Pitfalls in Interpretive Applications of Artificial Intelligence in Radiology.

Interpretive artificial intelligence (AI) tools are poised to change the future of radiology. However, certain pitfalls may pose particular challenges for optimal AI interpretative performance. These include anatomic variants, age-related changes, postoperative changes, medical devices, image artifacts, lack of integration of prior and concurrent imaging examinations and clinical information, as well as the satisfaction-of-search effect. Model training and development should account for such pitfalls, to minimize errors and optimize interpretation accuracy. More broadly, AI algorithms should be exposed to diverse and complex training data sets, to yield a holistic interpretation that considers all relevant information beyond the individual examination. Successful clinical deployment of AI tools will require that radiologist end-users recognize these pitfalls and other limitations of the available models. Furthermore, developers should incorporate explainable AI techniques (e.g., heat maps) into their tools, to improve radiologists' understanding of model outputs and to enable radiologists to provide feedback for guiding continuous learning and iterative refinement. In this article, we provide an overview of common pitfalls that radiologists may encounter when using interpretive AI products in daily practice. We present how such pitfalls lead to AI errors and offer potential strategies that AI developers may use for their mitigation.

A systematic review and meta-analysis on the diagnostic utility of ultrasound for clavicle fractures.

BACKGROUND: Ultrasound's real-time, high-resolution imaging, and accessibility at the point of care make it a valuable tool for diagnosing clavicle fractures, with growing evidence supporting its diagnostic accuracy compared to other imaging modalities. OBJECTIVE: To assess the diagnostic utility of ultrasound in detecting clavicle fractures. METHODS: A systematic review and meta-analysis were conducted by performing a comprehensive literature search in PubMed, Scopus, Web of Science, and Embase databases up to March 10, 2023, following established guidelines. Eligible studies that reported outcomes of interest were included, relevant data elements were extracted, and data analysis was performed using STATA software version 17.0. RESULTS: Meta-analysis of seven included studies showed high-pooled sensitivity (0.94) and specificity (0.98) values for ultrasonography in diagnosing clavicle fractures, with low to moderate heterogeneity for sensitivity and high heterogeneity for specificity. Meta-regression and subgroup analyses revealed that pediatric studies had higher sensitivity but significantly lower specificity (P=0.01) compared to mixed or adult studies. Additional subgroup analysis in the pediatric group indicated decreased heterogeneity for specificity. Fagan plot analysis demonstrated favorable post-test probabilities for both positive and negative results across varying pre-test probabilities. Additionally, the likelihood ratio scatter matrix showed moderate to high test performance for both exclusion and confirmation purposes. CONCLUSION: The current literature supports ultrasound as a reliable imaging modality for detecting clavicle fractures. It offers accurate diagnosis without exposing patients, especially children, to radiation.

Imaging of lower extremity infections: predisposing conditions, atypical infections, mimics, and differentiating features.

Imaging evaluation for lower extremity infections can be complicated, especially in the setting of underlying conditions and with atypical infections. Predisposing conditions are discussed, including diabetes mellitus, peripheral arterial disease, neuropathic arthropathy, and intravenous drug abuse, as well as differentiating features of infectious versus non-infectious disease. Atypical infections such as viral, mycobacterial, fungal, and parasitic infections and their imaging features are also reviewed. Potential mimics of lower extremity infection including chronic nonbacterial osteomyelitis, foreign body granuloma, gout, inflammatory arthropathies, lymphedema, and Morel-Lavallée lesions, and their differentiating features are also explored.

Lower extremity infections: Essential anatomy and multimodality imaging findings.

In modern practice, imaging plays an integral role in the diagnosis, evaluation of extent, and treatment planning for lower extremity infections. This review will illustrate the relevant compartment anatomy of the lower extremities and highlight the role of plain radiographs, CT, US, MRI, and nuclear medicine in the diagnostic workup. The imaging features of cellulitis, abscess and phlegmon, necrotizing soft tissue infection, pyomyositis, infectious tenosynovitis, septic arthritis, and osteomyelitis are reviewed. Differentiating features from noninfectious causes of swelling and edema are discussed.

Artificial intelligence in the detection of non-biological materials.

Artificial Intelligence (AI) has emerged as a transformative force within medical imaging, making significant strides within emergency radiology. Presently, there is a strong reliance on radiologists to accurately diagnose and characterize foreign bodies in a timely fashion, a task that can be readily augmented with AI tools. This article will first explore the most common clinical scenarios involving foreign bodies, such as retained surgical instruments, open and penetrating injuries, catheter and tube malposition, and foreign body ingestion and aspiration. By initially exploring the existing imaging techniques employed for diagnosing these conditions, the potential role of AI in detecting non-biological materials can be better elucidated. Yet, the heterogeneous nature of foreign bodies and limited data availability complicates the development of computer-aided detection models. Despite these challenges, integrating AI can potentially decrease radiologist workload, enhance diagnostic accuracy, and improve patient outcomes.

Diagnostic utility of whole-body computed tomography/pan-scan in trauma: a systematic review and meta-analysis study.

Trauma is a significant cause of mortality and morbidity. It is crucial to diagnose trauma patients quickly to provide effective treatment interventions in such conditions. Whole-body computed tomography (WBCT)/pan-scan is an imaging technique that enables a faster and more efficient diagnosis for polytrauma patients. The purpose of this systematic review and meta-analysis is to evaluate the efficacy of WBCT in diagnosing injuries in polytrauma patients. We will also assess its impact on the mortality rate and length of hospital stay among trauma centers between patients who underwent WBCT and those who did not (non-WBCT). Twenty-seven studies meeting our inclusion criteria were selected among PubMed, Scopus, Web of Science, and Google Scholar. The criteria were centered on the significance of WBCT/pan-scan application in trauma patients. Stata version 15 was used to perform statistical analysis on the data. The authors have also used I2 statistics to evaluate heterogeneity. Egger and Begg's tests were performed to rule out any publication bias. Total of twenty-seven studies including 68,838 trauma patients with a mean age of 45.0 ± 24.7 years were selected. Motor vehicle collisions were the most common cause of blunt injuries (80.0%). Head, neck, and face injuries were diagnosed in 44% (95% CI, 0.28-0.60; I2 = 99.8%), 6% (95% CI, 0.02-0.09; I2 = 97.2%), and 9% (95% CI, 0.05-0.13; I2 = 97.1%), respectively. Chest injuries were diagnosed by WBCT in 39% (95% CI, 0.28-0.51; I2 = 99.8%), abdominal injuries in 23% (95% CI, 0.03-0.43; I2 = 99.9%) of cases, spinal injuries 19% (95% CI, 0.11-0.27; I2 = 99.4%), extremity injuries 33% (95% CI, 0.23-0.43; I2 = 99.2%), and pelvic injuries 11% (95% CI, 0.04-0.18; I2 = 97.4%). A mortality odd ratio of 0.94 (95% CI, 0.83-1.06; I2 = 40.1%) was calculated while comparing WBCT and non-WBCT groups. This systematic review and meta-analysis provide insight into the possible safety, efficacy, and efficiency of WBCT/pan-scan as a diagnostic tool for trauma patients with serious injuries, regardless of their hemodynamic status. In patients with serious injuries from trauma, whether or not there are indicators of hemodynamic instability, our recommended approach is to, wherever possible, perform a WBCT without stopping the hemostatic resuscitation. By using this technology, the optimal surgical strategy for these patients can be decided upon without causing any delays in their final care or greatly raising their radiation dose.

Computed tomography pulmonary angiography (CTPA) for the detection of pulmonary embolism (PE) among trauma patients: a systematic review and meta-analysis.

BACKGROUND AND OBJECTIVES: Computed tomography pulmonary angiography (CTPA) is a standard imaging technique employed for the detection of pulmonary embolism (PE). This systematic review and meta-analysis aims to examine the prevalence of PE among the trauma patients undergoing CTPA. METHODS: A comprehensive search across PubMed, Scopus, Google Scholar, and Web of Science yielded 13 studies encompassing 5,570 individuals conducted following Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guideline. Studies that used CTPA for the detection of PE among the trauma patients were selected. This resulted in an evaluation of prevalence, trauma types, clinical manifestations, radiological findings, and mortality rates of PE among traumatic patients undergoing CTPA. RESULTS: The overall prevalence of PE among trauma patients undergoing CTPA was 18% (95% CI = 13-24%). After pooling the existing data, femur fractures were determined to be the most prevalent trauma type (12%). The most prevalent clinical manifestations of PE among trauma patients included shortness of breath, chest pain, and altered vital signs. Radiological findings encompassed various pulmonary abnormalities, such as opacity, ground-glass opacities, and pleural effusions. Mortality rates of PE among the trauma patients ranged from 0% to 29.4% across the included studies. CONCLUSION: This study provides comprehensive insights into the prevalence, clinical manifestations, radiological findings and mortality of PE among trauma patients undergoing CTPA. According to our findings, lower threshold for CTPA is recommended in patients with lower extremity or spine fractures.

A meta-analysis on the diagnostic utility of ultrasound in pediatric distal forearm fractures.

Pediatric distal forearm fractures, comprising 30% of musculoskeletal injuries in children, are conventionally diagnosed using radiography. Ultrasound has emerged as a safer diagnostic tool, eliminating ionizing radiation, enabling bedside examinations with real-time imaging, and proving effective in non-hospital settings. The objective of this study is to evaluate the diagnostic efficacy of ultrasound for detecting distal forearm fractures in the pediatric population. A systematic review and meta-analysis were conducted through a comprehensive literature search in PubMed, Scopus, Web of Science, and Embase databases until October 1, 2023, following established guidelines. Eligible studies, reporting diagnostic accuracy measures of ultrasound in pediatric patients with distal forearm fractures, were included. Relevant data elements were extracted, and data analysis was performed. The analysis included 14 studies with 1377 patients, revealing pooled sensitivity and specificity of 94.5 (95% CI 92.7-95.9) and 93.5 (95% CI 89.6-96.0), respectively. Considering pre-test probabilities of 25%, 50%, and 75% for pediatric distal forearm fractures, positive post-test probabilities were 83%, 44%, and 98%, while negative post-test probabilities were 2%, 6%, and 15%, respectively. The bivariate model indicated significantly higher diagnostic accuracy in the subgroup with trained ultrasound performers vs. untrained performers (p = 0.03). Furthermore, diagnostic accuracy was significantly higher in the subgroup examining radius fractures vs. ulna fractures (p < 0.001), while no significant differences were observed between 4-view and 6-view ultrasound subgroups or between radiologist ultrasound interpreters and non-radiologist interpreters. This study highlighted ultrasound's reliability in detecting pediatric distal forearm fractures, emphasizing the crucial role of expertise in precisely confirming fractures through ultrasound examinations.

Diagnostic utility of ultrasound in pediatric nasal bone fractures: a systematic review and meta-analysis.

Ultrasonography, a radiation-free and cost-effective modality, stands out as a promising tool for evaluating nasal bone fractures. Despite limited literature on its pediatric application, there is an increasing recognition of its potential to enhance diagnostic precision. To evaluate the diagnostic efficacy of ultrasound in detecting pediatric nasal bone fractures. Employing established guidelines, a systematic review and meta-analysis were conducted through a comprehensive literature search in PubMed, Scopus, Web of Science, and Embase databases until December 5, 2023. Inclusion criteria encompassed studies reporting diagnostic accuracy measures of ultrasound in pediatric patients with nasal bone fractures. Data extraction and analysis were undertaken for the selected studies. Involving four studies with 277 patients, ultrasound demonstrated a pooled sensitivity of 66.1% (95% CI: 35.1-87.5%) and specificity of 86.8% (95% CI: 80.1-91.4%) in diagnosing pediatric nasal fractures. The area under the receiver operating characteristic curve (AUC) was 0.88 (95% CI: 0.72-0.93). After excluding an outlier study, sensitivity and specificity increased to 78.0% (95% CI: 65.6-86.9%) and 87.8 (95% CI: 78.1-93.6%), respectively, with an AUC of 0.79 (95% CI: 0.75-0.94). Pooled positive and negative likelihood ratios were 5.11 (95% CI: 2.12-9.15) and 0.40 (95% CI: 0.14-0.77) before exclusion and 6.75 (95% CI: 3.47-12.30) and 0.26 (95% CI: 0.15-0.40) after exclusion of an outlier study, respectively. This study highlighted ultrasonography's utility in diagnosing pediatric nasal bone fractures with high accuracy and specificity. However, caution is advised in relying solely on ultrasound due to suboptimal overall diagnostic performance, evident in likelihood ratios.

Diagnostic utility of multidetector CT scan in penetrating diaphragmatic injuries: A systematic review and meta-analysis.

Penetrating diaphragmatic injuries pose diagnostic and management challenges. Computed tomography (CT) scans are valuable for stable patients, but concern exists for missed injuries and complications in nonoperatively managed cases. The objective of this study was to explore the diagnostic utility of multidetector CT scan (MDCT) in identifying diaphragmatic injuries resulting from penetrating trauma. A systematic review and meta-analysis were conducted, following established guidelines, by searching PubMed, Scopus, Web of Science, and Embase databases up to July 6, 2023. Eligible studies reporting MDCT's diagnostic accuracy in detecting penetrating diaphragmatic injuries were included. Relevant data elements were extracted and analyzed using STATA software. The study included 9 articles comprising 294 patients with confirmed penetrating diaphragmatic injuries through surgical procedures. MDCT's diagnostic performance revealed a pooled sensitivity of 74% (95% CI: 56%-87%) and a pooled specificity of 92% (95% CI: 79%-97%) (Fig. two), with significant heterogeneity in both sensitivity and specificity across the studies. The Fagan plot demonstrated that higher pre-test probabilities correlated with higher positive post-test probabilities for penetrating diaphragmatic injury diagnosis using MDCT, but even with negative results, there remained a small chance of having the injury, especially in cases with higher pre-test probabilities. This study highlights MDCT's effectiveness in detecting diaphragmatic injury from penetrating trauma, with moderate to high diagnostic accuracy. However, larger sample sizes, multicenter collaborations, and prospective designs are needed to address observed heterogeneity, enhancing understanding and consistency in MDCT's diagnostic capabilities in this context.

Disparities in computed tomography utilization for pediatric blunt trauma: a systematic review and meta-analysis comparing pediatric and non-pediatric trauma centers.

Pediatric blunt trauma is a major cause of morbidity and mortality, and computed tomography (CT) imaging is vital for accurate evaluation and management. Pediatric trauma centers (PTCs) have selective CT practices, while non-PTCs may differ, resulting in potential variations in CT utilization. The objective of this study is to delineate disparities in CT utilization for pediatric blunt trauma patients between PTCs and non-PTCs. A systematic review and meta-analysis were conducted following established guidelines, searching PubMed, Scopus, and Web of Science up to March 3, 2023. All studies examining CT utilization in the management of pediatric (aged < 21 years) blunt trauma and specifying the type of trauma center(s) were included, and data were extracted and analyzed using STATA software version 17.0. An analysis of 30 studies revealed significant variations in CT scan utilization among pediatric blunt trauma patients across different types of trauma centers. PTCs exhibited lower pooled rates of abdominopelvic CT scans (35.4% vs. 44.9%, p < 0.01), cranial CT scans (36.9% vs. 42.9%, p < 0.01), chest CT scans (14.5% vs. 25.4%, p < 0.01), and cervical spine CT scans (23% vs. 45%, p < 0.01) compared to adult or mixed trauma centers (ATCs/MTCs). PTCs had a pooled rate of 54% for receiving at least one CT scan, while ATCs/MTCs had a higher rate of 69.3% (p < 0.05). The studies demonstrated considerable heterogeneity. These findings underscore the need to conduct further research to understand the reasons for the observed variations and to promote appropriate imaging usage, minimize radiation exposure, and encourage collaboration between pediatric and adult trauma centers.

How low can we go? Strategies and recommendations to combat the iodinated contrast shortage.

After GE Healthcare, one of the major producers of iodinated contrast dye, was forced to close their Shanghai factory due to a recent COVID-19 outbreak, iodinated contrast media shortages have rocked healthcare systems to their core. Clinicians nationwide are now caught between the desire to provide patients with optimal care and the need to conserve the minimal remaining supplies of iodinated contrast media. While GE Healthcare has reopened their factory and other sources of contrast agents have become available, experts report that levels may not return to normal through June 2022. Thankfully and ironically, radiology departments are all too familiar with COVID-19 associated operational disruptions and have been quick to adapt and implement novel protocols to evade this and other crises. Overall, this shortage emphasizes the importance of interprofessional communication, adaptation, and preparation for future emergent situations as this is not the first iodinated contrast material shortage and it likely would not be the last.

Coronavirus disease 2019 (COVID-19) in patients with systemic autoimmune diseases or vasculitis: radiologic presentation.

Coronavirus disease 2019 (COVID-19) has transformed into a worldwide challenge, since its outbreak in December 2019. Generally, patients with underlying medical conditions are at a higher risk of complications and fatality of pneumonias. Whether patients with systemic autoimmune diseases or vasculitides, are at increased risk for serious complications associated with COVID-19, is not established yet. Computed tomography (CT) has been employed as a diagnostic tool in the evaluation of patients with clinical suspicion of severe acute respiratory syndrome coronavirus 2 (SARS-Cov-2) infection with a reported sensitivity of higher than reverse transcription polymerase chain reaction (RT-PCR) test. Multifocal bilateral ground-glass opacities (GGOs) with peripheral and posterior distribution and subsequent superimposition of consolidations are considered the main imaging features of the disease in chest CT. However, chest CT images of underlying rheumatologic or autoimmune diseases or vasculitides, such as systemic sclerosis, systemic lupus erythematosus, rheumatoid arthritis, Behçet disease, and granulomatosis with polyangiitis, especially those with extensive lung involvement can overshadow or obliterate features of COVID-19. In addition, CT findings of such diseases may resemble manifestations of COVID-19 (such as ground glass opacities with or without superimposed consolidation), making the diagnosis of viral infections, more challenging on imaging. Comparing the imaging findings with prior studies (if available) for any interval change is the most helpful approach. Otherwise, the diagnosis of COVID-19 in such patients must be cautiously made according to the clinical context and laboratory results, considering a very high clinical index of suspicion on imaging.

COVID-19 pandemic revisited: lessons the radiology community has learned a year later.

For more than 1 year, COVID-19 pandemic has impacted every aspect of our lives. This paper reviews the major challenges that the radiology community faced over the past year and the impact the pandemic had on the radiology practice, radiologist-in-training education, and radiology research. The lessons learned from COVID-19 pandemic can help the radiology community to be prepared for future outbreaks and new pandemics, preserve good habits, enhance cancer screening programs, and adapt to the changes in radiology education and scientific meetings.

The lingering manifestations of COVID-19 during and after convalescence: update on long-term pulmonary consequences of coronavirus disease 2019 (COVID-19).

The long-term sequelae of coronavirus disease 2019 (COVID-19) are still unknown. Lessons from past viral epidemics reveal that, after recovery, patients with viral pulmonary infections can suffer from irreversible pulmonary dysfunction and demonstrate residual imaging or functional abnormalities. Residual ground glass opacities, consolidations, reticular and linear opacities, residual crazy paving pattern, melted sugar sign, and parenchymal fibrotic bands are several features found in the late or remission stages of COVID-19. These radiologic findings have been observed weeks after symptom onset, even after hospital discharge, and they may or may not correlate with clinical manifestations. High-resolution CT may be indicated to establish new baselines and track changes in residual impairments. In our previous review, we observed significant pulmonary sequelae in some COVID-19 survivors at follow-up. In this update, we review the current literature on the clinical and radiologic manifestations of post-recovery COVID-19 toward the end of hospital admission and after discharge.

Severe acute respiratory syndrome (SARS), Middle East respiratory syndrome (MERS), influenza, and COVID-19, beyond the lungs: a review article.

BACKGROUND: In the past 20 years four major viral infectious diseases outbreaks caused hundreds of thousands of deaths worldwide: SARS, Influenza H1N1, MERS, and COVID-19. They all present clinically initially as upper and lower respiratory tract infections and may progress to multi-organ failure. METHODS: This study was a systematic review of literature conducted in September 2020 to study extra-pulmonary complications of SARS, FLU, MERS, and current COVID-19. We carried out a systematic search using the keywords in online databases of PubMed, EMBASE, and Google Scholar until June 2020. OBJECTIVE: This article aims to review the most common extra-pulmonary manifestations of SARS, Influenza, MERS, and COVID-19. DISCUSSION: Several studies have reported extra-pulmonary conditions in patients diagnosed with SARS, Influenza, MERS, and COVID-19, either by direct viral injury or from the systemic response to the initial infection. CONCLUSION: SARS, Influenza, MERS, and COVID-19 have all been associated with dysfunction of kidneys, endocrine system, neuromuscular symptoms, perinatal complications, and myocardial injury. Progression from pulmonary disease to a systemic condition has a poor outcome and can result in multi-organ failure.

Neuroimaging and neurologic findings in COVID-19 and other coronavirus infections: A systematic review in 116 patients.

Various neurologic syndromes have been described in patients with COVID-19 and other coronavirus infections. In this paper, we systematically reviewed the available imaging findings of patients diagnosed with neurological symptoms associated with coronavirus infections. Diverse radiologic results in the context of different neurologic presentations have been demonstrated using CT and MRI. While many patients have normal imaging evaluations, some patients present with intra-axial and extra-axial abnormalities. Stroke (both ischemic and hemorrhagic), encephalomyelitis, meningitis, demyelinating disorders such as acute disseminated encephalomyelitis (ADEM), and encephalopathy have been reported. Familiarity with these radiologic patterns will guide radiologists and referring clinicians to consider coronavirus infections in patients with worsening or progressive neurologic findings, particularly during the current COVID-19 pandemic. As data on this topic is very limited, further research and investigation are required.

Coronavirus disease 2019 (COVID-19) imaging reporting and data system (COVID-RADS) and common lexicon: a proposal based on the imaging data of 37 studies.

BACKGROUND: In the vast majority of the laboratory-confirmed coronavirus disease 2019 (COVID-19) patients, computed tomography (CT) examinations yield a typical pattern and the sensitivity of this modality has been reported to be 97% in a large-scale study. Structured reporting systems simplify the interpretation and reporting of imaging examinations, serve as a framework for consistent generation of recommendations, and improve the quality of patient care. PURPOSE: To compose a comprehensive lexicon for description of the imaging findings and propose a grading system and structured reporting format for CT findings in COVID-19. MATERIAL AND METHODS: We updated our published systematic review on imaging findings in COVID-19 to include 37 published studies pertaining to diagnostic features of COVID-19 in chest CT. Using the reported imaging findings of 3647 patients, we summarized the typical chest CT findings, atypical features, and temporal changes of COVID-19 in chest CT. Subsequently, we extracted a list of descriptive terms and mapped it to the terminology that is commonly used in imaging literature. RESULTS: We composed a comprehensive lexicon that can be used for documentation and reporting of typical and atypical CT imaging findings in COVID-19 patients. Using the same data, we propose a grading system with five COVID-RADS categories. Each COVID-RADS grade corresponds to a low, moderate, or high level of suspicion for pulmonary involvement of COVID-19. CONCLUSION: The proposed COVID-RADS and common lexicon would improve the communication of findings to other healthcare providers, thus facilitating the diagnosis and management of COVID-19 patients. KEY POINTS: • Chest CT has high sensitivity in diagnosing the coronavirus disease 2019 (COVID-19). • Structured reporting systems simplify the interpretation and reporting of imaging examinations, serve as a framework for consistent generation of recommendations, and improve the quality of patient care. • The proposed COVID-RADS and common lexicon would improve the communication of findings to other healthcare providers, thus facilitating the diagnosis and management of COVID-19 patients.

Coronavirus Disease 2019 (COVID-19): A Systematic Review of Imaging Findings in 919 Patients.

OBJECTIVE. Available information on CT features of the 2019 novel coronavirus disease (COVID-19) is scattered in different publications, and a cohesive literature review has yet to be compiled. MATERIALS AND METHODS. This article includes a systematic literature search of PubMed, Embase (Elsevier), Google Scholar, and the World Health Organization database. RESULTS. Known features of COVID-19 on initial CT include bilateral multilobar ground-glass opacification (GGO) with a peripheral or posterior distribution, mainly in the lower lobes and less frequently within the right middle lobe. Atypical initial imaging presentation of consolidative opacities superimposed on GGO may be found in a smaller number of cases, mainly in the elderly population. Septal thickening, bronchiectasis, pleural thickening, and subpleural involvement are some of the less common findings, mainly in the later stages of the disease. Pleural effusion, pericardial effusion, lymphadenopathy, cavitation, CT halo sign, and pneumothorax are uncommon but may be seen with disease progression. Follow-up CT in the intermediate stage of disease shows an increase in the number and size of GGOs and progressive transformation of GGO into multifocal consolidative opacities, septal thickening, and development of a crazy paving pattern, with the greatest severity of CT findings visible around day 10 after the symptom onset. Acute respiratory distress syndrome is the most common indication for transferring patients with COVID-19 to the ICU and the major cause of death in this patient population. Imaging patterns corresponding to clinical improvement usually occur after week 2 of the disease and include gradual resolution of consolidative opacities and decrease in the number of lesions and involved lobes. CONCLUSION. This systematic review of current literature on COVID-19 provides insight into the initial and follow-up CT characteristics of the disease.

Radiology Perspective of Coronavirus Disease 2019 (COVID-19): Lessons From Severe Acute Respiratory Syndrome and Middle East Respiratory Syndrome.

OBJECTIVE. Since the outbreak of the novel coronavirus pulmonary illness coronavirus disease 2019 (COVID-19) in China, more than 79,000 people have contracted the virus worldwide. The virus is rapidly spreading with human-to-human transmission despite imposed precautions. Because similar pulmonary syndromes have been reported from other strains of the coronavirus family, our aim is to review the lessons from imaging studies obtained during severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS) outbreaks. CONCLUSION. The review of experiences with the MERS and SARS outbreaks will help us better understand the role of the radiologist in combating the outbreak of COVID-19. The known imaging manifestations of the novel coronavirus and the possible unknowns will also be discussed.