Abstract. Background. Post operative radiographs following total joint arthroplasty are requested as part of routine follow up in many institutions. These studies have a significant cost to the local departments, in terms of financial and clinic resources, however, previous research has suggested they may not alter the course of the patients treatment. The purpose of this study was to assess the significance of elective post operative radiographs on changes in management of patients who underwent total joint arthroplasty. Method. All patients who underwent total knee arthroplasty and total hip arthroplasty at a District General Hospital from 2019 to 2020 were included. Data was collected retrospectively from medical records and radiograph requests. Alterations to clinical management based on radiographic findings were reviewed in clinic letters. Results. A total of 227 Total joint arthroplasty were retrieved. With 111(49%) total hip arthroplasty and 116 (51%) total knee arthroplasty. 54 were excluded due to having no clinical follow up and 173 met inclusion criteria. 56 (32%) had their post operative elective radiograph, while 93 (53.8%) patients had none. There were no abnormalities detected from the elective radiographs and none of the patients returned to the theatre. 24 patients (13%) presented with symptoms and had non-elective radiographs, 16 (67%) did not have any interventions and 8 (4.6%) required intervention and were taken to theatre. Discussion: Not performing these radiographs saves time, cost, and prevents unnecessary radiation exposure. In our institution, a 2-view joint radiograph costs £29 and takes roughly 15 minutes. This does not include indirect costs of additional clinic time and patient waiting time. In the larger context, the cost associated with elective radiographs is significant and our data suggests that routine post-operative radiographs are not beneficial as part of standard post-operative protocol for asymptomatic patients. However, performing imaging remains beneficial for patients who re-present with symptoms. Conclusion. Routine elective post-operative joint radiographs did not detect any true abnormalities. Information from elective radiographs has no clinical significance and did not change management. Therefore, this study recommends that there is no rationale requesting elective post-operative joint radiographs. Declaration of Interest. (b) declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research reported:I declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research project

Malalignment is often postulated as the main reason for the high failure rate of total ankle replacements (TARs). Only a few studies have been performed to correlate radiographic TAR malalignment to the clinical outcome, but no consistent trends between TAR alignment parameters and the clinical outcome were found. No standard TAR alignment measurement method is present, so reliable comparison between studies is difficult. Standardizing TAR alignment measurements and increasing measurable parameters on radiographs in the clinic might lead to a better insight into the correlation between malalignment and the clinical outcome. This study aims to develop and validate a tool to semi-automatic measure TAR alignment, and to improve alignment measurement on radiographs in the clinic. A tool to semi-automatically measure TAR alignment on anteroposterior and lateral radiographs was developed and used by two observers to measure TAR alignment parameters of ten patients. The Intraclass Coefficient (ICC) was calculated and accuracy was compared to the manual measurement method commonly used in the clinic. The tool showed an accuracy of 76% compared to 71% for the method used during follow-up in the clinic. ICC values were 0.94 (p<0.01) and higher for both inter-and intra-observer reliability. The tool presents an accurate, consistent, and reliable method to measure TAR alignment parameters. Three-dimensional alignment parameters are obtained from two-dimensional radiographs, and as the tool can be applied to any TAR design, it offers a valuable addition in the clinic and for research purposes

Knee joint distraction (KJD) has been associated with clinical and structural improvement and synovial fluid (SF) marker changes. However, structural changes have not yet been shown satisfactorily in regular care, since radiographic acquisition was not fully standardized. AI-based modules have shown great potential to reduce reading time, increase inter-reader agreement and therefore function as a tool for treatment outcome assessment. The objective was to analyse structural changes after KJD in patients using this AI-based measurement method, and relate these changes to clinical outcome and SF markers. 20 knee OA patients (<65 years old) were included in this study. KJD treatment was performed using an external fixation device, providing 5 mm distraction for 6 weeks. SF was aspirated before, during and immediately after treatment. Weight-bearing antero-posterior knee radiographs and WOMAC questionnaires were collected before and ~one year after treatment. Radiographs were analysed with the Knee Osteoarthritis Labelling Assistant (KOALA, IB Lab GmbH, Vienna, Austria), and 10 pre-defined biomarker levels in SF were measured by immunoassay. Radiographic one-year changes were analysed and linear regression was used to calculate associations between changes in standardized joint space width (JSW) and WOMAC, and changes in JSW and SF markers. After treatment, radiographs showed an improvement in Kellgren-Lawrence grade in 7 of 16 patients that could be evaluated; 3 showed a worsening. Joint space narrowing scores and continuous JSW measures improved especially medially. A greater improvement in JSW was significantly associated with a greater improvement in WOMAC pain (β=0.64;p=0.020). A greater increase in MCP1 (β=0.67;p=0.033) and lower increase in TGFβ1 (β=-0.787;p=0.007) were associated with JSW improvement. Despite the small number of patients, also in regular care KJD treatment shows joint repair as measured automatically on radiographs, significantly associated with certain SF marker change and even with clinical outcome

Introduction. Knee arthroplasty (KA), encompassing Total Knee Replacement (TKR) and Unicompartmental Knee Replacement (UKR), is one of the most common orthopedic procedures, aimed at alleviating severe knee arthritis. Postoperative KA management, especially radiographic imaging, remains a substantial financial burden and lacks standardised protocols for its clinical utility during follow-up. Method. In this retrospective multicentre cohort study, data were analysed from January 2014 to March 2020 for adult patients undergoing primary KA at Imperial NHS Trust. Patients were followed over a five-year period. Four machine learning models were developed to evaluate if post-operative X-ray frequency can predict revision surgery. The best-performing model was used to assess the risk of revision surgery associated with different number of X-rays. Result. The study assessed 289 knees with a 2.4% revision rate. The revision group had more X-rays on average than the primary group. The best performing model was Logistic Regression (LR), which indicated that each additional X-ray raised the revision risk by 52% (p<0.001). Notably, having four or more X-rays was linked to a three-fold increase in risk of revision (OR=3.02; p<0.001). Our results align with the literature that immediate post-operative X-rays have limited utility, making the 2nd post-operative X-ray of highest importance in understanding the patient's trajectory. These insights can enhance management by improving risk stratification for patients at higher revision surgery risk. Despite LR being the best-performing model, it is limited by the dataset's significant class imbalance. Conclusion. X-ray frequency can independently predict revision surgery. This study provides insights that can guide surgeons in evidence-based post-operative decision-making. To use those findings and influence post-operative management, future studies should build on this predictive model by incorporating a more robust dataset, surgical indications, and X-ray findings. This will allow early identification of high-risk patients, allowing for personalised post-operative recommendations

Introduction. Routine radiographs in the follow-up of circular frames is commonplace, however the effect on clinical decision making is unclear. Previous work locally has suggested that >95% of radiographs, particularly at early time points, do not affect clinical management. This study was conducted to assess the impact of a transition to early remote follow-up on circular frame patients with limited radiographic assessment. Materials and Methods. Patients were identified from a prospective limb reconstruction database. Data were collected including the number of clinic appointments, type of clinic appointment, number of radiographs performed, and impact this had on clinical management. This was compared to our previous cohort of 85 patients undergoing standard follow-up. Results. Fourteen patients were eligible for inclusion (mean age 45, range 26–75). Circular frames were indicated for trauma (12), or limb reconstruction (2). Following introduction of remote follow-up, the mean number of face-to-face appointments reduced from 6.1 to 1.7 to the point of frame removal. Conversion from telephone follow-up to face-to-face follow-up was required in just one case where hardware failure occurred. The number of radiographs during treatment was reduced from a mean of 22 to 11 (range 4–20). Conclusions. Remote follow-up of circular frame patients was associated with significantly fewer radiographs and face-to-face appointments, without significantly increasing complications. We believe this is a safe and effective method of follow-up, optimising resource use in line with the NHS long term plan. Data collection is ongoing, and a larger cohort would be available for presentation

Polyethylene wear represents a significant risk factor for the long-term success of knee arthroplasty [1]. This work aimed to develop and in vivo validate an automated algorithm for accurate and precise AI based wear measurement in knee arthroplasty using clinical AP radiographs for scientifically meaningful multi-centre studies. Twenty postoperative radiographs (knee joint AP in standing position) after knee arthroplasty were analysed using the novel algorithm. A convolutional neural network-based segmentation is used to localize the implant components on the X-Ray, and a 2D-3D registration of the CAD implant models precisely calculates the three-dimensional position and orientation of the implants in the joint at the time of acquisition. From this, the minimal distance between the involved implant components is determined, and its postoperative change over time enables the determination of wear in the radiographs. The measured minimum inlay height of 335 unloaded inlays excluding the weight-induced deformation, served as ground truth for validation and was compared to the algorithmically calculated component distances from 20 radiographs. With an average weight of 94 kg in the studied TKA patient cohort, it was determined that an average inlay height of 6.160 mm is expected in the patient. Based on the radiographs, the algorithm calculated a minimum component distance of 6.158 mm (SD = 81 µm), which deviated by 2 µm in comparison to the expected inlay height. An automated method was presented that allows accurate and precise determination of the inlay height and subsequently the wear in knee arthroplasty based on a clinical radiograph and the CAD models. Precision and accuracy are comparable to the current gold standard RSA [2], but without relying on special radiographic setups. The developed method can therefore be used to objectively investigate novel implant materials with meaningful clinical cohorts, thus improving the quality of patient care

Introduction and Objective. Up to 30% of thoracolumbar (TL) fractures are missed in the emergency room. Failure to identify these fractures can result in neurological injuries up to 51% of the casesthis article aimed to clarify the incidence and risk factors of traumatic fractures in China. The China National Fracture Study (CNFS. Obtaining sagittal and anteroposterior radiographs of the TL spine are the first diagnostic step when suspecting a traumatic injury. In most cases, CT and/or MRI are needed to confirm the diagnosis. These are time and resource consuming. Thus, reliably detecting vertebral fractures in simple radiographic projections would have a significant impact. We aim to develop and validate a deep learning tool capable of detecting TL fractures on lateral radiographs of the spine. The clinical implementation of this tool is anticipated to reduce the rate of missed vertebral fractures in emergency rooms. Materials and Methods. We collected sagittal radiographs, CT and MRI scans of the TL spine of 362 patients exhibiting traumatic vertebral fractures. Cases were excluded when CT and/or MRI where not available. The reference standard was set by an expert group of three spine surgeons who conjointly annotated (fracture/no-fracture and AO Classification) the sagittal radiographs of 171 cases. CT and/or MRI were used confirm the presence and type of the fracture in all cases. 302 cropped vertebral images were labelled “fracture” and 328 “no fracture”. After augmentation, this dataset was then used to train, validate, and test deep learning classifiers based on the ResNet18 and VGG16 architectures. To ensure that the model's prediction was based on the correct identification of the fracture zone, an Activation Map analysis was conducted. Results. Vertebras T12 to L2 were the most frequently involved, accounting for 48% of the fractures. Accuracies of 88% and 84% were obtained with ResNet18 and VGG16 respectively. The sensitivity was 89% with both architectures but ResNet18 had a significantly higher specificity (88%) compared to VGG16 (79%). The fracture zone used was precisely identified in 81% of the heatmaps. Conclusions. Our AI model can accurately identify anomalies suggestive of TL vertebral fractures in sagittal radiographs precisely identifying the fracture zone within the vertebral body

Over the last few years low dose digital radiography (DR) has all but replaced traditional chemical image processing. This appears to have created a paradigm shift in the suitability of intraoperative radiographic guidance for total hip arthroplasty. It is the purpose of this publication to describe our preferred technique and assess its reliability in achieving the desired parameters of a successful total hip arthroplasty. A consecutive prospective evaluation of 150 primary total hip arthroplasties employing intraoperative digital radiography was carried out. An anteroposterior pelvic radiograph with the patient in the lateral decubitus position was obtained for all hips. The orientation of the intraoperative film was matched to that of the preoperative pelvic radiograph. The image was taken after placement of the acetabular component and best estimate of femoral trial size, position, and head and neck length. The DR system produced an image within 6 seconds of exposure. This trial radiograph was then used to make adjustments. Given that the cassette does not have to be moved for image processing, a precise anteroposterior film was obtained by simply adjusting the operating table. Two to three minutes were allotted for each radiograph. Corrections to stem size, cup position, screw length and position, limb length, and offset were made based on this intraoperative radiograph. The final intraoperative image was then compared to a postoperative standard radiograph in supine position at 2 weeks after total hip arthroplasty to verify the accuracy of intraoperative digital radiography. Abduction angle, limb length, offset, and canal fit and fill were assessed for confirmation of the validity of the intraoperative imaging technique. Acetabular abduction angle was determined with a mean of 43 degrees (range, 35 to 48 degrees). The intraoperative measurement was within 3 degrees of the postoperative measurement in all cases. Adjustment of acetabular cup orientation was performed 10% of the time based on the intraoperative radiograph. Apposition was within 2 mm 100% of the time. Re-seating of the cup was carried out in one hip only. Femoral component was neutral in 92% and between 3 and 5 degrees of varus in 8%. Femoral component was upsized 55% of the time. Intraoperatively measured limb length discrepancy and offset were within 3 mm of the postoperative measurement in all hips. Intraoperative digital imaging is a reliable tool for achieving the desired radiographic results in THA. The technique is efficient and affordable. The high rate of success in this series suggests that this technology should contribute to a paradigm shift in the standard of care in total hip arthroplasty

Introduction

Accurate assessment of alignment in pre-operative and post-operative knee radiographs is important for planning and evaluating knee replacement surgery. Existing methods predominantly rely on manual measurements using long-leg radiographs, which are time-consuming to perform and are prone to reliability errors. In this study, we propose a machine-learning-based approach to automatically measure anatomical varus/valgus alignment in pre-operative and post-operative standard AP knee radiographs.

Evaluation of patient specific spinopelvic mobility requires the detection of bony landmarks in lateral functional radiographs. Current manual landmarking methods are inefficient, and subjective. This study proposes a deep learning model to automate landmark detection and derivation of spinopelvic measurements (SPM).

A deep learning model was developed using an international multicenter imaging database of 26,109 landmarked preoperative, and postoperative, lateral functional radiographs (HREC: Bellberry: 2020-08-764-A-2). Three functional positions were analysed: 1) standing, 2) contralateral step-up and 3) flexed seated. Landmarks were manually captured and independently verified by qualified engineers during pre-operative planning with additional assistance of 3D computed tomography derived landmarks. Pelvic tilt (PT), sacral slope (SS), and lumbar lordotic angle (LLA) were derived from the predicted landmark coordinates. Interobserver variability was explored in a pilot study, consisting of 9 qualified engineers, annotating three functional images, while blinded to additional 3D information. The dataset was subdivided into 70:20:10 for training, validation, and testing.

The model produced a mean absolute error (MAE), for PT, SS, and LLA of 1.7°±3.1°, 3.4°±3.8°, 4.9°±4.5°, respectively. PT MAE values were dependent on functional position: standing 1.2°±1.3°, step 1.7°±4.0°, and seated 2.4°±3.3°, p< 0.001. The mean model prediction time was 0.7 seconds per image. The interobserver 95% confidence interval (CI) for engineer measured PT, SS and LLA (1.9°, 1.9°, 3.1°, respectively) was comparable to the MAE values generated by the model.

The model MAE reported comparable performance to the gold standard when blinded to additional 3D information. LLA prediction produced the lowest SPM accuracy potentially due to error propagation from the SS and L1 landmarks. Reduced PT accuracy in step and seated functional positions may be attributed to an increased occlusion of the pubic-symphysis landmark. Our model shows excellent performance when compared against the current gold standard manual annotation process.

Introduction. Cross table lateral (CTL) radiographs are commonly used to measure acetabular component anteversion after total hip arthroplasty (THA). CTL measurements may differ by >10 degrees from CT scan measurements, but the reasons for this discrepancy are poorly understood. We compare anteversion measurements made on CTL radiographs and CT scans to identify spinopelvic parameters predictive of inaccuracy. Methods. THA patients (n=47) with preoperative spinopelvic radiographic analysis and postoperative CT scans were retrospectively reviewed. Acetabular component anteversion was measured on post-operative CTL radiographs, and CT scans using 3D reconstructions of the pelvis. Patients were grouped by error (CTL-CT)>10° (n=11) or <10° (n=36), and spinopelvic mobility parameters were compared using t-tests. Correlation between error and mobility parameters was assessed with Pearson coefficient. Results. Patients with CTL error >10° (range 10–14) had stiffer lumbar spines with less lumbar flexion (38° vs 47°, p=0.03), greater sagittal imbalance measured by pelvic incidence-lumbar lordosis mismatch (6° vs −2°, p=0.04), more pelvic extension when seated (pelvic tilt −10° vs −2°, p=0.05), and greater change in pelvic tilt between supine and seated positions (13° vs 4°, p=0.04). The error of CTL measurements showed a positive correlation with increased CTL anteversion (r=0.5, p=0.001), standing lordosis (r=0.23, p=0.05), seated lordosis (r=0.4, p=0.01) and pelvic tilt change between supine and step-up positions (r=0.34, p=0.01). Discussion. Differences in spinopelvic mobility patterns may explain the variable accuracy of acetabular anteversion measurements on CTL radiographs. Patients with stiff spines and increased compensatory pelvic motion have less accurate measurements on CTL radiographs. Flexion of the contralateral hip is required to obtain clear CTL radiographs. In patients with a stiff lumbar spine, this movement may extend the pelvis and increase anteversion of the acetabulum on CTL views. Reliable analysis of acetabular component anteversion in this patient population may require advanced imaging with a CT scan

When performing scarf osteotomies some surgeons use intraoperative radiography and others do not. Our experience is that when using intraoperative radiography we often change the osteotomy position to improve the correction of the hallux valgus angle and sesamoid position. We report the results of a single surgeon series of 62 consecutive patients who underwent a scarf osteotomy for hallux valgus. The first 31 patients underwent surgery without the use of intraoperative radiographs and the subsequent 31 patients underwent surgery with the use of intraoperative radiographs, this reflects a change in the surgeons practice. Hallux valgus angle, intermetatarsal angle, distal metatarsal articular angle and sesamoid position using the Hardy Clapham grading system were recorded. All patients had measurements recorded from weight baring radiographs taken pre operatively as well as at 6 and 12 weeks post operatively. Intraoperative measurements were also recorded for all patients in the intraoperative radiography group. The mean hallux valgus angle preoperatively was 28.5° in the control group and 30.5° in the intraoperative radiography group. The mean hallux valgus angle in the control group at 6 weeks was 12.4° and at 12 weeks was 12.6°. The mean hallux valgus angle in the intraoperative radiography group at 6 weeks was 10.5° and at 12 weeks was 9.8°. The median sesamoid position pre operatively was 4 for both groups. At 6 and 12 weeks the sesamoid position improved by a median of 1 position in the control group and 2 positions in the intraoperative radiography group (p<0.05). We recommend that surgeons who do not routinely use intraoperative radiography undertake a trial of this. We have found that the use of intraoperative radiography improves the correction of hallux valgus angle and sesamoid position. These have been shown to increase patient satisfaction and reduce recurrence

The function of the knee joint is to allow for locomotion and is comprised of various bodily structures including the four major ligaments; medial collateral ligament (MCL), lateral collateral ligament (LCL), anterior cruciate ligament (ACL) and posterior cruciate ligament (PCL). The primary function of the ligaments are to provide stability to the joint. The knee is prone to injury as a result of osteoarthritis as well as ligamentous and meniscal lesions. Furthermore, compromised joint integrity due to ligamentous injury may be a result of direct and indirect trauma, illness, occupational hazard as well as lifestyle. A device capable of non-invasively determining the condition of the ligaments in the knee joint would be a useful tool to assist the clinician in making a more informed diagnosis and prognosis of the injury. Furthermore, the device would potentially reduce the probability of a misdiagnosis, timely diagnosis and avoidable surgeries. The existing Laxmeter prototype (UK IPN: GB2520046) is a Stress Radiography Device currently limited to measuring the laxity of the MCL and LCL at multiple fixed degrees of knee flexion. Laxity refers to the measure of a ligament's elasticity and stiffness i.e. the condition of the ligament, by applying a known load (200N) to various aspects of the proximal tibial and thereby inducing tibial translation. The extent of translation would indicate the condition of the ligament. The Laxmeter does not feature a load applying component as of yet, however, it allows for the patient to be in the most comfortable and ideal position during radiographic laxity measurement testing. The entire structure is radiolucent and attempts to address the limitations of existing laxity measurement devices, which includes: excessive radiation exposure to the radiographic assistant, little consideration for patient ergonomics and restrictions to cruciate or collateral ligament laxity measurements. The study focusses on further developing and modifying the Laxmeter to allow for: the laxity measurement of all four major ligaments of the knee joint, foldability for improved storage and increased structural integrity. Additionally, a load applicator has been designed as an add-on to the system thereby making the Laxmeter a complete Stress Radiography Device. Various materials including Nylon, Polycarbonate, Ultra High Molecular Weight Polyethylene (UHMWPE) – PE 1000, and Acetal/ POM were tested, using the Low Dose X-ray (Lodox) scanner, to determine their radiolucency. All materials were found to be radiolucent enough for the manufacture of the Laxmeter structure as well as the load applicator in order to identify and measure the translation of the tibia with respect to the stationary femur. The Laxmeter allows for the measurement of the laxity of the MCL and LCL at multiple fixed degrees of flexion by providing the ideal patient position for testing. The next iteration of the device will present an affordable and complete Stress Radiography Device capable of measuring the laxity of all four major ligaments of the knee joint at multiple fixed degrees of flexion. Future work would include aesthetic considerations as well as an investigation into carbon-fibre-reinforced plastics

Introduction

There are nearly 500,000 people with undiagnosed diabetes mellitus in the UK. The incidental finding vascular calcification on plain radiographs in patients with undiagnosed diabetes has the potential to alter patient management in those presenting with pathology. We hypothesised that the presence of vascular calcification on plain radiographs of the foot may predict the diagnosis of diabetes. The primary aim of this case control study was to determine the positive predictive value of vascular calcification to diagnose diabetes. Secondary aims were to determine the odds of having diabetes dependent on other known risk factors for calcification.

Anteroposterior (AP) radiographs remain the standard of care for pre- and post-operative imaging during total hip arthroplasty (THA), despite known limitation of plain films, including the inability to adequately account for distortion caused by variations in pelvic orientation. Of specific interest to THA surgeons are distortions associated with pelvic tilt, as unaccounted for tilt can significantly alter radiographic measurements of cup position. Several authors have proposed methods for correcting for pelvic tilt on radiographs but none have proven reliable in a THA population. The purpose of our study was to develop a method for correcting pelvic tilt on AP radiographs in patients undergoing primary or revision THA. CT scans from 20 patients/cadaver specimens (10 male, 10 female) were used to create 3D renderings, from which synthetic radiographs of each pelvis were generated (Figure 1). For each pelvis, 13 synthetic radiographs were generated, showing the pelvis at between −30° and 30° of pelvic tilt, in 5° increments. On each image, 8 unique parameters/distances were measured to determine the most appropriate parameters for calculation of pelvic tilt (Figure 2). The most reliable and accurate of these parameters was determined via regression analysis and used to create gender-specific nomograms from which pelvic tilt measurements could be calculated (Figure 3). The accuracy and reliability of the nomograms and correction method were subsequently validated using both synthetic radiographs (n=50) and stereoradiographic images (n=58). Of 8 parameters measured, the vertical distance between the superior margin of the pubic symphysis and the transischial line (PSTI) was determined to be the most reliable (r=−0.96, ICC=0.94). Mean tilt calculated from synthetic radiographs (0.6°±18.6°) correlated very strongly (r=0.96) with mean known tilt (0.5°±17.9°, p=0.98). Mean pelvic tilt calculated from AP EOS images (3.2°±9.9°) correlated strongly (r=0.77) with mean tilt measured from lateral EOS images (3.8°±8.2°, p=0.74). No gender differences were noted in mean tilt measurements in synthetic images (p=0.98) or EOS images (p=0.45). Our method of measuring PSTI and POD on AP images and applying these measurements to nomograms provides a validated and reliable method for estimating the degree of pelvic tilt on AP radiographs during THA. For any figures or tables, please contact authors directly

Diagnostic interpretation error of paediatric musculoskeletal (MSK) radiographs can lead to late presentation of injuries that subsequently require more invasive surgical interventions with increased risks of morbidity. We aimed to determine the radiograph factors that resulted in diagnostic interpretation challenges for emergency physicians reviewing pediatric MSK radiographs.

Emergency physicians provided diagnostic interpretations on 1,850 pediatric MSK radiographs via their participation in a web-based education platform. From this data, we derived interpretation difficulty scores for each radiograph using item response theory. We classified each radiograph by body region, diagnosis (fracture/dislocation absent or present), and, where applicable, the specific fracture location(s) and morphology(ies). We compared the interpretation difficulty scores by diagnosis, fracture location, and morphology. An expert panel reviewed the 65 most commonly misdiagnosed radiographs without a fracture/dislocation to identify normal imaging findings that were commonly mistaken for fractures.

We included data from 244 emergency physicians, which resulted in 185,653 unique radiograph interpretations, 42,689 (23.0%) of which were diagnostic errors. For humerus, elbow, forearm, wrist, femur, knee, tibia-fibula radiographs, those without a fracture had higher interpretation difficulty scores relative to those with a fracture; the opposite was true for the hand, pelvis, foot, and ankle radiographs (p < 0 .004 for all comparisons). The descriptive review demonstrated that specific normal anatomy, overlapping bones, and external artefact from muscle or skin folds were often mistaken for fractures. There was a significant difference in difficulty score by anatomic locations of the fracture in the elbow, pelvis, and ankle (p < 0 .004 for all comparisons). Ankle and elbow growth plate, fibular avulsion, and humerus condylar were more difficult to diagnose than other fracture patterns (p < 0 .004 for all comparisons).

We identified actionable learning opportunities in paediatric MSK radiograph interpretation for emergency physicians. We will use this information to design targeted education to referring emergency physicians and their trainees with an aim to decrease delayed and missed paediatric MSK injuries.

Diagnostic interpretation error of paediatric musculoskeletal (MSK) radiographs can lead to late presentation of injuries that subsequently require more invasive surgical interventions with increased risks of morbidity. We aimed to determine the radiograph factors that resulted in diagnostic interpretation challenges for emergency physicians reviewing pediatric MSK radiographs.

Emergency physicians provided diagnostic interpretations on 1,850 pediatric MSK radiographs via their participation in a web-based education platform. From this data, we derived interpretation difficulty scores for each radiograph using item response theory. We classified each radiograph by body region, diagnosis (fracture/dislocation absent or present), and, where applicable, the specific fracture location(s) and morphology(ies). We compared the interpretation difficulty scores by diagnosis, fracture location, and morphology. An expert panel reviewed the 65 most commonly misdiagnosed radiographs without a fracture/dislocation to identify normal imaging findings that were commonly mistaken for fractures.

We included data from 244 emergency physicians, which resulted in 185,653 unique radiograph interpretations, 42,689 (23.0%) of which were diagnostic errors. For humerus, elbow, forearm, wrist, femur, knee, tibia-fibula radiographs, those without a fracture had higher interpretation difficulty scores relative to those with a fracture; the opposite was true for the hand, pelvis, foot, and ankle radiographs (p < 0 .004 for all comparisons). The descriptive review demonstrated that specific normal anatomy, overlapping bones, and external artefact from muscle or skin folds were often mistaken for fractures. There was a significant difference in difficulty score by anatomic locations of the fracture in the elbow, pelvis, and ankle (p < 0 .004 for all comparisons). Ankle and elbow growth plate, fibular avulsion, and humerus condylar were more difficult to diagnose than other fracture patterns (p < 0 .004 for all comparisons).

We identified actionable learning opportunities in paediatric MSK radiograph interpretation for emergency physicians. We will use this information to design targeted education to referring emergency physicians and their trainees with an aim to decrease delayed and missed paediatric MSK injuries.

INTRODUCTION. Despite our best efforts, orthopaedic surgeons do not always achieve desired results in acetabular cup positioning in total hip arthroplasty. New advancements in digital radiography and image analysis software allow contemporaneous assessment of cup position in real-time during the surgical procedure. The purpose of this study was to describe and validate a technique in obtaining a true AP Pelvis radiograph in the lateral decubitus position to accurately assess cup position intra-operatively (Figure 1). METHODS. 350 consecutive patients undergoing THA through a soft-tissue sparing posterior approach were prospectively enrolled. Standard pre-operative supine radiographs were taken in the office to serve as a reference for intra-operative pelvic orientation and templating. Intra-operative AP Pelvis radiographs were obtained with the patient in the lateral decubitus position to appropriately match the pre-operative radiograph. Adjustments were made to correct for pelvic rotation by rotating the operating room table forward or backward. Radiographic beam angle adjustments allowed the surgeon to match pre-operative and intra-operative pelvic tilt (Figure 2). Two independent observers measured cup abduction angle. RESULTS. 95% of cups were placed within 30–50 degrees of abduction, with a mean angle of 38 degrees (STD +/− 5). 100% of cups measured post-operatively were placed within 3 degrees of their intra-operative measurement. Mean anteversion was 27.5 degrees (STD +/− 3.5). Intra-operative radiographs were repeated in 88% of cases in order to match to the pre-operative radiographs. The cup was repositioned in 28% of cases based on intra-operative measurements. Impingement during range of motion testing occurred in 3% of cases despite acceptable measurements, necessitating cup reposition. The intercross correlation coefficient between the two observers was 0.92. There was one dislocation reported in the 2-year follow-up. Changes in the pelvic inlet and outlet orientation changed the abduction angle measurement in a predictable way. We developed a formula and 3D model to predict the abudction angle based on the pelvic tilt, where a more outlet view would increase the abduction angle measurement (Figure 3). DISCUSSION AND CONCLUSION. Advancements in digital radiography allow for real-time cup position assessment, creating the opportunity for the surgeon to make the appropriate changes and confirm precise placement during the procedure. For figures/tables, please contact authors directly.

Pelvic x-ray is a routine part of the primary survey of Advanced Trauma Life Support (ATLS) guidelines. However, pelvic CT is the gold standard in the diagnosis of pelvic fractures. This study aims to confirm the safety of a modified ATLS algorithm omitting pelvic x-ray in hemodynamically stable polytraumatized patients with clinically stable pelvis, in favour of later pelvic CT scan.

A retrospective analysis of polytraumatized patients in our emergency room was conducted between 2005 and 2006. Inclusion criteria were blunt abdominal trauma, initial hemodynamic stability and clinically stable pelvis. We excluded patients requiring immediate intervention.

We reviewed the records of 452 patients. 91 fulfilled inclusion criteria (56% male, mean age 45 years). 43% were road traffic accidents and 47% falls. In 68/91 (75%) patients, both pelvic x-ray and CT examination were performed; the remainder had only pelvic CT. In 6/68 (9%) patients, pelvic fracture was diagnosed by pelvic x-ray. None false positive pelvic x-ray was detected. In 3/68 (4%) cases a fracture was missed in the pelvic x-ray, but confirmed on CT. 5 (56%) were classified type A fractures, and another 4 (44%) B 2.1 in computed tomography (AO classification). One A 2.1 fracture was found in a clinically stable patient who only received CT scan (1/23).

In hemodynamically stable patients with clinically stable pelvis, x-ray sensitivity is only 67% and it may safely be omitted in favor of a pelvic CT examination. The results support the safety and utility of our modified ATLS algorithm

Background. Dislocation is a common complication following total hip arthroplasty (THA), and accounts for a high percentage of subsequent revisions. The purpose of this study was to develop a convolutional neural network (CNN) model to identify patients at high risk for dislocation based on postoperative anteroposterior (AP) pelvis radiographs. Methods. We retrospectively evaluated radiographs for a cohort of 13,970 primary THAs with 374 dislocations over 5 years of follow-up. Overall, 1,490 radiographs from dislocated and 91,094 from non-dislocated THAs were included in the analysis. A CNN object detection model (YOLO-V3) was trained to crop the images by centering on the femoral head. A ResNet18 classifier was trained to predict subsequent hip dislocation from the cropped imaging. The ResNet18 classifier was initialized with ImageNet weights and trained using FastAI (V1.0) running on PyTorch. The training was run for 15 epochs using ten-fold cross validation, data oversampling and augmentation. Results. The hip dislocation prediction classifier achieved the following mean performance: accuracy= 49.5(±4.1)%, sensitivity= 89.0(±2.2)%, specificity= 48.8(±4.2)%, positive predictive value= 3.3(±0.3)%, negative predictive value= 99.5(±0.1)%, and area under the receiver operating characteristic curve= 76.7(±3.6)%. Saliency maps demonstrated that the model placed the greatest emphasis on the femoral head and acetabular component. Conclusions. Existing prediction methods fail to identify patients at high risk of dislocation following THA. Our prediction model has high sensitivity and negative predictive value. Therefore, it can be helpful in rapid assessment of risk for dislocation following THA. The model further suggests radiographic locations which may be important in understanding the etiology of prosthesis dislocation