<h4>Objective</h4>To report and assess the usefulness of ultrasound (US) findings for occult fractures of growing bones.<h4>Materials and methods</h4>For six years, US scans were performed in children younger than 15 years who were referred with trauma-related local pain and swelling of the extremities. As a routine US examination, the soft tissue, bones, and adjacent joints were examined in the area of discomfort, in addition to the asymptomatic contralateral extremity for comparison. Twenty-five occult fractures in 25 children (age range, five months-15 years; average age, 7.7 years) were confirmed by initial and follow-up radiograms, additional imaging studies, and clinical observation longer than three weeks.<h4>Results</h4>The most common site of occult fractures was the elbow (n = 9, 36%), followed by the knee (n = 7, 28%), ischium (n = 4, 16%), distal fibula (n = 3, 12%), proximal femur (n = 1, 4%), and humeral shaft (n = 1, 4%). On the retrograde review of the routine radiographs, 13 out of the 25 cases showed no bone abnormalities except for various soft tissue swelling. For the US findings, cortical discontinuity (direct sign of a fracture) was clearly visualized in 23 cases (92%) and was questionable in two (8%). As auxiliary US findings (indirect signs of a fracture), step-off deformities, tiny avulsed bone fragments, double-line appearance of cortical margins, and diffuse irregularity of the bone surfaces were identified.<h4>Conclusion</h4>Performing US for soft tissue and bone surfaces with pain and swelling, with or without trauma history in the extremities, is important for diagnosing occult or missed fractures of immature bones in pediatric-aged children.

Fractures in infants and children are different to those seen in adults. Many are very subtle and difficult to detect with certainty. Furthermore, variations in bone contour and epiphyseal plate configuration are endless and at first may suggest pathology. Comparative views are therefore invaluable and are emphasized throughout this communication, which deals with: (1) plastic bending fractures, (2) hairline fractures, (3) impaction fractures, (4) subtle epiphyseal-metaphyseal Salter-Harris fractures, and (5) subtle angle buckle fractures. Helpful points to assist one in detecting these fractures are presented.

<h4>Background</h4>A radiographic fat pad sign after an elbow injury in children may indicate an occult fracture. Different incidences and locations of occult fractures have been reported. The primary objective of this meta-analysis was to assess the overall rate of occult fractures in children with a positive fat pad sign from the data of original studies. Secondary objectives were to assess the fracture types and to identify risk factors for sustaining an occult fracture.<h4>Methods</h4>A systematic literature search of the Embase, MEDLINE, and Cochrane databases was performed according to PRISMA guidelines. Studies on pediatric populations with a positive fat pad sign identified using a lateral elbow radiograph and with follow-up imaging were included in this meta-analysis. Included studies were assessed for risk of bias with use of the MINORS (Methodological Index for NOn-Randomized Studies) instrument.<h4>Results</h4>Ten studies with a total of 250 patients, of whom 104 had an occult fracture, were included. Accounting for heterogeneity between the studies, the overall occult fracture rate was 44.6% (95% confidence interval: 30.4% to 59.7%). The most common fracture locations were the supracondylar humerus (43%), proximal ulna (19%), proximal radius (17%), and lateral humeral condyle (14%). Definitions of a positive pad fad sign were not uniform among studies, and the follow-up imaging modality also varied (radiography, magnetic resonance imaging, or computed tomography). The average MINORS score was 10.1 for the 7 noncomparative studies and 18.7 for the 3 comparative studies, with both averages classified as moderate quality. We were not able to identify risk factors for an occult fracture in the presence of a positive fat pad sign.<h4>Conclusions</h4>The occult fracture rate was 44.6% in pediatric elbow injuries with a positive fat pad sign. Supracondylar humeral fractures were the most frequently encountered type. The findings of this meta-analysis underline the potential clinical relevance of a positive fat pad sign in children and denote the opportunity for future studies to create evidence-based guidelines.<h4>Level of evidence</h4>Level II. See Instructions for Authors for a complete description of levels of evidence.

Supracondylar humerus fractures in children are among the most common elbow fractures in pediatrics. However, their diagnosis can be particularly challenging due to the anatomical characteristics and imaging features of the pediatric skeleton. In recent years, convolutional neural networks (CNNs) have achieved notable success in medical image analysis, though their performance typically relies on large-scale, high-quality labeled datasets. Unfortunately, labeled samples for pediatric supracondylar fractures are scarce and difficult to obtain. To address this issue, this paper introduces a deep learning-based multi-scale patch residual network (MPR) for the automatic detection and localization of subtle pediatric supracondylar fractures. The MPR framework combines a CNN for automatic feature extraction with a multi-scale generative adversarial network to model skeletal integrity using healthy samples. By leveraging healthy images to learn the normal skeletal distribution, the approach reduces the dependency on labeled fracture data and effectively addresses the challenges posed by limited pediatric datasets. Datasets from two different hospitals were used, with data augmentation techniques applied during both training and validation. On an independent test set, the proposed model achieves an accuracy of 90.5%, with 89% sensitivity, 92% specificity, and an F1 score of 0.906-outperforming the diagnostic accuracy of emergency medicine physicians and approaching that of pediatric radiologists. Furthermore, the model demonstrates a fast inference speed of 1.1 s per sheet, underscoring its substantial potential for clinical application.

During 1974 156 patients with pelvic fractures were admitted to our hospital. Of them 63 (40.4%) had double vertical lesions, which broke the pelvic ring in two sites. In 12 patients the diagnosis of a sacral hairline fracture was not made initially. The difficulties in making a radiological diagnosis are mainly due to the curved form of the sacrum in plain radiographs. The use of sophisticated radiological methods does not remove the difficulties. Double lesions were missed most often in elderly female patients with low-energy hairline fractures in osteoporotic sacra. The typical indirect signs observed in combination with sacral fractures were no help in the search for these missed hairline fractures, and the contribution of these fractures to the prediction of dangerous complications can be regarded as minimal.