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

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. Methods. The CNN was trained and tested on radiographs sourced from 11 hospitals in Australia and externally validated on radiographs from the Netherlands. Each radiograph was paired with corresponding CT scans to serve as the reference standard based on dual independent evaluation by trained researchers and attending orthopaedic surgeons. Presence of a fracture, classification (non- to minimally displaced; two-part, multipart, and glenohumeral dislocation), and four characteristics were determined on 2D and 3D CT scans and subsequently allocated to each series of radiographs. Fracture characteristics included greater tuberosity displacement ≥ 1 cm, NSA ≤ 100°, shaft translation (0% to < 75%, 75% to 95%, > 95%), and the extent of articular involvement (0% to < 15%, 15% to 35%, or > 35%). Results. For detection and classification, the algorithm was trained on 1,709 radiographs (n = 803), tested on 567 radiographs (n = 244), and subsequently externally validated on 535 radiographs (n = 227). For characterization, healthy shoulders and glenohumeral dislocation were excluded. The overall accuracy for fracture detection was 94% (area under the receiver operating characteristic curve (AUC) = 0.98) and for classification 78% (AUC 0.68 to 0.93). Accuracy to detect greater tuberosity fracture displacement ≥ 1 cm was 35.0% (AUC 0.57). The CNN did not recognize NSAs ≤ 100° (AUC 0.42), nor fractures with ≥ 75% shaft translation (AUC 0.51 to 0.53), or with ≥ 15% articular involvement (AUC 0.48 to 0.49). For all objectives, the model’s performance on the external dataset showed similar accuracy levels. Conclusion. CNNs proficiently rule out proximal humerus fractures on plain radiographs. Despite rigorous training methodology based on CT imaging with multi-rater consensus to serve as the reference standard, artificial intelligence-driven classification is insufficient for clinical implementation. The CNN exhibited poor diagnostic ability to detect greater tuberosity displacement ≥ 1 cm and failed to identify NSAs ≤ 100°, shaft translations, or articular fractures. Cite this article: Bone Joint J 2024;106-B(11):1348–1360

Introduction

In cementless THA the incidence of intraoperative fracture has been reported to be as high 28% [1]. To mitigate these surgical complications, investigators have explored vibro-acoustic techniques for identifying fracture [2–5]. These methods, however, must be simple, efficient, and robust as well as integrate with workflow and sterility. Early work suggests an energy-based method using inexpensive sensors can detect fracture and appears robust to variability in striking conditions [4–5]. The orthopaedic community is also considering powered impaction as another way to minimize the risk of fracture [6– 8], yet the authors are unaware of attempts to provide sensor feedback perhaps due to challenges from the noise and vibrations generated during powered impaction. Therefore, this study tests the hypothesis that vibration frequency analysis from an accelerometer mounted on a powered impactor coupled to a seated femoral broach can be used to distinguish between intact and fractured bone states.

Aims. The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?. Methods. The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS). Results. Out of 1,349 studies, 36 reported development of a CNN for fracture detection and/or classification. Of these, only four (11%) reported a form of EV. One study used temporal EV, one conducted both temporal and geographical EV, and two used geographical EV. When comparing the CNN’s performance on the IV set versus the EV set, the following were found: AUCs of 0.967 (IV) versus 0.975 (EV), 0.976 (IV) versus 0.985 to 0.992 (EV), 0.93 to 0.96 (IV) versus 0.80 to 0.89 (EV), and F1-scores of 0.856 to 0.863 (IV) versus 0.757 to 0.840 (EV). Conclusion. The number of externally validated CNNs in orthopaedic trauma for fracture recognition is still scarce. This greatly limits the potential for transfer of these CNNs from the developing institute to another hospital to achieve similar diagnostic performance. We recommend the use of geographical EV and statements such as the Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI), the Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence (SPIRIT-AI) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis–Machine Learning (TRIPOD-ML) to critically appraise performance of CNNs and improve methodological rigor, quality of future models, and facilitate eventual implementation in clinical practice. Cite this article: Bone Jt Open 2021;2(10):879–885

Aims. The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. Methods. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared. Results. At the time of the study, the CNN model showed an area under the receiver operating curve of 0.97. AI assistance improved the physician’s sensitivity (correct fracture detection) from 80% to 87%, and the specificity (correct fracture exclusion) from 91% to 95%. The overall error rate (combined false positive and false negative) was reduced from 14% without AI to 9% with AI. Conclusion. The use of a CNN model as a second opinion can improve the diagnostic accuracy of DRF detection in the study setting. Cite this article: Bone Joint Res 2024;13(10):588–595

Aims. To investigate if preoperative CT improves detection of unstable trochanteric hip fractures. Methods. A single-centre prospective study was conducted. Patients aged 65 years or older with trochanteric hip fractures admitted to Stavanger University Hospital (Stavanger, Norway) were consecutively included from September 2020 to January 2022. Radiographs and CT images of the fractures were obtained, and surgeons made individual assessments of the fractures based on these. The assessment was conducted according to a systematic protocol including three classification systems (AO/Orthopaedic Trauma Association (OTA), Evans Jensen (EVJ), and Nakano) and questions addressing specific fracture patterns. An expert group provided a gold-standard assessment based on the CT images. Sensitivities and specificities of surgeons’ assessments were estimated and compared in regression models with correlations for the same patients. Intra- and inter-rater reliability were presented as Cohen’s kappa and Gwet’s agreement coefficient (AC1). Results. We included 120 fractures in 119 patients. Compared to radiographs, CT increased the sensitivity of detecting unstable trochanteric fractures from 63% to 70% (p = 0.028) and from 70% to 76% (p = 0.004) using AO/OTA and EVJ, respectively. Compared to radiographs alone, CT increased the sensitivity of detecting a large posterolateral trochanter major fragment or a comminuted trochanter major fragment from 63% to 76% (p = 0.002) and from 38% to 55% (p < 0.001), respectively. CT improved intra-rater reliability for stability assessment using EVJ (AC1 0.68 to 0.78; p = 0.049) and for detecting a large posterolateral trochanter major fragment (AC1 0.42 to 0.57; p = 0.031). Conclusion. A preoperative CT of trochanteric fractures increased detection of unstable fractures using the AO/OTA and EVJ classification systems. Compared to radiographs, CT improved intra-rater reliability when assessing fracture stability and detecting large posterolateral trochanter major fragments. Cite this article: Bone Jt Open 2024;5(6):524–531

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as ‘big data’, AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI’s limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction.

Cite this article: Bone Joint Res 2023;12(7):447–454.

Introduction. Each year, a large number of total hip arthroplasties (THA) are performed, of which 60 % use cementless fixation. The initial fixation is one of the most important factors for a long lasting fixation [Gheduzzi 2007]. The point of optimal initial fixation, the endpoint of insertion, is not easy to achieve, as the margin between optimal fixation and a femoral fracture is small. Femoral fractures are caused by peak stresses induced during broaching or by the hammer blows when the implant is excessively press-fitted in the femur. In order to reduce the peak stresses during broaching, IMT Integral Medizintechnik (Luzern, Switzerland) designed the Woodpecker, a pneumatic broach that generates impulses at a frequency of 70 Hz. This study explores the feasibility of using the Woodpecker for implant insertion by measuring both the strain in the cortical bone and the vibrational response. An in vitro study is presented. Material and Methods. A Profemur Gladiator modular stem (MicroPort Orthopedics Inc. Arlington, TN, USA) and two artificial femora (composite bone 4th generation #3403, Sawbones Europe AB, Malmö, Sweden) were used. One artificial femur was instrumented with three rectangular strain gauge rosettes (Micro-Measurements, Raleigh, NC, USA). The rosettes were placed medially, posteriorly and anteriorly proximally on the cortical bone. Five paired implant insertions were repeated on both artificial bones, alternating between standard hammering and Woodpecker insertions. During the insertion processes the vibrational response was measured at the implant and Woodpecker side (fig. 1) using two shock accelerometers (PCB Piezotronics, Depew, NY, USA). Frequency spectra were derived from the vibrational responses. The endpoint of insertion was defined as the point when the static strain stopped increasing during the insertion. Results. Peak stress values calculated out of the strain measurement during the insertion showed to be significantly (p < 0.05) lower at two locations using the Woodpecker compared to the hammer blows at the same level of static strain. However, the final static strain at the endpoint of insertion was approximately a factor two lower using the Woodpecker compared to the hammer. During the last hammer insertion a fracture occurred, which was clearly visible in the frequency spectra. Figure 2 shows the sudden change between the spectra of the hit prior and after the fracture. Discussion/Conclusion. Peak stresses showed to be lower using the Woodpecker compared to hammer insertion, which is a promising result concerning fracture prevention. However it needs to be taken into account that it was not possible to reach the same level of static strain using the Woodpecker as with the hammer insertion. It is expected that the Woodpecker in its actual design is not able to reach a similar level of press-fit as hammer blows. Using vibrational data showed to be promising for fracture detection, as fractures are not always visible due to the soft tissue. For figures, please contact authors directly

Introduction. Cementless femoral hip stems crucially depend on the initial stability to ensure a long survival of the prosthesis. There is only a small margin between obtaining the optimal press fit and a femoral fracture. The incidence of an intraoperative fracture is reported to be as high as 30% for revision surgery. The aim of this study is to assess what information is contained in the acoustic sound produced by the insertion hammer blows and explore whether this information can be used to assess optimal seating and warn for impeding fractures. Materials and Methods. Acoustic measurements of the stem insertion hammer blows were taken intra-operatively during 7 cementless primary (Wright Profemur Primary) and 2 cementless revision surgeries (Wright Profemur R Revision). All surgeries were carried out by the same experienced surgeon. The sound was recorded using 6 microphones (PCB 130E2), mounted at a distance of approximately 1 meter from the surgical theater. The 7 primary implants were inserted without complication, 1 revision stem induced a fracture distally during the insertion process. Two surgeons were asked to listen independently to the acoustic sounds post-surgery and to label the hits in the signal they would associate with either a fully fixated implant or with a fracture sound. For 3 out of 7 primary measurements the data was labeled the same by the two surgeons, 4 were labeled differently or undecided and both indicated several hits that would be associated with fracture for the fractured revision case. The acquired time signals were processed using a number of time and frequency domain processing techniques. Results. Figure 1 shows the convergence of a set of time and frequency features (selected temporal moments, decay and 99% energy time [1]) during a primary cementless insertion for which both surgeons labeled hit 12 as the final insertion hit. However, such convergence of the feature set was not as clear for the other 6 cases. Figure 2 shows the result of a feature that tracks the relative weight of low frequency content in the signal relative to the peak power present in the total frequency range for the two revision surgeries. This feature shows several spikes above 0.4 during the case with fractures, whereas none are present for the non-fractured revision case. The spikes concurred with the hits indicated by the surgeon panel post-surgery to have a sound associated with fractures. Conclusions. Assessment of this initial stability is a challenging task for the surgeon, who mainly has to rely on auditory and sensatory feedback. Although these findings look promising for an early detection and warning for (micro-) fractures, endpoint detection based on acoustic information is more challenging. The difficulty to determine the endpoint based solely on acoustic information was also reflected by the challenge of the surgeon panel to label the acoustic signals post-surgery. Data gathering is currently in progress to extend both the primary and revision set to 15 intra-operative measurements for further validation of these preliminary results

Introduction:. Cone Based CT (CBCT) scanning uses a point source and a planar detector with parallel data acquisition and volumetric coverage of the area of interest. The pedCAT (Curvebeam USA) scanner is marketed as a low radiation dose, compact, faster and inexpensive CT scanner that can be used to obtain both non- weightbearing and true 3 dimensional weightbearing views. Method:. A review of the first 100 CBCT scanning in our unit has been performed to assess ease of scanning, imaging time, radiation dose and value of imaging as opposed to conventional imaging. Results:. A pedcat CT scan was available within minutes of the request, similar to plain radiographs but much earlier than a 6 week delay for a patient to attend a new appointment for a conventional CT. All patients returned to see the clinician for a clinical decision in the same NHS clinic and did not require a new clinic visit; illustrative cases include fracture/subluxation detection, surgical planning, extent of arthritis and 3D assessment of union of arthrodeses. All patients were able to transfer to the scanner with ease and the imaging time was 10 times than a conventional CT. The radiation dose to the patients was 9% that of a full gantry system. Weightbearing CT scanning enabled a 3D evaluation of reduction of joint space and ankle/hindfoot alignment. Anterior ankle and sesamoid impingement have been diagnosed in patients with previously obscure pain. Conclusion:. 3D Cone Beam imaging has been found to be easily accessible, rapidly performed and safer to the patient in providing a lower radiation dose. Weightbearing 3D imaging provides additional diagnostic information

Aims

To evaluate whether an ultra-low-dose CT protocol can diagnose selected limb fractures as well as conventional CT (C-CT).

The incidence and long-term outcome of undisplaced fatigue fractures of the femoral neck treated conservatively were examined in Finnish military conscripts between 1970 and 1990.

From 106 cases identified, 66 patients with 70 fractures were followed for a mean of 18.3 years (11 to 32). The original medical records and radiographs were studied and physical and radiological follow-up data analysed for evidence of risk factors for this injury. The development of avascular necrosis and osteoarthritis was determined from the follow-up radiographs and MR scans.

The impact of new military instructions on the management of hip-related pain was assessed following their introduction in 1986. The preventive regimen (1986) improved awareness and increased the detected incidence from 13.2 per 100 000 service-years (1970 to 1986) to 53.2 per 100 000 (1987 to 1990). No patient developed displacement of the fracture or avascular necrosis of the femoral head, or suffered from adverse complications. No differences were found in MRI-measured hip joint spaces at final follow-up. The mean Harris Hip Score was 97 (70 to 100) and the Visual Analogue Scale 5.85 mm (0 to 44).

Non-operative treatment, including avoidance of or reduced weight-bearing, gave favourable short- and long-term outcomes. Undisplaced fatigue fractures of the femoral neck neither predispose to avascular necrosis nor the subsequent development of osteoarthritis of the hip.