Prevalence and clinical significance of incidental findings in chest and abdominopelvic CT scans of trauma patients; A cross-sectional study.

BACKGROUND: Imaging may inadvertently reveal pathologies unrelated to their performing purpose, known as incidental findings (IF). This study aimed to assess the prevalence, clinical significance, and documentation of IFs in chest and abdominopelvic computed tomography (CT) scans of trauma patients. METHODS: This observational study was conducted at two urban level-1 trauma centers from March 2019 through April 2022. Official radiology reports of trauma patients who underwent chest and/or abdominopelvic CT scans at the emergency department (ED) were explored, and IF were extracted. Predictive factors of the presence of IFs and their documenting were investigated. RESULTS: Out of 656 chest and 658 abdominopelvic CT scans, 167 (25.37%) and 212 (32.31%) scans harbored at least one IF, respectively. Patients with IFs tended to be of higher age and female in both chest (age: 48 [IQR: 35-62] vs. 34 [IQR: 25-42.5]; female: 31.14% vs 14.66%, p < 0.001 for both) and abdominopelvic CT scans (age: 41 [IQR: 30-57.5] vs 33 [IQR: 25-43], female: 26.42% vs. 13.96%, p < 0.001 for both). As for documentation of significant IFs, only 49 of 112 chest IFs (43.8%) and 55 of 176 abdominopelvic IFs (31.3%) were documented. Investigating factors associated with documentation of clinically significant IFs, shorter length of hospital stay (1.5 (IQR: 0-4) vs. 3 (IQR: 2-8), p = 0.003), and discharging by ED physicians (documentation rate: 13.2% vs 42.6%, p < 0.001) were associated with poorer documentation of IFs only in abdominopelvic scans. CONCLUSION: CT imaging in ED trauma patients often reveals incidental findings, especially in older patients. Over 50% of these findings are clinically significant, yet they are frequently ignored and not documented. Physicians need to be more vigilant in recognizing and documenting these incidental findings and informing patients of the need for further evaluation.

Artificial intelligence in the healthcare sector: comparison of deep learning networks using chest X-ray images.

Purpose: Artificial intelligence has led to significant developments in the healthcare sector, as in other sectors and fields. In light of its significance, the present study delves into exploring deep learning, a branch of artificial intelligence. Methods: In the study, deep learning networks ResNet101, AlexNet, GoogLeNet, and Xception were considered, and it was aimed to determine the success of these networks in disease diagnosis. For this purpose, a dataset of 1,680 chest X-ray images was utilized, consisting of cases of COVID-19, viral pneumonia, and individuals without these diseases. These images were obtained by employing a rotation method to generate replicated data, wherein a split of 70 and 30% was adopted for training and validation, respectively. Results: The analysis findings revealed that the deep learning networks were successful in classifying COVID-19, Viral Pneumonia, and Normal (disease-free) images. Moreover, an examination of the success levels revealed that the ResNet101 deep learning network was more successful than the others with a 96.32% success rate. Conclusion: In the study, it was seen that deep learning can be used in disease diagnosis and can help experts in the relevant field, ultimately contributing to healthcare organizations and the practices of country managers.

Assessment of the comparative agreement between chest radiographs and CT scans in intensive care units.

PURPOSE: Chest radiographs in critically ill patients can be difficult to interpret due to technical and clinical factors. We sought to determine the agreement of chest radiographs and CT scans, and the inter-observer variation of chest radiograph interpretation, in intensive care units (ICUs). METHODS: Chest radiographs and corresponding thoracic computerised tomography (CT) scans (as reference standard) were collected from 45 ICU patients. All radiographs were analysed by 20 doctors (radiology consultants, radiology trainees, ICU consultants, ICU trainees) from 4 different centres, blinded to CT results. Specificity/sensitivity were determined for pleural effusion, lobar collapse and consolidation/atelectasis. Separately, Fleiss' kappa for multiple raters was used to determine inter-observer variation for chest radiographs. RESULTS: The median sensitivity and specificity of chest radiographs for detecting abnormalities seen on CTs scans were 43.2% and 85.9% respectively. Diagnostic sensitivity for pleural effusion was significantly higher among radiology consultants but no specialty/experience distinctions were observed for specificity. Median inter-observer kappa coefficient among assessors was 0.295 ("fair"). CONCLUSIONS: Chest radiographs commonly miss important radiological features in critically ill patients. Inter-observer agreement in chest radiograph interpretation is only "fair". Consultant radiologists are least likely to miss thoracic radiological abnormalities. The consequences of misdiagnosis by chest radiographs remain to be determined.

Paediatric diagnostic reference levels for common radiological examinations using the European guidelines.

OBJECTIVE: The purpose of this study was to explore the feasibility to determine regional diagnostic reference levels (RDRLs) for paediatric conventional and CT examinations using the European guidelines and to compare RDRLs derived from weight and age groups, respectively. METHODS: Data were collected from 31 hospitals in 4 countries, for 7 examination types for a total of 2978 patients. RDRLs were derived for each weight and age group, respectively, when the total number of patients exceeded 15. RESULTS: It was possible to derive RDRLs for most, but not all, weight-based and age-based groups for the seven examinations. The result using weight-based and age-based groups differed substantially. The RDRLs were lower than or equal to the European and recently published national DRLs. CONCLUSION: It is feasible to derive RDRLs. However, a thorough review of the clinical indications and methodologies has to be performed previous to data collection. This study does not support the notion that DRLs derived using age and weight groups are exchangeable. ADVANCES IN KNOWLEDGE: Paediatric DRLs should be derived using weight-based groups with access to the actual weight of the patients. DRLs developed using weight differ markedly from those developed with the use of age. There is still a need to harmonize the method to derive solid DRLs for paediatric radiological examinations.

Deep Learning Algorithm for COVID-19 Classification Using Chest X-Ray Images.

Early diagnosis of the harmful severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), along with clinical expertise, allows governments to break the transition chain and flatten the epidemic curve. Although reverse transcription-polymerase chain reaction (RT-PCR) offers quick results, chest X-ray (CXR) imaging is a more reliable method for disease classification and assessment. The rapid spread of the coronavirus disease 2019 (COVID-19) has triggered extensive research towards developing a COVID-19 detection toolkit. Recent studies have confirmed that the deep learning-based approach, such as convolutional neural networks (CNNs), provides an optimized solution for COVID-19 classification; however, they require substantial training data for learning features. Gathering this training data in a short period has been challenging during the pandemic. Therefore, this study proposes a new model of CNN and deep convolutional generative adversarial networks (DCGANs) that classify CXR images into normal, pneumonia, and COVID-19. The proposed model contains eight convolutional layers, four max-pooling layers, and two fully connected layers, which provide better results than the existing pretrained methods (AlexNet and GoogLeNet). DCGAN performs two tasks: (1) generating synthetic/fake images to overcome the challenges of an imbalanced dataset and (2) extracting deep features of all images in the dataset. In addition, it enlarges the dataset and represents the characteristics of diversity to provide a good generalization effect. In the experimental analysis, we used four distinct publicly accessible datasets of chest X-ray images (COVID-19 X-ray, COVID Chest X-ray, COVID-19 Radiography, and CoronaHack-Chest X-Ray) to train and test the proposed CNN and the existing pretrained methods. Thereafter, the proposed CNN method was trained with the four datasets based on the DCGAN synthetic images, resulting in higher accuracy (94.8%, 96.6%, 98.5%, and 98.6%) than the existing pretrained models. The overall results suggest that the proposed DCGAN-CNN approach is a promising solution for efficient COVID-19 diagnosis.

An Approach for Thoracic Syndrome Classification with Convolutional Neural Networks.

There have been remarkable changes in our lives and the way we perceive the world with advances in computing technology. Healthcare sector is evolving with the intervention of the latest computer-driven technology and has made a remarkable change in the diagnosis and treatment of various diseases. Due to many governing factors including air pollution, there is a rapid rise in chest-related diseases and the number of such patients is rising at an alarming rate. In this research work, we have employed machine learning approach for the detecting various chest-related problems using convolutional neural networks (CNN) on an open dataset of chest X-rays. The method has an edge over the traditional approaches for image segmentation including thresholding, k-means clustering, and edge detection. The CNN cannot scan and process the whole image at an instant; it needs to recursively scan small pixel spots until it has scanned the whole image. Spatial transformation layers and VGG19 have been used for the purpose of feature extraction, and ReLU activation function has been employed due to its inherent low complexity and high computation efficiency; finally, stochastic gradient descent has been used as an optimizer. The main advantage of the current method is that it retains the essential features of the image for prediction along with incorporating a considerable dimensional reduction. The model delivered substantial improvement over existing research in terms of precision, f-score, and accuracy of prediction. This model if used precisely can be very effective for healthcare practitioners in determining the thoracic or pneumonic symptoms in the patient at an early stage thus guiding the practitioner to start the treatment immediately leading to fast improvement in the health status of the patient.

Covid-19 infection in pregnant women in Dubai: a case-control study.

BACKGROUND: Whilst the impact of Covid-19 infection in pregnant women has been examined, there is a scarcity of data on pregnant women in the Middle East. Thus, the aim of this study was to examine the impact of Covid-19 infection on pregnant women in the United Arab Emirates population. METHODS: A case-control study was carried out to compare the clinical course and outcome of pregnancy in 79 pregnant women with Covid-19 and 85 non-pregnant women with Covid-19 admitted to Latifa Hospital in Dubai between March and June 2020. RESULTS: Although Pregnant women presented with fewer symptoms such as fever, cough, sore throat, and shortness of breath compared to non-pregnant women; yet they ran a much more severe course of illness. On admission, 12/79 (15.2%) Vs 2/85 (2.4%) had a chest radiograph score [on a scale 1-6] of ≥3 (p-value = 0.0039). On discharge, 6/79 (7.6%) Vs 1/85 (1.2%) had a score ≥3 (p-value = 0.0438). They also had much higher levels of laboratory indicators of severity with values above reference ranges for C-Reactive Protein [(28 (38.3%) Vs 13 (17.6%)] with p < 0.004; and for D-dimer [32 (50.8%) Vs 3(6%)]; with p < 0.001. They required more ICU admissions: 10/79 (12.6%) Vs 1/85 (1.2%) with p=0.0036; and suffered more complications: 9/79 (11.4%) Vs 1/85 (1.2%) with p=0.0066; of Covid-19 infection, particularly in late pregnancy. CONCLUSIONS: Pregnant women presented with fewer Covid-19 symptoms but ran a much more severe course of illness compared to non-pregnant women with the disease. They had worse chest radiograph scores and much higher levels of laboratory indicators of disease severity. They had more ICU admissions and suffered more complications of Covid-19 infection, such as risk for miscarriage and preterm deliveries. Pregnancy with Covid-19 infection, could, therefore, be categorised as high-risk pregnancy and requires management by an obstetric and medical multidisciplinary team.

Patient, Provider, and Health Care System Characteristics Associated With Overuse in Bronchiolitis.

BACKGROUND AND OBJECTIVES: The American Academy of Pediatrics recommends against the routine use of ß-agonists, corticosteroids, antibiotics, chest radiographs, and viral testing in bronchiolitis, but use of these modalities continues. Our objective for this study was to determine the patient, provider, and health care system characteristics that are associated with receipt of low-value services. METHODS: Using the Virginia All-Payers Claims Database, we conducted a retrospective cross-sectional study of children aged 0 to 23 months with bronchiolitis (code J21, International Classification of Diseases, 10th Revision) in 2018. We recorded medications within 3 days and chest radiography or viral testing within 1 day of diagnosis. Using Poisson regression, we identified characteristics associated with each type of overuse. RESULTS: Fifty-six percent of children with bronchiolitis received ≥1 form of overuse, including 9% corticosteroids, 17% antibiotics, 20% ß-agonists, 26% respiratory syncytial virus testing, and 18% chest radiographs. Commercially insured children were more likely than publicly insured children to receive a low-value service (adjusted prevalence ratio [aPR] 1.21; 95% confidence interval [CI]: 1.15-1.30; P < .0001). Children in emergency settings were more likely to receive a low-value service (aPR 1.24; 95% CI: 1.15-1.33; P < .0001) compared with children in inpatient settings. Children seen in rural locations were more likely than children seen in cities to receive a low-value service (aPR 1.19; 95% CI: 1.11-1.29; P < .0001). CONCLUSIONS: Overuse in bronchiolitis remains common and occurs frequently in emergency and outpatient settings and rural locations. Quality improvement initiatives aimed at reducing overuse should include these clinical environments.

The Practice of Obtaining a Chest Radiograph in Pediatric Patients Presenting With Their First Episode of Wheezing: A Survey of Resident Physicians.

A chest radiograph (CXR) is not routinely indicated in children presenting with their first episode of wheezing; however, it continues to be overused. A survey was distributed electronically to determine what trainees are taught and their current practice of obtaining a CXR in children presenting with their first episode of wheezing and the factors that influence this practice. Of the 1513 trainees who completed surveys, 35.3% (535/1513) reported that they were taught that pediatric patients presenting with their first episode of wheezing should be evaluated with a CXR. In all, 22.01% (333/1513) indicated that they would always obtain a CXR in these patients, and 13.75% (208/1513) would always obtain a CXR under a certain age (4 weeks to 12 years, median of 2 years). Our study identifies a target audience that would benefit from education to decrease the overuse of CXRs in children.

A Statewide Quality Improvement Collaborative's Adherence to the 2017 American Urological Association Guidelines Regarding Initial Evaluation of Patients With Clinical T1 Renal Masses.

OBJECTIVE: To evaluate MUSIC-KIDNEY's adherence to the American Urological Association (AUA) guidelines regarding the initial evaluation of patient's with clinical T1 (cT1) renal masses. METHODS: We reviewed MUSIC-KIDNEY registry data for patients with newly diagnosed cT1 renal masses to assess for adherence with the 2017 AUA guideline statements regarding recommendations to obtain (1) CMP, (2) CBC, (3) UA, (4) abdominal cross-sectional imaging, and (5) chest imaging. An evaluation consisting of all 5 guideline measures was considered "complete compliance." Variation with guideline adherence was assessed by contributing practice, management strategy, and renal mass size. RESULTS: We identified 1808 patients with cT1 renal masses in the MUSIC-KIDNEY registry, of which 30% met the definition of complete compliance. Most patients received care that was compliant with recommendations to obtain laboratory testing with 1448 (80%), 1545 (85%), and 1472 (81%) patients obtaining a CMP, CBC, and UA respectively. Only 862 (48%) patients underwent chest imaging. Significant variation exists in complete guideline compliance for contributing practices, ranging from 0% to 45% as well as for patients which underwent immediate intervention compared with initial observation (37% vs 23%) and patients with cT1b masses compared with cT1a masses (36% vs 28%). CONCLUSION: Complete guideline compliance in the initial evaluation of patients with cT1 renal masses is poor, which is mainly driven by omission of chest imaging. Significant variation in guideline adherence is seen across practices, as well as patients undergoing an intervention vs observation, and cT1a vs cT1b masses. There are ample quality improvement opportunities to increase adherence and decrease variability with guideline recommendations.

Predictors of delayed sputum smear conversion among pulmonary tuberculosis patients in Kota Kinabalu, Malaysia: A retrospective cohort study.

ABSTRACT: Smear-positive pulmonary tuberculosis (SPPTB) is the major contributor to the spread of tuberculosis (TB) infection, and it creates high morbidity and mortality worldwide. The objective of this study was to determine the predictors of delayed sputum smear conversion at the end of the intensive phase of TB treatment in Kota Kinabalu, Malaysia.This retrospective study was conducted utilising data of SPPTB patients treated in 5 TB treatment centres located in Kota Kinabalu, Malaysia from 2013 to 2018. Pulmonary TB (PTB) patients included in the study were those who had at least completed the intensive phase of anti-TB treatment with sputum smear results at the end of the 2nd month of treatment. The factors associated with delayed sputum smear conversion were analyzed using multiple logistic regression analysis. Predictors of sputum smear conversion at the end of intensive phase were evaluated.A total of 2641 patients from the 2013 to 2018 periods were included in this study. One hundred eighty nine (7.2%) patients were identified as having delayed sputum smear conversion at the end of the intensive phase treatment. Factors of moderate (advanced odd ratio [aOR]: 1.7) and advanced (aOR: 2.7) chest X-ray findings at diagnosis, age range of >60 (aOR: 2.1), year of enrolment 2016 (aOR: 2.8), 2017 (aOR: 3.9), and 2018 (aOR: 2.8), smokers (aOR: 1.5), no directly observed treatment short-course (DOTS) supervisor (aOR: 6.9), non-Malaysian citizens (aOR: 1.5), and suburban home locations (aOR: 1.6) were associated with delayed sputum smear conversion at the end of the intensive phase of the treatment.To improve sputum smear conversion success rate, the early detection of PTB cases has to be fine-tuned so as to reduce late or severe case presentation during diagnosis. Efforts must also be in place to encourage PTB patients to quit smoking. The percentage of patients assigned with DOTS supervisors should be increased while at the same time ensuring that vulnerable groups such as those residing in suburban localities, the elderly and migrant TB patients are provided with proper follow-up treatment and management.

Reducing Chest Radiographs in Bronchiolitis Through High-Reliability Interventions.

BACKGROUND AND OBJECTIVES: Bronchiolitis is a leading cause of pediatric hospitalization in the United States, resulting in significant morbidity and health care resource use. Despite American Academy of Pediatrics recommendations against obtaining chest radiographs (CXRs) for bronchiolitis, variation in care continues. Historically, clinical practice guidelines and educational campaigns have had mixed success in reducing unnecessary CXR use. Our aim was to reduce CXR use for children <2 years with a primary diagnosis of bronchiolitis, regardless of emergency department (ED) disposition or preexisting conditions, from 42.1% to <15% of encounters by March 2020. METHODS: A multidisciplinary team was created at our institution in 2012 to standardize bronchiolitis care. Given success with higher reliability interventions in asthma, similar interventions affecting workflow were subsequently pursued with bronchiolitis, starting in 2017, by using quality improvement science methods. The primary outcome was the percent of bronchiolitis encounters with a CXR. The balancing measure was return visits within 72 hours to the ED. Statistical process control charts were used to monitor and analyze data obtained from an internally created dashboard. RESULTS: From 2012 to 2020, our hospital had 12 120 bronchiolitis encounters. Preimplementation baseline revealed a mean of 42.1% for CXR use. Low reliability interventions, like educational campaigns, resulted in unsustained effects on CXR use. Higher reliability interventions were associated with sustained reductions to 23.3% and 18.9% over the last 4 years. There was no change in ED return visits. CONCLUSIONS: High-reliability workflow redesign was more effective in translating American Academy of Pediatrics recommendations into sustained practice than educational campaigns.

Development of a Health Disparities Index: Proof of Concept with Chest Radiography in Asthma.

OBJECTIVES: To develop a tool for quantifying health disparity (Health Disparity Index[HDI]) and explore hospital variation measured by this index using chest radiography (CXR) in asthma as the proof of concept. STUDY DESIGN: This was a retrospective cohort study using the Pediatric Health Information System database including children with asthma between 5 and 18 years old. Inpatient and emergency department (ED) encounters from January 1, 2017, to December 31, 2018, with low or moderate severity were included. Exclusions included hospitals with <10 cases in any racial/ethnic group. The HDI measured variation in CXR use among children with asthma based on race/ethnicity. The HDI was calculated as the absolute difference between maximum and minimum percentages of CXR use (range = 0-100) when there was statistical evidence that the percentages were different. RESULTS: Data from 36 hospitals included 16 744 inpatient and 75 805 ED encounters. Overall, 19.7% of encounters had a CXR (34.3% for inpatient; 16.5% for ED). In inpatient encounters, 47.2% (17/36) of hospitals had a significant difference in imaging across racial/ethnic groups. Of these, the median hospital-level HDI was 19.4% (IQR 13.5-20.1). In ED encounters, 78.8% (28/36) of hospitals had a statistically significant difference in imaging across racial/ethnic groups, with a median hospital-level HDI of 10.2% (IQR 8.3-14.1). There was no significant association between the inpatient HDI and ED HDI (P = .46). CONCLUSIONS: The HDI provides a practical measure of disparity. To improve equity in healthcare, metrics are needed that are intuitive, accurate, usable, and actionable. Next steps include application of this index to other conditions.

The relationship between thoracic kyphosis and age, and normative values across age groups: a systematic review of healthy adults.

BACKGROUND: Thoracic kyphosis is reported to increase with ageing. However, this relationship has not been systematically investigated. Peoples' kyphosis often exceeds 40°, but 40° is the widely accepted cut-off and threshold for normality. Consequently, patients may be misclassified. Accurate restoration of kyphosis is important to avoid complications following spinal surgery. Therefore, specific reference values are needed. The objective of the review is to explore the relationship between thoracic kyphosis and age, provide normative values of kyphosis for different age groups and investigate the influence of gender and ethnicity. METHODS: Two reviewers independently conducted a literature search, including seven databases and the Spine Journal, from inception to April 2020. Quantitative observational studies on healthy adults (18 years of age or older) with no known pathologies, and measuring kyphosis with Cobb's method, a flexicurve, or a kyphometer, were included. Study selection, data extraction, and study quality assessment (AQUA tool) were performed independently by two reviewers. The authors were contacted if clarifications were necessary. Correlation analysis and inferential statistics were performed (Microsoft Excel). The results are presented narratively. A modified GRADE was used for evidence quality assessment. RESULTS: Thirty-four studies (24 moderate-quality, 10 high-quality) were included (n = 7633). A positive moderate correlation between kyphosis and age was found (Spearman 0.52, p < 0.05, T5-T12). Peoples' kyphosis resulted greater than 40° in 65% of the cases, and it was significantly smaller in individuals younger than 40 years old (x < 40) than in those older than 60 years old (x > 60) 75% of the time (p < 0.05). No differences between genders were found, although a greater kyphosis angle was observed in North Americans and Europeans. CONCLUSION: Kyphosis increases with ageing, varying significantly between x < 40 and x > 60. Furthermore, kyphosis appears to be influenced by ethnicity, but not gender. Peoples' thoracic sagittal curvature frequently exceeds 40°. TRIAL REGISTRATION: The review protocol was devised following the PRISMA-P Guidelines, and it was registered on PROSPERO ( CRD42020175058 ) before study commencement.

An Overview of Deep Learning Techniques on Chest X-Ray and CT Scan Identification of COVID-19.

Pneumonia is an infamous life-threatening lung bacterial or viral infection. The latest viral infection endangering the lives of many people worldwide is the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which causes COVID-19. This paper is aimed at detecting and differentiating viral pneumonia and COVID-19 disease using digital X-ray images. The current practices include tedious conventional processes that solely rely on the radiologist or medical consultant's technical expertise that are limited, time-consuming, inefficient, and outdated. The implementation is easily prone to human errors of being misdiagnosed. The development of deep learning and technology improvement allows medical scientists and researchers to venture into various neural networks and algorithms to develop applications, tools, and instruments that can further support medical radiologists. This paper presents an overview of deep learning techniques made in the chest radiography on COVID-19 and pneumonia cases.

Chest x-ray scoring as a predictor of COVID-19 disease; correlation with comorbidities and in-hospital mortality.

OBJECTIVES: To devise a novel, simple chest x-ray (CXR) scoring system which would help in prognosticating the disease severity and ability to predict comorbidities and in-hospital mortality. METHODS: We included a total of 343 consecutive hospitalised patients with COVID-19 in this study. The chest x-rays of these patients were scored retrospectively by three radiologists independently. We divided CXR in to six zones (right upper, mid & lower and left, upper mid & lower zones). We scored each zone as- 0, 1 or 2 as follows- if that zone was clear (0) Ground glass opacity (1) or Consolidation (2). A total of score from 0 to 12 could be obtained. RESULTS: A CXR score cut off ≥3 independently predicted mortality. Along with a relatively higher NPV ≥80%, it reinforced the importance of CXR score is a screening tool to triage patients according to risk of mortality. CONCLUSIONS: We propose that Pennine score is a simple tool which can be adapted by various countries, experiencing a large surge in number of patients, to decide which patient would need a tertiary Hospital referral/admission as opposed to patients that can be managed locally or at basic/primary care hospitals.

Screening performance of the chest X-ray in adult blunt trauma evaluation: Is it effective and what does it miss?

BACKGROUND: Although chest x-ray (CXR) is often used as a screening tool for thoracic injury in adult blunt trauma assessment, its screening performance is unclear. Using chest CT as the referent standard, we sought to determine the screening performance of CXR for injury. METHODS: We analyzed data from the NEXUS Chest CT study, in which we prospectively enrolled blunt trauma patients older than 14 years who received chest imaging as part of their evaluation at nine level I trauma centers. For this analysis, we included patients who had both CXR and chest CT. We used CT as the referent standard and categorized injuries as clinically major or minor according to an a priori expert panel classification. RESULTS: Of 11,477 patients enrolled, 4501 had both CXR and chest CT; 1496 (33.2%) were found to have injury, of which 256 (17%) were classified as major injury. CXR missed injuries in 818 patients (54.7%), of which 63 (7.7%) were classified as major injuries. For injuries of major clinical significance, CXR had a sensitivity of 75.4% (95% confidence interval [CI] 69.6-80.4%), specificity of 86.2% (95% CI 85.1-87.2%), negative predictive value of 98.3 (95%CI 97.9-98.6%), and positive predictive value of 24.7 (95%CI 22.9-26.7%). For any injury CXR had a sensitivity of 45.3% (95% CI 42.8-47.9%), specificity of 96.6% (95% CI 95.9-97.2%), negative predictive value of 78% (95% CI 77.2-78.8%), and positive predictive value of 86.9% (95% CI 84.5-89.0%). The most common missed major injuries were pneumothorax (30/185; 16.2%), spinal fractures (19/39; 48.7%), and hemothorax (8/70; 11.4%). The most common missed minor injuries were rib fractures (381/836; 45.6%), pulmonary contusion (203/462; 43.9%), and sternal fractures (153/229; 66.8%). CONCLUSIONS: When used alone, without other trauma screening criteria, CXR has poor screening performance for blunt thoracic injury.

Cardiothoracic ratio measurement using artificial intelligence: observer and method validation studies.

BACKGROUND: Artificial Intelligence (AI) is a promising tool for cardiothoracic ratio (CTR) measurement that has been technically validated but not clinically evaluated on a large dataset. We observed and validated AI and manual methods for CTR measurement using a large dataset and investigated the clinical utility of the AI method. METHODS: Five thousand normal chest x-rays and 2,517 images with cardiomegaly and CTR values, were analyzed using manual, AI-assisted, and AI-only methods. AI-only methods obtained CTR values from a VGG-16 U-Net model. An in-house software was used to aid the manual and AI-assisted measurements and to record operating time. Intra and inter-observer experiments were performed on manual and AI-assisted methods and the averages were used in a method variation study. AI outcomes were graded in the AI-assisted method as excellent (accepted by both users independently), good (required adjustment), and poor (failed outcome). Bland-Altman plot with coefficient of variation (CV), and coefficient of determination (R-squared) were used to evaluate agreement and correlation between measurements. Finally, the performance of a cardiomegaly classification test was evaluated using a CTR cutoff at the standard (0.5), optimum, and maximum sensitivity. RESULTS: Manual CTR measurements on cardiomegaly data were comparable to previous radiologist reports (CV of 2.13% vs 2.04%). The observer and method variations from the AI-only method were about three times higher than from the manual method (CV of 5.78% vs 2.13%). AI assistance resulted in 40% excellent, 56% good, and 4% poor grading. AI assistance significantly improved agreement on inter-observer measurement compared to manual methods (CV; bias: 1.72%; - 0.61% vs 2.13%; - 1.62%) and was faster to perform (2.2 ± 2.4 secs vs 10.6 ± 1.5 secs). The R-squared and classification-test were not reliable indicators to verify that the AI-only method could replace manual operation. CONCLUSIONS: AI alone is not yet suitable to replace manual operations due to its high variation, but it is useful to assist the radiologist because it can reduce observer variation and operation time. Agreement of measurement should be used to compare AI and manual methods, rather than R-square or classification performance tests.

Diagnostic yield, safety, and advantages of ultra-low dose chest CT compared to chest radiography in early stage suspected SARS-CoV-2 pneumonia: A retrospective observational study.

ABSTRACT: To determine the role of ultra-low dose chest computed tomography (uld CT) compared to chest radiographs in patients with laboratory-confirmed early stage SARS-CoV-2 pneumonia.Chest radiographs and uld CT of 12 consecutive suspected SARS-CoV-2 patients performed up to 48 hours from hospital admission were reviewed by 2 radiologists. Dosimetry and descriptive statistics of both modalities were analyzed.On uld CT, parenchymal abnormalities compatible with SARS-CoV-2 pneumonia were detected in 10/12 (83%) patients whereas on chest X-ray in, respectively, 8/12 (66%) and 5/12 (41%) patients for reader 1 and 2. The average increment of diagnostic performance of uld CT compared to chest X-ray was 29%. The average effective dose was, respectively, of 0.219 and 0.073 mSv.Uld CT detects substantially more lung injuries in symptomatic patients with suspected early stage SARS-CoV-2 pneumonia compared to chest radiographs, with a significantly better inter-reader agreement, at the cost of a slightly higher equivalent radiation dose.