Anteroposterior Pelvic Radiographs Research Articles

Deep learning-based automated measurement of hip key angles and auxiliary diagnosis of developmental dysplasia of the hip

ObjectivesAnteroposterior pelvic radiographs remains the most widely employed method for diagnosing developmental dysplasia of the hip. This study aims to evaluate the accuracy of an artificial intelligence model in measuring angles in pelvic radiographs of the hip. The assessment seeks to demonstrate the efficacy of the artificial intelligence model in diagnosing both developmental dysplasia of the hip and borderline developmental dysplasia of the hip through the analysis of pelvic radiographs.MethodsA total of 1,029 patients, including 273 men and 757 women, were retrospectively included in this study. The anteroposterior pelvic radiographs were randomly divided into three sets: the training set (720 cases), the validation set (103 cases), and the test set (206 cases). Key anatomical points on the anteroposterior pelvic radiographs were identified. The Sharp, Tönnis, and Center Edge angles were calculated automatically based on the corresponding criteria. The hip development status was compared between measurements obtained from the artificial intelligence model and those defined manually by two radiologists. The area under the receiver operating characteristic curve was utilized to assess the diagnostic performance of the artificial intelligence model.ResultsThe results obtained from both manual measurements and the artificial intelligence model demonstrated no significant differences in the Sharp, Tönnis, and Center edge angles (all p > 0.05). The intra-class correlation coefficients and correlation coefficient r values exceeded 0.75, indicating that both the artificial intelligence model and manual measurements exhibited good repeatability and a positive correlation. Notably, the artificial intelligence model provided measurements more faster than those conducted by radiologists (p = 0.001). The artificial intelligence model also demonstrated high diagnostic accuracy, sensitivity, and specificity for developmental dysplasia of the hip. The performance of the artificial intelligence model in diagnosing developmental dysplasia of the hip was robust. Additionally, the results from the artificial intelligence model and manual measurements were largely consistent with clinical diagnosis results (p = 0.01). The artificial intelligence model can effectively evaluate hip conditions by measuring the Sharp, Tönnis, and Center edge angles, which are consistent closely with clinical diagnosis results.ConclusionsThe results of the artificial intelligence model measurements demonstrate a high degree of consistency with those obtained through manual measurements. The angles of Sharp, Tönnis, and Center edge, as evaluated by the deep learning-based convolutional neural network model, exhibit robust diagnostic performance in identifying both developmental dysplasia of the hip and borderline developmental dysplasia of the hip. Consequently, the artificial intelligence model has the potential to fully replace manual measurements of these critical hip angles, providing a more efficient and precise alternative for diagnosing both conditions of the hip.

Development and accuracy of an artificial intelligence model for predicting the progression of hip osteoarthritis using plain radiographs and clinical data: a retrospective study

BackgroundPredicting the progression of hip osteoarthritis (OA) remains challenging, and no reliable predictive method has been established. This study aimed to develop an artificial intelligence (AI) model to predict hip OA progression via plain radiographs and patient data and to determine its accuracy.MethodsThis retrospective study utilized anteroposterior pelvic radiographs of consecutive patients with hip OA who underwent primary unilateral total hip arthroplasty. Radiographs diagnosed with Kellgren–Lawrence (KL) grade 0–2 were extracted from 361 patients and 1697 images. This AI model was developed to predict whether OA would progress from KL grade 0–2 to KL grade ≥ 3 within n years (n = 3, 4, 5). A gradient-boosting decision tree approach was utilized according to feature extractions obtained by a convolutional neural network from radiographs and patient data (height, body weight, sex, age, and KL grade given by an orthopedic surgeon) with five-fold cross-validation. The model performance was assessed using accuracy, specificity, sensitivity, and the area under the receiver operating characteristic curve (AUC).ResultsThe mean accuracy, specificity, sensitivity, and AUC of our prediction model were, respectively, 81.8%, 88.0%, 66.7%, and 0.836 for 3 years; 79.8%, 85.0%, 71.6%, and 0.836 for 4 years; and 78.5%, 80.4%, 76.9%, and 0.846 for 5 years.ConclusionsThe proposed AI model performed adequately in predicting hip OA progression and may be clinically applicable with additional datasets and validation.

Can we identify abnormal pelvic tilt using pre-THA anteroposterior pelvic radiographs?

Patients with increased pelvic tilt (PT) are at risk for instability following total hip arthroplasty (THA). Identification of increased PT using anteroposterior (AP) pelvic radiographs could avoid additional spinopelvic radiographs. This study aimed to (1) describe which AP pelvic parameters most accurately estimate sagittal PT, and (2) determine thresholds for these parameters that can identify patients with increased PT. This was a retrospective, consecutive, cohort study in a tertiary referral hospital on 225 patients (age: 66 ± 12 years-old; 52% female) listed for THA. Patients underwent pre-operative standing AP pelvic radiographs to measure distance- and angular- based parameters from several anatomical landmarks. Sagittal PT was measured on a standing lateral spinopelvic radiograph and considered high when ≥ 20°. No AP pelvic parameters correlated strongly with sagittal PT. Ratio between horizontal and vertical diameter of the pelvic foramen (C/D ratio) (rho - 0.341; p < 0.001); and vertical distance between trans-SIJ and trans-ASIS line (SITA) (rho 0.307; p < 0.001) correlated moderately with sagittal PT. Sacro-femoral-pubic (SFP) angle < 60° had highest sensitivity (85%), but lowest specificity (52%) to differentiate between patients with and without increased PT. If SITA > 62mm, C/D ratio < 0.5 and SFP < 60°, specificity increased (88%), but sensitivity was low (49%). In the absence of computerized models, AP pelvic parameters cannot accurately predict sagittal PT. However, an SFP < 60° should alert a hip surgeon that a patient may have an increased PT, and would benefit from additional lateral spinopelvic imaging prior to THA. Level II, diagnostic study.

Femoroacetabular impingement syndrome in middle-aged individuals is strongly associated with the development of hip osteoarthritis within 10-year follow-up: a prospective cohort study (CHECK)

ObjectiveThe objective is to determine the association and absolute risk of femoroacetabular impingement syndrome (FAIS) for the development of radiographic hip osteoarthritis (RHOA).MethodsThis is a nationwide, multicentre prospective cohort study...

The Measurement of the Lateral Center-Edge Angle Is Underestimated on Radiographs Compared With 3-Dimensional Computed Tomography

PurposeTo determine if there is a significant difference using Femoral Heads (FH) as anatomical horizon when measuring the LCEA compared to Floor (F), Acetabular Teardrops (AT), and Ischial Tuberosities (IT) and to determine their accuracy by comparing to CT scan with commercially available software. MethodsBetween June 2019 and May 2020, patients with preoperative supine anteroposterior (AP) pelvis radiographs and CT scans were included and retrospectively analyzed. The LCEA was measured on all preoperative supine AP pelvis radiographs four times per hip, using the four methods. The four anatomical horizons used to measure LCEA were compared to each other to determine statistically significant difference. The LCEA measured in the CT scan at the 12 o’clock position was used to compare and determine radiographs’ LCEA accuracy. ResultsNinety-six patients (100 hips) met the inclusion criteria. Sixty-two were females (65%), and the mean age was 35.2 ± 15 years. The mean value for LCEA in CT was 32.2 and 31.1 for the four anatomical horizons in X-ray (P < 0.001). The lowest mean difference between CT scan and X-ray was obtained using the FH (2.3 ± 2.4). Less mean difference was obtained between FH and IT (1.0 ± 0.8). ConclusionIn this study, radiographic measurements underestimated LCEA compared with those from CT scans. Using the FH as an anatomic horizon on radiographs was a more accurate method to measure LCEA than using AT, IT, or F. While this difference is statistically significant, it is not likely to be clinically significant.

Artificial Intelligence-Based Surgery Support Model Using Intraoperative Radiographs for Assessing the Acetabular Component Angle

BackgroundThis study aimed to develop an artificial intelligence–based surgical support model for assessing the acetabular component angle using intraoperative radiographs during total hip arthroplasty and verify its accuracy. MethodsA total of 268 hips were analyzed. At first, 268 preoperative and intraoperative anteroposterior pelvic radiographs were amplified to 536. These radiographs were used to create a learning model to estimate the acetabular component angle from the radiographs intraoperatively. The ground truth was the anteversion and inclination angles obtained from the computed tomography–based navigation system intraoperatively. Bone landmarks on the preoperative and intraoperative radiographs were manually annotated. The distances and angles between each landmark were used as predictor variables. The estimation accuracy was assessed for internal and external test datasets. Mean absolute error (MAE) and R2 values were used as accuracy measures. ResultsThe MAE and R2 for the internal test set showed 2.19 and 0.850 for anteversion, and 1.18 and 0.805 for inclination, respectively. The MAE and R2 for the external test set showed 2.78 and 0.789 for anteversion, and 1.56 and 0.744 for inclination, respectively. ConclusionsWe developed an artificial intelligence–based surgical support model for accurately assessing the acetabular component angle using intraoperative radiographs. Excellent estimation accuracy was confirmed for the external test set. In the future, the model may help to reduce the risk of adverse postoperative events.

How to Best Identify Acetabular Retroversion on Radiographs: Thresholds to Guide Clinical Practice

Background: Acetabular retroversion is associated with impingement and instability. An adequate interpretation of acetabular version and coverage on radiographs is essential to determine the optimal treatment strategy (periacetabular osteotomy vs hip arthroscopic surgery). The crossover sign (COS) has been associated with the presence of acetabular retroversion, and the anterior wall index (AWI) and posterior wall index (PWI) assess anteroposterior acetabular coverage. However, the radiographic appearance of the acetabulum is sensitive to anterior inferior iliac spine (AIIS) morphology and pelvic tilt (PT), which differs between the supine and standing positions. Purpose: To (1) identify differences in the acetabular appearance between the supine and standing positions among patients presenting with hip pain; (2) determine factors (acetabular version, AIIS morphology, and spinopelvic characteristics) associated with the crossover ratio (COR), AWI, and PWI; and (3) define relevant clinical thresholds to guide management. Study Design: Cross-sectional study; Level of evidence, 3. Methods: Patients who presented to a hip preservation surgical unit (n = 134) were included (mean age, 35 ± 8 years; 58% female; mean body mass index, 27 ± 6). All participants underwent supine and standing anteroposterior pelvic radiography to assess the COS, COR, AWI, and PWI as well as standing lateral radiography to determine standing PT. Computed tomography was used to measure supine PT, acetabular version, and AIIS morphology. Acetabular version was measured at 3 transverse levels, corresponding to the 1-, 2-, and 3-o’clock positions. The correlation between radiographic characteristics (COR, AWI, and PWI) and acetabular version, AIIS morphology, and PT was calculated using the Spearman correlation coefficient. Receiver operating characteristic curve analysis was performed to define thresholds for the COR, AWI, and PWI to identify retroversion (version thresholds: <10°, <5°, and <0°). Results: The COS was present in 55% of hips when supine and 30% when standing, with a mean difference in the COR of 12%. The supine COR (rho = −0.661) and AWI/PWI ratio (rho = −0.618) strongly correlated with acetabular version. The COS was more prevalent among patients with type 2 AIIS morphology (71%) than among those with type 1 AIIS morphology (43%) (P = .003). COR thresholds of 23% and 28% were able to identify acetabular version <5° (sensitivity = 81%; specificity = 80%) and <0° (sensitivity = 88%; specificity = 85%), respectively. An AWI/PWI ratio >0.6 was able to reliably identify acetabular version <0° (sensitivity = 83%; specificity = 84%). In the presence of a COR >30% and an AWI/PWI ratio >0.6, the specificity to detect retroversion was significantly increased (>90%). Conclusions: The presence of the COS was very common among patients with hip pain. False-positive results (high COR/normal version) may occur because of AIIS morphology/low PT. Relevant thresholds of COR >30% and AWI/PWI ratio >0.6 can help with diagnostic accuracy. In cases in which either the COR or AWI/PWI ratio is high, axial cross-sectional imaging can further help to avoid false-positive results.

Lower Extremity Arterial Calcification Predicts Referral to a Closed Unit After Primary Total Hip Arthroplasty

BackgroundWe aimed to determine the association between lower extremity arterial calcification (LEAC) and referral to a closed unit (CU), length of stay, 90-day readmissions, and 1-year mortality in primary total hip arthroplasty (THA) patients. MethodsWe retrospectively analyzed 705 patients who underwent primary THA, identifying 64 patients (9.13%) who had LEAC and 641 who did not have LEAC. Patients who had LEAC were older (77 ± 10.0 versus 67 ± 11.5 years; P < 0.001) and had more comorbidities, except for a history of thromboembolic and oncologic diseases (P > 0.05). A preoperative antero-posterior pelvic radiograph was used to assess the presence of LEAC. Admission to CU, length of stay, 90-day readmissions, and 1-year mortality were recorded. A logistic regression model was used to identify risk factors for referral to CU. ResultsPatients who had LEAC had a higher incidence of admission to the intensive care unit (8 of 64 [12.5%] versus 8 of 641 [1.09%]; P < 0.001), a longer hospital stay (4.7 ± 1.8 versus 4.2 ± 1.3 days; P = 0.006), more readmissions (16 of 64 [25%] versus 33 of 641 [5.15%]; P < 0.001), and a higher 1-year mortality rate (6 of 64 [9.3%] versus 0 of 641 [0%]; P < 0.001) than patients who did not have LEAC. Of the patients who had LEAC admitted to CU, only 3 of 8 had a previous indication to do so in the preoperative assessment performed by the Department of Anesthesiology, while all non-LEAC ones referred to CU did so. Logistic regression analysis showed that LEAC was a risk factor for admission to CU (odds ratio = 4.77; 95% confidence interval: 1.12 to 20.25; P = 0.034). ConclusionsThe presence of LEAC was a risk factor for transfer to CU, longer in-hospital stays, more readmissions, and a higher 1-year mortality rate. Identifying patients who have LEAC can aid in the preoperative assessment and risk stratification of patients planned for primary THA.

Is it feasible to develop a supervised learning algorithm incorporating spinopelvic mobility to predict impingement in patients undergoing total hip arthroplasty?

Precise implant positioning, tailored to individual spinopelvic biomechanics and phenotype, is paramount for stability in total hip arthroplasty (THA). Despite a few studies on instability prediction, there is a notable gap in research utilizing artificial intelligence (AI). The objective of our pilot study was to evaluate the feasibility of developing an AI algorithm tailored to individual spinopelvic mechanics and patient phenotype for predicting impingement. This international, multicentre prospective cohort study across two centres encompassed 157 adults undergoing primary robotic arm-assisted THA. Impingement during specific flexion and extension stances was identified using the virtual range of motion (ROM) tool of the robotic software. The primary AI model, the Light Gradient-Boosting Machine (LGBM), used tabular data to predict impingement presence, direction (flexion or extension), and type. A secondary model integrating tabular data with plain anteroposterior pelvis radiographs was evaluated to assess for any potential enhancement in prediction accuracy. We identified nine predictors from an analysis of baseline spinopelvic characteristics and surgical planning parameters. Using fivefold cross-validation, the LGBM achieved 70.2% impingement prediction accuracy. With impingement data, the LGBM estimated direction with 85% accuracy, while the support vector machine (SVM) determined impingement type with 72.9% accuracy. After integrating imaging data with a multilayer perceptron (tabular) and a convolutional neural network (radiograph), the LGBM's prediction was 68.1%. Both combined and LGBM-only had similar impingement direction prediction rates (around 84.5%). This study is a pioneering effort in leveraging AI for impingement prediction in THA, utilizing a comprehensive, real-world clinical dataset. Our machine-learning algorithm demonstrated promising accuracy in predicting impingement, its type, and direction. While the addition of imaging data to our deep-learning algorithm did not boost accuracy, the potential for refined annotations, such as landmark markings, offers avenues for future enhancement. Prior to clinical integration, external validation and larger-scale testing of this algorithm are essential.

The Association Between the Development of Cam Morphology During Skeletal Growth in High-Impact Athletes and the Presence of Cartilage Loss and Labral Damage in Adulthood: A Prospective Cohort Study With a 12-Year Follow-up

Background: Cam morphology develops during skeletal growth, but its influence on cartilage and the labrum in high-impact athletes later in life is unknown. Purpose: To (1) explore the association between the presence and duration of cam morphology during adolescence and the cartilage and labral status 7 to 12 years later and (2) report the prevalence of cartilage loss and labral damage in a population of young male athletes (<32 years old) who played professional soccer during skeletal growth. Study Design: Cohort study (Prognosis); Level of evidence, 2. Methods: A total of 89 healthy male academy soccer players from the Dutch soccer club Feyenoord (aged 12-19 years) were included at baseline. At baseline and 2.5- and 5-year follow-ups, standardized supine anteroposterior pelvis and frog-leg lateral radiographs of each hip were obtained. At 12-year follow-up, magnetic resonance imaging of both hips was performed. Cam morphology was defined by a validated alpha angle ≥60° on radiographs at baseline or 2.5- or 5-year follow-up when the growth plates were closed. Hips with the presence of cam morphology at baseline or at 2.5-year follow-up were classified as having a “longer duration” of cam morphology. Hips with cam morphology only present since 5-year follow-up were classified as having a “shorter duration” of cam morphology. At 12-year follow-up, cartilage loss and labral abnormalities were assessed semiquantitatively. Associations were estimated using logistic regression, adjusted for age and body mass index. Results: Overall, 35 patients (70 hips) with a mean age of 28.0 ± 2.0 years and mean body mass index of 24.1 ± 1.8 participated at 12-year follow-up. Cam morphology was present in 56 of 70 hips (80%). The prevalence of cartilage loss was 52% in hips with cam morphology and 21% in hips without cam morphology (adjusted odds ratio, 4.52 [95% CI, 1.16-17.61]; P = .03). A labral abnormality was present in 77% of hips with cam morphology and in 64% of hips without cam morphology (adjusted odds ratio, 1.99 [95% CI, 0.59-6.73]; P = .27). The duration of cam morphology did not influence these associations. Conclusion: The development of cam morphology during skeletal growth was associated with future magnetic resonance imaging findings consistent with cartilage loss in young adults but not with labral abnormalities.

Generalized Joint Hypermobility Is Associated with Type-A Hip Dysplasia in Patients Undergoing Periacetabular Osteotomy.

Joint hypermobility may be associated with developmental dysplasia of the hip (DDH), but no definite conclusion has been reached. On the basis of long-term clinical observations, we hypothesized that joint hypermobility was associated with the occurrence, imaging findings, and clinical symptoms of DDH. We conducted a case-control study that included 175 Chinese Han patients between 13 and 45 years of age with Hartofilakidis type-A hip dysplasia. All of these patients underwent periacetabular osteotomy (PAO) between November 2021 and February 2023. An additional 76 individuals of comparable age and sex but without hip dysplasia were selected from the general population to serve as healthy controls. The Beighton 9-point scoring system was used to evaluate joint hypermobility, and a score of ≥4 was defined as generalized joint hypermobility. Standing anteroposterior pelvic radiographs were reviewed. For patients with DDH, the lateral center-edge angle, Tönnis angle, Sharp angle, lateralization of the femoral head, and patient-reported outcomes (iHOT-12, HHS, and WOMAC) were also collected to determine the radiographic severity or clinical symptoms of DDH. Patients with DDH had an elevated prevalence of generalized joint hypermobility compared with that in the healthy population (27% versus 12%; p = 0.009). Among patients with DDH, those with concomitant generalized joint hypermobility had lower lateral center-edge angles (3.55° versus 9.36°; p = 0.012), greater lateralization of the femoral head (13.78 versus 12.17 mm; p = 0.020), greater standardized lateralization of the femoral head (0.64 versus 0.54; p = 0.009), and lower iHOT-12 scores (35.22 versus 40.96; p = 0.009) than did those without concomitant generalized joint hypermobility. Further multivariable linear regression analysis revealed that higher Beighton scores and younger age were predictive of more severe hip dysplasia. However, the Beighton score was not found to be independently associated with patient-reported outcomes according to multivariable linear regression analysis. The prevalence of generalized joint hypermobility was greater in patients with DDH than in healthy controls. A higher degree of joint hypermobility was also correlated with more severe hip dysplasia. These results suggest that joint laxity, in addition to bone or cartilage factors, is an important factor related to DDH. Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Change in cup orientation from supine to standing posture: a prospective cohort study of 419 total hip arthroplasties.

Arthroplasty surgeons traditionally assess cup orientation after total hip arthroplasty (THA) on supine radiographs. Contemporary hip-spine analyses provide information on standing, functional cup orientation. This study aims to (i) characterize cup orientations when supine and standing; (ii) determine orientation differences between postures; and (iii) identify factors associated with magnitude of orientation differences. This is a 2-center, multi-surgeon, prospective, consecutive cohort study. 419 primary THAs were included (57% women; mean age: 64 years, standard deviation [SD] 11). All patients underwent supine and standing antero-posterior pelvic and lateral spinopelvic radiographs. Cup orientation and spinopelvic parameters were measured. Target cup orientation was defined as inclination/anteversion of 40°/20° ± 10°. A change in orientation (Δinclination/Δanteversion) between postures > 5° was defined as clinically significant. Variability was defined as 2 x SD. Inclination increased from 40° (supine) to 42° (standing) corresponding to a Δinclination of 2° (95% confidence interval [CI] 2-3). Anteversion increased from 25° (supine) to 30° (standing) corresponding to a Δanteversion of 5° (CI 5-6). When supine, 69% (CI 65-74) of THAs were within target, but only 44% (CI 39-49) were within target when standing, resulting in a further 26% (CI 21-30) being out of target when standing. From supine to standing, a clinically significant change in anteversion (> 5°) was seen in 47% (CI 42-52) of cases. Δanteversion was higher in women than in men (6°, CI 5-7 vs 5°, CI 4-5) corresponding to a difference of 1° (CI 1-2), which was dependent on tilt change, standing cup anteversion, age, and standing pelvic tilt. Cup inclination and version increase upon standing but significant variability exists due to patient factors.

Prevalence and Risk Factors for Stiffness Following Open Reduction for Developmental Dysplasia of the Hip.

Most prior investigations on adverse outcomes after open reduction (OR) for developmental dysplasia of the hip (DDH) have focused on avascular necrosis, redislocation, and residual dysplasia. To our knowledge, no previous study has investigated risk factors for stiffness, an underappreciated source of postoperative morbidity. The goals of this study were to define the entity more clearly and evaluate the prevalence and risk factors for arthrofibrosis after OR for DDH. A retrospective study was conducted, including all open hip reductions for DDH performed by a single surgeon from 2009 to 2022. Preoperative anteroposterior pelvic radiographs were used to calculate superior displacement, which was defined as the distance from the highest point of the proximal femoral metaphysis to the Hilgenreiner line, normalized by pelvic width. Cases treated with premature postoperative bracing cessation and/or referral to physical therapy with a resolution of stiffness within 6 months were categorized as mild arthrofibrosis. Cases that required >6 months of formal physical therapy for persistent range of motion concerns, manipulation under anesthesia, and/or inpatient rehabilitation admission were categorized as significant arthrofibrosis. This study included 170 hips with a mean age of 21.6 months (range: 6.1 to 93.6mo) and a mean follow-up of 46.8 months. 156 ORs (91.8%) were done through an anterior approach. Sixty-four patients (37.6%) had a concomitant isolated pelvic osteotomy, and 34 (20.0%) had both pelvic and femoral osteotomies. During the postoperative course, 109 patients (64.1%) had no arthrofibrosis, 38 (22.4%) had mild stiffness, and 23 (13.5%) had significant arthrofibrosis. On multivariable analysis, older age, superior displacement, and concomitant pelvic osteotomy were associated with any degree of arthrofibrosis ( P < 0.05). Children older than 18 months or with dislocations higher than 16% of pelvic width had a 4.7 and 2.7 times higher risk, respectively, of experiencing some degree of stiffness postoperatively. Older age, high dislocations, and concomitant pelvic osteotomy without femoral shortening are risk factors for stiffness after OR for DDH. Surgeons should counsel families about the risk of postoperative stiffness, which occurred to some degree in 36% of our patients. Level IV.

Assessment of Pelvic Tilt in Anteroposterior Radiographs by Area Ratio Based on Deep Learning.

Diagnostics. Based on deep learning semantic segmentation model, we sought to assess pelvic tilt by area ratio of the lesser pelvic and the obturator foramen in anteroposterior (AP) radiographs. Pelvic tilt is a critical factor in hip and spinal surgery, commonly evaluated by medical professionals through sagittal pelvic radiographs. The inherent pelvic asymmetry, as well as potential obstructions from clothing and musculature in roentgenography, may result in ghosting and blurring artifacts, thereby complicating precise measurement. PT directly affects the area ratio of the lesser pelvis to the obturator foramen in AP radiographs. An exponential regression analysis of simulated radiographs from ten male and ten female pelvises in specific tilt positions derived a formula correlating this area ratio with PT. Two blinded investigators evaluated this formula using 161 simulated AP pelvic radiographs. A deep learning semantic segmentation model was then fine-tuned to automatically calculate the area ratio, enabling intelligent PT evaluation. This model and the regression function were integrated for automated PT measurement and tested on a dataset of 231 clinical cases. We observed no disparity between men and women in the aforementioned area ratio. The test results from two blinded investigators analyzing 161 simulated radiographs revealed a mean absolute error of 0.19° (SD ±4.71°), with a correlation coefficient between them reaching 0.96. In addition, the mean absolute error obtained from testing 231 clinical AP radiographs using the fine-tuned semantic segmentation model mentioned earlier is -0.58° (SD ±5.97°). We found that using deep learning neural networks enabled a more accurate and robust automatic measurement of PT through the area ratio of the lesser pelvis and obturator foramen.

Impact of Offset and Leg Length on Functional Outcomes Post-Total Hip Arthroplasty: How Accurate Should Coronal Reconstruction Be?

BackgroundAccurate hip reconstruction is associated with improved biomechanical behavior following total hip arthroplasty (THA). However, whether this is associated with improved patient-reported outcomes (PROs) is unknown. Hypothesis/PurposeThis study aimed to: 1) describe the ability to reconstruct coronal geometry during THA without advanced technology; 2) assess whether restoration of global offset (GO) and leg length (LL) is associated with improved PROs; and 3) investigate whether increased femoral offset (FO) to compensate for reduced acetabular offset (AO) influences PROs. MethodThis was a prospective, multicenter, consecutive cohort study of 500 patients treated with primary THA without robotics or navigation. The Oxford Hip score (OHS) was obtained preoperatively and at 1-year follow-up. Supine anteroposterior pelvic radiographs were analyzed to determine AO, FO, GO, and LL relative to the native contralateral side. Contour plots for ΔOHS based on ΔLL and ΔGO were created, and ΔOHS was calculated within and outside various ranges (±2.5, ±5, or ±10 mm). ResultsIn the operated hip, mean FO increased by 3 ± 6 mm (range, −16 to 27), while AO decreased by 2 ± 4 mm (range, −17 to 10). The contour graph for ±2.5 mm zones showed the best outcomes (ΔOHS >25) with GO and LL centered on 0 ± 2.5 mm (P < .01). However, only 10% achieved such reconstruction. When GO and LL differences were within ±10 mm, ΔOHS was superior when both AO and FO were within ±5 mm (mean: 24 ± 10; range, −5 to 40) compared with when FO was above 5 mm to compensate for a reduction in AO (mean: 22 ± 11; range, −10 to 46; P = .040). ConclusionsThe PROs were associated with biomechanical reconstruction, and the best clinical improvement can be expected when GO and LL differences are both within 2.5 mm. Maintenance of AO is important, as compensation by increasing FO is associated with inferior OHS.

Decreasing Hip Offset in Total Hip Arthroplasty Results in Decreased Physical Function Scores

BackgroundAcetabular and femoral offset play an important role in total hip arthroplasty (THA) for postoperative stability and biomechanical function. However, it is unknown whether offset impacts patient-reported outcomes (PROs). This study evaluated patients undergoing direct anterior (DA) THA with the hypothesis that patients who have a decrease in hip offset postoperatively would have lower physical function scores and higher pain interference. MethodsThere were 499 patients who underwent DA THA at a single tertiary academic institution who were retrospectively evaluated. Preoperative and postoperative hip offset was measured by 2 reviewers using the Sundsvall method on standing anteroposterior pelvis radiographs. Postoperative changes in hip offset were categorized as increased (> 5 mm), matched (within 5 mm of the preoperative offset measurement), or decreased ( >5 mm). Postoperative PROs with a minimum 1-year follow-up were recorded. A one-way analysis of variance was utilized to compare postoperative pain and PROs between groups. ResultsPatients who had decreased offset had the lowest mean postoperative physical function scores at 39.4 (8.0), followed by the increased offset group at 42.2 (10.4) and the matched offset group at 42.8 (9.8) (P < .01). There were significant differences in postoperative physical function scores between matched offset (42.8) and decreased offset (39.4) groups (P < .01), as well as between increased offset (42.2) and decreased offset (39.4) groups (P = .04). There was no difference between matched and increased offset cohorts. ConclusionsOur data suggests that reducing hip offset may result in worse physical function scores compared to those who have matched or increased hip offset. This should be considered intraoperatively, and efforts should be made to avoid reduced offset even in the presence of hip stability.

Surgeon's Experience and Accuracy of Preoperative Digital Templating in Primary Total Hip Arthroplasty.

Preoperative planning has become essential in performance of total hip arthroplasty (THA). However, data regarding the effect of the planner's experience on the accuracy of digital preoperative planning is limited. The objective of this study was to assess the accuracy of digital templating in THA based on the surgeon's experience. A retrospective study was conducted. An analysis of 98 anteroposterior pelvic radiographs, which were individually templated by four surgeons (two hip surgeons and two orthopaedic residents) using TraumaCad® digital planning, was performed. A comparison of preoperatively planned sizes with implanted sizes was performed to evaluate the accuracy of predicting component size. The results of preoperative planning performed by hip surgeons and orthopaedic residents were compared for testing of the planner's experience. Femoral stem was precisely predicted in 32.4% of cases, acetabular component in 40.3%, and femoral offset in 76.7%. Prediction of cup size showed greater accuracy than femoral size among all observers. No differences in any variable were observed among the four groups (acetabular cup P=0.07, femoral stem P=0.82, femoral offset P=0.06). All measurements showed good reliability (intraclass correlation coefficient [ICC] acetabular cup: 0.76, ICC femoral stem: 0.79). The results of this study might suggest that even though a surgeon's experience supports improved precision during the planning stage, it should not be restricted only to surgeons with a high level of experience. We consider preoperative planning an essential part of the surgery, which should be included in training for orthopaedics residents.

Morphological features of the acetabulum with coxa profunda in women: a retrospective observational study

BackgroundThe morphology of coxa profunda remains inadequately understood. However, knowledge about the characteristics of the acetabulum in coxa profunda can help to predict pelvic morphology in three dimensions based on radiographic findings, as well as help to diagnose and predict hip pathologies. Therefore, this study aimed to investigate the relationship between the morphological characteristics of the pelvis and coxa profunda.MethodsWe conducted a retrospective analysis including women who had undergone unilateral total hip arthroplasty. Only those with normal hip joint morphology on the opposite side, as evidenced by anteroposterior pelvic radiography showing a distance of ≥ 2 mm between the ilioischial line and acetabular floor, were included. Five parameters related to acetabular anteversion, thickness, and the position of the ilioischial line were measured using axial computed tomography at the central hip joint. The coxa profunda group (n = 39) and control group (n = 34) were compared.ResultsThe mean acetabular anteversion angle was 12.5° ± 4° in the control group and 22.3° ± 5.6° in the coxa profunda group. The mean thickness from the acetabular fossa to the medial wall was 7.5 ± 1.7 mm in the control group and 3.9 ± 1.2 mm in the coxa profunda group. Furthermore, the bony region representing the ilioischial line was positioned more posteriorly in the coxa profunda group than it was in the control group.ConclusionOur findings suggest that coxa profunda in women is associated with anterior acetabular dysplasia and a thin acetabulum, in contrast to previous interpretations of excessive coverage. This insight suggests a conversion of coxa profunda from a finding of pincer-type femoroacetabular impingement to a finding of acetabular dysplasia, a revelation that also draws attention to cup positioning for total hip arthroplasty.

Application of deep learning algorithms in classification and localization of implant cutout for the postoperative hip.

This study aims to explore the feasibility of employing convolutional neural networks for detecting and localizing implant cutouts on anteroposterior pelvic radiographs. The research involves the development of two Deep Learning models. Initially, a model was created for image-level classification of implant cutouts using 40191 pelvic radiographs obtained from a single institution. The radiographs were partitioned into training, validation, and hold-out test datasets in a 6/2/2 ratio. Performance metrics including the area under the receiver operator characteristics curve (AUROC), sensitivity, and specificity were calculated using the test dataset. Additionally, a second object detection model was trained to localize implant cutouts within the same dataset. Bounding box visualizations were generated on images predicted as cutout-positive by the classification model in the test dataset, serving as an adjunct for assessing algorithm validity. The classification model had an accuracy of 99.7%, sensitivity of 84.6%, specificity of 99.8%, AUROC of 0.998 (95% CI: 0.996, 0.999) and AUPRC of 0.774 (95% CI: 0.646, 0.880). From the pelvic radiographs predicted as cutout-positive, the object detection model could achieve 95.5% localization accuracy on true positive images, but falsely generated 14 results from the 15 false-positive predictions. The classification model showed fair accuracy for detection of implant cutouts, while the object detection model effectively localized cutout. This serves as proof of concept of using a deep learning-based approach for classification and localization of implant cutouts from pelvic radiographs.

Minimum 10-Year Survivorship of Uncemented Acetabular Reconstruction With Bulk Femoral Head Autografting in Crowe Type IV Developmental Hip Dysplasia

BackgroundIn total hip arthroplasty (THA) for severe dislocations such as Crowe type IV developmental dysplasia of the hip (DDH), sufficient bone volume for stable fixation of the acetabular component can be achieved by placing a reinforcing bone graft prepared from the resected femoral head into the deficient acetabulum. The purpose of the current study was to examine the long-term survivorship of uncemented THA in conjunction with a bulk femoral head autograft in patients who have Crowe type IV DDH. MethodsA total of 35 patients (42 hips) who have Crowe type IV DDH and underwent THA using uncemented cup fixation with bulk femoral head autografting were followed up for a mean period of 15.0 years (range, 10.0 to 20.0) postoperatively. Anteroposterior pelvic radiographs were used for measurements such as the horizontal coverage of the grafted bone and the center-edge angle. Kaplan–Meier survivorship analyses were performed with revision of the acetabular component as the endpoint. ResultsThe Kaplan–Meier analysis indicated 15-year survival rates of 90.4%. The mean horizontal coverage of grafted bone was 46.1% (range, 23.7 to 66.0), and there were 16 cases with horizontal coverage of ≥ 50%. There was no difference in the appearance of a thin (< 1 mm) radiolucency line around the cup between cases with < 50% versus ≥ 50% of the horizontal coverage of grafted bone (4 versus 2 hips; P = .446). Trabecular bridging and remodeling were seen in all cases after mean periods of 4.1 and 9.0 months postoperatively, respectively. Trabecular reorientation was seen in 41 of 42 hips (97.6%) at a mean follow-up of 19.9 months. ConclusionsAcetabular reconstruction with femoral bulk bone grafting for Crowe type IV DDH resulted in high survival rates and was a good method to restore bone stock and obtain long-term fixation.