ACR Appropriateness Criteria Blunt Chest Trauma

Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study

BACKGROUND

Chest radiography is the standard investigation for identifying rib fractures. The application of artificial intelligence (AI) for detecting rib fractures on chest radiographs is limited by image quality control and multilesion screening. To our knowledge, few studies have developed and verified the performance of an AI model for detecting rib fractures by using multi-center radiographs. And existing studies using chest radiographs for multiple rib fracture detection have used more complex and slower detection algorithms, so we aimed to create a multiple rib fracture detection model by using a convolutional neural network (CNN), based on multi-center and quality-normalised chest radiographs.

METHODS

A total of 1080 radiographs with rib fractures were obtained and randomly divided into the training set (918 radiographs, 85%) and the testing set (162 radiographs, 15%). An object detection CNN, You Only Look Once v3 (YOLOv3), was adopted to build the detection model. Receiver operating characteristic (ROC) and free-response ROC (FROC) were used to evaluate the model's performance. A joint testing group of 162 radiographs with rib fractures and 233 radiographs without rib fractures was used as the internal testing set. Furthermore, an additional 201 radiographs, 121 with rib fractures and 80 without rib fractures, were independently validated to compare the CNN model performance with the diagnostic efficiency of radiologists.

RESULTS

The sensitivity of the model in the training and testing sets was 92.0% and 91.1%, respectively, and the precision was 68.0% and 81.6%, respectively. FROC in the testing set showed that the sensitivity for whole-lesion detection reached 91.3% when the false-positive of each case was 0.56. In the joint testing group, the case-level accuracy, sensitivity, specificity, and area under the curve were 85.1%, 93.2%, 79.4%, and 0.92, respectively. At the fracture level and the case level in the independent validation set, the accuracy and sensitivity of the CNN model were always higher or close to radiologists' readings.

CONCLUSIONS

The CNN model, based on YOLOv3, was sensitive for detecting rib fractures on chest radiographs and showed great potential in the preliminary screening of rib fractures, which indicated that CNN can help reduce missed diagnoses and relieve radiologists' workload. In this study, we developed and verified the performance of a novel CNN model for rib fracture detection by using radiography.

Effect of deep learning-based assistive technology use on chest radiograph interpretation by emergency department physicians: a prospective interventional simulation-based study

BACKGROUND

Interpretation of chest radiographs (CRs) by emergency department (ED) physicians is inferior to that by radiologists. Recent studies have investigated the effect of deep learning-based assistive technology on CR interpretation (DLCR), although its relevance to ED physicians remains unclear. This study aimed to investigate whether DLCR supports CR interpretation and the clinical decision-making of ED physicians.

METHODS

We conducted a prospective interventional study using a web-based performance assessment system. Study participants were recruited through the official notice targeting board for certified emergency physicians and residents working at the present ED. Of the eight ED physicians who volunteered to participate in the study, seven ED physicians were included, while one participant declared withdrawal during performance assessment. Seven physicians' CR interpretations and clinical decision-making were assessed based on the clinical data from 388 patients, including detecting the target lesion with DLCR. Participant performance was evaluated by area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and accuracy analyses; decision-making consistency was measured by kappa statistics. ED physicians with < 24 months of experience were defined as 'inexperienced'.

RESULTS

Among the 388 simulated cases, 259 (66.8%) had CR abnormality. Their median value of abnormality score measured by DLCR was 59.3 (31.77, 76.25) compared to a score of 3.35 (1.57, 8.89) for cases of normal CR. There was a difference in performance between ED physicians working with and without DLCR (AUROC: 0.801, P < 0.001). The diagnostic sensitivity and accuracy of CR were higher for all ED physicians working with DLCR than for those working without it. The overall kappa value for decision-making consistency was 0.902 (95% confidence interval [CI] 0.884-0.920); concurrently, the kappa value for the experienced group was 0.956 (95% CI 0.934-0.979), and that for the inexperienced group was 0.862 (95% CI 0.835-0.889).

CONCLUSIONS

This study presents preliminary evidence that ED physicians using DLCR in a clinical setting perform better at CR interpretation than their counterparts who do not use this technology. DLCR use influenced the clinical decision-making of inexperienced physicians more strongly than that of experienced physicians. These findings require prospective validation before DLCR can be recommended for use in routine clinical practice.

Acute traumatic injury of the aorta: presentation, diagnosis, and treatment

Despite advances in detection and treatment, acute traumatic aortic injury (ATAI) is associated with high rates of morbidity and mortality. Both physical and hemodynamic forces have been postulated as mechanisms of aortic injury during a traumatic event. For patients who survive the initial injury, rapid detection is critical for diagnosis and procedural planning, which requires a thorough knowledge of both its clinical presentation and the available diagnostic imaging modalities. Radiography, computed tomography (CT), and magnetic resonance imaging (MRI) can each have a role in the diagnosis of ATAI. After stabilization of the patient, the management of ATAI is guided by the severity of injury. Appropriately selected patients with low grade injuries may be managed non-operatively. When treatment is required, there are both open surgical and endovascular options. In current practice, endovascular approaches with stent-graft placement are preferred due to their high clinical success and low rates of complications. Complications from endograft placement can include: endoleak, endograft collapse, infection, endograft failure, and endograft migration. Open surgical repair is now reserved for patients with unfavorable anatomy for endovascular therapies. This review provides a comprehensive overview of ATAI including its epidemiology and demographics, mechanisms of injury, clinical and radiographic diagnosis, treatment options, and post-therapeutic follow-up.

Chest ultrasonography versus supine chest radiography for diagnosis of pneumothorax in trauma patients in the emergency department

BACKGROUND

Chest X-ray (CXR) is a longstanding method for the diagnosis of pneumothorax but chest ultrasonography (CUS) may be a safer, more rapid, and more accurate modality in trauma patients at the bedside that does not expose the patient to ionizing radiation. This may lead to improved and expedited management of traumatic pneumothorax and improved patient safety and clinical outcomes.

OBJECTIVES

To compare the diagnostic accuracy of chest ultrasonography (CUS) by frontline non-radiologist physicians versus chest X-ray (CXR) for diagnosis of pneumothorax in trauma patients in the emergency department (ED). To investigate the effects of potential sources of heterogeneity such as type of CUS operator (frontline non-radiologist physicians), type of trauma (blunt vs penetrating), and type of US probe on test accuracy.

SEARCH METHODS

We conducted a comprehensive search of the following electronic databases from database inception to 10 April 2020: Cochrane Database of Systematic Reviews, Cochrane Central Register of Controlled Trials, MEDLINE, Embase, Cumulative Index to Nursing and Allied Health Literature (CINAHL) Plus, Database of Abstracts of Reviews of Effects, Web of Science Core Collection and Clinicaltrials.gov. We handsearched reference lists of included articles and reviews retrieved via electronic searching; and we carried out forward citation searching of relevant articles in Google Scholar and looked at the "Related articles" on PubMed.

SELECTION CRITERIA

We included prospective, paired comparative accuracy studies comparing CUS performed by frontline non-radiologist physicians to supine CXR in trauma patients in the emergency department (ED) suspected of having pneumothorax, and with computed tomography (CT) of the chest or tube thoracostomy as the reference standard.

DATA COLLECTION AND ANALYSIS

Two review authors independently extracted data from each included study using a data extraction form. We included studies using patients as the unit of analysis in the main analysis and we included those using lung fields in the secondary analysis. We performed meta-analyses by using a bivariate model to estimate and compare summary sensitivities and specificities.

MAIN RESULTS

We included 13 studies of which nine (410 traumatic pneumothorax patients out of 1271 patients) used patients as the unit of analysis; we thus included them in the primary analysis. The remaining four studies used lung field as the unit of analysis and we included them in the secondary analysis. We judged all studies to be at high or unclear risk of bias in one or more domains, with most studies (11/13, 85%) being judged at high or unclear risk of bias in the patient selection domain. There was substantial heterogeneity in the sensitivity of supine CXR amongst the included studies. In the primary analysis, the summary sensitivity and specificity of CUS were 0.91 (95% confidence interval (CI) 0.85 to 0.94) and 0.99 (95% CI 0.97 to 1.00); and the summary sensitivity and specificity of supine CXR were 0.47 (95% CI 0.31 to 0.63) and 1.00 (95% CI 0.97 to 1.00). There was a significant difference in the sensitivity of CUS compared to CXR with an absolute difference in sensitivity of 0.44 (95% CI 0.27 to 0.61; P < 0.001). In contrast, CUS and CXR had similar specificities: comparing CUS to CXR, the absolute difference in specificity was -0.007 (95% CI -0.018 to 0.005, P = 0.35). The findings imply that in a hypothetical cohort of 100 patients if 30 patients have traumatic pneumothorax (i.e. prevalence of 30%), CUS would miss 3 (95% CI 2 to 4) cases (false negatives) and overdiagnose 1 (95% CI 0 to 2) of those without pneumothorax (false positives); while CXR would miss 16 (95% CI 11 to 21) cases with 0 (95% CI 0 to 2) overdiagnosis of those who do not have pneumothorax.

AUTHORS' CONCLUSIONS

The diagnostic accuracy of CUS performed by frontline non-radiologist physicians for the diagnosis of pneumothorax in ED trauma patients is superior to supine CXR, independent of the type of trauma, type of CUS operator, or type of CUS probe used. These findings suggest that CUS for the diagnosis of traumatic pneumothorax should be incorporated into trauma protocols and algorithms in future medical training programmes; and that CUS may beneficially change routine management of trauma.

[Management of thoracic trauma and intrathoracic injuries]

More than 45% of polytraumatized patients in Germany suffer from severe thoracic trauma. Due to the urgent time factor (e.g. respiratory insufficiency and severe bleeding), a structured procedure in the diagnostics and treatment according to the advanced trauma life support (ATLS) criteria is necessary both prehospital and in the emergency room in order to provide the patient with adequate care. If a patient is stable or can be stabilized there is the option of using extended diagnostics, such as whole body computer tomography (CT) scanning with contrast medium, to select a treatment that is optimally adapted to the injury pattern. This can be performed by open surgery, minimally invasive surgery and interventional radiologically/endoscopically and depends on the injured organ as well as the extent of the injury. This means that only an interdisciplinary approach guarantees optimal care for patients with thoracic trauma.

Clinical Approach to and Work-up of Bleeding Patients

A bleeding patient is a common consult for interventional radiologists. Prompt triage, preprocedural evaluation specific to the site of hemorrhage, and knowledge of resuscitative strategies allow for a potentially life-saving procedure to be appropriately and safely performed. Having a firm understanding of the clinical work-up and management of a bleeding patient has never been more important. In this article, a discussion of the clinical approach and work-up of a bleeding patient for whom interventional radiology is consulted is followed by a discussion of etiology-specific preprocedural work-up.

Cross-sectional imaging of thoracic traumatic aortic injury

Aortic injury remains a major contributor to morbidity and mortality from acute thoracic trauma. While such injuries were once nearly uniformly fatal, the advent of cross-sectional imaging in recent years has facilitated rapid diagnosis and triage, greatly improving outcomes. In fact, cross-sectional imaging is now the diagnostic test of choice for traumatic aortic injury (TAI), specifically computed tomography angiography (CTA) in the acute setting and CTA or magnetic resonance angiography (MRA) in follow-up. In this review, we present an up-to-date discussion of acute traumatic thoracic aortic injury with a focus on optimal and emerging CT/MR techniques, imaging findings of TAI, and potential pitfalls.

Thoracic wall trauma-misdiagnosed lesions on radiographs and usefulness of ultrasound, multidetector computed tomography and magnetic resonance imaging

Blunt injuries to the chest wall are an important chapter on emergency room (ER) departments, being the third most common injuries in trauma patients which ominous complications could appear. This article describes different types of traumatic events affecting the chest wall, which maybe misdiagnosed with conventional X-ray. Special emphasis has been done in computed tomography (CT) and multidetector CT (MDCT) imaging. This technique is considered the "gold-standard" for those traumatic patients, due to its fast acquisition covering the whole area of interest in axial plane, reconstructing multiplanar (2D, 3D) volume-rendered images with a superb quality and angiographic CT capabilities for evaluating vascular damage. Complementary techniques such as ultrasonography (US) and magnetic resonance imaging (MRI) may improve the diagnostic accuracy due to its great capacity in visualising soft-tissue trauma (muscle-tendinous tears) and subtle fractures. All these imaging methods have an important role in quantifying the severity of chest wall trauma. The findings of this study have been exposed with cases of our archives in a didactic way.

Early detection of myocardial infarction following blunt chest trauma by computed tomography: a case report

Background

Blunt cardiac trauma encompasses a wide range of clinical entities, including myocardial contusion, cardiac rupture, valve avulsion, pericardial injuries, arrhythmia, and even myocardial infarction. Acute myocardial infarction due to coronary artery dissection after blunt chest trauma is rare and may be life threatening. Differential diagnosis of acute myocardial infarction from cardiac contusion at this setting is not easy.

Case presentation

Here we demonstrated a case of blunt chest trauma, with computed tomography detected myocardium enhancement defect early at emergency department. Under the impression of acute myocardial infarction, emergent coronary angiography revealed left anterior descending artery occlusion. Revascularization was performed and coronary artery dissection was found after thrombus aspiration. Finally, the patient survived after coronary stenting.

Conclusion

Perfusion defects of myocardium enhancement on CT after blunt chest trauma can be very helpful to suggest myocardial infarction and facilitate the decision making of emergent procedure. This valuable sign should not be missed during the initial interpretation.

Usefulness of low dose chest CT for initial evaluation of blunt chest trauma

We aimed to compare the diagnostic performance and inter-observer consistency between low dose chest CT (LDCT) and standard dose chest CT (SDCT) in the patients with blunt chest trauma.A total of 69 patients who met criteria indicative of blunt chest trauma (77% of male; age range, 16-85) were enrolled. All patients underwent LDCT without intravenous (IV) contrast and SDCT with IV contrast using parameters as following: LDCT, 40 mAs with automatic tube current modulation (ATCM) and 100 kVp (BMI <25, n = 51) or 120 kVp (BMI>25, n = 18); SDCT, 180 mAs with ATCM and 120 kVp. Transverse, coronal, sagittal images were reconstructed with 3-mm slice thickness without gap and provided for evaluation of 3 observers. Reference standard images (transverse, coronal, sagittal) were reconstructed using SDCT data with 1-mm slice thickness without gap. Reference standard was established by 2 experienced thoracic radiologists by consensus. Three observers independently evaluated each data set of LDCT and SDCT.Multiple-reader receiver operating characteristic analysis for comparing areas under the ROC curves demonstrated that there was no significant difference of diagnostic performance between LDCT and SDCT for the diagnosis of pulmonary injury, skeletal trauma, mediastinal injury, and chest wall injury (P > 0.05). The intraclass correlation coefficient was measured for inter-observer consistency and revealed that there was good inter-observer consistency in each examination of LDCT and SDCT for evaluation of blunt chest injury (0.8601-1.000). Aortic and upper abdominal injury could not be appropriately compared as LDCT was performed without using contrast materials and this was limitation of this study.The effective radiation dose of LDCT (average DLP = 1.52 mSv⋅mGy cm) was significantly lower than those of SDCT (7.21 mSv mGy cm).There is a great potential benefit to use of LDCT for initial evaluation of blunt chest trauma because LDCT could maintain diagnostic image quality as SDCT and provide significant radiation dose reduction. A further study of LDCT with IV contrast for evaluation of aortic and upper abdominal injury is needed.

[Imaging of blunt chest trauma]

CLINICAL/METHODOLOGICAL ISSUE

Blunt chest trauma is associated with high morbidity and mortality. Consequently, all patients should be evaluated radiologically after blunt chest trauma to allow timely and appropriate treatment.

STANDARD RADIOLOGICAL METHODS

Conventional chest radiographs and computed tomography (CT) are proven modalities with which to evaluate patients after blunt chest trauma.

METHODOLOGICAL INNOVATIONS

Over the last several years extended focused assessment with sonography for trauma (eFAST) has gained increasing importance for the initial assessment of seriously injured patients.

PRACTICAL RECOMMENDATIONS

In the acute phase of severely injured patients eFAST examinations are helpful to exclude pneumothorax, hemothorax and hemopericardium. Chest radiographs may also be used to diagnose a pneumothorax or hemothorax; however, the sensitivity is limited and CT is the diagnostic modality of choice to evaluate severely injured patients.

Computed Tomography and Shifts to Alternate Imaging Modalities in Hospitalized Children

BACKGROUND

Many studies have demonstrated a rise in computed tomography (CT) utilization in abstract children's hospitals. However, CT utilization may be declining, perhaps due to awareness of potential hazards of pediatric ionizing radiation, such as increased risk of malignancy. Th e objective is to assess the trend in CT utilization in hospitalized children at freestanding children's hospitals from 2004 to 2012 and we hypothesize decreases are associated with shifts to alternate imaging modalities.

METHODS

Multicenter cross-sectional study of children admitted to 33 pediatric tertiary-care hospitals participating in the Pediatric Health Information System between January 1, 2004, and December 31, 2012. The rates of CT, ultrasound, and MRI for the top 10 All-Patient Refined Diagnosis Related Groups (APR-DRGs) for which CT was performed in 2004 were determined by billing data. Rates of each imaging modality for those top 10 APR-DRGs were followed through the study period. Odds ratios of imaging were adjusted for demographics and illness severity.

RESULTS

For all included APR-DRGs except ventricular shunt procedures and nonbacterial gastroenteritis, the number of children imaged with any modality increased. CT utilization decreased for all APR-DRGs (P values , .001). For each of the APR-DRGs except seizure and infections of upper respiratory tract, the decrease in CT was associated with a significant rise in an alternative imaging modality (P values # .005).

CONCLUSIONS

For the 10 most common APR-DRGs for which children received CT in 2004,a decrease in CT utilization was found in 2012. Alternative imaging modalities for 8 of the diagnoses were used.

Interruptions of Trauma Resuscitations for Radiographic Procedures

BACKGROUND

Although x-ray studies provide important diagnostic information during trauma resuscitations, they may also lead to significant interruptions in care.

OBJECTIVES

We sought to determine the frequency and duration of interruptions for chest x-ray studies (CXR) and pelvic x-ray studies (PXR) and the frequency of lead apron use among providers who exited trauma rooms during resuscitation.

METHODS

Using a convenience sampling method, we conducted a prospective, observational study from August 2013 to March 2014, enrolling adult trauma patients at a Level I trauma center who received CXR and PXR in the first 30 min of evaluation. An observer stood outside resuscitation rooms and recorded the time elapsed from the first provider exiting the room to the last provider returning. We recorded how many exiting providers wore lead aprons and whether unused aprons were available.

RESULTS

Of the 156 trauma cases observed, 67.3% were of male patients with a mean age of 52 years (interquartile range [IQR] 34-67 years); 97.4% (184/189) of radiographs resulted in interruptions of trauma evaluation. Mean and median interruption times were 67 s and 50 s, respectively (IQR 25-95) for CXR; 37 s and 27 s, respectively (IQR 16-43) for PXR; and 160 s and 180 s, respectively (IQR 120-180) for combined CXR/PXR. A mean of 3.5 providers (IQR 3-5) left the immediate bedside and exited the room during x-ray studies. Most (91%) providers leaving the room were not wearing lead aprons, and extra aprons were available in the room 91% (167/184) of the time.

CONCLUSIONS

Radiographic procedures often result in interruptions of trauma resuscitations despite the availability of lead aprons.

Rising utilization of CT in adult fall patients

OBJECTIVE. Falls are a common cause of emergency department (ED) visits in the United States. We evaluated trends in CT utilization for adult fall patients in the United States from 2001 to 2010. MATERIALS AND METHODS. Using the National Hospital Ambulatory Medical Care Survey, we identified all visits from 2001 to 2010 of adult patients presenting to EDs after falls. This database surveys approximately 500 EDs annually for 4 weeks, providing national estimates on ED resource utilization and outcomes. We studied trends in CT utilization and proportion of visits with life-threatening conditions (intracranial hemorrhage, organ laceration, axial skeletal fractures) after falls. We also studied the association between CT utilization rates and demographic characteristics and admission status. RESULTS. A total of 22,166 unweighted observations representing 73,241,368 visits were identified. The proportion of adult fall patient visits during which CT was performed increased from 11.4% in 2001 to 28.0% in 2010 (p < 0.0001), whereas the proportion of adult fall visits with life-threatening conditions increased from 5.7% to 8.2% (p < 0.0001). On adjusted analysis (adjusting for life-threatening condition and demographic variables), each successive year was independently associated with CT utilization (odds ratio, 1.21 [95% CI, 1.21-1.21]). The odds of CT utilization in 2010 compared with 2001 were 2.62 (95% CI, 2.61-2.62). CONCLUSION. There was a 2.5-fold increase in CT utilization among adult fall patient visits from 2001 to 2010. When demographic and clinical variables were controlled for, increasing year was independently associated with CT utilization. These findings suggest that CT may be overutilized among adult fall patients.

Dual-source computed tomography may define cardiac contusion in patients with blunt chest trauma in ED

We report a 20-year-old woman with blunt chest trauma because of a motor vehicle injury who has traumatic asphyxia and hypotension. The diagnosis of blunt cardiac injury was put by using dual-energy computed tomography in the emergency department because other laboratory and imaging modalities were useless. After hospitalization in intensive care unit, she was treated with supportive and antiedema therapy. The patient was extubated on the fifth day and discharged on the ninth day without any sequel. Coexistence of traumatic asphyxia with blunt cardiac injury is rare. Several imaging techniques such as transthoracic and transesophageal echocardiography, contrast-enhanced multislice thorax computed tomography or initial electrocardiogram, and troponin I levels are used to detect the myocardial damage, but diagnostic capability is low. Dual-energy computed tomography is a promising new technology with the ability of defining blunt cardiac injuries and may have an indication in the emergency setting in patients with hemodynamic instability to rule in traumatic cardiac complications especially when electrocardiogram and transthoracic echocardiography are useless in the emergency department.