Segond Fractures Can Be Identified With Excellent Accuracy Utilizing Deep Learning on Anteroposterior Knee Radiographs
Ontology highlight
ABSTRACT:
SUBMITTER: Oeding J
PROVIDER: S-EPMC11240019 | biostudies-literature | 2024 Apr
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeTo investigate the relationship between the Segond fracture and the anterolateral complex of the knee.MethodsBetween January 2014 and March 2020, patients who presented with an anterior cruciate ligament (ACL) tear requiring acute surgical reconstruction (within 10 days from trauma) were evaluated for inclusion in this study. Patients were included if they had an acute ACL tear with an associated Segond fracture (or "Segond lesion") as detected by radiograph or magnetic resonance imaging. The lateral compartment was exposed in all cases using a 5-cm lateral hockey-stick incision, which was carried down to the iliotibial band. The fascia lata was first inspected and then longitudinally divided along its fibers to expose lateral compartment. The posterolateral corner to Gerdy's tubercle anteriorly was exposed and examined. Once the Segond fracture was identified, it was recorded and photographed.ResultsSeventeen patients were enrolled in the study. Dissection of the Segond fracture demonstrated attachment to the anterolateral capsule only. No other discernible attachment to the Segond fracture was noted. Surgical exploration of the anterolateral knee did not reveal injury to the iliotibial band.ConclusionsCareful dissection of Segond fractures during repair revealed that there is a discernible attachment with the anterolateral capsule to the bone injury in all patients with acute ACL tears undergoing surgical reconstruction and no connections to the iliotibial band.Clinical relevanceThe precise pathogenesis of Segond fractures has been the subject of debate, partially due to the complexity of the anatomy of the anterolateral aspect of the knee. Proper understanding of the anatomy of type IV ALL injures with Segond fractures is important to improve treatment of these injuries.
| S-EPMC8220572 | biostudies-literature
Project description: Not available
| S-EPMC10784052 | biostudies-literature
Project description:BackgroundMorphological parameters of the lumbar spine are valuable in assessing lumbar spine diseases. However, manual measurement of lumbar morphological parameters is time-consuming. Deep learning has automatic quantitative and qualitative analysis capabilities. To develop a deep learning-based model for the automatic quantitative measurement of morphological parameters from anteroposterior digital radiographs of the lumbar spine and to evaluate its performance.MethodsThis study used 1,368 anteroposterior digital radiographs of the lumbar spine to train a deep learning model to measure the quantitative morphological indicators, including L1 to L5 vertebral body height (VBH) and L1-L2 to L4-L5 intervertebral disc height (IDH). The means of the manual measurements by three radiologists were used as the reference standard. The parameters predicted by the model were analyzed against the manual measurements using paired t-tests. Percentage of correct key points (PCK), intra-class correlation coefficient (ICC), Pearson correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), and Bland-Altman plots were performed to assess the performance of the model.ResultsWithin the 3-mm distance threshold, the model had a PCK range of 99.77-99.46% for the L1 to L4 vertebrae and 77.37% for the L5 vertebrae. Except for VBH-L5 and IDH_L3-L4, IDH_L4-L5 (P<0.05), the estimated values of the model in the remaining parameters were not statistically significant compared with the reference standard (P>0.05). Except for VBH-L5 and IDH_L4-L5, the model showed good correlation and consistency with the reference standard (ICC =0.84-0.96, r=0.85-0.97, MAE =0.5-0.66, RMSE =0.66-0.95). The model outperformed other models (EfficientDet + Unet, EfficientDet + DarkPose, HRNet, and Unet) in predicting landmarks within a distance threshold of 1.5 to 5 mm.ConclusionsThe model developed in this study can automatically measure the morphological parameters of the L1 to L4 vertebrae from anteroposterior digital radiographs of the lumbar spine. Its performance is close to the level of radiologists.
| S-EPMC11320550 | biostudies-literature
Project description:PurposeThe purpose of this study was to determine the rates of concomitant knee pathology in patients with ACL injuries and Segond fractures.MethodsA retrospective study is undertaken with patients identified via query of CPT codes for ACL reconstruction from 2014 to 2020. All patients with preoperative radiographs were reviewed for the presence of Segond fractures. Operative reports were analyzed for the presence of concurrent pathology, including meniscus, cartilage, and other ligamentous injuries at the time of arthroscopic ACL reconstruction.ResultsA total of 1,058 patients were included in the study. Segond fractures were identified in 50 (4.7%) patients. Ipsilateral concomitant knee pathology was identified in 84% of Segond patients. Thirty-eight (76%) patients had meniscal pathology with a total 49 meniscal injuries, of which 43 were treated operatively. Multiligamentous injuries were present in 16 patients (32%), with 8 patients undergoing further ligament repair/reconstruction at the time of surgery. Chondral injuries were identified in 13 patients (26%).ConclusionsA high prevalence of concomitant meniscal, chondral, and ligamentous injuries was found in patients with Segond fractures. These additional injuries may require further operative management and may place patients at increased risk for future instability or degenerative changes. Patients with Segond fractures should be counseled preoperatively on the nature of their injuries and risk of associated pathologies.Level of evidenceLevel IV, prognostic case series.
| S-EPMC10123414 | biostudies-literature
Project description:PurposeDetermining the magnitude of displacement in pediatric lateral humeral condyle fractures can be difficult. The purpose of this study was to (1) assess the effect of forearm rotation on true fracture displacement using a cadaver model and to (2) determine the accuracy of radiographic measurements of the fracture gap.MethodsA non-displaced fracture was created in three human cadaveric arms. The specimens were mounted on a custom apparatus allowing forearm rotation with the humerus fixed. First, the effect of pure rotation on fracture displacement was simulated by rotating the forearm from supination to pronation about the central axis of the forearm, to isolate the effects of muscle pull. Then, the clinical condition of obtaining a lateral oblique radiograph was simulated by rotating the forearm about the medial aspect of the forearm. Fracture displacements were measured using a motion-capture system (true-displacement) and clinical radiographs (apparent-displacement).ResultsDuring pure rotation of the forearm, there were no significant differences in fracture displacement between supination and pronation, with changes in displacement of <1.0 mm. During rotation about the medial aspect of the forearm, there was a significant difference in true displacements between supination and pronation at the posterior edge (p < 0.05).ConclusionOverall, true fracture displacement measurements were larger than apparent radiographic displacement measurements, with differences from 1.6 to 6.0 mm, suggesting that the current clinical methods may not be sensitive enough to detect a displacement of 2.0 mm, especially when positioning the upper extremity for an internal oblique lateral radiograph.
| S-EPMC3935020 | biostudies-literature
Project description:ObjectiveTo develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children.Materials and methodsThis retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs).ResultsThe AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850).ConclusionA deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.
| S-EPMC8876653 | biostudies-literature
Project description:An important quality criterion for radiographs is the correct anatomical side marking. A deep neural network is evaluated to predict the correct anatomical side in radiographs of the knee acquired in anterior-posterior direction. In this retrospective study, a ResNet-34 network was trained on 2892 radiographs from 2540 patients to predict the anatomical side of knees in radiographs. The network was evaluated in an internal validation cohort of 932 radiographs of 816 patients and in an external validation cohort of 490 radiographs from 462 patients. The network showed an accuracy of 99.8% and 99.9% on the internal and external validation cohort, respectively, which is comparable to the accuracy of radiographers. Anatomical side in radiographs of the knee in anterior-posterior direction can be deduced from radiographs with high accuracy using deep learning.
| S-EPMC8900105 | biostudies-literature
Project description:UNLABELLED: Neutral pelvic positioning during recording of anteroposterior pelvic radiographs has been recommended for precise interpretation of acetabular deformities. Because the effect of pelvic positioning is controversial in the literature, we asked whether the weightbearing position would alter radiographic interpretations. We obtained sets of supine and weightbearing anteroposterior pelvic radiographs of 31 patients with developmental dysplasia of the hip and measured pelvic tilt, acetabular version, center edge angle, acetabular index, joint space width and femoral head translation. For both genders the pelvis extended when patients were repositioned from supine to weightbearing but extension was more pronounced in women compared with men. The number of patients with apparent acetabular retroversion was reduced from 11 supine to four when weightbearing. The center edge angle, acetabular index, joint space width and femoral head translation were similar in both views. We recommend weightbearing anteroposterior pelvic radiographs be obtained to assess DDH given the differences in pelvic flexion-extension and interpretations of acetabular version. LEVEL OF EVIDENCE: Level III, diagnostic study. See the Guidelines for Authors for a complete description of levels of evidence.
| S-EPMC2504653 | biostudies-other
Project description:ObjectivesAge estimation, especially in pediatric patients, is regularly used in different contexts ranging from forensic over medicolegal to clinical applications. A deep neural network has been developed to automatically estimate chronological age from knee radiographs in pediatric patients.MethodsIn this retrospective study, 3816 radiographs of the knee from pediatric patients from a German population (acquired between January 2008 and December 2018) were collected to train a neural network. The network was trained to predict chronological age from the knee radiographs and was evaluated on an independent validation cohort of 423 radiographs (acquired between January 2019 and December 2020) and on an external validation cohort of 197 radiographs.ResultsThe model showed a mean absolute error of 0.86 ± 0.72 years and 0.9 ± 0.71 years on the internal and external validation cohorts, respectively. Separating age classes (< 14 years from ≥ 14 years and < 18 years from ≥ 18 years) showed AUCs between 0.94 and 0.98.ConclusionsThe chronological age of pediatric patients can be estimated with good accuracy from radiographs of the knee using a deep neural network.Key points• Radiographs of the knee can be used for age estimations in pediatric patients using a standard deep neural network. • The network showed a mean absolute error of 0.86 ± 0.72 years in an internal validation cohort and of 0.9 ± 0.71 years in an external validation cohort. • The network can be used to separate the age classes < 14 years from ≥ 14 years with an AUC of 0.97 and < 18 years from ≥ 18 years with an AUC of 0.94.
| S-EPMC9213267 | biostudies-literature
Project description:Knee osteoarthritis (OA) is the most common musculoskeletal disorder. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process suffers from subjectivity. In this study, we present a new transparent computer-aided diagnosis method based on the Deep Siamese Convolutional Neural Network to automatically score knee OA severity according to the Kellgren-Lawrence grading scale. We trained our method using the data solely from the Multicenter Osteoarthritis Study and validated it on randomly selected 3,000 subjects (5,960 knees) from Osteoarthritis Initiative dataset. Our method yielded a quadratic Kappa coefficient of 0.83 and average multiclass accuracy of 66.71% compared to the annotations given by a committee of clinical experts. Here, we also report a radiological OA diagnosis area under the ROC curve of 0.93. Besides this, we present attention maps highlighting the radiological features affecting the network decision. Such information makes the decision process transparent for the practitioner, which builds better trust toward automatic methods. We believe that our model is useful for clinical decision making and for OA research; therefore, we openly release our training codes and the data set created in this study.
| S-EPMC5789045 | biostudies-literature