parenchymal scarring and fibrosis.

The diagnostic performance of deep-learning-based CT severity score to identify COVID-19 pneumonia

Objective:

To determine the diagnostic accuracy of a deep-learning (DL)-based algorithm using chest computed tomography (CT) scans for the rapid diagnosis of coronavirus disease 2019 (COVID-19), as compared to the reference standard reverse-transcription polymerase chain reaction (RT-PCR) test.

Methods:

In this retrospective analysis, data of COVID-19 suspected patients who underwent RT-PCR and chest CT examination for the diagnosis of COVID-19 were assessed. By quantifying the affected area of the lung parenchyma, severity score was evaluated for each lobe of the lung with the DL-based algorithm. The diagnosis was based on the total lung severity score ranging from 0 to 25. The data were randomly split into a 40% training set and a 60% test set. Optimal cut-off value was determined using Youden-index method on the training cohort.

Results:

A total of 1259 patients were enrolled in this study. The prevalence of RT-PCR positivity in the overall investigated period was 51.5%. As compared to RT-PCR, sensitivity, specificity, positive predictive value, negative predictive value and accuracy on the test cohort were 39.0%, 80.2%, 68.0%, 55.0% and 58.9%, respectively. Regarding the whole data set, when adding those with positive RT-PCR test at any time during hospital stay or “COVID-19 without virus detection”, as final diagnosis to the true positive cases, specificity increased from 80.3% to 88.1% and the positive predictive value increased from 68.4% to 81.7%.

Conclusion:

DL-based CT severity score was found to have a good specificity and positive predictive value, as compared to RT-PCR. This standardized scoring system can aid rapid diagnosis and clinical decision making.

Advances in knowledge:

DL-based CT severity score can detect COVID-19-related lung alterations even at early stages, when RT-PCR is not yet positive.

CHEST CT USAGE IN COVID-19 PNEUMONIA: MULTICENTER STUDY ON RADIATION DOSES AND DIAGNOSTIC QUALITY IN BRAZIL

We assessed variations in chest CT usage, radiation dose and image quality in COVID-19 pneumonia. Our study included all chest CT exams performed in 533 patients from 6 healthcare sites from Brazil. We recorded patients' age, gender and body weight and the information number of CT exams per patient, scan parameters and radiation doses (volume CT dose index-CTDIvol and dose length product-DLP). Six radiologists assessed all chest CT exams for the type of pulmonary findings and classified CT appearance of COVID-19 pneumonia as typical, indeterminate, atypical or negative. In addition, each CT was assessed for diagnostic quality (optimal or suboptimal) and presence of artefacts. Artefacts were frequent (367/841), often related to respiratory motion (344/367 chest CT exams with artefacts) and resulted in suboptimal evaluation in mid-to-lower lungs (176/344) or the entire lung (31/344). There were substantial differences in CT usage, patient weight, CTDIvol and DLP across the participating sites.

Does the initial chest radiograph severity in COVID-19 impact the short- and long-term outcome? - a perspective from India

PURPOSE

The chest radiograph (CXR) is among the most widely used investigations in coronavirus disease 2019 (COVID-19) patients. Little is known about its predictive role on the long-term outcome. The purpose of this study was to explore its association with the short and long-term outcome in COVID-19 patients.

METHODS

A total of 1530 patients were assessed for the presence, radiographic pattern and distribution of lung lesions observed on baseline chest radiographs obtained at admission. The Brixia scoring system was applied for semiquantitative assessment of lesion severity. Short-term outcome was determined by clinical severity, duration of hospitalization and mortality. The 1415 survivors in this group were assessed after 5-6 months for the presence of residual symptoms.

RESULTS

About 67% patients had an abnormal baseline CXR. Bilateral involvement with a basal preponderance was observed and ground-glass opacification was the most frequent finding. The Brixia score ranged from 0 to 16, median 2, interquartile range (IQR) [0-6]. About 36% patients were symptomatic on 5-6-month follow-up, with fatigability being the commonest symptom. A good correlation was observed between the CXR score and disease severity as well as duration of hospitalization. On multivariate analysis, the CXR score was found to be a significant independent predictor of in-patient mortality as well as presence of long-term residual symptoms in survivors.

CONCLUSIONS

Disease severity as seen on the chest radiograph appears to play an important role in driving the short and long-term consequences of COVID-19 and could serve as a prognostic indicator, which influences short-term management and long-term follow-up.

Adaptive UNet-based Lung Segmentation and Ensemble Learning with CNN-based Deep Features for Automated COVID-19 Diagnosis

COVID-19 disease is a major health calamity in twentieth century, in which the infection is spreading at the global level. Developing countries like Bangladesh, India, and others are still facing a delay in recognizing COVID-19 cases. Hence, there is a need for immediate recognition with perfect identification of infection. This clear visualization helps to save the life of suspected COVID-19 patients. With the help of traditional RT-PCR testing, the combination of medical images and deep learning classifiers delivers more hopeful results with high accuracy in the prediction and recognition of COVID-19 cases. COVID-19 disease is recently researched through sample chest X-ray images, which have already proven its efficiency in lung diseases. To emphasize corona virus testing methods and to control the community spreading, the automatic detection process of COVID-19 is processed through the detailed medication reports from medical images. Although there are numerous challenges in the manual understanding of traces in COVID-19 infection from X-ray, the subtle differences among normal and infected X-rays can be traced by the data patterns of Convolutional Neural Network (CNN). To improve the detection performance of CNN, this paper plans to develop an Ensemble Learning with CNN-based Deep Features (EL-CNN-DF). In the initial phase, image scaling and median filtering perform the pre-processing of the chest X-ray images gathered from the benchmark source. The second phase is lung segmentation, which is the significant step for COVID detection. It is accomplished by the Adaptive Activation Function-based U-Net (AAF-U-Net). Once the lungs are segmented, it is subjected to novel EL-CNN-DF, in which the deep features are extracted from the pooling layer of CNN, and the fully connected layer of CNN are replaced with the three classifiers termed "Support Vector Machine (SVM), Autoencoder, Naive Bayes (NB)". The final detection of COVID-19 is done by these classifiers, in which high ranking strategy is utilized. As a modification, a Self Adaptive-Tunicate Swarm Algorithm (SA-TSA) is adopted as a boosting algorithm to enhance the performance of segmentation and detection. The overall analysis has shown that the precision of the enhanced CNN by using SA-TSA was 1.02%, 4.63%, 3.38%, 1.62%, 1.51% and 1.04% better than SVM, autoencoder, NB, Ensemble, RNN and LSTM respectively. The comparative performance analysis on existing model proves that the proposed algorithm is better than other algorithms in terms of segmentation and classification of COVID-19 detection.

Can chest radiographic findings determine disease severity in Covid-19-positive patients? A single-center study

Objectives

The purpose of this study was to describe the severity of the radiographic findings of COVID-19 over time and to assess their correlation with the duration of symptoms prior to admission, CT scores, and disease severity.

Methods

A retrospective analysis of patients with COVID-19 confirmed by reverse transcription polymerase chain reaction (RT-PCR) and CXR who were admitted at the university hospital was performed between March 25 and 30 April 2020. Baseline and serial CXRs were reviewed, along with onset and disease time courses. Correlations between CXR scores and CT scores, durations of symptoms and disease severity were evaluated; and also between regression times and disease severity.

Results

Of 208 total patients, there were 33 mild (15.9%), 103 moderate (49.5%), and 72 severe-critical (34.6%) cases. The most frequent symptoms were fever, cough, fatigue, and dyspnea. Dyspnea was more frequent in patients with severe and critical disease ( p < 0.001). The duration of symptoms experienced prior to admission was longer in patients with severe and critical disease than in moderate cases ( p < 0.05). Abnormalities on CXR were present on admission in 83.2% patients, with reticulations being the most common finding. CXR scores correlated with duration of symptoms prior to admission and CT scores ( p < 0.05 and p < 0.001, respectively). The median radiographic score of the severe-critical-type group was significantly higher than the moderate type ( p <  0.001) and regression time correlated with disease severity ( p < 0.001).

Conclusion

Our study showed that despite the limitations, CXR remains a very important tool for diagnosing and managing patients with COVID-19.

Diagnostic performance of the RSNA-proposed classification for COVID-19 pneumonia versus pre-pandemic controls

Objective

To evaluate the diagnostic accuracy of the Radiological Society of North America (RSNA) classification system for coronavirus disease 2019 (COVID-19) pneumonia compared to pre-pandemic chest computed tomography (CT) scan images to mitigate the risk of bias regarding the reference standard.

Materials and methods

This was a retrospective, cross-sectional, diagnostic test accuracy study. Chest CT scans, carried out from May 1 to June 30, 2020, and from May 1 to July 17, 2017, were consecutively selected for the COVID-19 (positive reverse transcription-polymerase chain reaction [RT-PCR] for severe acute respiratory syndrome coronavirus 2 result) and control (pre-pandemic) groups, respectively. Four expert thoracic radiologists blindly interpreted each CT scan image. Sensitivity and specificity were calculated.

Results

A total of 160 chest CT scan images were included: 79 in the COVID-19 group (56 [43.5–67] years old, 41 men) and 81 in the control group (62 [52–72] years old, 44 men). Typically, an estimated specificity of 98.5% (95% confidence interval [CI] 98.1%–98.4%) was obtained. For the indeterminate classification as a diagnostic threshold, an estimated sensitivity of 88.3% (95% CI 84.7%–91.7%) and a specificity of 79.0% (95% CI 74.5%–83.4%), with an area under the curve of 0.865 (95% CI 0.838–0.895), were obtained.

Conclusion

The RSNA classification system shows strong diagnostic accuracy for COVID-19 pneumonia, even against pre-pandemic controls. It can be an important aid in clinical decision-making, especially when a typical or indeterminate pattern is found, possibly advising retesting following an initial negative RT-PCR result and streamlining early management and isolation.

The radiological findings of COVID-19

Background/aim

Available information on the radiological findings of the 2019 novel coronavirus disease (COVID-19) is constantly updated. Ground glass opacities (GGOs) and consolidation with bilateral and peripheral distribution have been reported as the most common CT findings, but less typical features can also be identified. According to the reported studies, SARS-CoV-2 infection is not limited to the respiratory system, and it can also affect other organs. Renal dysfunction, gastrointestinal complications, liver dysfunction, cardiac manifestations, and neurological abnormalities are among the reported extrapulmonary features. This review aims to provide updated information for radiologists and all clinicians to better understand the radiological manifestations of COVID-19.

Materials and methods

Radiological findings observed in SARS-CoV-2 virus infections were explored in detail in PubMed and Google Scholar databases.

Results

The typical pulmonary manifestations of COVID-19 pneumonia were determined as GGOs and accompanying consolidations that primarily involve the periphery of the bilateral lower lobes. The most common extrapulmonary findings were increased resistance to flow in the kidneys, thickening of vascular walls, fatty liver, pancreas, and heart inflammation findings. However, these findings were not specific and significantly overlapped those caused by other viral diseases, and therefore alternative diagnoses should be considered in patients with negative diagnostic tests.

Conclusion

Radiological imaging plays a supportive role in the care of patients with COVID-19. Both clinicians and radiologists need to know associated pulmonary and extrapulmonary findings and imaging features to help diagnose and manage the possible complications of the disease at an early stage. They should also be familiar with CT findings in patients with COVID-19 since the disease can be incidentally detected during imaging performed with other indications.