Search

The COVID-19 pandemic disrupted the delivery of preventative care and management of acute diseases. This study assesses the effect of the COVID-19 pandemic on coronary calcium score and coronary CT angiography imaging volume.A single institution retrospective review of consecutive patients presenting for coronary calcium score or coronary CT angiography examinations between January 1, 2020 to January 4, 2022 was performed. The weekly volume of calcium score and coronary CT angiogram exams were compared.In total, 1,817 coronary calcium score CT and 5,895 coronary CT angiogram examinations were performed. The average weekly volume of coronary CTA and coronary calcium score CT exams decreased by up to 83% and 100%, respectively, during the COVID-19 peak period compared to baseline (P0.0001). The post-COVID recovery through 2020 saw weekly coronary CTA volumes rebound to 86% of baseline (P = 0.024), while coronary calcium score CT volumes remained muted at only a 53% recovery (P0.001). In 2021, coronary CTA imaging eclipsed pre-COVID rates (P = 0.012), however coronary calcium score CT volume only reached 67% of baseline (P0.001).A significant decrease in both coronary CTA and coronary calcium score CT volume occurred during the peak-COVID-19 period. In 2020 and 2021, coronary CTA imaging eventually superseded baseline rates, while coronary calcium score CT volumes only reached two thirds of baseline. These findings highlight the importance of resumption of screening exams and should prompt clinicians to be aware of potential undertreatment of patients with coronary artery disease.

Hundreds of imaging-based artificial intelligence (AI) models have been developed in response to the COVID-19 pandemic. AI systems that incorporate imaging have shown promise in primary detection, severity grading, and prognostication of outcomes in COVID-19, and have enabled integration of imaging with a broad range of additional clinical and epidemiologic data. However, systematic reviews of AI models applied to COVID-19 medical imaging have highlighted problems in the field, including methodologic issues and problems in real-world deployment. Clinical use of such models should be informed by both the promise and potential pitfalls of implementation. How does a practicing radiologist make sense of this complex topic, and what factors should be considered in the implementation of AI tools for imaging of COVID-19? This critical review aims to help the radiologist understand the nuances that impact the clinical deployment of AI for imaging of COVID-19. We review imaging use cases for AI models in COVID-19 (e.g., diagnosis, severity assessment, and prognostication) and explore considerations for AI model development and testing, deployment infrastructure, clinical user interfaces, quality control, and institutional review board and regulatory approvals, with a practical focus on what a radiologist should consider when implementing an AI tool for COVID-19.

To assess radiology representation, multimedia content, and multilingual content of United States lung cancer screening (LCS) program websites.We identified the websites of US LCS programs with the Google internet search engine using the search terms lung cancer screening, low-dose CT screening, and lung screening. We used a standardized checklist to assess and collect specific content, including information regarding LCS staff composition and references to radiologists and radiology. We also tabulated types and frequencies of included multimedia and multilingual content and patient narratives.We analyzed 257 unique websites. Of these, only 48% (124 of 257) referred to radiologists or radiology in text, images, or videos. Radiologists were featured in images or videos on only 14% (36 of 257) of websites. Radiologists were most frequently acknowledged for their roles in reading or interpreting imaging studies (35% [90 of 574]). Regarding multimedia content, only 36% (92 of 257) of websites had 1 image, 27% (70 of 257) included 2 or more images, and 26% (68 of 257) of websites included one or more videos. Only 3% (7 of 257) of websites included information in a language other than English. Patient narratives were found on only 15% (39 of 257) of websites.The field of Radiology is mentioned in text, images, or videos by less than half of LCS program websites. Most websites make only minimal use of multimedia content such as images, videos, and patient narratives. Few websites provide LCS information in languages other than English, potentially limiting accessibility to diverse populations.

Community-acquired pneumonia is the most common cause of death among infectious diseases, and responsible for millions of hospitalizations annually. Pneumonia may be classified based on how it is acquired, etiology, and clinical presentation. Chest radiographs are the gold standard for initial imaging evaluation and chest computed tomography plays an important role in diagnostic problem-solving and evaluation of complicated and treatment-resistant pneumonia. Follow-up imaging with chest radiographs or computed tomography post-illness resolution may be used to identify treatment-resistant inflammation or unidentified underlying malignancies.

Objectives Many patients with interstitial lung disease (ILD) have autoimmune manifestations but do not meet criteria for a systemic rheumatic disease. A subset meets criteria for interstitial pneumonia with autoimmune features (IPAF) and have ILD requiring therapy. We conducted a multicentre observational study to examine the use of rituximab (RTX) in IPAF. Methods Patients from Mass General Brigham (MGB) and University of Chicago Medicine (UCM) were included if they were ≥18 years old, met the 2015 classification criteria for IPAF and were treated with RTX. Clinical improvement was defined as improvement in four out of four domains at 1 year after RTX initiation: documented clinician global assessment; oxygen requirement; need for respiratory-related hospitalization; and survival. Results At MGB, 36 IPAF patients (mean age 61 years, 44% female) were treated with RTX. At 1 year, 18 (50%) were clinically improved, 12 (33%) were stable, and 6 (17%) died from progressive respiratory failure. At UCM, 14 IPAF patients (mean age 53 years, 71% female) were treated with RTX. At 1 year, eight (57%) were improved, two (14%) were stable, three (21%) died from progressive respiratory failure, and one (7%) was lost to follow-up. Two patients experienced minor infusion reactions, and two patients discontinued therapy owing to adverse events (infections). Conclusion In patients with IPAF treated with RTX at two medical centres, the majority (40 [80%]) demonstrated improvement/stability at 1 year. These findings call for prospective studies, including randomized clinical trials, to determine the risks, benefits and cost effectiveness of RTX in IPAF.

Background RSNA COVID-19 chest CT consensus guidelines are widely used, but their true positive rate for COVID-19 pneumonia has not been assessed among vaccinated patients. Purpose To assess true positive rate of RSNA typical chest CT findings of COVID-19 among fully vaccinated subjects with PCR-confirmed COVID-19 infection compared with unvaccinated subjects. Materials and Methods Patients with COVID Typical chest CT findings and one positive or two negative PCR tests for COVID-19 within 7 days of their chest CT between January 2021 - January 2022 at a quaternary academic medical center were included. True positives were defined as chest CTs interpreted as COVID Typical and PCR-confirmed COVID-19 infection within 7 days. Logistic regression models were constructed to quantify the association between PCR results and vaccination status, vaccination status and COVID-19 variants, and vaccination status and months. Results 652 subjects (median age 59, [IQR, 48-72]); 371 [57%] men) with CT scans classified as COVID Typical were included. 483 (74%) were unvaccinated and 169 (26%) were fully vaccinated. The overall true positive rate of COVID Typical CTs was lower among vaccinated versus unvaccinated (70/169 [41%; 95% CI: 34, 49%] vs 352/483 [73%; 69, 77%]; OR (95% CI): 3.8 (2.6, 5.5); P.001). Unvaccinated subjects were more likely to have true positive CTs compared with fully vaccinated subjects during the peaks of COVID-19 variants Alpha (OR, 16 [95% CI: 6.1, 42]

In the third year of the SARS-CoV-2 pandemic, much has been learned about the long- term effect of COVID-19 pneumonia on the lungs. Approximately one-third of patients with moderate-to-severe pneumonia, especially those requiring intensive care therapy or mechanical ventilation, have residual abnormalities on chest CT one year after presentation. Abnormalities range from parenchymal bands to bronchial dilation to frank fibrosis. Less is known about the long-term pulmonary vascular sequelae, but there appears to be a persistent, increased risk of venothromboembolic events in a small cohort of patients. Finally, the associated histologic abnormalities resulting from SARS- CoV-2 infection are similar to those of patients with other causes of acute lung injury.

The purpose of this study was to evaluate the readability of breast cancer online patient educational materials (OPEM) written in Spanish and to compare to equivalent English-language OPEM.The breast cancer-related terms cáncer de seno (breast cancer), detección de cáncer de seno (breast cancer screening), and biopsia de seno (breast biopsy) were queried using an online search engine. After each query, educational information related to the queried term was downloaded from each website appearing on the first five search engine result pages. Readability of Spanish-language OPEM was evaluated using the Crawford reading grade score. When available, equivalent English-language OPEM from the same website was then evaluated using the mean of five validated readability indices. Differences in readability, word count, and reading time between Spanish- and English-language OPEM were compared using an unpaired t test. The Fisher exact test was used to compare the proportion of websites meeting AMA recommendations for patient educational resources.Queries for cáncer de seno, detección de cáncer de seno, and biopsia de seno yielded 27, 31, and 30 results of term-specific OPEM. Equivalent English-language versions were available for 19 (70.4%), 18 (58.1%), and 20 (66.7%) websites, respectively. Spanish-language OPEM were written at a lower grade reading level than equivalent English-language versions overall (5.49 ± 0.50 versus 7.77 ± 1.95, P.01). Spanish-language OPEM were also more likely than English-language OPEM to meet AMA recommendations (82.9% versus 40.4%, P.01).Breast cancer-related Spanish-language OPEM were written at a significantly lower grade reading level compared with equivalent information written in English.

Infection with SARS-CoV-2 ranges from an asymptomatic condition to a severe and sometimes fatal disease, with mortality most frequently being the result of acute lung injury. The role of imaging has evolved during the pandemic, with CT initially being an alternative and possibly superior testing method compared with reverse transcriptase-polymerase chain reaction (RT-PCR) testing and evolving to having a more limited role based on specific indications. Several classification and reporting schemes were developed for chest imaging early during the pandemic for patients suspected of having COVID-19 to aid in triage when the availability of RT-PCR testing was limited and its level of performance was unclear. Interobserver agreement for categories with findings typical of COVID-19 and those suggesting an alternative diagnosis is high across multiple studies. Furthermore, some studies looking at the extent of lung involvement on chest radiographs and CT images showed correlations with critical illness and a need for mechanical ventilation. In addition to pulmonary manifestations, cardiovascular complications such as thromboembolism and myocarditis have been ascribed to COVID-19, sometimes contributing to neurologic and abdominal manifestations. Finally, artificial intelligence has shown promise for use in determining both the diagnosis and prognosis of COVID-19 pneumonia with respect to both radiography and CT.

Background: Right ventricular (RV) dysfunction is common and associated with worse outcomes in patients with coronavirus disease 2019 (COVID-19). In non-COVID-19 acute respiratory distress syndrome, RV dysfunction develops due to pulmonary hypoxic vasoconstriction, inflammation, and alveolar overdistension or atelectasis. Although similar pathogenic mechanisms may induce RV dysfunction in COVID-19, other COVID-19-specific pathology, such as pulmonary endothelialitis, thrombosis, or myocarditis, may also affect RV function. We quantified RV dysfunction by echocardiographic strain analysis and investigated its correlation with disease severity, ventilatory parameters, biomarkers, and imaging findings in critically ill COVID-19 patients. Methods: We determined RV free wall longitudinal strain (FWLS) in 32 patients receiving mechanical ventilation for COVID-19-associated respiratory failure. Demographics, comorbid conditions, ventilatory parameters, medications, and laboratory findings were extracted from the medical record. Chest imaging was assessed to determine the severity of lung disease and the presence of pulmonary embolism. Results: Abnormal FWLS was present in 66% of mechanically ventilated COVID-19 patients and was associated with higher lung compliance (39.6 vs 29.4 mL/cmH2O, P = 0.016), lower airway plateau pressures (21 vs 24 cmH2O, P = 0.043), lower tidal volume ventilation (5.74 vs 6.17 cc/kg, P = 0.031), and reduced left ventricular function. FWLS correlated negatively with age (r = −0.414, P = 0.018) and with serum troponin (r = 0.402, P = 0.034). Patients with abnormal RV strain did not exhibit decreased oxygenation or increased disease severity based on inflammatory markers, vasopressor requirements, or chest imaging findings. Conclusions: RV dysfunction is common among critically ill COVID-19 patients and is not related to abnormal lung mechanics or ventilatory pressures. Instead, patients with abnormal FWLS had more favorable lung compliance. RV dysfunction may be secondary to diffuse intravascular micro- and macro-thrombosis or direct myocardial damage. Trial Registration: National Institutes of Health #NCT04306393. Registered 10 March 2020, https://clinicaltrials.gov/ct2/show/NCT04306393

It is unclear whether patients and providers have started to knowingly request lung cancer screening (LCS) outside US guidelines and insurance coverage for risk factors besides a history of heavy smoking. The authors analyzed their institution's best practices advisory (BPA) clinical decision support system to determine whether providers knowingly order guideline-discordant LCS and the indications given.CT examinations ordered for LCS at an academic medical center that triggered BPA alerts from November 2018 to December 2019 were reviewed. Alerts were triggered by attempts to order examinations outside Medicare coverage, which resembles most US guidelines. Providers can override alerts to order the examinations. Primary outcomes were the number of examinations performed using orders with overridden BPA alerts and indications given. Qualitative exploratory and directed content analyses identified motivators and decision-making processes that drove guideline-discordant screening use.Forty-two patients underwent guideline-discordant LCS, constituting 1.9% of all patients screened (42 of 2,248): 42.9% (18 of 42) were54 or77 years old, 14.3% (6 of 42) had never smoked, 40.5% (17 of 42) had quit15 years earlier, and 31% (13 of 42) had smoked30 pack-years; 45.2% (19 of 42) fell outside all US guidelines. The most common indication was a family history of lung cancer (21.4% [9 of 42]). Perceptions of elevated cancer risk from both patients and referring providers drove guideline-discordant screening use.Referring providers knowingly ordered screening CT examinations outside Medicare coverage and US guidelines, including for never smokers, for indications including a family history of lung cancer. LCS programs may need tailored strategies to guide these patients and providers, such as help with cancer risk assessment.

Background Disease severity on chest radiographs has been associated with higher risk of disease progression and adverse outcomes from coronavirus disease 2019 (COVID-19). Few studies have evaluated COVID-19-related racial and/or ethnic disparities in radiology. Purpose To evaluate whether non-White minority patients hospitalized with confirmed COVID-19 infection presented with increased severity on admission chest radiographs compared with White or non-Hispanic patients. Materials and Methods This single-institution retrospective cohort study was approved by the institutional review board. Patients hospitalized with confirmed COVID-19 infection between March 17, 2020, and April 10, 2020, were identified by using the electronic medical record (n = 326; mean age, 59 years ±17 [standard deviation]; male-to-female ratio: 188:138). The primary outcome was the severity of lung disease on admission chest radiographs, measured by using the modified Radiographic Assessment of Lung Edema (mRALE) score. The secondary outcome was a composite adverse clinical outcome of intubation, intensive care unit admission, or death. The primary exposure was the racial and/or ethnic category: White or non-Hispanic versus non-White (ie, Hispanic, Black, Asian, or other). Multivariable linear regression analyses were performed to evaluate the association between mRALE scores and race and/or ethnicity. Results Non-White patients had significantly higher mRALE scores (median score, 6.1; 95% confidence interval [CI]: 5.4, 6.7) compared with White or non-Hispanic patients (median score, 4.2; 95% CI: 3.6, 4.9) (unadjusted average difference, 1.8; 95% CI: 0.9, 2.8; P < .01). For both White (adjusted hazard ratio, 1.3; 95% CI: 1.2, 1.4; P < .001) and non-White (adjusted hazard ratio, 1.2; 95% CI: 1.1, 1.3; P < .001) patients, increasing mRALE scores were associated with a higher likelihood of experiencing composite adverse outcome with no evidence of interaction (P = .16). Multivariable linear regression analyses demonstrated that non-White patients presented with higher mRALE scores at admission chest radiography compared with White or non-Hispanic patients (adjusted average difference, 1.6; 95% CI: 0.5, 2.7; P < .01). Adjustment for hypothesized mediators revealed that the association between race and/or ethnicity and mRALE scores was mediated by limited English proficiency (P < .01). Conclusion Non-White patients hospitalized with coronavirus disease 2019 infection were more likely to have a higher severity of disease on admission chest radiographs than White or non-Hispanic patients, and increased severity was associated with worse outcomes for all patients. © RSNA, 2020 Online supplemental material is available for this article.

OBJECTIVE. The purpose of this study is to characterize the CT findings of 30 children from mainland China who had laboratory-confirmed coronavirus disease (COVID-19). Although recent American College of Radiology recommendations assert that CT should not be used as a screening or diagnostic tool for patients with suspected COVID-19, radiologists should be familiar with the imaging appearance of this disease to identify its presence in patients undergoing CT for other reasons. MATERIALS AND METHODS. We retrospectively reviewed the CT findings and clinical symptoms of 30 pediatric patients with laboratory-confirmed COVID-19 who were seen at six centers in China from January 23, 2020, to February 8, 2020. Patient age ranged from 10 months to 18 years. Patients older than 18 years of age or those without chest CT examinations were excluded. Two cardiothoracic radiologists and a cardiothoracic imaging fellow characterized and scored the extent of lung involvement. Cohen kappa coefficient was used to calculate interobserver agreement between the readers. RESULTS. Among children, CT findings were often negative (77%). Positive CT findings seen in children included ground-glass opacities with a peripheral lung distribution, a crazy paving pattern, and the halo and reverse halo signs. There was a correlation between increasing age and increasing severity of findings, consistent with reported symptomatology in children. Eleven of 30 patients (37%) underwent follow-up chest CT, with 10 of 11 examinations (91%) showing no change, raising questions about the utility of CT in the diagnosis and management of COVID-19 in children. CONCLUSION. The present study describes the chest CT findings encountered in children with COVID-19 and questions the utility of CT in the diagnosis and management of pediatric patients.

Background In randomized controlled trials, lung cancer screening with low-dose chest computed tomography (LCS) has been reported to reduce lung cancer mortality. Although initial studies suggested that only approximately 5% of eligible patients have undergone LCS, recent studies have indicated that use of LCS may be increasing nationwide. The objective of the current study was to estimate recent LCS use using cross-sectional survey data from the 2018 Behavioral Risk Factor Surveillance System (BRFSS) survey. Methods The BRFSS is a nationally representative, cross-sectional telephone survey of adults in the United States (response rate of approximately 50%). The 2018 BRFSS survey included questions regarding LCS eligibility and use in 8 states. The primary outcome was the percentage of participants (aged 55-79 years with a smoking history of >30 pack-years) who reported undergoing LCS. Logistic regression analyses evaluated the association between LCS use and sociodemographic characteristics, adjusted for potential confounders and accounting for complex survey design elements. Results A total of 26,910 participants were included, 9.9% of whom were eligible for LCS (95% CI, 8.8%-10.6%). Of the eligible patients, 19.2% reported undergoing LCS (95% CI, 14.0%-24.4%). Approximately 16.4% of current smokers were eligible for LCS (95% CI, 14.2%-18.6%). In our multiple variable analyses of eligible patients, age, sex, marital status, current smoking status, and race were not found to be associated with statistically significant differences in reported LCS (P > .05). Retired patients, patients with personal physicians, and patients who did not complete a high school education were more likely to report receiving LCS (P Conclusions Compared with previously published studies, the results of the current study suggested that LCS use is increasing. However, LCS use remains low (19%) among eligible participants.

The inability to accurately, efficiently label large, open-access medical imaging datasets limits the widespread implementation of artificial intelligence models in healthcare. There have been few attempts, however, to automate the annotation of such public databases; one approach, for example, focused on labor-intensive, manual labeling of subsets of these datasets to be used to train new models. In this study, we describe a method for standardized, automated labeling based on similarity to a previously validated, explainable AI (xAI) model-derived-atlas, for which the user can specify a quantitative threshold for a desired level of accuracy (the probability-of-similarity, pSim metric). We show that our xAI model, by calculating the pSim values for each clinical output label based on comparison to its training-set derived reference atlas, can automatically label the external datasets to a user-selected, high level of accuracy, equaling or exceeding that of human experts. We additionally show that, by fine-tuning the original model using the automatically labelled exams for retraining, performance can be preserved or improved, resulting in a highly accurate, more generalized model.

Interstitial lung diseases (ILDs) may present a diagnostic dilemma due to their many classifications and overlapping imaging findings. In this review, we present an algorithmic approach for assessing ILDs based on identifying and understanding key imaging features to aid in narrowing a differential diagnosis or reaching a specific diagnosis. We use the recently introduced Interstitial Lung Disease Reporting And Data System (ILD-RADS) as a framework for our discussion.

Purpose To determine the variability in out-of-pocket costs of lung cancer screening (LCS) for uninsured patients and assess accessibility of this information by telephone or Internet. Methods LCS centers from the ACR’s LCS database were randomly selected. Centers were called between July and August 2019 to determine out-of-pocket cost. Telephone call variables, accessibility of cost information on screening centers’ websites, screening centers’ chargemasters, and publicly available facility and state insurance coverage variables were obtained. Cost information was summarized using descriptive analyses. Multiple variable linear regression analyses were conducted to evaluate effects of facility and state-level characteristics on out-of-pocket costs. Results Fifty-five ACR-accredited LCS centers were included with 78% (43 of 55) willing to provide out-of-pocket cost. Average out-of-pocket cost was $583 ± $607 (mean ± standard deviation), range $49 to $2,409. Average telephone call length 6 ± 3.8 min. Two of fifty-five screening centers’ websites provided out-of-pocket cost information, and one matched cost given over the telephone. A chargemaster was found for 30 of 55 screening centers. No statistically significant differences in out-of-pocket costs were found by geographic region, state percentages of uninsured residents, state percentages of residents with public insurance, or facility safety net hospital affiliation. Discussion Out-of-pocket LCS costs for uninsured patients and availability of this information is highly variable. Radiology practices should be aware of this variability that may influence participation rates among uninsured patients.

For diagnosis of coronavirus disease 2019 (COVID-19), a SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test is routinely used. However, this test can take up to 2 d to complete, serial testing may be required to rule out the possibility of false negative results and there is currently a shortage of RT-PCR test kits, underscoring the urgent need for alternative methods for rapid and accurate diagnosis of patients with COVID-19. Chest computed tomography (CT) is a valuable component in the evaluation of patients with suspected SARS-CoV-2 infection. Nevertheless, CT alone may have limited negative predictive value for ruling out SARS-CoV-2 infection, as some patients may have normal radiological findings at early stages of the disease. In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19. Among a total of 905 patients tested by real-time RT-PCR assay and next-generation sequencing RT-PCR, 419 (46.3%) tested positive for SARS-CoV-2. In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT-PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.

Objective: To predict short-term outcomes in hospitalized COVID-19 patients using a model incorporating clinical variables with automated convolutional neural network (CNN) chest radiograph analysis. Methods: A retrospective single center study was performed on patients consecutively admitted with COVID-19 between March 14 and April 21 2020. Demographic, clinical and laboratory data were collected, and automated CNN scoring of the admission chest radiograph was performed. The two outcomes of disease progression were intubation or death within 7 days and death within 14 days following admission. Multiple imputation was performed for missing predictor variables and, for each imputed data set, a penalized logistic regression model was constructed to identify predictors and their functional relationship to each outcome. Cross-validated area under the characteristic (AUC) curves were estimated to quantify the discriminative ability of each model. Results: 801 patients (median age 59; interquartile range 46–73 years, 469 men) were evaluated. 36 patients were deceased and 207 were intubated at 7 days and 65 were deceased at 14 days. Cross-validated AUC values for predictive models were 0.82 (95% CI, 0.79–0.86) for death or intubation within 7 days and 0.82 (0.78–0.87) for death within 14 days. Automated CNN chest radiograph score was an important variable in predicting both outcomes. Conclusion: Automated CNN chest radiograph analysis, in combination with clinical variables, predicts short-term intubation and death in patients hospitalized for COVID-19 infection. Chest radiograph scoring of more severe disease was associated with a greater probability of adverse short-term outcome. Advances in knowledge: Model-based predictions of intubation and death in COVID-19 can be performed with high discriminative performance using admission clinical data and convolutional neural network-based scoring of chest radiograph severity.

Hundreds of imaging-based artificial intelligence (AI) models have been developed in response to the COVID-19 pandemic. AI systems that incorporate imaging have shown promise in primary detection, severity grading, and prognostication of outcomes in COVID-19, and have enabled integration of imaging with a broad range of additional clinical and epidemiologic data. However, systematic reviews of AI models applied to COVID-19 medical imaging have highlighted problems in the field, including methodologic issues and problems in real-world deployment. Clinical use of such models should be informed by both the promise and potential pitfalls of implementation. How does a practicing radiologist make sense of this complex topic, and what factors should be considered in the implementation of AI tools for imaging of COVID-19? This critical review aims to help the radiologist understand the nuances that impact the clinical deployment of AI for imaging of COVID-19. We review imaging use cases for AI models in COVID-19 (e.g., diagnosis, severity assessment, and prognostication) and explore considerations for AI model development and testing, deployment infrastructure, clinical user interfaces, quality control, and institutional review board and regulatory approvals, with a practical focus on what a radiologist should consider when implementing an AI tool for COVID-19.

Background Recent studies have demonstrated a complex interplay between comorbid cardiovascular disease, COVID-19 pathophysiology, and poor clinical outcomes. Coronary artery calcification (CAC) may therefore aid in risk stratification of COVID-19 patients. Methods Non-contrast chest CT studies on 180 COVID-19 patients ≥ age 21 admitted from March 1, 2020 to April 27, 2020 were retrospectively reviewed by two radiologists to determine CAC scores. Following feature selection, multivariable logistic regression was utilized to evaluate the relationship between CAC scores and patient outcomes. Results The presence of any identified CAC was associated with intubation (AOR: 3.6, CI: 1.4–9.6) and mortality (AOR: 3.2, CI: 1.4–7.9). Severe CAC was independently associated with intubation (AOR: 4.0, CI: 1.3–13) and mortality (AOR: 5.1, CI: 1.9–15). A greater CAC score (UOR: 1.2, CI: 1.02–1.3) and number of vessels with calcium (UOR: 1.3, CI: 1.02–1.6) was associated with mortality. Visualized coronary stent or coronary artery bypass graft surgery (CABG) had no statistically significant association with intubation (AOR: 1.9, CI: 0.4–7.7) or death (AOR: 3.4, CI: 1.0–12). Conclusion COVID-19 patients with any CAC were more likely to require intubation and die than those without CAC. Increasing CAC and number of affected arteries was associated with mortality. Severe CAC was associated with higher intubation risk. Prior CABG or stenting had no association with elevated intubation or death.

Trauma is the leading cause of death among individuals under 40 years of age, and pulmonary trauma is common in high-impact injuries. Unlike most other organs, the lung is elastic and distensible, with a physiologic capacity to withstand significant changes in contour and volume. The most common types of lung parenchymal injury are contusions, lacerations, and hematomas, each having characteristic imaging appearances. A less common type of lung injury is herniation. Chest radiography is often the first-line imaging modality performed in the assessment of the acutely injured patient, although there are inherent limitations in the use of this modality in trauma. CT images are more accurate for the assessment of the nature and extent of pulmonary injury than the single-view anteroposterior chest radiograph that is typically obtained in the trauma bay. However, the primary limitations of CT concern the need to transport the patient to the CT scanner and a longer processing time. The American Association for the Surgery of Trauma has established the most widely used grading scale to describe lung injury, which serves to communicate severity, guide management, and provide useful prognostic factors in a systematic fashion. The authors provide an in-depth exploration of the most common types of pulmonary parenchymal, pleural, and airway injuries. Injury grading, patient management, and potential complications of pulmonary injury are also discussed. ©RSNA, 2021.

Background Coronary artery calcification (CAC) is a common and important incidental finding in low-dose computed tomography (LDCT) performed for lung cancer screening (LCS). The impact of these incidental findings on patient management is unclear. Purpose The goals of our study were to determine the impact of reporting CAC on patient management and to determine whether standardized reporting of CAC affects the likelihood of future interventions. Methods In this IRB-approved retrospective study, we queried our LCS database for reports of LDCT performed between January 2016 and September 2018. All reports with significant findings of CAC designated with the letter "S" for any Lung-RADS category were selected. The grading of CAC was extracted from the reports. Medical records were reviewed for each patient to determine demographics, clinical history, medications, and cardiac-related diagnostic and interventional procedures. The changes in management after the report of significant CAC on LDCT were documented. Statistical analysis with Student t test and Pearson χ test was performed. Results A total of 756/3110 patients (mean age: 67±6.4 y; M=466, 61.6%: F=290, 38.4%) were reported to have significant CAC on LDCT for LCS. Of them, 236/756 patients (31.2%) had established coronary artery disease (CAD) at baseline, before the initial LDCT. A change in management was observed in 155/756 patients (20.5%). The most common changes in management included the following: alteration in medication regimen (n=114/155, 73.5%), stress testing (n=65/155, 41.9%), and referral to a cardiologist (36/155, 23.2%). Percutaneous coronary intervention (4, 2.6%) and surgery (3, 1.9%) were uncommon. Changes in management were more common in those without established CAD and in those whose CAC was semiquantitatively graded (35% vs. 25%, P=0.02). Conclusion CAC is a common significant finding in LDCT for LCS. Reporting of CAC in patients with nonestablished CAD and semiquantitative assessment resulted in changes in management.

Calcifying fibrous pseudotumor (CFP) is a rare, benign soft tissue tumor that may uncommonly arise in the pleura. These tumors can show multifocal dissemination across the pleural surface, but the mechanism underlying this dissemination is unclear. Review of previously reported cases of pleural CFP demonstrates a strong predilection for basal and diaphragmatic pleural surfaces, and a significantly higher rate of multifocality compared with other locations. We present a 59-year-old male with multiple CFP of the pleura. Reactive-appearing adhesions spanning the pleural surfaces were present, and by electron microscopy, were involved by tumor. We suggest this is the likely mode of dissemination across the pleural surfaces.

Purpose: To improve and test the generalizability of a deep learning-based model for assessment of COVID-19 lung disease severity on chest radiographs (CXRs) from different patient populations. Materials and Methods: A published convolutional Siamese neural network-based model previously trained on hospitalized patients with COVID-19 was tuned using 250 outpatient CXRs. This model produces a quantitative measure of COVID-19 lung disease severity (pulmonary x-ray severity (PXS) score). The model was evaluated on CXRs from four test sets, including 3 from the United States (patients hospitalized at an academic medical center (N=154), patients hospitalized at a community hospital (N=113), and outpatients (N=108)) and 1 from Brazil (patients at an academic medical center emergency department (N=303)). Radiologists from both countries independently assigned reference standard CXR severity scores, which were correlated with the PXS scores as a measure of model performance (Pearson r). The Uniform Manifold Approximation and Projection (UMAP) technique was used to visualize the neural network results. Results: Tuning the deep learning model with outpatient data improved model performance in two United States hospitalized patient datasets (r=0.88 and r=0.90, compared to baseline r=0.86). Model performance was similar, though slightly lower, when tested on the United States outpatient and Brazil emergency department datasets (r=0.86 and r=0.85, respectively). UMAP showed that the model learned disease severity information that generalized across test sets. Conclusions: Performance of a deep learning-based model that extracts a COVID-19 severity score on CXRs improved using training data from a different patient cohort (outpatient versus hospitalized) and generalized across multiple populations.

ObjectivesTo assess the diagnostic performance of lung point-of-care ultrasound (POCUS) compared to either a positive nucleic acid test (NAT) or a COVID-19-typical pattern on computed tomography (CT) and to evaluate opportunities to simplify a POCUS algorithm.MethodsHospital-admitted adult inpatients with (1) either confirmed or suspected COVID-19 and (2) a completed or ordered CT within the preceding 24 hours were recruited. Twelve lung zones were scanned with a handheld POCUS machine. POCUS, CT, and X-ray (CXR) images were reviewed independently by blinded experts. A simplified POCUS algorithm was developed via machine learning.ResultsOf 79 enrolled subjects, 26.6% had a positive NAT and 31.6% had a CT typical for COVID-19. The receiver operator curve (ROC) for a 12-zone POCUS protocol had an area under the curve (AUC) of 0.787 for positive NAT and 0.820 for typical CT. A simplified four-zone protocol had an AUC of 0.862 for typical CT and 0.862 for positive NAT. CT had an AUC of 0.815 for positive NAT; CXR had AUCs of 0.793 for positive NAT and 0.733 for typical CT. Performance of the four-zone protocol was superior to CXR for positive NAT (p=0.0471). Using a two-point cutoff system, the four-zone POCUS protocol had a sensitivity of 0.920 and 0.904 compared to CT and NAT, respectively, at the lower cutoff; it had a specificity of 0.926 and 0.948 at the higher cutoff, respectively.ConclusionPOCUS outperformed CXR to predict positive NAT. POCUS could potentially replace other chest imaging for persons under investigation for COVID-19.

BACKGROUND. Previous studies compared CT findings of COVID-19 pneumonia with those of other infections; however, to our knowledge, no studies to date have included noninfectious organizing pneumonia (OP) for comparison. OBJECTIVE. The objectives of this study were to compare chest CT features of COVID-19, influenza, and OP using a multireader design and to assess the performance of radiologists in distinguishing between these conditions. METHODS. This retrospective study included 150 chest CT examinations in 150 patients (mean [± SD] age, 58 ± 16 years) with a diagnosis of COVID-19, influenza, or non-infectious OP (50 randomly selected abnormal CT examinations per diagnosis). Six thoracic radiologists independently assessed CT examinations for 14 individual CT findings and for Radiological Society of North America (RSNA) COVID-19 category and recorded a favored diagnosis. The CT characteristics of the three diagnoses were compared using random-effects models; the diagnostic performance of the readers was assessed. RESULTS. COVID-19 pneumonia was significantly different (p < .05) from influenza pneumonia for seven of 14 chest CT findings, although it was different (p < .05) from OP for four of 14 findings (central or diffuse distribution was seen in 10% and 7% of COVID-19 cases, respectively, vs 20% and 21% of OP cases, respectively; unilateral distribution was seen in 1% of COVID-19 cases vs 7% of OP cases; non-tree-in-bud nodules was seen in 32% of COVID-19 cases vs 53% of OP cases; tree-in-bud nodules were seen in 6% of COVID-19 cases vs 14% of OP cases). A total of 70% of cases of COVID-19, 33% of influenza cases, and 47% of OP cases had typical findings according to RSNA COVID-19 category assessment (p < .001). The mean percentage of correct favored diagnoses compared with actual diagnoses was 44% for COVID-19, 29% for influenza, and 39% for OP. The mean diagnostic accuracy of favored diagnoses was 70% for COVID-19 pneumonia and 68% for both influenza and OP. CONCLUSION. CT findings of COVID-19 substantially overlap with those of influenza and, to a greater extent, those of OP. The diagnostic accuracy of the radiologists was low in a study sample that contained equal proportions of these three types of pneumonia. CLINICAL IMPACT. Recognized challenges in diagnosing COVID-19 by CT are furthered by the strong overlap observed between the appearances of COVID-19 and OP on CT. This challenge may be particularly evident in clinical settings in which there are substantial proportions of patients with potential causes of OP such as ongoing cancer therapy or autoimmune conditions.

Background Lung cancer screening (LCS) with low-dose computed tomography (LDCT) helps early lung cancer detection, commonly presenting as small pulmonary nodules. Artificial intelligence (AI)-based vessel suppression (AI-VS) and automatic detection (AI-AD) algorithm can improve detection of subsolid nodules (SSNs) on LDCT. We assessed the impact of AI-VS and AI-AD in detection and classification of SSNs [ground-glass nodules (GGNs) and part-solid nodules (PSNs)], on LDCT performed for LCS. Methods Following regulatory approval, 123 LDCT examinations with sub-solid pulmonary nodules (average diameter ≥6 mm) were processed to generate three image series for each examination-unprocessed, AI-VS, and AI-AD series with annotated lung nodules. Two thoracic radiologists in consensus formed the standard of reference (SOR) for this study. Two other thoracic radiologists (R1 and R2; 5 and 10 years of experience in thoracic CT image interpretation) independently assessed the unprocessed images alone, then together with AI-VS series, and finally with AI-AD for detecting all ≥6 mm GGN and PSN. We performed receiver operator characteristics (ROC) and Cohen's Kappa analyses for statistical analyses. Results On unprocessed images, R1 and R2 detected 232/310 nodules (R1: 114 GGN, 118 PSN) and 255/310 nodules (R2: 122 GGN, 133 PSN), respectively (P>0.05). On AI-VS images, they detected 249/310 nodules (119 GGN, 130 PSN) and 277/310 nodules (128 GGN, 149 PSN), respectively (P≥0.12). When compared to the SOR, accuracy (AUC) for detection of PSN on the AI-VS images (AUC 0.80-0.81) was greater than on the unprocessed images (AUC 0.70-0.76). AI-VS images enabled detection of solid components in five nodules deemed as GGN on the unprocessed images. Accuracy of AI-AD was lower than both the radiologists (AUC 0.60-0.72). Conclusions AI-VS improved the detection and classification of SSN into GGN and PSN on LDCT of the chest for the two radiologist (R1 and R2) readers.

The COVID-19 pandemic has led to delays in cancer diagnosis, in part due to postponement of cancer screening. We used Google Trends data to assess public attention to cancer screening during the first peak of the COVID-19 pandemic. Search volume for terms related to established cancer screening tests (“colonoscopy,” “mammogram,” “lung cancer screening,” and “pap smear”) showed a marked decrease of up to 76% compared to the pre-pandemic period, a significantly greater drop than for search volume for terms denoting common chronic diseases. Maintaining awareness of cancer screening during future public health crises may decrease delays in cancer diagnosis.

Background: Establishing a diagnosis of Granulomatous Lymphocytic-Interstitial Lung Disease (GL-ILD) is difficult due to the overlapping CT imaging and histologic features, and are often confused with infection, sarcoidosis and/or follicular bronchiolitis. Research Question: Identify specific CT imaging features and clinical characteristics to suggest a confident diagnosis of Granulomatous Lymphocytic-Interstitial Lung Disease (GL-ILD).Study Design and Methods: IRB-approved retrospective case series study involving the review of the electronic medical record and CT chest imaging of eight patients with GL-ILD.Results: Bronchocentric airway-centered lower lobe predominant (part solid nodules more common than ground glass or solid nodules) ranging from 5 to 10 mm in size were found consistently in a majority of the eight patients with GL-ILD. Interpretation: In combination with the above pulmonary nodular pattern, mediastinal and hilar lymphadenopathy in conjunction, either splenomegaly or splenectomy and/or abdominal lymphadenopathy are excellent CT imaging features to prospectively suggest the diagnosis of GL-ILD in a patient with CVID.

See also the editorial by Little in this issue.

Rationale and Objectives Radiographic findings of COVID-19 pneumonia can be used for patient risk stratification; however, radiologist reporting of disease severity is inconsistent on chest radiographs (CXRs). We aimed to see if an artificial intelligence (AI) system could help improve radiologist interrater agreement. Materials and Methods We performed a retrospective multi-radiologist user study to evaluate the impact of an AI system, the PXS score model, on the grading of categorical COVID-19 lung disease severity on 154 chest radiographs into four ordinal grades (normal/minimal, mild, moderate, and severe). Four radiologists (two thoracic and two emergency radiologists) independently interpreted 154 CXRs from 154 unique patients with COVID-19 hospitalized at a large academic center, before and after using the AI system (median washout time interval was 16 days). Three different thoracic radiologists assessed the same 154 CXRs using an updated version of the AI system trained on more imaging data. Radiologist interrater agreement was evaluated using Cohen and Fleiss kappa where appropriate. The lung disease severity categories were associated with clinical outcomes using a previously published outcomes dataset using Fisher's exact test and Chi-square test for trend. Results Use of the AI system improved radiologist interrater agreement (Fleiss κ = 0.40 to 0.66, before and after use of the system). The Fleiss κ for three radiologists using the updated AI system was 0.74. Severity categories were significantly associated with subsequent intubation or death within 3 days. Conclusion An AI system used at the time of CXR study interpretation can improve the interrater agreement of radiologists.

Background: Clinical and radiologic studies investigating Coronavirus disease 2019 (COVID-19) indicate that a possible cause of severe hypoxia is marked ventilation-perfusion (VA/Q) mismatch. Published histopathology reports diffuse alveolar damage (DAD) in fatal COVID-19 is indistinguishable from other causes of DAD. We compared lung parenchymal and vascular alterations between COVID-19 and DAD of other etiologies using a multidimensional approach. Methods: This autopsy cohort consisted of consecutive COVID-19 patients (n=20) and patients with clinical acute respiratory distress syndrome and histologic DAD (n=21; non-COVID-19 viral and non-viral etiologies). Premortem chest CTs were evaluated for mosaic attenuation and vascular changes. Postmortem lung tissues were compared using histopathological, immunohistochemical, transcriptomics and computational analyses. Machine-learning-derived morphometric analysis of microvasculature was performed, with a random forest classifier quantifying vascular congestion (VSCong), in different microscopic compartments. Findings: On premortem CT, COVID-19 patients showed more mosaic attenuation (p

BACKGROUND AND PURPOSE: Severe respiratory distress in patients with COVID-19 has been associated with higher rate of neurologic manifestations. Our aim was to investigate whether the severity of chest imaging findings among patients with coronavirus disease 2019 (COVID-19) correlates with the risk of acute neuroimaging findings. MATERIALS AND METHODS: This retrospective study included all patients with COVID-19 who received care at our hospital between March 3, 2020, and May 6, 2020, and underwent chest imaging within 10 days of neuroimaging. Chest radiographs were assessed using a previously validated automated neural network algorithm for COVID-19 (Pulmonary X-ray Severity score). Chest CTs were graded using a Chest CT Severity scoring system based on involvement of each lobe. Associations between chest imaging severity scores and acute neuroimaging findings were assessed using multivariable logistic regression. RESULTS: Twenty-four of 93 patients (26%) included in the study had positive acute neuroimaging findings, including intracranial hemorrhage (n = 7), infarction (n = 7), leukoencephalopathy (n = 6), or a combination of findings (n = 4). The average length of hospitalization, prevalence of intensive care unit admission, and proportion of patients requiring intubation were significantly greater in patients with acute neuroimaging findings than in patients without them (P < .05 for all). Compared with patients without acute neuroimaging findings, patients with acute neuroimaging findings had significantly higher mean Pulmonary X-ray Severity scores (5.0 [SD, 2.9] versus 9.2 [SD, 3.4], P < .001) and mean Chest CT Severity scores (9.0 [SD, 5.1] versus 12.1 [SD, 5.0], P = .041). The pulmonary x-ray severity score was a significant predictor of acute neuroimaging findings in patients with COVID-19. CONCLUSIONS: Patients with COVID-19 and acute neuroimaging findings had more severe findings on chest imaging on both radiographs and CT compared with patients with COVID-19 without acute neuroimaging findings. The severity of findings on chest radiography was a strong predictor of acute neuroimaging findings in patients with COVID-19.

Background Concerns about false-negative (FN) severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) nucleic acid amplification tests (NAATs) have prompted recommendations for repeat testing if suspicion for coronavirus disease 2019 (COVID-19) infection is moderate to high. However, the frequency of FNs and patient characteristics associated with FNs are poorly understood. Methods We retrospectively reviewed test results from 15 011 adults who underwent ≥1 SARS-CoV-2 NAATs; 2699 had an initial negative NAAT and repeat testing. We defined FNs as ≥1 negative NAATs followed by a positive NAAT within 14 days during the same episode of illness. We stratified subjects with FNs by duration of symptoms before the initial FN test (≤5 days versus >5 days) and examined their clinical, radiologic, and laboratory characteristics. Results Sixty of 2699 subjects (2.2%) had a FN result during the study period. The weekly frequency of FNs among subjects with repeat testing peaked at 4.4%, coinciding with peak NAAT positivity (38%). Most subjects with FNs had symptoms (52 of 60; 87%) and chest radiography (19 of 32; 59%) consistent with COVID-19. Of the FN NAATs, 18 of 60 (30%) were performed early (ie, ≤1 day of symptom onset), and 18 of 60 (30%) were performed late (ie, >7 days after symptom onset) in disease. Among 17 subjects with 2 consecutive FNs on NP NAATs, 9 (53%) provided lower respiratory tract (LRT) specimens for testing, all of which were positive. Conclusions Our findings support repeated NAATs among symptomatic patients, particularly during periods of higher COVID-19 incidence. The LRT testing should be prioritized to increase yield among patients with high clinical suspicion for COVID-19.