Introduction. With advances in artificial intelligence, the use of computer-aided detection and diagnosis in clinical imaging is gaining traction. Typically, very large datasets are required to train machine-learning models, potentially limiting use of this technology when only small datasets are available. This study investigated whether pretraining of fracture detection models on large, existing datasets could improve the performance of the model when locating and classifying wrist fractures in a small X-ray image dataset. This concept is termed “transfer learning”. Method. Firstly, three detection models, namely, the faster region-based convolutional neural network (faster R-CNN), you only look once version eight (YOLOv8), and RetinaNet, were pretrained using the large, freely available dataset, common objects in context (COCO) (330000 images). Secondly, these models were pretrained using an open-source wrist X-ray dataset called “Graz Paediatric Wrist Digital X-rays” (GRAZPEDWRI-DX) on a (1) fracture detection dataset (20327 images) and (2) fracture location and classification dataset (14390 images). An orthopaedic surgeon classified the small available dataset of 776 distal radius X-rays (Arbeidsgmeischaft für Osteosynthesefragen Foundation / Orthopaedic Trauma Association; AO/OTA), on which the models were tested. Result. Detection models without pre-training on the large datasets were the least precise when tested on the small distal radius dataset. The model with the best accuracy to detect and classify wrist fractures was the YOLOv8 model pretrained on the GRAZPEDWRI-DX fracture detection dataset (mean average precision at intersection over union of 50=59.7%). This model showed up to 33.6% improved detection precision compared to the same models with no pre-training. Conclusion. Optimisation of machine-learning models can be challenging when only relatively small datasets are available. The findings of this study support the potential of transfer learning from large datasets to improve model performance in smaller datasets. This is encouraging for wider application of machine-learning technology in medical imaging evaluation, including less common orthopaedic pathologies

Introduction. Patients (2.7M in EU) with positive cancer prognosis frequently develop metastases (≈1M) in their remaining lifetime. In 30-70% cases, metastases affect the spine, reducing the strength of the affected vertebrae. Fractures occur in ≈30% patients. Clinicians must choose between leaving the patient exposed to a high fracture risk (with dramatic consequences) and operating to stabilise the spine (exposing patients to unnecessary surgeries). Currently, surgeons rely on their sole experience. This often results in to under- or over-treatment. The standard-of-care are scoring systems (e.g. Spine Instability Neoplastic Score) based on medical images, with little consideration of the spine biomechanics, and of the structure of the vertebrae involved. Such scoring systems fail to provide clear indications in ≈60% patients. Method. The HEU-funded METASTRA project is implemented by biomechanicians, modellers, clinicians, experts in verification, validation, uncertainty quantification and certification from 15 partners across Europe. METASTRA aims to improve the stratification of patients with vertebral metastases evaluating their risk of fracture by developing dedicated reliable computational models based on Explainable Artificial Intelligence (AI) and on personalised Physiology-based biomechanical (VPH) models. Result. The METASTRA-AI model is expected to be able to stratify most patients with limited effort end cost, based on parameters extracted semi-automatically from the medical files and images. The cases which are not reliably stratified through the AI model, are examined through a more detailed and personalised biomechanical VPH model. These METASTRA numerical tools are trained through an unprecedentedly large multicentric retrospective study (2000 cases) and validated against biomechanical ex vivo experiments (120 specimens). Conclusion. The METASTRA decision support system is tested in a multicentric prospective observational study (200 patients). The METASTRA approach is expected to cut down the indeterminate diagnoses from the current 60% down to 20% of cases. METASTRA project funded by the European Union, HEU topic HLTH-2022-12-01, grant 101080135

Aims. This Delphi study assessed the challenges of diagnosing soft-tissue knee injuries (STKIs) in acute settings among orthopaedic healthcare stakeholders. Methods. This modified e-Delphi study consisted of three rounds and involved 32 orthopaedic healthcare stakeholders, including physiotherapists, emergency nurse practitioners, sports medicine physicians, radiologists, orthopaedic registrars, and orthopaedic consultants. The perceived importance of diagnostic components relevant to STKIs included patient and external risk factors, clinical signs and symptoms, special clinical tests, and diagnostic imaging methods. Each round required scoring and ranking various items on a ten-point Likert scale. The items were refined as each round progressed. The study produced rankings of perceived importance across the various diagnostic components. Results. In Round 1, the study revealed widespread variability in stakeholder opinions on diagnostic components of STKIs. Round 2 identified patterns in the perceived importance of specific items within each diagnostic component. Round 3 produced rankings of perceived item importance within each diagnostic component. Noteworthy findings include the challenges associated with accurate and readily available diagnostic methods in acute care settings, the consistent acknowledgment of the importance of adopting a patient-centred approach to diagnosis, and the transition from divergent to convergent opinions between Rounds 2 and 3. Conclusion. This study highlights the potential for a paradigm shift in acute STKI diagnosis, where variability in the understanding of STKI diagnostic components may be addressed by establishing a uniform, evidence-based framework for evaluating these injuries. Cite this article: Bone Jt Open 2024;5(11):984–991

Aims

Developmental cervical spinal stenosis (DcSS) is a well-known predisposing factor for degenerative cervical myelopathy (DCM) but there is a lack of consensus on its definition. This study aims to define DcSS based on MRI, and its multilevel characteristics, to assess the prevalence of DcSS in the general population, and to evaluate the presence of DcSS in the prediction of developing DCM.

Aims

The purpose of this study was to develop a convolutional neural network (CNN) for fracture detection, classification, and identification of greater tuberosity displacement ≥ 1 cm, neck-shaft angle (NSA) ≤ 100°, shaft translation, and articular fracture involvement, on plain radiographs.

Aims

Surgical limb sparing for knee-bearing paediatric bone sarcoma is considered to have a clinically significant influence on postoperative function due to complications and leg-length discrepancies. However, researchers have not fully evaluated the long-term postoperative functional outcomes. Therefore, in this study, we aimed to elucidate the risk factors and long-term functional prognosis associated with paediatric limb-sparing surgery.

Aims

Paediatric triplane fractures and adult trimalleolar ankle fractures both arise from a supination external rotation injury. By relating the experience of adult to paediatric fractures, clarification has been sought on the sequence of injury, ligament involvement, and fracture pattern of triplane fractures. This study explores the similarities between triplane and trimalleolar fractures for each stage of the Lauge-Hansen classification, with the aim of aiding reduction and fixation techniques.

Aims

Complete ruptures of the ulnar collateral ligament (UCL) of the thumb are a common injury, yet little is known about their current management in the UK. The objective of this study was to assess the way complete UCL ruptures are managed in the UK.

Aims

In this study, we aimed to visualize the spatial distribution characteristics of femoral head necrosis using a novel measurement method.

Introduction. Tibial Pilon fractures are potentially limb threatening, yet standards of care are lacking from BOFAS and the BOA. The mantra of “span, scan, plan” describes staged management with external fixation to allow soft tissue resuscitation, followed by a planning CT-scan. Our aim was to evaluate how Tibial Pilon fractures are acutely managed. Methods. ENFORCE was a multi-centre retrospective observational study of the acute management of partial and complete articular Tibial Pilon fractures over a three-year period. Mechanism, imaging, fracture classification, time to fracture reduction and cast, and soft tissue damage control details were determined. Results. 656 patients (670 fractures) across 27 centres were reported. AO fracture classifications were: partial articular (n=294) and complete articular (n=376). Initial diagnostic imaging mobilities were: plain radiographs (n=602) and CT-scan (n=54), with all but 38 cases having a planning CT-scan. 526 fractures had a cast applied in the Emergency Department (91 before radiological diagnosis), with the times taken to obtain post cast imaging being: mean 2.7 hours, median 2.3 hours, range 28 mins – 14 hours). 35% (102/294) of partial articular and 57% (216/376) of complete articular (length unstable) fractures had an external fixator applied, all of which underwent a planning CT-scan. Definitive management consisted of: open reduction internal fixation (n=495), fine wire frame (n=86), spanning external fixator (n=25), intramedullary nail (n=25), other (n=18). Conclusion. The management of Tibial Pilon fractures is variable, with prolonged delays in obtaining post cast reduction radiographs, and just over half of length unstable complete articular fractures being managed with the gold standard “span, scan, plan” staged soft tissue resuscitation. A BOFAS endorsed BOAST (British Orthopaedic Association Standard for Trauma) for Tibial Pilon fractures is suggested for standardisation of the acute management of these potentially limb threatening injuries, together with setting them apart from more straightforward ankle fractures

Aims

Ilium is the most common site of pelvic Ewing’s sarcoma (ES). Resection of the ilium and iliosacral joint causes pelvic disruption. However, the outcomes of resection and reconstruction are not well described. In this study, we report patients’ outcomes after resection of the ilium and iliosacral ES and reconstruction with a tibial strut allograft.

In 2017, the British Society for Children’s Orthopaedic Surgery engaged the profession and all relevant stakeholders in two formal research prioritization processes. In this editorial, we describe the impact of this prioritization on funding, and how research in children’s orthopaedics, which was until very recently a largely unfunded and under-investigated area, is now flourishing. Establishing research priorities was a crucial step in this process.

Cite this article: Bone Joint J 2024;106-B(5):422–424.

The April 2024 Foot & Ankle Roundup³⁶⁰ looks at: Safety of arthroscopy combined with radial extracorporeal shockwave therapy for osteochondritis of the talus; Bipolar allograft transplantation of the ankle; Identifying risk factors for osteonecrosis after talar fracture; Balancing act: immediate versus delayed weightbearing in ankle fracture recovery; Levelling the field: proximal supination osteotomy’s efficacy in severe and super-severe hallux valgus; Restoring balance: how adjusting the tibiotalar joint line influences movement after ankle surgery.

Aims

Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool.

Aims

Low-grade central osteosarcoma (LGCOS), a rare type of osteosarcoma, often has misleading radiological and pathological features that overlap with those of other bone tumours, thereby complicating diagnosis and treatment. We aimed to analyze the clinical, radiological, and pathological features of patients with LGCOS, with a focus on diagnosis, treatment, and outcomes.

The December 2023 Research Roundup³⁶⁰ looks at: Tissue integration and chondroprotective potential of acetabular labral augmentation with autograft tendon: study of a porcine model; The Irish National Orthopaedic Register under cyberattack: what happened, and what were the consequences?; An overview of machine learning in orthopaedic surgery: an educational paper; Beware of the fungus…; New evidence for COVID-19 in patients undergoing joint replacement surgery.

Aims

We aimed to assess the cumulative risk of total hip arthroplasty (THA) from in situ fixation for slipped capital femoral epiphysis (SCFE) after a follow-up of almost 50 years.

The October 2023 Children’s orthopaedics Roundup³⁶⁰ looks at: Outcomes of open reduction in children with developmental hip dislocation: a multicentre experience over a decade; A torn discoid lateral meniscus impacts lower-limb alignment regardless of age; Who benefits from allowing the physis to grow in slipped capital femoral epiphysis?; Consensus guidelines on the management of musculoskeletal infection affecting children in the UK; Diagnosis of developmental dysplasia of the hip by ultrasound imaging using deep learning; Outcomes at a mean of 13 years after proximal humeral fracture during adolescence; Clubfeet treated according to Ponseti at four years; Controlled ankle movement boot provides improved outcomes with lower complications than short leg walking cast.

Cite this article: Bone Joint Res 2023;12(8):494–496.

Femoro-acetabular impingement involves a deformity of the hip joint and is associated with hip osteoarthritis. Although 15% of the asymptomatic population exhibits a deformity, it is not clear who will develop symptoms. Current diagnostic imaging measures have either low specificity or low sensitivity and do not consider the dynamic nature of impingement during daily activities. The goal of this study is to determine stresses in the cartilage, subchondral bone and labrum of normal and impinging hips during activities such as walking and sitting down. Quantitative CT scans were obtained of a healthy Control and a participant with a symptomatic femoral cam deformity (‘Bump’). 3D models of the hip were created from automatic segmentation of CT scans. Cartilage layers were added so the articular surface was the mid-line of the joint. Finite element meshes were generated in each region. Bone elastic modulus was assigned element-by-element, calculated from CT intensity converted to bone mineral density using a calibration phantom. Cartilage was modelled as poroelastic, E=0.467 MPa, v=0.167, and permeability 3×10. -16. m. 4. /N s. The pelvis was fixed while rotations and contact forces from Bergmann et al. (2001) were applied to the femur over one load cycle for walking and sitting in a chair. All analyses were performed in FEBio. High shear stresses were seen near the acetabular cartilage-labrum junction in the Bump model, up to 0.12 MPa for walking and were much higher than in the Control. Patient-specific modelling can be used to assess contact and tissue stresses during different activities to better understand the risk of degeneration in individuals, especially for activities that involve high hip flexion. The high stresses at the cartilage labrum interface could explain so-called bucket-handle tears of the labrum