Trauma Radiology Research Articles

Applications of Deep Learning in Trauma Radiology: A Narrative Review

Diagnostic imaging is essential in modern trauma care for initial evaluation and identifying injuries requiring intervention. Deep learning (DL) has become mainstream in medical image analysis and has shown promising efficacy for classification, segmentation, and lesion detection. This narrative review provides the fundamental concepts for developing DL algorithms in trauma imaging and presents an overview of current progress in each modality. DL has been applied to detect free fluid on Focused Assessment with Sonography for Trauma (FAST), traumatic findings on chest and pelvic X-rays, and computed tomography (CT) scans, identify intracranial hemorrhage on head CT, detect vertebral fractures, and identify injuries to organs like the spleen, liver, and lungs on abdominal and chest CT. Future directions involve expanding dataset size and diversity through federated learning, enhancing model explainability and transparency to build clinician trust, and integrating multimodal data to provide more meaningful insights into traumatic injuries. Though some commercial artificial intelligence products are Food and Drug Administration-approved for clinical use in the trauma field, adoption remains limited, highlighting the need for multi-disciplinary teams to engineer practical, real-world solutions. Overall, DL shows immense potential to improve the efficiency and accuracy of trauma imaging, but thoughtful development and validation are critical to ensure these technologies positively impact patient care.

An ASER AI/ML expert panel formative user research study for an interpretable interactive splenic AAST grading graphical user interface prototype.

The AAST Organ Injury Scale is widely adopted for splenic injury severity but suffers from only moderate inter-rater agreement. This work assesses SpleenPro, a prototype interactive explainable artificial intelligence/machine learning (AI/ML) diagnostic aid to support AAST grading, for effects on radiologist dwell time, agreement, clinical utility, and user acceptance. Two trauma radiology ad hoc expert panelists independently performed timed AAST grading on 76 admission CT studies with blunt splenic injury, first without AI/ML assistance, and after a 2-month washout period and randomization, with AI/ML assistance. To evaluate user acceptance, three versions of the SpleenPro user interface with increasing explainability were presented to four independent expert panelists with four example cases each. A structured interview consisting of Likert scales and free responses was conducted, with specific questions regarding dimensions of diagnostic utility (DU); mental support (MS); effort, workload, and frustration (EWF); trust and reliability (TR); and likelihood of future use (LFU). SpleenPro significantly decreased interpretation times for both raters. Weighted Cohen's kappa increased from 0.53 to 0.70 with AI/ML assistance. During user acceptance interviews, increasing explainability was associated with improvement in Likert scores for MS, EWF, TR, and LFU. Expert panelists indicated the need for a combined early notification and grading functionality, PACS integration, and report autopopulation to improve DU. SpleenPro was useful for improving objectivity of AAST grading and increasing mental support. Formative user research identified generalizable concepts including the need for a combined detection and grading pipeline and integration with the clinical workflow.

Interpretable Severity Scoring of Pelvic Trauma Through Automated Fracture Detection and Bayesian Inference.

Pelvic ring disruptions result from blunt injury mechanisms and are potentially lethal mainly due to associated injuries and massive pelvic hemorrhage. The severity of pelvic fractures in trauma victims is frequently assessed by grading the fracture according to the Tile AO/OTA classification in whole-body Computed Tomography (CT) scans. Due to the high volume of whole-body CT scans generated in trauma centers, the overall information content of a single whole-body CT scan and low manual CT reading speed, an automatic approach to Tile classification would provide substantial value, e. g., to prioritize the reading sequence of the trauma radiologists or enable them to focus on other major injuries in multi-trauma patients. In such a high-stakes scenario, an automated method for Tile grading should ideally be transparent such that the symbolic information provided by the method follows the same logic a radiologist or orthopedic surgeon would use to determine the fracture grade. This paper introduces an automated yet interpretable pelvic trauma decision support system to assist radiologists in fracture detection and Tile grading. To achieve interpretability despite processing high-dimensional whole-body CT images, we design a neurosymbolic algorithm that operates similarly to human interpretation of CT scans. The algorithm first detects relevant pelvic fractures on CTs with high specificity using Faster-RCNN. To generate robust fracture detections and associated detection (un)certainties, we perform test-time augmentation of the CT scans to apply fracture detection several times in a self-ensembling approach. The fracture detections are interpreted using a structural causal model based on clinical best practices to infer an initial Tile grade. We apply a Bayesian causal model to recover likely co-occurring fractures that may have been rejected initially due to the highly specific operating point of the detector, resulting in an updated list of detected fractures and corresponding final Tile grade. Our method is transparent in that it provides fracture location and types, as well as information on important counterfactuals that would invalidate the system's recommendation. Our approach achieves an AUC of 0.89/0.74 for translational and rotational instability,which is comparable to radiologist performance. Despite being designed for human-machine teaming, our approach does not compromise on performance compared to previous black-box methods.

Canadian Association of Radiologists Trauma Diagnostic Imaging Referral Guideline.

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.

500 CT imaging requests in Major Trauma Patients

Abstract Introduction There is a correlation between adequate CT Trauma orders and accuracy of radiological reporting. In this audit, the aim is to improve accuracy of reporting by following the Royal College of Radiologists (RCR) indications for polytrauma CT imaging in the document ‘Standards of practice and guidance for trauma radiology in severely injured patients, 2nd edition’. Standard 7 in this guidance states that a CT request in the trauma setting should comply with the Ionising Radiation (Medical Exposure) Regulations justification regulations in the same way as any other request for imaging involving ionising radiation. Method Clinical information in CT orders of 57 major trauma patients in the East Midlands Major Trauma Centre were reviewed against ‘Standards of practice and guidance for trauma radiology in severely injured patients, 2nd edition’. The request should have two essential pieces of information: mechanism of injury and suspected injuries. In these 57 patient, 96% had appropriate requests. Since the target is 100%, an email was sent out and a teaching session was carried out to improve practice. A second cycle including 80 patients in the same centre was carried out. Results Before intervention, 96% of the CT in major trauma patients were compliant with guidelines. After intervention, this improved to 100%. Conclusion Compliance with RCR criteria improved after intervention, this surely helped avoid unnecessary radiation exposure and enhanced radiological reporting in major trauma patient scans.

Post-traumatic spinal hematoma in diffuse idiopathic skeletal hyperostosis (DISH)

ObjectivesTo determine the incidence of spinal hematoma and its relation to neurological deficit after trauma in patients with spinal ankylosis from diffuse idiopathic skeletal hyperostosis (DISH).Materials and methodsA retrospective review of 2256 urgent or emergency MRI referrals over a period of 8 years and nine months revealed 70 DISH patients who underwent CT and MRI scans of the spine. Spinal hematoma was the primary outcome. Additional variables were spinal cord impingement, spinal cord injury (SCI), trauma mechanism, fracture type, spinal canal narrowing, treatment type, and Frankel grades during injury, before and after treatment. Two trauma radiologists reviewed MRI scans blinded to initial reports.ResultsOf 70 post-traumatic patients (54 men, median age 73, IQR 66–81) with ankylosis of the spine from DISH, 34 (49%) had spinal epidural hematoma (SEH) and 3 (4%) had spinal subdural hematoma, 47 (67%) had spinal cord impingement, and 43 (61%) had SCI. Ground-level fall (69%) was the most common trauma mechanism. A transverse, AO classification type B spine fracture (39%) through the vertebral body was the most common injury type. Spinal canal narrowing (p < .001) correlated and spinal cord impingement (p = .004) associated with Frankel grade before treatment. Of 34 patients with SEH, one, treated conservatively, developed SCI.ConclusionsSEH is a common complication after low-energy trauma in patients with spinal ankylosis from DISH. SEH causing spinal cord impingement may progress to SCI if not treated by decompression.Clinical relevance statementLow-energy trauma may cause unstable spinal fractures in patients with spinal ankylosis caused by DISH. The diagnosis of spinal cord impingement or injury requires MRI, especially for the exclusion of spinal hematoma requiring surgical evacuation.Key Points• Spinal epidural hematoma is a common complication in post-traumatic patients with spinal ankylosis from DISH.• Most fractures and associated spinal hematomas in patients with spinal ankylosis from DISH result from low-energy trauma.• Spinal hematoma can cause spinal cord impingement, which may lead to SCI if not treated by decompression.

Clinical Role of Interventional Radiology in Abdominal Solid Organ Trauma

Interventional management is commonly used for traumatic injuries to the abdominal solid organs. The American Association for the Surgery of Trauma (AAST) and the World Society of Emergency Surgery (WSES) recently published guidelines for the management and treatment of liver, spleen, and kidney injuries, emphasizing the importance of interventions. Here, we discuss the characteristics of each organ and the procedure method for each organ that interventional radiologists need to know when treating trauma patients.

Importance of the Mechanism of Injury in Trauma Radiology Decision-Making.

Importance of the Mechanism of Injury in Trauma Radiology Decision-Making.

Are we meeting the standards of practice for trauma radiology at a district general hospital in the UK?

Are we meeting the standards of practice for trauma radiology at a district general hospital in the UK?

Impact of easing COVID-19 safety measures on trauma computed tomography imaging volumes

PurposeThe coronavirus disease 2019 (COVID-19) pandemic has led to substantial disruptions in healthcare staffing and operations. Stay-at-home (SAH) orders and limitations in social gathering implemented in spring 2020 were followed by initial decreases in healthcare and imaging utilization. This study aims to evaluate the impact of subsequent easing of SAH on trauma volumes, demand for, and turnaround times for trauma computed tomography (CT) exams, hypothesizing that after initial decreases, trauma volumes have increased as COVID safety measures have been reduced.MethodsPatient characteristics, CT imaging volumes, and turnaround time were analyzed for all adult activated emergency department trauma patients requiring CT imaging at a single Level-I trauma center (1/2018–2/2022) located in the sixth most populous county in the USA. Based on COVID safety measures in place in the state of California, three time periods were compared: baseline (PRE, 1/1/2018–3/19/2020), COVID safety measures (COVID, 3/20/2020–1/25/2021), and POST (1/26/2021–2/28/2022).ResultsThere were 16,984 trauma patients across the study (PRE = 8289, COVID = 3139, POST = 5556). The average daily trauma patient volumes increased significantly in the POST period compared to the PRE and COVID periods (13.9 vs. 10.3 vs. 10.1, p < 0.001), with increases in both blunt (p < 0.001) and penetrating (p = 0.002) trauma. The average daily number of trauma CT examinations performed increased significantly in the POST period compared to the PRE and COVID periods (56.7 vs. 48.3 vs. 47.6, p < 0.001), with significant increases in average turnaround time (47 min vs. 31 and 37, p < 0.001).ConclusionAfter initial decreases in trauma radiology volumes following stay-at-home orders, subsequent easing of safety measures has coincided with increases in trauma imaging volumes above pre-pandemic levels and longer exam turnaround times.

Proactive Use of Whole-Body Computed Tomography and Resuscitative Endovascular Balloon Occlusion of the Aorta in Hemodynamically Unstable Trauma Patients

It is well known that whole body computed tomography (WBCT) scans in hemodynamically unstable trauma patients (HUPs) should not be performed due to time concerns. Recently, with the shortening of CT scan time accomplished by quick preparation and scanning, WBCT in the patient population utilizing resuscitative endovascular balloon occlusion of the aorta (REBOA) in trauma cases could lead to better subsequent management, especially for patients with unknown bleeding points without known mechanism of injury, possible traumatic brain injury, and geriatric trauma with coagulopathy. During a CT scan with contrast, the REBOA balloon is not necessarily deflated further. The training of the CT scan team could shorten the CT room stay time to under 5 min. The images should be read quickly following focused assessment of the scans for trauma by trauma radiologists. REBOA WBCT scans in HUPs with appropriate protocols and image readings might be the tool for choosing a better management in order to restrain hemorrhage.

Trends in Aortic Occlusion and How to Minimize the Risk of Complications in REBOA

Resuscitative endovascular balloon occlusion of the aorta (REBOA) increases proximal aortic pressure in order to maintain central organ perfusion pressure, and simultaneously regulates distal arterial flow by endovascular aortic occlusion, which is applied during subdiaphragmatic hemorrhage. This article briefly introduces the history of REBOA and discusses its potential effectiveness and harmfulness. The article also mentions the technical aspects of REBOA, and reconsiders the term “REBOA” and “resuscitation.” The risks of aortic occlusion and ischemia-reperfusion injury have not been fully elucidated. It is hoped that REBOA can be used appropriately as a powerful option for the resuscitation of hemorrhagic patients and save the lives of as many patients as possible. The Society of Diagnostic and Interventional Radiology in Emergency, Critical Care, and Trauma will publish continuous medical education articles on REBOA.

Transfer Patient Imaging: A Novel Peer Feedback Program Beyond Institutional Boundaries

At our level 1 trauma center, we overread cross-sectional scans on all transferred patients, initially reported by community radiologists (CR). We designed a unique peer feedback learning model to address discrepancies encountered with outside overreads with the goal of practice improvement on the part of the CRs. Although there is ample literature on internal peer review and peer learning programs, no publications address errors committed by peers outside institutional boundaries. In this paper we describe our model and report a survey analyzing the perception of the program by the CRs. Outside CT and MR exams and reports of patients transferred to our level 1 trauma center were imported into PACS and prospectively overread by specialist trauma radiologists. Our report contained a summary of the outside findings as well as our findings. In the case of a significant discrepancy, a paper copy of our final report was sent by US mail to the originating CR. When the program had been active for 18 months, an invitation to participate in a survey was sent to all radiologists who had been sent reports. Eight thousand three hundred forty patients were transferred, of which 4331 (52%) had 9175 exams with outside reports (8666 CT scans and 509 MRI). One hundred seventy six final report letters containing significant discrepancies were sent to 139 individual radiologists. These 139 radiologists also later received our survey letter. Thirty-eight (27%) responses were received. Thirty-two respondents (84%) recalled receiving the report and reviewed the exam in question. Twenty-eight of them (85%) agreed with the overread and 30 (88%) believed that our feedback program should be continued. We have designed a novel peer feedback learning model to address discrepancies in outside overreads which is administratively simple and well received by the CRs getting feedback. Those CR who responded to the survey rated the experience favorably and wanted the practice continued, although the overall response rate did not allow statistical analysis. Also, institutions trying to design similar or new peer learning models can benefit from our experience.

Trauma radiology teaching for foundation doctors working within the Scottish Trauma Network improves radiology requests and patient safety: a multidepartmental quality improvement project

The importance of radiology in trauma management is particularly relevant today as Scotland develops its Scottish Trauma Network. Trauma and radiology are scarcely covered in the 2016 and 2021 Foundation...

Trauma radiology teaching for foundation doctors working within the Scottish Trauma Network improves radiology requests and patient safety: a multidepartmental quality improvement project.

The importance of radiology in trauma management is particularly relevant today as Scotland develops its Scottish Trauma Network. Trauma and radiology are scarcely covered in the 2016 and 2021 Foundation Programme Curriculum. Trauma is a significant and endemic public health challenge, while radiology is ever growing in use as a diagnostic and interventional tool. Currently, the majority of radiological investigation requests in trauma are made by foundation doctors. Accordingly, there is an urgent need to ensure foundation doctors are adequately trained in trauma radiology. This prospective, multidepartmental quality improvement project at a single major trauma centre primarily analysed the impact of trauma radiology teaching on the quality of foundation doctors' radiology requests according to Ionising Radiation Medical Exposure Regulations (IRMER) criteria. As a secondary outcome, the impact of teaching on patient safety was also evaluated. 50 foundation doctors across three departments dealing with trauma patients had their trauma radiology requests analysed before and after the intervention of trauma-focused radiology teaching. Results showed cancelled and altered radiology requests decreased from 20% to 5% and from 25% to 10%, respectively, with a p value of 0.01. This translated to fewer delays in trauma patients receiving radiological investigations. The foundation curriculum would benefit from the introduction of trauma radiology teaching for its foundation doctors, in parallel to the demands of a growing national trauma network. Education globally improves radiology request quality by raising awareness and respect of IRMER criteria and ultimately leads to positive changes for patient safety.

The trauma pelvic X-ray: Not all pelvic fractures are created equally

BackgroundThe primary aim of this study was to evaluate the role of the initial pelvic X-ray in identifying significant pelvic fractures, which could result in changes in the management of the patient. MethodsPatients admitted to a level I trauma center (2010–2019) with a severe blunt pelvic fracture (AIS ≥3) were identified. Included in the analysis were patients who underwent emergency department pelvic X-ray followed by CT scan. A control group of patients without pelvic fractures was also included in the study. All investigations were reviewed by a blinded attending trauma radiologist. Pelvic X-ray findings and CT scan reports were compared according to the specific pelvic fracture location, and severity. ResultsOverall, pelvic X-ray was diagnosed 252 of the 285 pelvic fractures (sensitivity 88.4%) and wrongly diagnosed a facture in 3 of 97 patients without a fracture (specificity 96.9%). In 29/184 (15.8%) of patients with pelvic fracture AIS 3, the pelvic X-ray was read as normal, missing the fracture, compared with 4/101 (4.0%) in the AIS 4/5 group (p = 0.003). Pelvic X-ray had the lowest sensitivity in ischial (10.7%), iliac (28.7%), acetabular (42.4%), and sacral fractures (49.1%) and was best for detecting symphysis diastasis (89.8%). ConclusionPelvic X-ray is useful in identifying pubic symphysis diastasis. However, it misses or underestimates a significant number of fractures. CT scan evaluation should be performed in patients with a suspicious mechanism or clinical suspicion of pelvic fracture.

Current Standards for and Clinical Impact of Emergency Radiology in Major Trauma.

In industrialized countries, high energy trauma represents the leading cause of death and disability among people under 35 years of age. The two leading causes of mortality are neurological injuries and bleeding. Clinical evaluation is often unreliable in determining if, when and where injuries should be treated. Traditionally, surgery was the mainstay for assessment of injuries but advances in imaging techniques, particularly in computed tomography (CT), have contributed in progressively changing the classic clinical paradigm for major traumas, better defining the indications for surgery. Actually, the vast majority of traumas are now treated nonoperatively with a significant reduction in morbidity and mortality compared to the past. In this sense, another crucial point is the advent of interventional radiology (IR) in the treatment of vascular injuries after blunt trauma. IR enables the most effective nonoperative treatment of all vascular injuries. Indications for IR depend on the CT evidence of vascular injuries and, therefore, a robust CT protocol and the radiologist’s expertise are crucial. Emergency and IR radiologists form an integral part of the trauma team and are crucial for tailored management of traumatic injuries.

The Role of Interventional Radiology in Splenic Trauma

The purpose of this case report is to discuss the different treatment options available in splenic trauma patients by following the story of Mr. H. I will focus particularly on the role of splenic arterial embolisation (SAE)—an interventional radiological procedure—and how it weighs up against its surgical counterparts. In order to give a balanced view this case report includes a literature review around splenic artery embolisation. This report concludes that when managing splenic trauma, interventional radiology (IR) is a useful tool particularly when used in conjunction with surgery. The future of this field needs to allow SAE to become a stand-alone therapy. Furthermore, research needs to investigate which cohorts of patients are best suited to which intervention such that we can capitalise on the advantages of each intervention for the benefit of all.

Emergency angiography for trauma patients and potential association with acute kidney injury

BackgroundAngiography has been conducted as a hemostatic procedure for trauma patients. While several complications, such as tissue necrosis after embolization, have been reported, little is known regarding subsequent acute kidney injury (AKI) due to contrast media. To elucidate whether emergency angiography would introduce kidney dysfunction in trauma victims, we compared the incidence of AKI between patients who underwent emergency angiography and those who did not.MethodsA retrospective cohort study was conducted using a nationwide trauma database (2004–2019), and adult trauma patients were included. The indication of emergency angiography was determined by both trauma surgeons and radiologists, and AKI was diagnosed by treating physicians based on a rise in serum creatinine and/or fall in urine output according to any published standard criteria. Incidence of AKI was compared between patients who underwent emergency angiography and those who did not. Propensity score matching was conducted to adjust baseline characteristics including age, comorbidities, mechanism of injury, vital signs on admission, Injury Severity Scale (ISS), degree of traumatic kidney injury, surgical procedures, and surgery on the kidney, such as nephrectomy and nephrorrhaphy.ResultsAmong 230,776 patients eligible for the study, 14,180 underwent emergency angiography. The abdomen/pelvis was major site for angiography (10,624 [83.5%]). Embolization was performed in 5,541 (43.5%). Propensity score matching selected 12,724 pairs of severely injured patients (median age, 59; median ISS, 25). While the incidence of AKI was rare, it was higher among patients who underwent emergency angiography than in those who did not (140 [1.1%] vs. 67 [0.5%]; odds ratio = 2.10 [1.57–2.82]; p < 0.01). The association between emergency angiography and subsequent AKI was observed regardless of vasopressor usage or injury severity in subgroup analyses.ConclusionsEmergency angiography in trauma patients was probably associated with increased incidence of AKI. The results should be validated in future studies.

Impact of 24/7 Onsite Emergency Radiology Staff Coverage on Emergency Department Workflow.

Assess the impact of 24/7/365 emergency trauma radiology (ETR) coverage on Emergency Department (ED) patient flow in an urban, quaternary-care teaching hospital. Patient ED visit and imaging information were extracted from the hospital patient care information system for 2008 to 2018. An interrupted time-series approach with a comparison group was used to study the impact of 24/7/365 ETR on average monthly ED length of stay (ED-LOS) and Emergency Physician to disposition time (EP-DISP). Linear regression models were fit with abrupt and permanent interrupts for 24/7/365 ETR, a coefficient for comparison series and a SARIMA error term; subgroup analyses were performed by patient arrival time, imaging type and chief complaint. During the study period, there were 949,029 ED visits and 739,796 diagnostic tests. Following implementation of 24/7/365 coverage, we found a significant decrease in EP-DISP time for patients requiring only radiographs (-29 min;95%CI:-52,-6) and a significant increase in EP-DISP time for major trauma patients (46 min;95%CI:13,79). No significant change in patient throughput was observed during evening hours for any patient subgroup. For overnight patients, there was a reduction in EP-DISP for patients with symptoms consistent with stroke (-78 min;95%CI:-131,-24) and for high acuity patients who required imaging (-33 min;95%CI:-57,-10). Changes in ED-LOS followed a similar pattern. At our institution, 24/7/365 in-house ETR staff radiology coverage was associated with improved ED flow for patients requiring only radiographs and for overnight stroke and high acuity patients. Major trauma patients spent more time in the ED, perhaps reflecting the required multidisciplinary management.