To evaluate a newly proposed ‘Shock Thyroid Imaging Score’ (STIS) for predicting mortality in hemodynamically unstable trauma patients and to assess association of STIS with the Hypovolemic Shock Complex (HSC). This is a retrospective, single-center study of consecutive hemodynamically unstable trauma patients receiving contrast-enhanced CT between January 2016 and September 2018. A STIS was calculated from scored signs of shock thyroid on chest CTs and correlated to well published abdominal CT signs of HSC. Multivariable logistic regression evaluated STIS association with mortality and compared STIS with Glasgow Coma Scale (GCS) and systolic blood pressure (SBP) in predicting mortality. A total of 748 patients (mean age 47 years ± 22; 554 men) were evaluated. STIS was associated with all abdominal visceral signs of HSC on CT, for example adrenal hyperenhancement in 75

Purpose To evaluate the performance of the winning machine learning models from the 2023 RSNA Abdominal Trauma Detection AI Challenge. Materials and Methods The competition was hosted on Kaggle and took place between July 26 and October 15, 2023. The multicenter competition dataset consisted of 4274 abdominal trauma CT scans, in which solid organs (liver, spleen, and kidneys) were annotated as healthy, low-grade, or high-grade injury. Studies were labeled as positive or negative for the presence of bowel and mesenteric injury and active extravasation. In this study, performances of the eight award-winning models were retrospectively assessed and compared using various metrics, including the area under the receiver operating characteristic curve (AUC), for each injury category. The reported mean values of these metrics were calculated by averaging the performance across all models for each specified injury type. Results The models exhibited strong performance in detecting solid organ injuries, particularly high-grade injuries. For binary detection of injuries, the models demonstrated mean AUC values of 0.92 (range, 0.90-0.94) for liver, 0.91 (range, 0.87-0.93) for splenic, and 0.94 (range, 0.93-0.95) for kidney injuries. The models achieved mean AUC values of 0.98 (range, 0.96-0.98) for high-grade liver, 0.98 (range, 0.97-0.99) for high-grade splenic, and 0.98 (range, 0.97-0.98) for high-grade kidney injuries. For the detection of bowel and mesenteric injuries and active extravasation, the models demonstrated mean AUC values of 0.85 (range, 0.74-0.93) and 0.85 (range, 0.79-0.89), respectively. Conclusion The award-winning models from the artificial intelligence challenge demonstrated strong performance in the detection of traumatic abdominal injuries on CT scans, particularly high-grade injuries. These models may serve as a performance baseline for future investigations and algorithms. Keywords: Abdominal Trauma, CT, American Association for the Surgery of Trauma, Machine Learning, Artificial Intelligence Supplemental material is available for this article. © RSNA, 2024.

PURPOSE:To evaluate diagnostic performance of split-bolus single-pass CT (SBSP-CT) for splenic vascular injury (SVI) and clinically relevant splenic vascular injury requiring treatment (CR-SVI) in trauma patients with splenic injury. METHODS:This retrospective observer study included 111 consecutive trauma patients (76% male), mean age 37 years (9-81), median ISS 27 (interquartile range (IQR) 26-33), with splenic injury and primary SBSP-CT at a level-1 trauma center between December 2012 and December 2018. Four radiologists independently scored CTs for SVI presence and likelihood. Consensus reference standards for SVI and CR-SVI were based on clinical, imaging and 3-month follow-up data. Image adequacy was assessed quantitively and qualitatively and diagnostic performance and interobserver agreement analyzed. RESULTS:37 of 111 (33.3%) patients had SVI and 27 (24.3%) had CR-SVI requiring treatment. Five patients died prior to SVI treatment from unrelated injuries; no mortality was attributed to undetected SVI. Two patients had delayed splenic rupture, both survived. Median attenuation was 292 HU (IQR 250-348) in the aorta and 130 HU (IQR 114-150) in splenic parenchyma. Images were adequate in 107 of 111 (96.4%) patients. Interobserver agreement for SVI was substantial (0.741; 95% CI: 0.67-0.82). NPV for SVI ranged from 89.2 to 94.4% (95% CI: 89.2-97.4) and for CR-SVI from 94.4 to 97.1% (95% CI: 88.5-98.9). AUROC for SVI ranged from 0.825 to 0.862 and for CR-SVI from 0.825 to 0.862. CONCLUSION:SBSP-CT provides adequate image quality and high diagnostic confidence for evaluating splenic vascular injury with high negative predictive value for relevant splenic vascular injuries.

Chest X-ray (CXR) imaging plays a pivotal role in the diagnosis and prognosis of viral pneumonia. However, distinguishing COVID-19 CXRs from other viral infections remains challenging due to highly similar radiographic features. Most existing deep learning (DL) models focus on differentiating COVID-19 from community-acquired pneumonia (CAP) rather than other viral pneumonias and often overlook baseline CXRs, missing the critical window for early detection and intervention. Moreover, manual severity scoring of COVID-19 CXRs by radiologists is subjective and time-intensive, highlighting the need for automated systems. This study introduces a DL system for distinguishing COVID-19 from other viral pneumonias on baseline CXRs acquired within three days of PCR testing, and for automated severity scoring of COVID-19 CXRs. The system was developed using a dataset of 2,547 patients (808 COVID-19, 936 non-COVID viral pneumonia, and 803 normal cases) and validated externally on several publicly accessible datasets. Compared to four experienced radiologists, the model achieved higher diagnostic accuracy (76.4% vs. 71.8%) and enhanced COVID-19 identification (F1-score: 74.1% vs. 61.3%), with an AUC of 93% for distinguishing between viral pneumonia and normal cases, and 89.8% for differentiating COVID-19 from other viral pneumonias. The severity-scoring module exhibited a high Pearson correlation of 93% and a low mean absolute error (MAE) of 2.35 compared to the radiologists' consensus. External validation on independent public datasets confirmed the model's generalizability. Subgroup analyses stratified by patient age, sex, and severity levels further demonstrated consistent performance, supporting the system's robustness across diverse clinical populations. These findings suggest that the proposed DL system could assist radiologists in the early diagnosis and severity assessment of COVID-19 from baseline CXRs, particularly in resource-limited settings.

To evaluate the impact of overnight in-house emergency radiologist coverage on turnaround time (TAT) for emergent imaging of ED and inpatients, during the night and following morning, in a coverage model tailored to preserving resident autonomy. Retrospective analysis of TAT for all emergent imaging of ED and inpatients at an academic Level-1 trauma center from September 2015 to August 2019, two years before and after changing coverage model. Median and 90th percentile were assessed for overnight (22:00—07:00 h.) and morning (07:00—10:00 h.) emergent imaging TAT for both the ‘First report’ and ‘Final report’. Statistical significance of TAT changes between study years was assessed with quantile regression. Trainee report volumes and their rotation evaluations were assessed. 128,433 emergent ED and inpatient imaging studies (82,482 overnight and 45,951 morning) were included; 40,136 CTs, 83,993 X-rays, 2018 US and 2286 MRIs. Imaging volumes increased over time. Except 90th percentile MRI First report TAT, all overnight TAT metrics statistically significantly improved with the new coverage model. For example, ED CT median Final report TAT decreased from 8.45 h to 1.38 h. Morning imaging showed statistically significant reduction for all TATs, except for MRI TATs and 90th percentile US Final report TAT. For example, ED CT median Final report TAT decreased from 1.56 h to 1.19 h. Absolute imaging volume reported by trainees increased by 14

The YEARS criteria combine D-dimer testing and clinical features (hemoptysis, signs of deep vein thrombosis, and pulmonary embolism as the most likely diagnosis) to risk stratify patients with symptoms of pulmonary embolism who may undergo CT pulmonary angiography in the emergency department (ED). Electronic clinical decision support can optimize CT pulmonary angiography utilization in EDs, yet its effectiveness with the YEARS criteria remains unstudied. Our goal is to increase the percentage of CT pulmonary angiograms performed with a D-dimer by 10

Introduction: Computed tomography angiography (CTA) plays an important role in assessing patients with suspected lower extremity traumatic vascular injury. However, CTA overutilization has been reported in some centres, and improper use has been linked to increased healthcare costs and prolonged Emergency Department wait times. This study evaluated CTA utilization in a Canadian Level I trauma centre, determined the rate of positive CTA studies requiring intervention, and identified factors that may reduce unnecessary examinations. Methods and Materials: This retrospective study included trauma patients who underwent lower extremity CTA between January 2020 and September 2024. Data regarding patient demographics, mechanism of injury, physical exam and computed tomography findings, ankle-brachial index value, and interventions were collected and evaluated. Statistical analysis included descriptive statistics and chi-square or Fisher's exact tests for categorical associations. Results: Six hundred twelve patients (82% male, median age 32 years) were included. Forty-six percent had a normal physical exam, and CTA was positive in 27% of cases. Eight percent of patients required an intervention, all of whom had at least one hard sign of vascular injury. A statistically significant association was identified between hard signs of a vascular injury and positive CTA findings (P < .001) and major vascular injuries (P < .01). No patients with a normal physical exam and a positive CTA required intervention. Conclusion: Nearly half of the CTA studies were performed on patients with a normal physical exam, none requiring intervention. Our findings suggest that implementing institution-specific appropriate criteria may reduce unnecessary CTA studies.

To evaluate diagnostic performance of split-bolus single-pass CT (SBSP-CT) for splenic vascular injury (SVI) and clinically relevant splenic vascular injury requiring treatment (CR-SVI) in trauma patients with splenic injury. This retrospective observer study included 111 consecutive trauma patients (76

The Canadian Association of Radiologists (CAR) Trauma Expert Panel consists of adult and pediatric emergency and trauma radiologists, emergency physicians, a family physician, a patient advisor, and an epidemiologist/guideline methodologist. After developing a list of 21 clinical/diagnostic scenarios, a systematic rapid scoping review was undertaken to identify systematically produced referral guidelines that provide recommendations for 1 or more of these clinical/diagnostic scenarios. Recommendations from 49 guidelines and contextualization criteria in the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) for guidelines framework were used to develop 50 recommendation statements across the 21 scenarios related to the evaluation of traumatic injuries. This guideline presents the methods of development and the recommendations for head, face, neck, spine, hip/pelvis, arms, legs, superficial soft tissue injury foreign body, chest, abdomen, and non-accidental trauma.

Trauma is the leading non-obstetric cause of maternal and fetal mortality and affects an estimated 5–7% of all pregnancies. Pregnant women, thankfully, are a small subset of patients presenting in the trauma bay, but they do have distinctive physiologic and anatomic changes. These increase the risk of certain traumatic injuries, and the gravid uterus can both be the primary site of injury and mask other injuries. The primary focus of the initial management of the pregnant trauma patient should be that of maternal stabilization and treatment since it directly affects the fetal outcome. Diagnostic imaging plays a pivotal role in initial traumatic injury assessment and should not deviate from normal routine in the pregnant patient. Radiographs and focused assessment with sonography in the trauma bay will direct the use of contrast-enhanced computed tomography (CT), which remains the cornerstone to evaluate the potential presence of further management-altering injuries. A thorough understanding of its risks and benefits is paramount, especially in the pregnant patient. However, like any other trauma patient, if evaluation for injury with CT is indicated, it should not be denied to a pregnant trauma patient due to fear of radiation exposure.

The RSNA Abdominal Traumatic Injury CT (ie, RATIC) dataset contains 4274 abdominal CT studies with annotations related to traumatic injuries and is available at https://www.kaggle.com/competitions/rsna-2023-abdominal-trauma-detection and https://imaging.rsna. org/dataset/5.

Imaging of pregnant patients who sustained trauma often causes fear and confusion among patients, their families, and health care professionals regarding the potential for detrimental effects from radiation exposure to the fetus. Unnecessary delays or potentially harmful avoidance of the justified imaging studies may result from this understandable anxiety. This guideline was developed by the Canadian Emergency, Trauma and Acute Care Radiology Society (CETARS) and the Canadian Association of Radiologists (CAR) Working Group on Imaging the Pregnant Trauma Patient, informed by a literature review as well as multidisciplinary expert panel opinions and discussions. The working group included academic subspecialty radiologists, a trauma team leader, an emergency physician, and an obstetriciangynaecologist/maternal fetal medicine specialist, who were brought together to provide updated, evidence-based recommendations for the imaging of pregnant trauma patients, including patient safety aspects (eg, radiation and contrast concerns) and counselling, initial imaging in maternal trauma, specific considerations for the use of fluoroscopy, angiography, and magnetic resonance imaging. The guideline strives to achieve clarity and prevent added anxiety in an already stressful situation of injury to a pregnant patient, who should not be imaged differently.

Establishing an emergency radiology division in a practice that has long-standing patterns of operational routines comes with both challenges and opportunities. In this article, considerations around scheduling and staffing, compensation, and equity and parity are provided with supporting literature references. Furthermore, a panel of experts having established, grown and managed emergency radiology divisions in North America and Europe share their experiences through a question and answer format.

Background Excessive use of CT pulmonary angiography (CTPA) to investigate pulmonary embolism (PE) in the emergency department (ED) contributes to adverse patient outcomes. Non-invasive D-dimer testing, in the context of a clinical algorithm, may help decrease unnecessary imaging but this has not been widely implemented in Canadian EDs. Aim To improve the diagnostic yield of CTPA for PE by 5% (absolute) within 12 months of implementing the YEARS algorithm. Measures and design Single centre study of all ED patients >18 years investigated for PE with D-dimer and/or CTPA between February 2021 and January 2022. Primary and secondary outcomes were the diagnostic yield of CTPA and frequency of CTPA ordered compared with baseline. Process measures included the percentage of D-dimer tests ordered with CTPA and CTPAs ordered with D-dimers <500 µg/L Fibrinogen Equivalent Units (FEU). The balancing measure was the number of PEs identified on CTPA within 30 days of index visit. Multidisciplinary stakeholders developed plan- do-study-act cycles based on the YEARS algorithm. Results Over 12 months, 2695 patients were investigated for PE, of which 942 had a CTPA. Compared with baseline, the CTPA yield increased by 2.9% (12.6% vs 15.5%, 95% CI −0.06% to 5.9%) and the proportion of patients that underwent CTPA decreased by 11.4% (46.4% vs 35%, 95% CI −14.1% to −8.8%). The percentage of CTPAs ordered with a D-dimer increased by 26.3% (30.7% vs 57%, 95% CI 22.2% 30.3%) and there were two missed PE (2/2695, 0.07%). Impact Implementing the YEARS criteria may safely improve the diagnostic yield of CTPAs and reduce the number of CTPAs completed without an associated increase in missed clinically significant PEs. This project provides a model for optimising the use of CTPA in the ED.

Benefits of overnight attending radiologist final reports are debated, often stating low resident discrepancy rates, usually assessed retrospectively. The objective of this study was to assess the impact of overnight final reporting on the recall rates for patients in the emergency department (ED) receiving overnight imaging. Retrospective matched cohorts of two separate years prior (prior-16 and prior-17) and 1 year after (post-18) introduction of overnight attending radiologist final reporting. Patients receiving imaging between 22:00 and 07:00 h and returned to ED within 48 h of initial visit discharge were electronically identified. String matching identified return visits possibly related to imaging completed on first visit. Identified return visit notes were scored by three observers individually. Unclear and discrepant cases were resolved by consensus meeting, using full patient charts where needed. Incidences were provided and logistic regression analysis defined if coverage model was a predictor for recall. Odds ratios were calculated. ED patient count with imaging completed overnight in prior-16 was 9200, in prior-17 was 9543, and in post-18 was 9992. The number of overnight imaging studies performed was respectively 13,883, 14,463, and 15,112. Imaging-related ED recalls were respectively 54, 61, and 7, a decrease with the new coverage model of 89% to true and at least 90% of expected recalls.Logistic regression demonstrated that coverage model was a significant predictor of ED recalls with chi-square of 59.86 and p < 0.001, an R2 of 0.03 (Hosmer and Lemeshow). Compared to post-18, ED patients had an odds ratio of 8.42 (prior-16) and 9.18 (prior-17) to be called back to ED. Overnight final reporting significantly decreases ED recalls for patients receiving diagnostic imaging overnight. While numbers are low even prior to rollout, the number should be minimized wherever possible to diminish patient anxiety and discomfort, reduce ED overcrowding and expedite definitive management. Section 1: What is already known on this subject • Radiology resident preliminary report discrepancy rates are low. • Overnight attending radiologist coverage is a model increasingly applied in academic and large non-academic centers. • Patient recalls to the ED are a burden to the patient and impact patient throughput in (over)crowded EDs. Section 2: What this study adds • First study to look at the impact of overnight attending final reports on the recall rate for ED patients with overnight imaging performed. • While absolute numbers are low, there is a significant decrease in patients returning to ED for imaging related issues after introducing overnight attending coverage. • Resident autonomy can be preserved and training enhanced while increasing patient safety and comfort

Emergency radiology (ER) is an important part of radiology. But what exactly is ER? How can the required competencies be acquired in a good and feasible way? Who should be in charge of this? Discussion of ER contents and suggestions for the improvement of the acquisition of respective competencies during radiology training. General literature review, in particular the current German blueprint for medical specialist training regulations (Weiterbildungsordnung, WBO 2020), publications by the German Radiological Society (DRG), the European Society of Radiology (ESR), the European Society of Emergency Radiology (ESER) and the American Society of Emergency Radiology (ASER). As proof of competence in ER in Germany, confirmation from the authorised residency training supervisor as to whether there is ‘competence to act’ either ‘independently’ or ‘under supervision’ in the case of ‘radiology in an emergency situation …, e.g. in the case of polytrauma, stroke, intensive care patients’ is sufficient. The ESER refers to all acute emergencies with clinical constellations requiring an immediate diagnosis 24/7 and, if necessary, acute therapy. The ESER and ASER offer, among other things, practical fellowships in specialised institutions, while the ESER complements this with a European Diploma in Emergency Radiology (EDER). On a national level, it would be advisable to use existing definitions, offers and concepts, from the ESR, ESER and ASER. Specialised institutions could support the acquisition of ER competencies with fellowships. For Germany, it seems sensible to set up a separate working group (Arbeitsgemeinschaft, AG) on ER within the DRG in order to drive the corresponding further ER development.

Since the advent of multidetecter computed tomography (CT), radiologist sensitivity in detection of traumatic bowel and mesenteric abnormalities has significantly improved. Although several CT signs have been described to identify intestinal injury, accurate interpretation of these findings can remain challenging. Early detection of bowel and mesenteric injury is important as it alters patient management, disposition, and follow-up. This article reviews the common imaging findings of traumatic small bowel and mesenteric injury.

In the aftermath of a Mass Casualty Incident (MCI) many patients require lifesaving treatments and surgeries. Due to the sudden surge in demand, the resources of the hospital are overwhelmed, making proper planning and use of the available resources crucial in minimizing mortality and morbidity. To help with planning, patients are triaged into four levels based on the clinical assessment of the criticality of their conditions. The triage decisions are however subject to error and a patient may be under or overtriaged. Mistriages can be identified by performing imaging, e.g., a Computed Tomography (CT) scan, but imaging also takes non-negligible time and has limited capacity. We propose a queueing network model of patient flow during an MCI and use simulation experiments to quantify the value of identifying mistriaged patients. Our results demonstrate the value of performing imaging, but also point out to the importance of accounting for its limited capacity.

A Correction to this paper has been published: https://doi.org/10.1007/s00330-020-07520-2