Explore the vast range of titles available.

Common pediatric distal forearm fractures necessitate precise detection. To support prompt treatment planning by clinicians, our study aimed to create a multi-class convolutional neural network (CNN) model for pediatric distal forearm fractures, guided by the AO Foundation/Orthopaedic Trauma Association (AO/ATO) classification system for pediatric fractures. The GRAZPEDWRI-DX dataset (2008–2018) of wrist X-ray images was used. We labeled images into four fracture classes (FRM, FUM, FRE, and FUE with F, fracture; R, radius; U, ulna; M, metaphysis; and E, epiphysis) based on the pediatric AO/ATO classification. We performed multi-class classification by training a YOLOv4-based CNN object detection model with 7006 images from 1809 patients (80% for training and 20% for validation). An 88-image test set from 34 patients was used to evaluate the model performance, which was then compared to the diagnosis performances of two readers—an orthopedist and a radiologist. The overall mean average precision levels on the validation set in four classes of the model were 0.97, 0.92, 0.95, and 0.94, respectively. On the test set, the model’s performance included sensitivities of 0.86, 0.71, 0.88, and 0.89; specificities of 0.88, 0.94, 0.97, and 0.98; and area under the curve (AUC) values of 0.87, 0.83, 0.93, and 0.94, respectively. The best performance among the three readers belonged to the radiologist, with a mean AUC of 0.922, followed by our model (0.892) and the orthopedist (0.830). Therefore, using the AO/OTA concept, our multi-class fracture detection model excelled in identifying pediatric distal forearm fractures.

Background This study evaluates the accuracy of an Artificial Intelligence (AI) system, specifically a convolutional neural network (CNN), in classifying elbow fractures using the detailed 2018 AO/OTA fracture classification system. Methods A retrospective analysis of 5,367 radiograph exams visualizing the elbow from adult patients (2002–2016) was conducted using a deep neural network. Radiographs were manually categorized according to the 2018 AO/OTA system by orthopedic surgeons. A pretrained Efficientnet B4 network with squeeze and excitation layers was fine-tuned. Performance was assessed against a test set of 208 radiographs reviewed independently by four orthopedic surgeons, with disagreements resolved via consensus. Results The study evaluated 54 distinct fracture types, each with a minimum of 10 cases, ensuring adequate dataset representation. Overall fracture detection achieved an AUC of 0.88 (95% CI 0.83–0.93). The weighted mean AUC was 0.80 for proximal radius fractures, 0.86 for proximal ulna, and 0.85 for distal humerus. These results underscore the AI system’s ability to accurately detect and classify a broad spectrum of elbow fractures. Conclusions AI systems, such as CNNs, can enhance clinicians’ ability to identify and classify elbow fractures, offering a complementary tool to improve diagnostic accuracy and optimize treatment decisions. The findings suggest AI can reduce the risk of undiagnosed fractures, enhancing clinical outcomes and radiologic evaluation.

Coronoid fractures are rarely isolated and are much more frequently associated with other osseous or ligamentous structures injuries. On the basis of the coronoid fracture patterns, described by the O’Driscoll classification, it is possible to recognize three main patterns of injury that differ on traumatic mechanism and on associated lesions: posterolateral rotatory instability, posteromedial rotatory instability, and axial load injuries. The management of coronoid fractures is challenging and varies according to characteristics of the fracture, associated lesions, and amount of elbow instability. In general, operative treatment is indicated in every case the fracture is at least 50% of the whole coronoid, whether the sublime tubercle is involved, and whether the ulno-humeral joint is not perfectly reduced. In conclusion, the correct management of the coronoid, especially in the setting of complex elbow instability, represents a predictive factor for patient outcomes and functional results. The stability of the elbow, rather than the size of the coronoid fragment, is the main parameter for surgical indication, aimed to fix the coronoid and/or repair the associated lesions.

Background Trans-ulnar fracture–dislocations of the elbow are rare injuries with complex fracture patterns and variable outcomes. Traditional classification systems offer limited prognostic value. A recently introduced coronoid-centric Mayo classification distinguishes injury subtypes based on coronoid attachment and identifies trans-ulnar basal coronoid (TUBC) fractures as a particularly challenging entity. This study evaluated outcomes across Mayo fracture types and explored factors associated with inferior results in TUBC injuries. Materials and methods In this retrospective cohort study, surgically treated trans-ulnar elbow fracture–dislocations managed at a level I trauma center between 2010 and 2022 were identified and classified according to the Mayo system. Demographic data, injury characteristics, surgical management, radiographic outcomes, and complications were recorded. Functional outcomes were assessed after a minimum follow-up of 12 months using the Mayo Elbow Performance Score (MEPS); Oxford Elbow Score (OES); Quick Disabilities of Arm, Shoulder and Hand Questionnaire (QuickDASH); European Quality of Life Five-Dimension, Five-Level Version (EQ-5D-5L); and range-of-motion measurements. Radiographs were analyzed for union, instability, heterotopic ossification, and post-traumatic osteoarthritis (OA). Results A total of 52 patients were included (14 trans-olecranon, 28 TUBC, 10 Monteggia-variant). TUBC injuries were the most common subtype (53.8%). Post-traumatic OA was significantly more frequent in TUBC injuries than in fractures with coronoid attachment to a major fragment (88% versus 61%,  P  = 0.047). Higher-grade OA and persistent instability were associated with inferior functional outcomes. Although functional scores tended to be lower in TUBC injuries, differences compared with other subtypes were not consistently statistically significant. Within the TUBC group, poorer outcomes were observed when stable screw fixation of the basal coronoid fragment could not be achieved. Conclusions TUBC fracture–dislocations represent a high-risk subgroup of trans-ulnar elbow injuries. Stable fixation of the coronoid base appears critical for achieving favorable outcomes. The Mayo classification provides clinically relevant stratification and prognostic insight for these complex injuries. Level of evidence : Level IV.

BackgroundMonteggia, Galeazzi, and Essex-Lopresti injuries are the most common types of fracture–dislocation of the forearm. Uncommon variants and rare traumatic patterns of forearm fracture–dislocations have sometimes been reported in literature. In this study we systematically review the literature to identify and classify all cases of forearm joint injury pattern according to the forearm joint and three-locker concepts.MethodsA comprehensive search of the PubMed database was performed based on major pathological conditions involving fracture–dislocation of the forearm. Essex-Lopresti injury, Monteggia and Galeazzi fracture–dislocations, and proximal and/or distal radioulnar joint dislocations were sought. After article retrieval, the types of forearm lesion were classified using the following numerical algorithm: proximal forearm joint 1 [including proximal radioulnar joint (PRUJ) dislocation with or without radial head fractures], middle radioulnar joint 2, if concomitant radial fracture R, if concomitant interosseous membrane rupture I, if concomitant ulnar fracture U, and distal radioulnar joint 3 [including distal radioulnar joint (DRUJ) dislocation with or without distal radial fractures].ResultsEighty hundred eighty-four articles were identified through PubMed, and after bibliographic research, duplication removal, and study screening, 462 articles were selected. According to exclusion criteria, 44 full-text articles describing atypical forearm fracture–dislocation were included. Three historical reviews were added separately to the process. We detected rare patterns of two-locker injuries, sometimes referred to using improper terms of variant or equivalent types of Monteggia and Galeazzi injuries. Furthermore, we identified a group of three-locker injuries, other than Essex-Lopresti, associated with ulnar and/or radial shaft fracture causing longitudinal instability. In addition to fracture–dislocations commonly referred to using historical eponyms (Monteggia, Galeazzi, and Essex-Lopresti), our classification system, to the best of the authors’ knowledge, allowed us to include all types of dislocation and fracture–dislocation of the forearm joint reported in literature. According to this classification, and similarly to that of the elbow, we could distinguish between simple dislocations and complex dislocations (fracture–dislocations) of the forearm joint.ConclusionsAll injury patterns may be previously identified using an alphanumeric code. This might avoid confusion in forearm fracture–dislocations nomenclature and help surgeons with detection of lesions, guiding surgical treatment.Level of evidenceV.

Pediatric forearm fractures, particularly involving the ulna and radius, are among the most common childhood injuries. However, the lack of standardized and openly available datasets has limited progress in artificial intelligence research and constrained clinical validation. To address this issue, we present the Pediatric Ulna and Radius Fractures (PediURF) dataset, a first-of-its-kind, publicly available collection of over 10,000 de-identified images. Each image is carefully annotated by expert radiologists and categorized into three clinically relevant types: proximal, midshaft, and distal fractures. By releasing PediURF, we aim to provide an accessible resource for deep learning-based models development, benchmarking, and clinical training. To validate its utility, we proposed URFNet, a dual-view classification model designed to integrate anteroposterior and lateral perspectives. The proposed model achieved the best performance when compared with other classification models. Collectively, the proposed PediURF dataset provides a valuable foundation for future deep learning-based studies in pediatric fracture classification.

Fractures of the radius and ulna are the most common fractures of the upper extremity, with distal fractures occurring more often than proximal fractures. A fall onto an outstretched hand is the most common mechanism of injury for fractures of the radius and ulna. Evaluation with radiography or ultrasonography usually can confirm the diagnosis. If initial imaging findings are negative and suspicion of fracture remains, splinting and repeat radiography in seven to 14 days should be performed. Incomplete compression fractures without cortical disruption, called buckle (torus) fractures, are common in children. Greenstick fractures, which have cortical disruption, are also common in children. Depending on the degree of angulation, buckle and greenstick fractures can be managed with immobilization. In adults, distal radius fractures are the most common forearm fractures and are typically caused by a fall onto an outstretched hand. A nondisplaced, or minimally displaced, distal radius fracture is initially treated with a sugar-tong splint, followed by a short-arm cast for a minimum of three weeks. It should be noted that these fractures may be complicated by a median nerve injury. Isolated midshaft ulna (nightstick) fractures are often caused by a direct blow to the forearm. These fractures are treated with immobilization or surgery, depending on the degree of displacement and angulation. Combined fractures involving both the ulna and radius generally require surgical correction. Radial head fractures may be difficult to visualize on initial imaging but should be suspected when there are limitations of elbow extension and supination following trauma. Treatment of radial head fractures depends on the specific characteristics of the fracture using the Mason classification.

Background Acute Essex-Lopresti injury is a rare and disabling condition of longitudinal instability of the forearm. When early diagnosed, patients report better outcomes with higher functional recovery. Aim of this study is to focus on the different lesion patterns causing forearm instability, reviewing literature and the cases treated by the Authors and to propose a new terminology for their identification. Methods Five patients affected by acute Essex-Lopresti injury have been enrolled for this study. ELI was caused in two patients by bike fall, two cases by road traffic accident and one patient by fall while walking. A literature search was performed using Ovid Medline, Ovid Embase, Scopus and Cochrane Library and the Medical Subject Headings vocabulary. The search was limited to English language literature. 42 articles were evaluated, and finally four papers were considered for the review. Results All patients were operated in acute setting with radial head replacement and different combinations of interosseous membrane reconstruction and distal radio-ulnar joint stabilization. Patients were followed for a mean of 15 months: a consistent improvement of clinical results were observed, reporting a mean MEPS of 92 and a mean MMWS of 90.8. One case complained persistent wrist pain associated to DRUJ discrepancy of 3 mm and underwent ulnar shortening osteotomy nine months after surgery, with good results. Discussion The clinical studies present in literature reported similar results, highlighting as patients properly diagnosed and treated in acute setting report better results than patients operated after four weeks. In this study, the definitions of “Acute Engaged” and “Undetected at Imminent Evolution” Essex-Lopresti injury are proposed, in order to underline the necessity to carefully investigate the anatomical and radiological features in order to perform an early and proper surgical treatment. Conclusions Following the observations, the definitions of “Acute Engaged” and “Undetected at Imminent Evolution” injuries are proposed to distinguish between evident cases and more insidious settings, with necessity of carefully investigate the anatomical and radiological features in order to address patients to an early and proper surgical treatment.

Blows with axes, machetes or blunt objects such as baseball bats, truncheons, etc. are often parried, resulting in typical parry injuries, or so-called nightstick fractures to the ulna. In this study, we sought to assess the impact energy required to break the ulna in such parry incidents in an experimental setting using semisynthetic and fully synthetic models. Twenty-seven sheep radii and 33 polyurethane synthetic bones were cast into gelatin prior to being fired at with missiles made of a section of an axe blade or steel rod at different firing velocities using a compressed-nitrogen cannon. Each model was then examined as to the presence of hair-line fractures or complete fractures. Sheep bones and synthetic bones displayed comparable results when struck by the axe missile; here, a clear fracture threshold was evident between 14.00 and 15.26 J. When struck by the rod missile, only the synthetic bones produced significant results, namely a fracture threshold between 20.15 and 23.59 J. In conclusion, our results show an ulnar fracture threshold of approximately 15 J when struck by an axe. The experiments regarding blows with a rod displayed a fracture threshold of around 22 J, but, as this could not be validated with biological bones, this result is questionable.

Purpose We described a morphological classification and grading system for volar Barton fractures. Methods We divided these fractures into four types: typical Barton, ulna Barton, radial Barton, comminuted Barton. Moreover, we graded the fractures into two degrees: simple split and split-depression. We retrospectively reviewed all wrist radiographs showing Barton fractures in our hospital between January 2013 and January 2015. We identified 100 cases whose records and radiographs were reviewed and included 36 men and 64 women with a mean age of 50 years (15–78). The morphological classification was applied to the 100 cases by three reviewers on two occasions using the Kappa statistic. Results The inter- and intra-observer reliability of the morphological classification was 0.71–0.80 and 0.68–0.88, respectively. The distribution of typical, ulna, radial and comminuted Barton type fractures was 69 %, 7 %, 5 % and 19 %, respectively. Grade 2 fractures accounted for 49 % in our series. Conclusions This classification and grading system of Barton fractures is likely to have implications in terms of pathophysiology and surgical technique.