Imaging of accidental paediatric head trauma

Deep Learning-Assisted Diagnosis of Pediatric Skull Fractures on Plain Radiographs

Objective

To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children.

Materials and Methods

This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs).

Results

The AI model showed an AUROC of 0.922 (95% CI, 0.842–0.969) in the internal test set and 0.870 (95% CI, 0.785–0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%–92.0%) and specificity of 91.3% (95% CI, 79.2%–97.6%) for the internal test set and 78.9% (95% CI, 54.4%–93.9%) and 88.2% (95% CI, 78.7%–94.4%), respectively, for the external test set. With the model’s assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020–0.168; p = 0.012) and 0.069 (95% CI, 0.002–0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074–0.090; p = 0.850).

Conclusion

A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

Linear skull fracture in infants after mild traumatic brain injury: influence of computed tomography in management

INTRODUCTION

Traumatic brain injury (TBI) is a common reason for pediatric emergency room visits. Surgical intervention for mild TBI is rarely necessary in children aged <2 years, but the intracranial findings can influence the management of the patient. This paper aims to evaluate the impact of computed tomography (CT) in the management of children aged <2 years with mild TBI and linear skull fractures on plain-film X-rays.

MATERIAL AND METHODS

This retrospective descriptive study analyzed skull X-rays obtained in children <2 years old attended for mild TBI in the emergency room of our tertiary hospital over a 4-year period.

RESULTS

A total of 88 CT studies were done for suspicion of linear skull fractures on plain-film X-rays. Fractures were confirmed in 74, representing a false-positive rate of 16%. Of the 74 infants with confirmed fractures, intracranial CT findings were normal in 68 (92%) and abnormal in 6 (8%). Two patients (2.7% of all patients with confirmed fractures) required hospital stays longer than 2 days; the other four patients with abnormal intracranial findings were discharged within 48hours of admission. None of the cases required surgery.

CONCLUSION

Systematic CT studies do not seem justified for all children aged <2 years with TBI and low/intermediate risk of intracranial lesions, even when they have linear skull fractures. In the absence of risk factors, we propose individualizing the imaging study based on clinical criteria.

Does the Addition of a "Black Bone" Sequence to a Fast Multisequence Trauma MR Protocol Allow MRI to Replace CT after Traumatic Brain Injury in Children?

BACKGROUND AND PURPOSE

Head CT is the current neuroimaging tool of choice in acute evaluation of pediatric head trauma. The potential cancer risks of CT-related ionizing radiation should limit its use in children. We evaluated the role of MR imaging, including a "black bone" sequence, compared with CT in detecting skull fractures and intracranial hemorrhages in children with acute head trauma.

MATERIALS AND METHODS

We performed a retrospective evaluation of 2D head CT and brain MR imaging studies including the black bone sequence of children with head trauma. Two experienced pediatric neuroradiologists in consensus created the standard of reference. Another pediatric neuroradiologist blinded to the diagnosis evaluated brain MR images and head CT images in 2 separate sessions. The presence of skull fractures and intracranial posttraumatic hemorrhages was evaluated. We calculated the sensitivity and specificity of CT and MR imaging with the black bone sequence in the diagnosis of skull fractures and intracranial hemorrhages.

RESULTS

Twenty-eight children (24 boys; mean age, 4.89 years; range, 0-15.5 years) with head trauma were included. MR imaging with the black bone sequence revealed lower sensitivity (66.7% versus 100%) and specificity (87.5% versus 100%) in identifying skull fractures. Four of 6 incorrectly interpreted black bone MR imaging studies showed cranial sutures being misinterpreted as skull fractures and vice versa.

CONCLUSIONS

Our preliminary results show that brain MR imaging complemented by a black bone sequence is a promising nonionizing alternative to head CT for the assessment of skull fractures in children. However, accuracy in the detection of linear fractures in young children and fractures of aerated bone remains limited.

The unique features of traumatic brain injury in children. review of the characteristics of the pediatric skull and brain, mechanisms of trauma, patterns of injury, complications, and their imaging findings--part 2

Traumatic brain injury (TBI) is a major cause of morbidity and mortality in children. The unique biomechanical, hemodynamical, and functional characteristics of the developing brain and the age-dependent variance in trauma mechanisms result in a wide range of age specific traumas and patterns of brain injuries. Detailed knowledge of the main primary and secondary pediatric injuries, which enhance sensitivity and specificity of diagnosis, will guide therapy and may give important information about the prognosis. In recent years, anatomical but also functional imaging methods have revolutionized neuroimaging of pediatric TBI. The purpose of this article is (1) to comprehensively review frequent primary and secondary brain injuries and (2) to give a short overview of two special types of pediatric TBI: birth related and nonaccidental injuries.

The unique features of traumatic brain injury in children. Review of the characteristics of the pediatric skull and brain, mechanisms of trauma, patterns of injury, complications and their imaging findings--part 1

Traumatic head/brain injury (TBI) is a leading cause of death and life-long disability in children. The biomechanical properties of the child's brain and skull, the size of the child, the age-specific activity pattern, and higher degree of brain plasticity result in a unique distribution, degree, and quality of TBI compared to adult TBI. A detailed knowledge about the various types of primary and secondary pediatric head injuries is essential to better identify and understand pediatric TBI. The goals of this review article are (1) to discuss the unique epidemiology, mechanisms, and characteristics of TBI in children, and (2) to review the anatomical and functional imaging techniques that can be used to study common and rare pediatric traumatic brain injuries and their complications.

A subacute epidural haematoma extending over the occipital region and posterior cranial fossa due to a laceration in the transverse sinus

A 6-year-old male was found dead on his stomach with massive reddish vomiting from his mouth and nose. Postmortem cranial CT revealed an epidural haematoma in the left occipital region, but the cause and origin of the haematoma were unclear. An autopsy revealed that the epidural haematoma expanded over the left temporal region and the left side of the occipital region and posterior cranial fossa, and its origin was a laceration in the left transverse sinus induced by diastases in the left lambdoidal and occipitomastoid sutures. A pathohistological examination revealed that one portion of the haematoma was an early-stage hemorrhage, while the other portion extended approximately 1 week after the hemorrhage. Moreover, approximately 1 week elapsed after the laceration of the transverse sinus. Thus, we believe that the primary haematoma was induced by the laceration in the transverse sinus approximately 1 week before death, but the haematoma ceased to enlarge due to hemostasis. However, later, the size of the haematoma rapidly increased again due to rebleeding from the laceration, which led to intracranial hypertension. Consequently, we diagnosed the direct cause of death as choking due to vomit aspiration that resulted from intracranial hypertension induced by a subacute epidural haematoma.

Minor head injury in children

PURPOSE OF REVIEW

This review will examine mild closed head injury (CHI) and the current evidence on head computed tomography (CT) imaging risks in children, prediction rules to guide decisions on CT scan use, and issues of concussion after initial evaluation.

RECENT FINDINGS

The current literature offers preliminary evidence on the risks of radiation exposure from CT scans in children. A recent study introduces a validated prediction rule for use in mild CHI, to limit the number of CT scans performed. Concurrent with this progress, fast (or short sequence) MRI represents an emerging technology that may prove to be a viable alternative to CT scan use in certain cases of mild CHI where imaging is desired. The initial emergency department evaluation for mild CHI is the start point for a sequence of follow-up to assure that postconcussive symptoms fully resolve. The literature on sports-related concussion offers some information that may be used for patients with non-sports-related concussion.

SUMMARY

It is clear that CT scan use should be as safe and limited in scope as possible for children. Common decisions on the use of CT imaging for mild head injury can now be guided by a prediction rule for clinically important traumatic brain injury. Parameters for the follow-up care of patients with mild CHI after emergency department discharge are needed in the future to assure that postconcussive symptoms are adequately screened for full resolution.