Showing papers in "Journal of Thoracic Imaging in 2020"

Radiological Society of North America Expert Consensus Statement on Reporting Chest CT Findings Related to COVID-19. Endorsed by the Society of Thoracic Radiology, the American College of Radiology, and RSNA - Secondary Publication.

Abstract: Routine screening CT for the identification of COVID-19 pneumonia is currently not recommended by most radiology societies. However, the number of CTs performed in persons under investigation (PUI) for COVID-19 has increased. We also anticipate that some patients will have incidentally detected findings that could be attributable to COVID-19 pneumonia, requiring radiologists to decide whether or not to mention COVID-19 specifically as a differential diagnostic possibility. We aim to provide guidance to radiologists in reporting CT findings potentially attributable to COVID-19 pneumonia, including standardized language to reduce reporting variability when addressing the possibility of COVID-19. When typical or indeterminate features of COVID-19 pneumonia are present in endemic areas as an incidental finding, we recommend contacting the referring providers to discuss the likelihood of viral infection. These incidental findings do not necessarily need to be reported as COVID-19 pneumonia. In this setting, using the term "viral pneumonia" can be a reasonable and inclusive alternative. However, if one opts to use the term "COVID-19" in the incidental setting, consider the provided standardized reporting language. In addition, practice patterns may vary, and this document is meant to serve as a guide. Consultation with clinical colleagues at each institution is suggested to establish a consensus reporting approach. The goal of this expert consensus is to help radiologists recognize findings of COVID-19 pneumonia and aid their communication with other healthcare providers, assisting management of patients during this pandemic.

Long-term Pulmonary Consequences of Coronavirus Disease 2019 (COVID-19): What We Know and What to Expect.

Abstract: C oronavirus disease 2019 (COVID-19), a viral pneumonia caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2 coronavirus), was initially called an outbreak and, in a short period of time, turned out to be the first pandemic from a coronavirus.1 Experts believe that the actual numbers of those infected are probably much higher than the reported confirmed numbers, as most cases of the disease are not diagnosed: not only because many patients have a subclinical or mild form of the disease and will not get medical attention, but also due to the limited diagnostic resources in many countries. Over the last couple of months, the clinical and imaging features of COVID-19 pneumonia have been discussed in numerous publications, and the major imaging findings of the disease have been described in detail. However, the postrecovery course of the disease, including its physical and psychological sequela, is not yet clear.2,3 The long-term effect of COVID-19 on lung parenchyma and pulmonary function remains an outstanding question. Although it is too early to completely answer this question, our limited observations demonstrate significant pulmonary sequela of the disease in some of the survivors (Fig. 1). In general, survivors of viral pneumonias are at risk of psychological and physical complications of the disease itself, as well as treatment-related lung damage and other organ injuries.4 Long-term lung disability is not uncommon in patients who have recovered from severe viral pneumonias. Although most survivors can return to work and normal life, a significant number of them will show residual ventilation and blood-gas diffusion abnormalities.4

Diagnostic Performance of Chest X-Ray for COVID-19 Pneumonia During the SARS-CoV-2 Pandemic in Lombardy, Italy.

Abstract: Chest x-ray (CXR) can play a role in diagnosing patients with suspected severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, but only few small-scale studies are available. We assessed the diagnostic performance of CXR in consecutive patients presenting at the emergency room at the Policlinico San Donato, Milan, Italy from February 24 to April 8, 2020 for suspected SARS-CoV-2 infection. The results of CXR were classified as positive or negative according to the original prospective radiologic reports. To overcome the limitations of reverse transcriptase-polymerase chain reaction (RT-PCR) swab, especially oscillating sensitivity, we added the information obtained from phone calls to discharged patients with negative initial RT-PCR. Thus, we included 535 patients with concomitant CXR and RT-PCR on admission (aged 65±17 y; 340 males, 195 females), resulting in 408 RT-PCR positive and 127 negative patients at the composite reference standard. Original CXR reports showed an 89.0% sensitivity (95% confidence intervals [CI], 85.5%-91.8%), 60.6% specificity (95% CI, 51.6%-69.2%), 87.9% positive predictive value (95% CI, 84.4%-90.9%), and 63.1% negative predictive value (95% CI, 53.9%-71.7%). The adoption of CXR alongside RT-PCR to triage patients with suspected SARS-CoV-2 infection could foster a safe and efficient workflow, counteracting possible false negative RT-PCR results.

Integrated Radiologic Algorithm for COVID-19 Pandemic.

Abstract: A new coronavirus (severe acute respiratory syndrome coronavirus 2, SARS-CoV-2) is contaminating the world; it has originated from China and has been infecting people since December 2019.1 Like other viruses, SARS-CoV-2 harbors in human cells and results in different degrees of cellular damage. The rapid diffusion and brutal effect of this virus have caused it to be rapidly ranked as a global threat, currently known as SARS-CoV-2 disease (COVID-19)2 and defined as a pandemic by the World Health Organization on March 11, 2020. The clinical presentation of COVID-19 might mimic seasonal flu,3 but it is nothing like that. COVID-19 has a much greater potential for diffuse alveolar damage (DAD), the therapy of which demands advanced respiratory assistance including artificial ventilation. Median age of COVID-19 is around 60 years, and its outcome strictly depends on the preparedness to appropriate clinical management, ranging from 1.4% to 15% mortality in China.3,4 Mortality in Italy is 8.1% (March 14, 2020).5 No one country in the world is prepared with sufficient capacity for this scenario, but might be able to adapt rapidly using shared experience. This is the ethical reason for this article that originates from the Italian area of COVID-19 burst in late February 2020. Early experience on clinical management of COVID-19 came from China.6 Chinese colleagues taught us about the limited accuracy of biological verification of SARS-CoV-2, and the potential role of medical imaging for triaging a patient referring with severe respiratory symptoms.7,8 Advantages of imaging were capacity and dispatch, something that substantially complements the time-consuming process of handling and analyzing biological samples from nasopharyngeal or oropharyngeal swabs. When COVID-19 was notified in Northern Italy (late February 2020), our regional parliament issued COVID-19 guidelines to organize first-level dedicated triage for respiratory symptoms, integrated with second-level triage including radiography and computed tomography (CT). First impression on this political decision raised some skepticism: no thoracic radiologist would ever propose radiology for management of respiratory virus, because we know its limited accuracy in the etiological definition of DAD and/or organizing pneumonia, namely the main underlying pathologic abnormalities in lung involvement from COVID-19.9 Indeed, our local first critical impression was substantially in line with the recent position statement of the American College of Radiology (ACR) on March 11, 2020.10 Nonetheless, we were somehow induced to use imaging and to witness its practical approach in this unique contingency where pretest probability of one specific etiology is substantially higher than any other hypothesis and swab-test results. First, we decided to use both radiography and CT, notably to use mainly radiography and offer supplementary CT in more severe cases or cases in whom radiography was difficult to interpret. This strategy quite overlaps the current ACR recommendation.10 But practical experience soon showed dilated times for swab analysis (>24 h) and the need to switch from radiography to CT with the purpose of increasing “both sides” of accuracy in a clinically integrated quick workflow: Rule-out task of radiology: CT allows some confidence in the definition of alternative diagnosis for severe acute respiratory symptoms and discharging the suspect of COVID-19 in favor of other diagnoses (eg, lobar pneumonia, bronchiolitis, heart failure etc.). Rule-in task of radiology: CT allows to detect subtle diffuse ground-glass opacities that are variably detected by radiography (think about supine radiography in severely ill patients) and are associated with a wide range of clinical severities (Fig. 1).

A Comparative Study of Chest Computed Tomography Features in Young and Older Adults With Corona Virus Disease (COVID-19).

Abstract: OBJECTIVE: To analyze the most common computed tomography (CT) findings of pneumonia caused by new coronavirus in younger patients (60 and younger) and older adults (older than 60). MATERIALS AND METHODS: The chest CT images of 72 symptomatic patients with corona virus disease (COVID-19) were analyzed retrospectively, including 44 younger patients (47.5±8.7 y old) and 28 older patients (68.4±6.0 y old). CT findings including density (pure ground-glass opacities, ground-glass opacities with consolidation, consolidation), the number of lobes involved, lesion distribution, and the main accompanying signs were analyzed and compared. RESULTS: Characteristic CT findings included the lobes of bilateral lung extensively involved, ground-glass opacity and ground-glass opacity with consolidation in the peripheral area, sometimes accompanied by interlobular septal thickening, and subpleural line and pleural thickening. Compared with the younger group, the proportion of extensive involvement of lung lobes was higher in the elderly group (71.4% vs. 36.4%, P=0.009), and subpleural line and pleural thickening were more likely to occur (50.0% vs. 25.0%, and 71.4% vs. 40.9%, P=0.030 and 0.011, respectively). CONCLUSION: Elderly and younger patients with corona virus disease have some common CT features, but older patients are more likely to have extensive lung lobe involvement, and subpleural line and pleural thickening. These differentiated characteristics may be related to the progress and prognosis of the disease.

Deep Learning Localization of Pneumonia: 2019 Coronavirus (COVID-19) Outbreak.

Abstract: BRIEF INTRO The ongoing coronavirus (COVID-19) outbreak beginning in December 2019 in Wuhan, China, has spread rapidly, with confirmed cases in multiple countries. This virus causes a severe lower respiratory tract infection, with ∼75% of COVID-19+ hospitalized patients developing a viral pneumonia. Seventeen percent of hospitalized patients go on to develop acute respiratory distress syndrome, and often fatal lung injury representing diffuse alveolar damage on pathologic examination.1 The 2% mortality rate associated with COVID-19+ in China is less than that seen with previous zoonotic coronavirus outbreaks such as SARS (10% mortality) and MERS (30% mortality); it is 20-fold higher than that associated with seasonal influenza according to CDC estimates for 2019-2020.2 Chest radiographs are often obtained as part of the diagnostic workup to triage and daily follow-up of patients with suspected pneumonia, including COVID-19 infection. The rapid recognition of pneumonia in these patients may allow for early isolation precautions and administration of supportive therapies. Deep learning (DL), a form of artificial intelligence, is beginning to show promise for supporting the diagnostic interpretation of chest x-rays. We recently described a DL approach to augment radiographs with a color probability overlay to improve the diagnosis of pneumonia.3 In contrast to common whole-image classification approaches, our method explicitly learns pixel-level likelihoods of pneumonia across the lung parenchyma. This provides natural transparency and explainability. We were interested in assessing the generalizability of our algorithm on frontal chest x-ray images recently published related to the recent COVID-19 outbreak. METHODS A total of 10 frontal chest radiographs from 5 patients treated in China and the United States were sourced from 5 recent COVID-19 epidemiologic and case-study publications.1,4–7 Publication figures with frontal chest radiographs were downloaded as JPEG files and manually cropped to only include the frontal radiograph. These images were used as inputs for our DL algorithm, implemented as a U-Net trained with 22K radiologist-annotated radiographs, which produces pneumonia probability maps overlaid onto an input radiograph.

Review of Chest Radiograph Findings of COVID-19 Pneumonia and Suggested Reporting Language.

Abstract: The diagnosis of coronavirus disease 2019 (COVID-19) is confirmed by reverse transcription polymerase chain reaction. The utility of chest radiography (CXR) remains an evolving topic of discussion. Current reports of CXR findings related to COVID-19 contain varied terminology as well as various assessments of its sensitivity and specificity. This can lead to a misunderstanding of CXR reports and makes comparison between examinations and research studies challenging. With this need for consistency, we propose language for standardized CXR reporting and severity assessment of persons under investigation for having COVID-19, patients with a confirmed diagnosis of COVID-19, and patients who may have radiographic findings typical or suggestive of COVID-19 when the diagnosis is not suspected clinically. We recommend contacting the referring providers to discuss the likelihood of viral infection when typical or indeterminate features of COVID-19 pneumonia on CXR are present as an incidental finding. In addition, we summarize the currently available literature related to the use of CXR for COVID-19 and discuss the evolving techniques of obtaining CXR in COVID-19-positive patients. The recently published expert consensus statement on reporting chest computed tomography findings related to COVID-19, endorsed by the Radiological Society of North American (RSNA), the Society of Thoracic Radiology (STR), and American College of Radiology (ACR), serves as the framework for our proposal.

Artificial Intelligence-based Fully Automated Per Lobe Segmentation and Emphysema-quantification Based on Chest Computed Tomography Compared With Global Initiative for Chronic Obstructive Lung Disease Severity of Smokers.

Abstract: OBJECTIVES The objective of this study was to evaluate an artificial intelligence (AI)-based prototype algorithm for the fully automated per lobe segmentation and emphysema quantification (EQ) on chest-computed tomography as it compares to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) severity classification of chronic obstructive pulmonary disease (COPD) patients. METHODS Patients (n=137) who underwent chest-computed tomography acquisition and spirometry within 6 months were retrospectively included in this Institutional Review Board-approved and Health Insurance Portability and Accountability Act-compliant study. Patient-specific spirometry data, which included forced expiratory volume in 1 second, forced vital capacity, and the forced expiratory volume in 1 second/forced vital capacity ratio (Tiffeneau-Index), were used to assign patients to their respective GOLD stage I to IV. Lung lobe segmentation was carried out using AI-RAD Companion software prototype (Siemens Healthineers), a deep convolution image-to-image network and emphysema was quantified in each lung lobe to detect the low attenuation volume. RESULTS A strong correlation between the whole-lung-EQ and the GOLD stages was found (ρ=0.88, P<0.0001). The most significant correlation was noted in the left upper lobe (ρ=0.85, P<0.0001), and the weakest in the left lower lobe (ρ=0.72, P<0.0001) and right middle lobe (ρ=0.72, P<0.0001). CONCLUSIONS AI-based per lobe segmentation and its EQ demonstrate a very strong correlation with the GOLD severity stages of COPD patients. Furthermore, the low attenuation volume of the left upper lobe not only showed the strongest correlation to GOLD severity but was also able to most clearly distinguish mild and moderate forms of COPD. This is particularly relevant due to the fact that early disease processes often elude conventional pulmonary function diagnostics. Earlier detection of COPD is a crucial element for positively altering the course of disease progression through various therapeutic options.

Computed Tomography-based Body Composition Analysis and Its Role in Lung Cancer Care.

Abstract: Body composition analysis, also referred to as analytic morphomics, morphomics, or morphometry, describes the measurement of imaging biomarkers of body composition such as muscle and adipose tissue, most commonly on computed tomography (CT) images. A growing body of literature supports the use of such metrics derived from routinely acquired CT images for risk prediction in various patient populations, including those with lung cancer. Metrics include cross-sectional area and attenuation of skeletal muscle and subcutaneous, visceral, and intermuscular adipose tissue. The purpose of this review is to provide an overview of the concepts, definitions, assessment tools, segmentation techniques and associated pitfalls, interpretation of those measurements on chest and abdomen CT, and a discussion of reported outcomes associated with body composition metrics in patients with early-stage and advanced lung cancer.

Generalizability of Deep Learning Tuberculosis Classifier to COVID-19 Chest Radiographs: New Tricks for an Old Algorithm?

Abstract: BRIEF INTRODUCTION Amidst the COVID-19 pandemic, chest radiographs (CXR) have been proposed as a potentially useful tool for triage and disease progression monitoring. Although CXR is less sensitive than computed tomography (CT), a classic pattern for COVID-19 pneumonia on CXR would preclude the need for further imaging with CT. Deep learning (DL) approaches for COVID-19 detection on CXR have been proposed1,2; however, these studies have been limited by small numbers of images available for model training. Although the lack of large COVID-19 image data sets is a barrier to DL development, the nonspecific findings of COVID-19 raise the possibility of repurposing CXRs with overlapping radiographic findings as training data. We previously used a similar approach to develop a DL algorithm to detect pulmonary tuberculosis (TB)3; this algorithm was trained using CXRs that did not have diagnoses of TB, but did have similar radiographic findings, in particular consolidation. On the basis of the observation that the CXR findings of COVID-19 and TB overlap considerably,4 we hypothesized that this model would generalize well to COVID-19 CXRs.

Computed Tomography Features of Coronavirus Disease 2019 (COVID-19): A Review for Radiologists.

Abstract: Coronavirus Disease 2019 (COVID-19) pneumonia has become a global pandemic. Although the rate of new infections in China has decreased, currently, 169 countries report confirmed cases, with many nations showing increasing numbers daily. Testing for COVID-19 infection is performed via reverse transcriptase polymerase chain reaction, but availability is limited in many parts of the world. The role of chest computed tomography is yet to be determined and may vary depending on the local prevalence of disease and availability of laboratory testing. A common but nonspecific pattern of disease with a somewhat predictable progression is seen in patients with COVID-19. Specifically, patchy ground-glass opacities in the periphery of the lower lungs may be present initially, eventually undergoing coalescence, consolidation, and organization, and ultimately showing features of fibrosis. In this article, we review the computed tomography features of COVID-19 infection. Familiarity with these findings and their evolution will help radiologists recognize potential COVID-19 and recognize the significant overlap with other causes of acute lung injury.

Machine Learning and Deep Neural Networks Applications in Coronary Flow Assessment: The Case of Computed Tomography Fractional Flow Reserve.

Abstract: Coronary computed tomography angiography (cCTA) is a reliable and clinically proven method for the evaluation of coronary artery disease. cCTA data sets can be used to derive fractional flow reserve (FFR) as CT-FFR. This method has respectable results when compared in previous trials to invasive FFR, with the aim of detecting lesion-specific ischemia. Results from previous studies have shown many benefits, including improved therapeutic guidance to efficiently justify the management of patients with suspected coronary artery disease and enhanced outcomes and reduced health care costs. More recently, a technical approach to the calculation of CT-FFR using an artificial intelligence deep machine learning (ML) algorithm has been introduced. ML algorithms provide information in a more objective, reproducible, and rational manner and with improved diagnostic accuracy in comparison to cCTA. This review gives an overview of the technical background, clinical validation, and implementation of ML applications in CT-FFR.

Thoracic Radiologists' Versus Computer Scientists' Perspectives on the Future of Artificial Intelligence in Radiology.

Abstract: BACKGROUND There is intense interest and speculation in the application of artificial intelligence (AI) to radiology. The goals of this investigation were (1) to assess thoracic radiologists' perspectives on the role and expected impact of AI in radiology, and (2) to compare radiologists' perspectives with those of computer science (CS) experts working in the AI development. METHODS An online survey was developed and distributed to chest radiologists and CS experts at leading academic centers and societies, comparing their expectations of AI's influence on radiologists' jobs, job satisfaction, salary, and role in society. RESULTS A total of 95 radiologists and 45 computer scientists responded. Computer scientists reported having read more scientific journal articles on AI/machine learning in the past year than radiologists (mean [95% confidence interval]=17.1 [9.01-25.2] vs. 7.3 [4.7-9.9], P=0.0047). The impact of AI in radiology is expected to be high, with 57.8% and 73.3% of computer scientists and 31.6% and 61.1% of chest radiologists predicting radiologists' job will be dramatically different in 5 to 10 years, and 10 to 20 years, respectively. Although very few practitioners in both fields expect radiologists to become obsolete, with 0% expecting radiologist obsolescence in 5 years, in the long run, significantly more computer scientists (15.6%) predict radiologist obsolescence in 10 to 20 years, as compared with 3.2% of radiologists reporting the same (P=0.0128). Overall, both chest radiologists and computer scientists are optimistic about the future of AI in radiology, with large majorities expecting radiologists' job satisfaction to increase or stay the same (89.5% of radiologists vs. 86.7% of CS experts, P=0.7767), radiologists' salaries to increase or stay the same (83.2% of radiologists vs. 73.4% of CS experts, P=0.1827), and the role of radiologists in society to improve or stay the same (88.4% vs. 86.7%, P=0.7857). CONCLUSIONS Thoracic radiologists and CS experts are generally positive on the impact of AI in radiology. However, a larger percentage, but still small minority, of computer scientists predict radiologist obsolescence in 10 to 20 years. As the future of AI in radiology unfolds, this study presents a historical timestamp of which group of experts' perceptions were closer to eventual reality.

A Novel Machine Learning-derived Radiomic Signature of the Whole Lung Differentiates Stable From Progressive COVID-19 Infection: A Retrospective Cohort Study.

Abstract: OBJECTIVE: This study aimed to use the radiomics signatures of a machine learning-based tool to evaluate the prognosis of patients with coronavirus disease 2019 (COVID-19) infection. METHODS: The clinical and imaging data of 64 patients with confirmed diagnoses of COVID-19 were retrospectively selected and divided into a stable group and a progressive group according to the data obtained from the ongoing treatment process. Imaging features from whole-lung images from baseline computed tomography (CT) scans were extracted and dimensionality reduction was performed. Support vector machines were used to construct radiomics signatures and to compare differences between the 2 groups. We also compared the differences of signature scores in the clinical, laboratory, and CT image feature subgroups and finally analyzed the correlation between the radiomics features of the constructed signature and the other features including clinical, laboratory, and CT imaging features. RESULTS: The signature has a good classification effect for the stable group and the progressive group, with area under curve, sensitivity, and specificity of 0.833, 80.95%, and 74.42%, respectively. Signature score differences in laboratory and CT imaging features between subgroups were not statistically significant (P>0.05); cough was negatively correlated with GLCM Entropy_angle 90_offset4 (r=-0.578), but was positively correlated with ShortRunEmphhasis_AllDirect_offset4_SD (r=0.454); C-reactive protein was positively correlated with Cluster Prominence_ AllDirect_offset 4_ SD (r=0.47). CONCLUSION: The radiomics signature of the whole lung based on machine learning may reveal the changes of lung microstructure in the early stage and help to indicate the progression of the disease.

Accuracy of an Artificial Intelligence Deep Learning Algorithm Implementing a Recurrent Neural Network With Long Short-term Memory for the Automated Detection of Calcified Plaques From Coronary Computed Tomography Angiography.

Abstract: Purpose The purpose of this study was to evaluate the accuracy of a novel fully automated deep learning (DL) algorithm implementing a recurrent neural network (RNN) with long short-term memory (LSTM) for the detection of coronary artery calcium (CAC) from coronary computed tomography angiography (CCTA) data. Materials and methods Under an IRB waiver and in HIPAA compliance, a total of 194 patients who had undergone CCTA were retrospectively included. Two observers independently evaluated the image quality and recorded the presence of CAC in the right (RCA), the combination of left main and left anterior descending (LM-LAD), and left circumflex (LCx) coronary arteries. Noncontrast CACS scans were allowed to be used in cases of uncertainty. Heart and coronary artery centerline detection and labeling were automatically performed. Presence of CAC was assessed by a RNN-LSTM. The algorithm's overall and per-vessel sensitivity, specificity, and diagnostic accuracy were calculated. Results CAC was absent in 84 and present in 110 patients. As regards CCTA, the median subjective image quality, signal-to-noise ratio, and contrast-to-noise ratio were 3.0, 13.0, and 11.4. A total of 565 vessels were evaluated. On a per-vessel basis, the algorithm achieved a sensitivity, specificity, and diagnostic accuracy of 93.1% (confidence interval [CI], 84.3%-96.7%), 82.76% (CI, 74.6%-89.4%), and 86.7% (CI, 76.8%-87.9%), respectively, for the RCA, 93.1% (CI, 86.4%-97.7%), 95.5% (CI, 88.77%-98.75%), and 94.2% (CI. 90.2%-94.6%), respectively, for the LM-LAD, and 89.9% (CI, 80.2%-95.8%), 90.0% (CI, 83.2%-94.7%), and 89.9% (CI, 85.0%-94.1%), respectively, for the LCx. The overall sensitivity, specificity, and diagnostic accuracy were 92.1% (CI, 92.1%-95.2%), 88.9% (CI. 84.9%-92.1%), and 90.3% (CI, 88.0%-90.0%), respectively. When accounting for image quality, the algorithm achieved a sensitivity, specificity, and diagnostic accuracy of 76.2%, 87.5%, and 82.2%, respectively, for poor-quality data sets and 93.3%, 89.2% and 90.9%, respectively, when data sets rated adequate or higher were combined. Conclusion The proposed RNN-LSTM demonstrated high diagnostic accuracy for the detection of CAC from CCTA.

Is COVID Evolution Due to Occurrence of Pulmonary Vascular Thrombosis

Abstract: In this hypothesis paper, we suggest that severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) may induce intravascular pulmonary thrombosis, which may result in the rapid worsening of clinical conditions and, eventually, exitus. Previously published papers have demonstrated that increased levels of D-dimer at hospital admission correlate with a more severe disease (0.5 mg/L) or occurrence of death (1 mg/L). The potential prothrombotic action of the SARS-CoV-2 is supported by the topographical involvement of the lung regions with a predilection for the lower lobe with peripheral involvement. If this hypothesis is demonstrated, this could suggest the benefit of using antithrombotic/coagulation regimens for SARS-CoV-2 and, at the same time, the urgency to identify drugs that could alter the inflammatory storm, thus protecting the vessel wall.

Artificial Intelligence in Diagnostic Imaging: Status Quo, Challenges, and Future Opportunities.

Abstract: In this review article, the current and future impact of artificial intelligence (AI) technologies on diagnostic imaging is discussed, with a focus on cardio-thoracic applications. The processing of imaging data is described at 4 levels of increasing complexity and wider implications. At the examination level, AI aims at improving, simplifying, and standardizing image acquisition and processing. Systems for AI-driven automatic patient iso-centering before a computed tomography (CT) scan, patient-specific adaptation of image acquisition parameters, and creation of optimized and standardized visualizations, for example, automatic rib-unfolding, are discussed. At the reading and reporting levels, AI focuses on automatic detection and characterization of features and on automatic measurements in the images. A recently introduced AI system for chest CT imaging is presented that reports specific findings such as nodules, low-attenuation parenchyma, and coronary calcifications, including automatic measurements of, for example, aortic diameters. At the prediction and prescription levels, AI focuses on risk prediction and stratification, as opposed to merely detecting, measuring, and quantifying images. An AI-based approach for individualizing radiation dose in lung stereotactic body radiotherapy is discussed. The digital twin is presented as a concept of individualized computational modeling of human physiology, with AI-based CT-fractional flow reserve modeling as a first example. Finally, at the cohort and population analysis levels, the focus of AI shifts from clinical decision-making to operational decisions.

Preparedness and Best Practice in Radiology Department for COVID-19 and Other Future Pandemics of Severe Acute Respiratory Infection.

Abstract: The COVID-19 global pandemic has emerged as an unprecedented health care crisis. To reduce risks of severe acute respiratory syndrome coronavirus 2 transmission in the Radiology Department, this article describes measures to increase the preparedness of Radiology Department, such as careful screening of staff and patients, thorough disinfection of equipments and rooms, appropriate use of personal protection equipment, and early isolation of patients with incidentally detected computed tomography findings suspicious for COVID-19. The familiarity of radiologists with clinical and imaging manifestations of COVID-19 pneumonia and their prognostic implications is essential to provide optimal care to patients.

A Diabetic Patient With 2019-nCoV (COVID-19) Infection Who Recovered and Was Discharged From Hospital.

Abstract: Novel coronavirus has become a global health hazard and its high infectivity is alarming. The imaging findings of the 2019-nCoV infection in our young diabetic patient featured ground-glass opacities and consolidations in both lungs. The lung lesions may involute rapidly during the course. The patient showed improvement both clinically and on computed tomography imaging at discharged after 2 weeks' treatment. Computed tomography scans of patients helped monitor the changes continuously, which could timely provide the information of the evolution of the disease or therapeutic effect to clinicians.

Impact of Significant Coronary Artery Calcification Reported on Low-Dose Computed Tomography Lung Cancer Screening.

Abstract: 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.

Machine Learning and Deep Neural Networks Applications in Computed Tomography for Coronary Artery Disease and Myocardial Perfusion.

Abstract: During the latest years, artificial intelligence, and especially machine learning (ML), have experienced a growth in popularity due to their versatility and potential in solving complex problems. In fact, ML allows the efficient handling of big volumes of data, allowing to tackle issues that were unfeasible before, especially with deep learning, which utilizes multilayered neural networks. Cardiac computed tomography (CT) is also experiencing a rise in examination numbers, and ML might help handle the increasing derived information. Moreover, cardiac CT presents some fields wherein ML may be pivotal, such as coronary calcium scoring, CT angiography, and perfusion. In particular, the main applications of ML involve image preprocessing and postprocessing, and the development of risk assessment models based on imaging findings. Concerning image preprocessing, ML can help improve image quality by optimizing acquisition protocols or removing artifacts that may hinder image analysis and interpretation. ML in image postprocessing might help perform automatic segmentations and shorten examination processing times, also providing tools for tissue characterization, especially concerning plaques. The development of risk assessment models from ML using data from cardiac CT could aid in the stratification of patients who undergo cardiac CT in different risk classes and better tailor their treatment to individual conditions. While ML is a powerful tool with great potential, applications in the field of cardiac CT are still expanding, and not yet routinely available in clinical practice due to the need for extensive validation. Nevertheless, ML is expected to have a big impact on cardiac CT in the near future.

Machine Learning and Deep Neural Networks: Applications in Patient and Scan Preparation, Contrast Medium, and Radiation Dose Optimization.

Abstract: Artificial intelligence (AI) algorithms are dependent on a high amount of robust data and the application of appropriate computational power and software. AI offers the potential for major changes in cardiothoracic imaging. Beyond image processing, machine learning and deep learning have the potential to support the image acquisition process. AI applications may improve patient care through superior image quality and have the potential to lower radiation dose with AI-driven reconstruction algorithms and may help avoid overscanning. This review summarizes recent promising applications of AI in patient and scan preparation as well as contrast medium and radiation dose optimization.

Imaging-guided Percutaneous Biopsy of Nodules ≤1 cm: Study of Diagnostic Performance and Risk Factors Associated With Biopsy Failure.

Abstract: Objective Percutaneous biopsy of lung nodules is established as a safe procedure with high diagnostic yield and accuracy. Its role in the diagnosis of subcentimeter nodules is, however, less clear. The goal of this study was to evaluate diagnostic yield, accuracy, and safety of computed tomography (CT)-guided needle biopsy in the diagnosis of subcentimeter lung nodules. Material and methods A retrospective review of a prospectively maintained database over a 12-year period identified 133 eligible CT-guided needle biopsies of lesions ≤1 cm. Diagnostic yield and accuracy for the diagnosis of malignancy were calculated. Lesion features and procedure characteristics were assessed using univariate and multivariate logistic regression analysis to identify risk factors associated with biopsy failure and complications. Results Biopsy specimens were adequate for diagnosis in 116/133(87%) cases; the diagnostic yield for malignant and benign lesions was 93% and 65%, respectively. Final benign diagnosis was the strongest independent risk factor for biopsy failure. In multivariate logistic regression, fine-needle aspiration was an independent risk factor for diagnostic failure. Core needle biopsy was an independent risk factor for pneumothorax, and core needle biopsy, number of passes, and age were independent risk factors for pneumothorax requiring tube drainage. Conclusions CT-guided percutaneous needle biopsy had high diagnostic yield for the diagnosis of subcentimeter lung nodules with a similar complication rate to biopsy of larger lesions. Fine-needle aspiration may be an independent factor for diagnostic failure even for malignant lesions.

Augmenting Interpretation of Chest Radiographs With Deep Learning Probability Maps.

Abstract: Purpose Pneumonia is a common clinical diagnosis for which chest radiographs are often an important part of the diagnostic workup. Deep learning has the potential to expedite and improve the clinical interpretation of chest radiographs. While earlier approaches have emphasized the feasibility of "binary classification" to accomplish this task, alternative strategies may be possible. We explore the feasibility of a "semantic segmentation" deep learning approach to highlight the potential foci of pneumonia on frontal chest radiographs. Materials and methods In this retrospective study, we trained a U-net convolutional neural network (CNN) to predict pixel-wise probability maps for pneumonia using a public data set provided by the Radiological Society of North America (RSNA) comprised of 22,000 radiographs and radiologist-defined bounding boxes. We reserved 3684 radiographs as an independent validation data set and assessed overall performance for localization using Dice overlap and classification performance using the area under the receiver-operator characteristic curve. Results For classification/detection of pneumonia, area under the receiver-operator characteristic curve on frontal radiographs was 0.854 with a sensitivity of 82.8% and specificity of 72.6%. Using this strategy of neural network training, probability maps localized pneumonia to lung parenchyma for essentially all validation cases. For segmentation of pneumonia for positive cases, predicted probability maps had a mean Dice score (±SD) of 0.603±0.204, and 60.0% of these had a Dice score >0.5. Conclusions A "semantic segmentation" deep learning approach can provide a probabilistic map to assist in the diagnosis of pneumonia. In combination with the patient's history, clinical findings and other imaging, this strategy may help expedite and improve diagnosis.

Chest Computed Tomography Manifestation of Coronavirus Disease 2019 (COVID-19) in Patients With Cardiothoracic Conditions.

Abstract: The coronavirus disease 2019 (COVID-19) pandemic is a serious public health concern, with an exponentially growing number of patients worldwide. Computed tomography (CT) has been suggested as a highly sensitive modality for the diagnosis of pulmonary involvement in the early stages of COVID-19. The typical features of COVID-19 in chest CT include bilateral, peripheral, and multifocal ground-glass opacities with or without superimposed consolidations. Patients with underlying medical conditions are at higher risks of complications and mortality. The diagnosis of COVID-19 on the basis of the imaging features may be more challenging in patients with preexisting cardiothoracic conditions, such as chronic obstructive pulmonary disease, interstitial lung disease, cardiovascular disease, and malignancies with cardiothoracic involvement. The extensive pulmonary involvement in some of these pathologies may obscure the typical manifestation of COVID-19, whereas other preexisting pathologies may resemble the atypical or rare CT manifestations of this viral pneumonia. Thus, understanding the specific CT manifestations in these special subgroups is essential for a prompt diagnosis.

Machine Learning and Deep Neural Network Applications in the Thorax: Pulmonary Embolism, Chronic Thromboembolic Pulmonary Hypertension, Aorta, and Chronic Obstructive Pulmonary Disease.

Abstract: The radiologic community is rapidly integrating a revolution that has not fully entered daily practice. It necessitates a close collaboration between computer scientists and radiologists to move from concepts to practical applications. This article reviews the current litterature on machine learning and deep neural network applications in the field of pulmonary embolism, chronic thromboembolic pulmonary hypertension, aorta, and chronic obstructive pulmonary disease.

Patient-centered Radiology Reporting for Lung Cancer Screening.

Abstract: Medicine is slowly transitioning toward a more patient-centered approach, with patients taking a more central role in their own care. A key part of this movement has involved giving patients increased access to their medical record and imaging results via electronic health portals. However, most patients lack the knowledge to fully understand medical documents, which are generally written above their comprehension level. Radiology reports, in particular, utilize complex terminology due to radiologists' historic function as consultants to other physicians, with little direct communication to patients. As a result, typical radiology reports lack standardized formatting, and they are often inscrutable to patients. Numerous studies examining patient preference also point to a trend for more accessible radiology reports geared toward patients. Reports designed with an infographic format, combining simple pictures and standardized text, may be an ideal format that radiologists can pursue to provide patient-centered care. Our team, through feedback from patient advisory groups, developed a patient-friendly low-dose computed tomography lung cancer screening report with an infographic format that is both visually attractive and comprehensible to the average patient. The report is designed with sections including a description of low-dose computed tomography, a section on individualized patient results, the meaning of the results, and a list of the next steps in their care. We believe that this form of the report has the potential to serve as a bridge between radiologists and patients, allowing for a better patient understanding of their health and empowering patients to participate in their health and health care.

Beyond the Artificial Intelligence Hype: What Lies Behind the Algorithms and What We Can Achieve.

Abstract: The field of artificial intelligence (AI) is currently experiencing a period of extensive growth in a wide variety of fields, medicine not being the exception. The base of AI is mathematics and computer science, and the current fame of AI in industry and research stands on 3 pillars: big data, high performance computing infrastructure, and algorithms. In the current digital era, increased storage capabilities and data collection systems, lead to a massive influx of data for AI algorithm. The size and quality of data are 2 major factors influencing performance of AI applications. However, it is highly dependent on the type of task at hand and algorithm chosen to perform this task. AI may potentially automate several tedious tasks in radiology, particularly in cardiothoracic imaging, by pre-readings for the detection of abnormalities, accurate quantifications, for example, oncologic volume lesion tracking and cardiac volume and image optimization. Although AI-based applications offer great opportunity to improve radiology workflow, several challenges need to be addressed starting from image standardization, sophisticated algorithm development, and large-scale evaluation. Integration of AI into the clinical workflow also needs to address legal barriers related to security and protection of patient-sensitive data and liability before AI will reach its full potential in cardiothoracic imaging.

Machine Learning/Deep Neuronal Network: Routine Application in Chest Computed Tomography and Workflow Considerations.

Abstract: The constantly increasing number of computed tomography (CT) examinations poses major challenges for radiologists. In this article, the additional benefits and potential of an artificial intelligence (AI) analysis platform for chest CT examinations in routine clinical practice will be examined. Specific application examples include AI-based, fully automatic lung segmentation with emphysema quantification, aortic measurements, detection of pulmonary nodules, and bone mineral density measurement. This contribution aims to appraise this AI-based application for value-added diagnosis during routine chest CT examinations and explore future development perspectives.

Multimodality Assessment of Thoracic Aortic Dimensions: Comparison of Computed Tomography Angiography, Magnetic Resonance Imaging, and Echocardiography Measurements.

Abstract: PURPOSE The purpose of this study was to compare thoracic aortic measurements between computed tomography (CT), magnetic resonance imaging (MRI), and transthoracic echocardiography (TTE). MATERIALS AND METHODS A total of 127 patients (mean age: 45±18 y, 49% male) who had undergone CT and MRI evaluation of the thoracic aorta at a single tertiary referral hospital within a 6-month interval between 2007 and 2017 were included in this retrospective study. TTE studies performed within the same 6-month interval were also evaluated. Thoracic aortic measurements were blindly evaluated using multiple techniques and were compared between modalities. RESULTS There was no significant difference in maximum aortic root diameter between CT and MRI when using the inner lumen-to-inner lumen technique (mean difference: 0.2±1.4 mm, P=0.51) or the outer lumen-to-outer lumen technique (mean difference: 0.5±1.4 mm, P=0.07). There were no significant differences between CT and MRI at any other level except for the distal descending aorta (20.2±4.6 vs. 19.8±4.6 mm, P<0.001). However, aortic root measurements by TTE using the leading edge-to-leading edge technique were significantly smaller compared with maximum aortic root diameters using the inner lumen-to-inner lumen and outer lumen-to-outer lumen techniques by both CT (mean difference: 4.9±2.7 mm, P<0.001 and 7.4±2.8 mm, P<0.001, respectively) and MRI (mean difference: 4.8±3.2 mm, P<0.001 and 8.2±3.0 mm, P<0.001, respectively). CONCLUSIONS There is excellent agreement in thoracic aortic measurements between CT and MRI. However, TTE significantly underestimates maximum aortic root diameter compared with CT and MRI. Therefore, caution should be used when interpreting small apparent changes in aortic root diameters between TTE and CT or MRI.