The role of plain radiography in paediatric wrist trauma

Suppression of immobilisation device on wrist radiography to improve fracture visualisation

OBJECTIVES

This study validates the use of CycleGAN-generated wrist radiographs with digitally removed splints, specifically assessing their impact on fracture visualisation.

MATERIALS AND METHODS

We retrospectively collected wrist radiographs from 1748 patients who had imaging before and after splint application at a single institution. The dataset was divided into training (1696 patients, 5353 images) and testing sets (52 patients, 965 images). A CycleGAN-based model was trained to generate splint-free wrist radiographs (generated "splint-less") from the original "splint" images. A pre-trained fracture detection model (YOLO8s) was used to assess fracture detection performance on three image groups: original "splint-less" radiographs, original "splint" radiographs, and generated "splint-less" radiographs. Two radiologists scored the generated images. Subtraction images quantified overall image alterations. Precision, recall, and F1 scores were used to compare fracture detection performance.

RESULTS

CycleGAN effectively generated splint-suppressed radiographs with minimal remaining splint density (< 10% remaining in 97.99%), hardware distortion (< 10% change in 100%), anatomical distortion (< 10% in 99.63%), and fracture lesion changes (< 10% change in 100%). New artefacts were rare (absent in 97.54%). Notably, the fracture detection model achieved higher precision (0.94 vs. 0.92), recall (0.63 vs. 0.5), and F1 score (0.75 vs. 0.65) on the generated "splint-less" radiographs compared to the original "splint" radiographs, approaching the performance on original "splint-less" radiographs (F1 0.71). Furthermore, greater image alterations by CycleGAN correlated with larger improvements in fracture detection.

CONCLUSION

CycleGAN successfully removed splint densities from wrist radiographs with splints.

KEY POINTS

Question Can CycleGAN (Generative Adversarial Networks), designed for image-to-image translation, generate synthetic "splint-less" radiographs to improve fracture visualisation in follow-up radiographs? Findings Removal of splint densities from wrist radiographs using Generative Adversarial Networks preserved anatomical structures and improved the performance of a fracture detection model. Clinical relevance Generated splint-less radiographs can enhance the performance of wrist fracture detection in wrist radiographs, benefiting both human clinicians and AI-powered diagnostic tools.

Domain Specific Transporter Framework to Detect Fractures in Ultrasound

Ultrasound examination for detecting fractures is ideally suited for Emergency Departments (ED) as it is fast, safe (from ionizing radiation), has dynamic imaging capability, and is easily portable. High variability in manual assessment of ultra-sound has piqued research interest in automatic assessment using Deep Learning (DL). Most DL techniques are trained on large labeled datasets which is expensive and requires many hours of careful annotation. We propose an unsupervised, domain-specific transporter framework to identify relevant key points from ultrasound scans providing a concise geometric representation highlighting regions with high structural variation. We incorporate domain-specific information using instantaneous local phase (LP) which detects bone features. We validate the technique on wrist 3DUS videos obtained from 30 subjects each independently assessed by 3 readers to identify fractures. The saliency of key points detected is compared against manual assessment based on distance from relevant features. Our approach was able to accurately detect 180/250 bone regions. We expect this technique to increase the applicability of ultrasound in fracture detection.

Ultrasound in the Diagnosis of Pediatric Distal Radius Fractures: Does it Really Change the Treatment Policy? An Orthopedic View

BACKGROUND

Distal radius fractures are the most common pediatric fractures, increasing in number in recent decades. Although simple bi-planar radiographs are sufficient for diagnosis, wrist ultrasonography has been popularized in recent years for fracture detection, mostly because of the concern about children's radiation exposure. Despite its availability and diagnostic accuracy, ultrasound has not gained widespread acceptance and popularity among orthopedic surgeons. We asked about the reasons for its lack of acceptance as a diagnostic tool by orthopedic surgeons, and its failure to be incorporated into diagnostic algorithms.

MATERIAL AND METHODS

We reviewed the latest articles concerning the use of ultrasound in the diagnosis of pediatric distal radius fracture. Data extraction was performed from each study with a focus on the following items: the specialty field of the authors, number of patients, number of fractures, mean age of the patients, and the gold standard method of diagnosis.

RESULTS

Nine studies concerning the diagnostic accuracy of ultrasound in detecting distal radius fractures in children were included in the review. The most common field of practice of the authors was emergency medicine. Only two studies had an orthopedic surgeon among their authors. All studies employed X-ray imaging as the gold standard method. All studies were designed as prospective trials without randomization of patients. Generally, there was no independent blinded reviewer for the interpretation of ultrasound and X-ray images.

CONCLUSIONS

Most studies were completed by emergency medicine physicians, without involving an orthopedic surgeon. Ultrasound evaluation was undertaken primarily by emergency medicine physicians with little experience. These studies were not randomized controlled trials, and knowledge of the history and clinical presentation of the subjects could have led to information bias. The relatively low number of included patients and lack of follow-up examinations were other limitations. As a result, we believe that ultrasound has not proven to be a suitable substitute for conventional X-ray imaging in the detection of pediatric distal radius fractures. We propose X-ray evaluation as the clinical gold standard method for pediatric wrist fractures.

Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries

Wrist trauma is common in children, typically requiring radiography for diagnosis and treatment planning. However, many children do not have fractures and are unnecessarily exposed to radiation. Ultrasound performed at bedside could detect fractures prior to radiography. Modern tools including three-dimensional ultrasound (3DUS) and artificial intelligence (AI) have not yet been applied to this task. Our purpose was to assess (1) feasibility, reliability, and accuracy of 3DUS for detection of pediatric wrist fractures, and (2) accuracy of automated fracture detection via AI from 3DUS sweeps. Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned on both the affected and unaffected limb. Radiographs of the symptomatic limb were obtained for comparison. Ultrasound scans were read by three individuals to determine reliability. An AI network was trained and compared against the human readers. Thirty participants were enrolled, resulting in scans from fifty-five wrists. Readers had a combined sensitivity of 1.00 and specificity of 0.90 for fractures. AI interpretation was indistinguishable from human interpretation, with all fractures detected in the test set of 36 images (sensitivity = 1.0). The high sensitivity of 3D ultrasound and automated AI ultrasound interpretation suggests that ultrasound could potentially rule out fractures in the emergency department.

Infrared thermal imaging as a screening tool for paediatric wrist fractures

Wrist injuries are common in paediatric trauma; however, only half of children evaluated with an x-ray for possible fractures will have one. Thermal imaging offers a possible non-ionising method of screening for fractures and thus reducing negative x-ray rates. One hundred five children attending the Emergency Department for wrist injuries were recruited. Two 30-s thermal videos were recorded from injured and uninjured wrists-in flat and 45° elevated positions. A region of interest (ROI) was defined on each wrist. Cases in which the ROI was covered or had ice applied were excluded, leaving 40 patients for analysis. Comparisons of ROI included (i) injured and uninjured wrists-flat and elevated positions; (ii) as in (i) with a reference region on the proximal forearm subtracted; (iii) injured wrist ROI-flat and elevated positions. Fractures and sprains increased the mean skin surface temperature by 1.519% (p = 0.008) and 0.971% (p = 0.055) respectively compared with the uninjured wrist. The mean temperature difference between flat and elevated positions for fractures was 0.268% and - 0.1291% for sprains. This difference was statistically significant for fracture (p = 0.004) but not sprain (p = 0.500). The temperature differences recorded by thermal imaging between fractured and sprained wrists may assist in differentiation of these injuries. Graphical abstract Operational stages involved from thermal video recording to generation of results.

Implementation of the Amsterdam Pediatric Wrist Rules

BACKGROUND

The Amsterdam Pediatric Wrist Rules have been developed and validated to reduce wrist radiographs following wrist trauma in pediatric patients. However, the actual impact should be evaluated in an implementation study.

OBJECTIVE

To evaluate the effect of implementation of the Amsterdam Pediatric Wrist Rules at the emergency department.

MATERIALS AND METHODS

A before-and-after comparative prospective cohort study was conducted, including all consecutive patients aged 3 to 18 years presenting at the emergency department with acute wrist trauma. The primary outcome was the difference in the number of wrist radiographs before and after implementation. Secondary outcomes were the number of clinically relevant missed fractures of the distal forearm, the difference in length of stay at the emergency department and physician compliance with the Amsterdam Pediatric Wrist Rules.

RESULTS

A total of 408 patients were included. The absolute reduction in radiographs was 19% compared to before implementation (chi-square test, P<0.001). Non-fracture patients who were discharged without a wrist radiograph had a 26-min shorter stay at the emergency department compared to patients who received a wrist radiograph (68 min vs. 94 min; Mann-Whitney U test, P=0.004). Eight fractures were missed following the recommendation of the Amsterdam Pediatric Wrist Rules. However, only four of them were clinically relevant.

CONCLUSION

Implementing the Amsterdam Pediatric Wrist Rules resulted in a significant reduction in wrist radiographs and time spent at the emergency department. The Amsterdam Pediatric Wrist Rules were able to correctly identify 98% of all clinically relevant distal forearm fractures.

Number of positive radiographic findings in pediatric trauma patients

PURPOSE

Conventional radiography is frequently performed in pediatric patients in whom fractures and dislocations are suspected. However, until now, the rate of positive findings of the most commonly performed radiographic examinations in pediatric patients is unknown. The aim of this study was to evaluate the number of positive findings in the 20 most frequently requested standard radiographic examinations in pediatric patients in a level 1 trauma center systematically.

METHODS

A transversal cohort study was conducted at a level 1 trauma center in Germany (2008-2014). In a statistical pre hoc analysis, a sample size of 200 images of each standard radiograph was determined. The picture archiving and communication system (PACS) was searched for radiographic examinations in patients under 18 years.

RESULTS

The following fracture rates for the investigated 20 most common examinations were found: 70.5% clavicle, 54.5% forearm, 53% wrist, 41.5% elbow, 30.5% lower leg, 20% hand, 18.5% finger, 12.5% toe, 12% forefoot, 11.5% ankle, 9% shoulder, 6.5% patella, 5.5% foot, 4% knee, 2% conventional rib series, 1.5% lumbar spine, 1% Towne view, 0.5% skull, 0% cervical spine, and 0% odontoid. Differences in the mean age of analyzed pediatric trauma patients in correlation to different standard radiographs were found.

CONCLUSIONS

In our study, a relevant amount of different standard radiographs revealed a low fracture rate. Therefore, indications for X-ray should be checked properly and alternative procedures should be discussed with the patient and the parents. Clinical decision rules should be developed and pathways have to be implemented to minimize radiation exposure, waiting time, and costs.

External validation of clinical decision rules for children with wrist trauma

BACKGROUND

Clinical decision rules help to avoid potentially unnecessary radiographs of the wrist, reduce waiting times and save costs.

OBJECTIVE

The primary aim of this study was to provide an overview of all existing non-validated clinical decision rules for wrist trauma in children and to externally validate these rules in a different cohort of patients. Secondarily, we aimed to compare the performance of these rules with the validated Amsterdam Pediatric Wrist Rules.

MATERIALS AND METHODS

We included all studies that proposed a clinical prediction or decision rule in children presenting at the emergency department with acute wrist trauma. We performed external validation within a cohort of 379 children. We also calculated the sensitivity, specificity, negative predictive value and positive predictive value of each decision rule.

RESULTS

We included three clinical decision rules. The sensitivity and specificity of all clinical decision rules after external validation were between 94% and 99%, and 11% and 26%, respectively. After external validation 7% to 17% less radiographs would be ordered and 1.4% to 5.7% of all fractures would be missed. Compared to the Amsterdam Pediatric Wrist Rules only one of the three other rules had a higher sensitivity; however both the specificity and the reduction in requested radiographs were lower in the other three rules.

CONCLUSION

The sensitivity of the three non-validated clinical decision rules is high. However the specificity and the reduction in number of requested radiographs are low. In contrast, the validated Amsterdam Pediatric Wrist Rules has an acceptable sensitivity and the greatest reduction in radiographs, at 22%, without missing any clinically relevant fractures.

[X‑ray of the thoracic and lumbar spine in injured children and adolescents : Incidence, fracture rates and therapeutic consequences]

INTRODUCTION

Usually, conventional radiographs are appropriate for injuries in the region of the thoracic and lumbar spine (TLS) in children and adolescents. The aim of our study was to determine the incidence of trauma-associated radiographic findings in this anatomical region and to present the therapeutic consequences.

MATERIAL AND METHODS

In a retrospective cohort study (2007-2015) of a level 1 trauma center all children and adolescents (0-17 years) with a TLS-trauma, in which conventional radiographs were performed anteroposterior and lateral as the initial imaging modality, were included.

RESULTS

In 396 children and adolescents conventional radiographs were performed, but only 5.6 % suffered a fracture. Conventional radiographs were performed in 188 cases of the thoracic spine, in 43 cases in the thoracolumbar junction and in 255 cases in the lumbar spine. On average, children and adolescents with fractures were 12.5 (5-17) years old. Fractures were classified as 38.7 % A1.1, 51.6 % A1.2, and 9.7 % were fractures of the transverse process. B and C fractures could not be detected. Of all fractures, 80 % were found in the mid-thoracic spine and the thoracolumbar junction. All fractures could be treated conservatively.

CONCLUSION

With 5.6 % TLS-injuries in children and adolescents, the study revealed a low fracture rate in a highly radiosensitive region. With regard to an expected stable fracture morphology and the absent surgical consequences, the indication for emergency radiographs should be provided restrictively.

A study to develop clinical decision rules for the use of radiography in wrist trauma: Karadeniz wrist rules

INTRODUCTION

The aim of this study was to evaluate patients presenting to the emergency department (ED) with wrist trauma using physical examination findings and functional tests and to identify findings with high sensitivity and specificity among the parameters assessed in patients with fracture in the wrist. The ultimate objective was thus to establish a reliable and widely usable clinical decision rule for determining the necessity of radiography in wrist trauma.

METHODS

This prospective, multicenter study was performed in 8 hospitals. The relation between radiologically determined fracture and clinical findings consisting of physical examination findings and functional tests was assessed in terms of whether or not these were markers of radiography requirement, with the aim of identifying predictive values for fracture.

RESULTS

A total of 603 eligible trauma patients presented to the participating EDs during the study period. Fracture was identified in 24.5% of patients (n = 148). The 4-way combination with the highest sensitivity was identified as axial compression and the positive distal radioulnar drawer test, and pain with radial deviation and dorsal flexion. Sensitivity at distal ulna palpation was added as a fifth parameter, and sensitivity and negative predictive value thus increased to 100%.

CONCLUSION

With their 100% sensitivity and 100% negative predictive values, the Karadeniz wrist rules may represent a clinical decision rule that can be used in practice in EDs. If all 5 findings are negative, there is no indication for wrist radiography.

A clinical decision rule for the use of plain radiography in children after acute wrist injury: development and external validation of the Amsterdam Pediatric Wrist Rules

BACKGROUND

In most hospitals, children with acute wrist trauma are routinely referred for radiography.

OBJECTIVE

To develop and validate a clinical decision rule to decide whether radiography in children with wrist trauma is required.

MATERIALS AND METHODS

We prospectively developed and validated a clinical decision rule in two study populations. All children who presented in the emergency department of four hospitals with pain following wrist trauma were included and evaluated for 18 clinical variables. The outcome was a wrist fracture diagnosed by plain radiography.

RESULTS

Included in the study were 787 children. The prediction model consisted of six variables: age, swelling of the distal radius, visible deformation, distal radius tender to palpation, anatomical snuffbox tender to palpation, and painful or abnormal supination. The model showed an area under the receiver operator characteristics curve of 0.79 (95% CI: 0.76-0.83). The sensitivity and specificity were 95.9% and 37.3%, respectively. The use of this model would have resulted in a 22% absolute reduction of radiographic examinations. In a validation study, 7/170 fractures (4.1%, 95% CI: 1.7-8.3%) would have been missed using the decision model.

CONCLUSION

The decision model may be a valuable tool to decide whether radiography in children after wrist trauma is required.

Determination of radiography requirement in wrist trauma

OBJECTIVES

The purpose of this study was to evaluate predetermined physical examination and function tests recommended to identify severe injury among patients presenting with wrist injury to the emergency department and to establish a reliable clinical decision rule capable of determining the need for radiography in wrist injuries.

MATERIALS AND METHODS

This was a multicenter prospective derivation study of wrist injuries. All patients were assessed in terms of mechanism of trauma, inspection findings, heart rate, sensitivity at palpation, presence of pain with active movement, grasp strength, and functional tests using an examination form under main headings. Sensitivity, specificity, and positive and negative predictive values were expressed for each sign and each examination finding.

RESULTS

One hundred nineteen adult patients were enrolled during the 6-month study period. Fracture was identified in 24.3% (n = 29). Presence of pain on the radial deviation, dorsal flexion, distal radioulnar drawer, and axial compression tests exhibited high sensitivity (82.8%, 89.7%, 82.8%, and 86.2%, respectively) and high negative predictive values (88.6%, 81.3%, 87.5%, and 93.6%, respectively) for wrist fracture. Sensitivity of 96.6% was observed when these 4 tests were evaluated together.

CONCLUSIONS

The presence of one of these examination findings increases the likelihood of fracture and is adequate to recommend wrist radiography. In addition, there is a strong possibility of radiography being unnecessary if all 4 test results are negative in patients presenting with wrist injury, potentially preventing many nonessential radiographs being performed.

A pilot study to identify clinical predictors for wrist fractures in adult patients with acute wrist injury

BACKGROUND

To date, no clinical decision rules for acute wrist injuries are available. In the past, clinical decision rules for the knee, ankle and spine injuries have been developed and validated. Implementation of these rules resulted in standardised clinical assessment at the emergency department and a substantial reduction of radiographic diagnostics. The objective of the study was to identify predictors for wrist fractures in patients with acute wrist injury which might potentiate a clinical decision rule in the future. This is a prospective pilot study in adult patients presenting with acute wrist injury at the emergency department of the Canisius-Wilhelmina Hospital in the Netherlands.

METHODS

Clinical variables were collected in a case report file by emergency physicians. Radiography was ordered according to common practice to confirm or rule out the presence of fractures. Independent associations between the presence of clinical variables and wrist fractures were calculated. Multivariable analysis was performed in order to quantify sensitivity and specificity for fracture prediction.

RESULTS

A total of 63 wrist fractures were detected in the study population of 95. Age over 55 years, inability to carry weight directly after trauma, support of injured wrist by the contralateral hand for pain relief, presence of swelling and/or hematoma, visible wrist deformity and reduced range of motion were associated with the presence of a wrist fracture.

CONCLUSIONS

Our study identified clinical predictors for wrist fractures in patients with acute wrist injury. Future studies are needed for justification of evidence-based wrist assessment and identification of a 100% sensitive decision rule for wrist fractures.