Deep learning for osteoporosis screening using an anteroposterior hip radiograph image.

PURPOSE: Osteoporosis is a common bone disorder characterized by decreased bone mineral density (BMD) and increased bone fragility, which can lead to fractures and eventually cause morbidity and mortality. It is of great concern that the one-year mortality rate for osteoporotic hip fractures could be as high as 22%, regardless of the treatment. Currently, BMD measurement is the standard method for osteoporosis diagnosis, but it is costly and requires special equipment. While a plain radiograph can be obtained more simply and inexpensively, it is not used for diagnosis. Deep learning technologies had been applied to various medical contexts, yet few to osteoporosis unless they were trained on the advanced investigative images, such as computed tomography. The purpose of this study was to develop a deep learning model using the anteroposterior hip radiograph images and measure its diagnostic accuracy for osteoporosis. METHODS: We retrospectively collected all anteroposterior hip radiograph images of patients from 2013 to 2021 at a tertiary care hospital. The BMD measurements of the included patients were reviewed, and the radiograph images that had a time interval of more than two years from the measurements were excluded. All images were randomized using a computer-generated unequal allocation into two datasets, i.e., 80% of images were used for the training dataset and the remaining 20% for the test dataset. The T score of BMD obtained from the ipsilateral femoral neck of the same patient closest to the date of the performed radiograph was chosen. The T score cutoff value of - 2.5 was used to diagnose osteoporosis. Five deep learning models were trained on the training dataset, and their diagnostic performances were evaluated using the test dataset. Finally, the best model was determined by the area under the curves (AUC). RESULTS: A total of 363 anteroposterior hip radiograph images were identified. The average time interval between the performed radiograph and the BMD measurement was 6.6 months. Two-hundred-thirteen images were labeled as non-osteoporosis (T score > - 2.5), and the other 150 images as osteoporosis (T score ≤ - 2.5). The best-selected deep learning model achieved an AUC of 0.91 and accuracy of 0.82. CONCLUSIONS: This study demonstrates the potential of deep learning for osteoporosis screening using anteroposterior hip radiographs. The results suggest that the deep learning model might potentially be used as a screening tool to find patients at risk for osteoporosis to perform further BMD measurement.

Biomechanical impact of meniscal ramp lesions on knee joint contact characteristics in ACL deficient knees: a cadaveric analysis.

PURPOSE: To evaluate the changes in contact characteristics of the tibiofemoral joint resulting from a meniscal ramp lesion in the medial meniscus. METHODS: Twelve cadaveric knees (six matched pairs) were subjected to a 600 N axial load using a custom testing jig, which allowed for knee positioning at 0°, 45°, and 90° of flexion without other constraints. The knees were randomly assigned to either a ramp lesion group (n = 6) or a posterior root lesion group (n = 6). Four testing conditions were examined: (1) intact, (2) isolated ramp lesion, (3) isolated posterior root tear of the medial meniscus, and (4) combined ramp lesion and posterior root tear of the medial meniscus. Contact characteristics were evaluated using a flexible pressure sensor, the I-Scan System. RESULTS: Peak contact pressure in isolated ramp lesions (4.15 ± 0.98 MPa, P = 0.206) showed non-significant increases compared to the intact condition (3.86 ± 1.32 MPa). Peak contact pressure in isolated posterior root tears (4.58 ± 1.70 MPa, P = 0.040) and, combined ramp and posterior root lesions (4.67 ± 1.47 MPa, P = 0.003) were significantly higher than that in the intact condition. The knee flexion position significantly affected the medial tibiofemoral joint's contact area, contact pressure, and peak contact pressure (P < 0.001 for all). CONCLUSION: Isolated ramp lesions did not significantly impact force transmission, contact area, or contact pressure. In contrast, isolated root lesions and combined ramp and posterior root tears of the medial meniscus significantly intensified the changes in contact characteristics in the medial tibiofemoral joint compared to the intact condition. LEVEL OF EVIDENCE: Level III.

Comparison of medial tibiofemoral joint mechanics between all-suture anchors and transtibial pullout technique for posterior medial meniscal root tears.

BACKGROUND: The posterior medial meniscal root tear (PMMRT) seriously impacts the tibiofemoral joint biomechanics. Two available techniques for PMMRT repair include the transtibial pullout (TPO) repair and all-suture anchor (ASA) repair techniques. These techniques have not been compared biomechanically. METHODS: A total of 20 fresh porcine cadaveric knee specimens were used. All 20 knees were randomly and evenly distributed into four groups (five specimens per group): (1) intact posterior meniscal root, (2) PMMRT, (3) TPO repair technique for PMMRT, and (4) ASA repair technique for PMMRT. The tibiofemoral contact mechanics were investigated using a pressure sensor. All knee specimens were tested by being loaded with 600 N axial compressive force at three different flexion angles (0°, 45°, and 90°). The contact surface area, contact pressure, peak pressure, and time-zero displacement were recorded. RESULTS: The PMMRT caused a significant decrease in contact surface area, an increase in contact pressure, and peak pressure from the reference values observed in the intact meniscus group (P = 0.05, 0.016, and 0.008, respectively). After fixation, no significant difference was observed between the ASA and intact group. Meanwhile, significant differences were found between the TPO and intact group in terms of contact surface area, contact pressure, and peak pressure. In the comparison between the two techniques, the ASA group demonstrated higher contact surface area than the TPO group at the average knee flexion angle (p = 0.05). CONCLUSION: For most testing conditions, the ASA technique demonstrated superior biomechanical property in terms of contact surface area compared with the TPO technique under compressive loading conditions. The ASA technique could also restore the tibiofemoral contact mechanics to be comparable with those of the native intact knee. Meanwhile, a significant difference in tibiofemoral mechanics, compared with the intact knee, could be observed in the TPO technique.

A Mid-Scapular Portal for Arthroscopic-Assisted Fixation of Severe Retraction Greater Tuberosity Avulsion Fracture.

Chronic displaced greater tuberosity avulsion fracture of the humerus causes severe retraction of the rotator cuff and resorption of the avulsion fragment. Many treatment options can be considered to solve this problem and return the patient to function. The arthroscopic technique is very challenging to achieve a reduction of the rotator cuff and fixation of greater tuberosity with minimized soft-tissue damage. This Technical Note describes a portal for arthroscopic-assisted reduction and fixation in severe retracted greater tuberosity avulsion fracture. The technique is easy to release and fix chronic displaced greater tuberosity and could avoid unnecessary open surgery.

Artificial intelligence (AI) vs. human in hip fracture detection.

Objective: This study aimed to assess the diagnostic accuracy and sensitivity of a YOLOv4-tiny AI model for detecting and classifying hip fractures types. Materials and methods: In this retrospective study, a dataset of 1000 hip and pelvic radiographs was divided into a training set consisting of 450 fracture and 450 normal images (900 images total) and a testing set consisting of 50 fracture and 50 normal images (100 images total). The training set images were each manually augmented with a bounding box drawn around each hip, and each bounding box was manually labeled either (1) normal, (2) femoral neck fracture, (3) intertrochanteric fracture, or (4) subtrochanteric fracture. Next, a deep convolutional neural network YOLOv4-tiny AI model was trained using the augmented training set images, and then model performance was evaluated with the testing set images. Human doctors then evaluated the same testing set images, and the performances of the model and doctors were compared. The testing set contained no crossover data. Results: The resulting output images revealed that the AI model produced bounding boxes around each hip region and classified the fracture and normal hip regions with a sensitivity of 96.2%, specificity of 94.6%, and an accuracy of 95%. The human doctors performed with a sensitivity ranging from 69.2 to 96.2%. Compared with human doctors, the detection rate sensitivity of the model was significantly better than a general practitioner and first-year residents and equivalent to specialist doctors. Conclusions: This model showed hip fracture detection sensitivity comparable to well-trained radiologists and orthopedists and classified hip fractures highly accurately.

Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs.

Background: Traumatic spinal cord injury (TSI) is a leading cause of morbidity and mortality worldwide, with the cervical spine being the most affected. Delayed diagnosis carries a risk of morbidity and mortality. However, cervical spine CT scans are time-consuming, costly, and not always available in general care. In this study, deep learning was used to assess and improve the detection of cervical spine injuries on lateral radiographs, the most widely used screening method to help physicians triage patients quickly and avoid unnecessary CT scans. Materials and methods: Lateral neck or lateral cervical spine radiographs were obtained for patients who underwent CT scan of cervical spine. Ground truth was determined based on CT reports. CiRA CORE, a codeless deep learning program, was used as a training and testing platform. YOLO network models, including V2, V3, and V4, were trained to detect cervical spine injury. The diagnostic accuracy, sensitivity, and specificity of the model were calculated. Results: A total of 229 radiographs (129 negative and 100 positive) were selected for inclusion in our study from a list of 625 patients with cervical spine CT scans, 181 (28.9%) of whom had cervical spine injury. The YOLO V4 model performed better than the V2 or V3 (AUC = 0.743), with sensitivity, specificity, and accuracy of 80%, 72% and 75% respectively. Conclusion: Deep learning can improve the accuracy of lateral c-spine or neck radiographs. We anticipate that this will assist clinicians in quickly triaging patients and help to minimize the number of unnecessary CT scans.

The Turtle Neck Sign: Identification of Severe Retracted Distal Biceps Tendon Rupture.

BACKGROUND: Chronic tendon retraction subsequent to distal biceps tendon rupture significantly increases repair difficulty and potential for tendon grafting. Biceps tendons that appear short or absent with magnetic resonance imaging (MRI) or that cannot be readily identified at surgery may erroneously be classified as irreparable. These apparent "absent" biceps tendons may actually be retracted and curled up inside the muscle, visually resembling the head-neck of a turtle retracted inside its shell (the "turtle neck sign"). When located, these tendons could be unfolded and repaired primarily. This type of tendon retraction seems to be associated with high-degree ruptures and larcertus fibrosus tears. PURPOSE: To test the hypothesis that tendon retractions with a turtle neck sign on MRI are more associated with high-degree ruptures and larcertus fibrosus tears versus tendon tears with simple linear retraction. STUDY DESIGN: Cross-sectional study; Level of evidence, 3. METHODS: Retracted distal biceps tendon ruptures on sagittal MRI were categorized as linear retraction or curled-up (turtle neck) retraction. Retraction length, injury severity, and lacertus fibrosus tears were analyzed. RESULTS: The authors retrospectively analyzed the patient records of 85 consecutive traumatic distal biceps tendon ruptures from 2003 to 2019; the final study cohort was 37 patients. Injury-to-surgery timing was as follows: <3 weeks, 43% (16 cases); 3 weeks to 3 months, 32% (12 cases); and >3 months, 24% (9 cases). Overall, 19 patients had linear retraction <7 cm (mean, 3.3 ± 1.9 cm) and 18 patients had a turtle neck retraction ≥7 cm (mean, 9.1 ± 1.6 cm). The injury-to-surgery time (median [± interquartile range]) was 27 days (±90 days) in the linear retraction group and 23 days (±65 days) in the turtle neck retraction group. The turtle neck retraction group had a significantly higher occurrence of abnormal hook test findings, complete distal biceps tendon rupture, and lacertus fibrosus tears compared with the linear retraction group (100% vs 58%, 100% vs 68%, and 100% vs 37%, respectively; P ≤ .02). However, significant repairability differences were not found. CONCLUSION: Highly retracted distal biceps turtle neck sign tendon ruptures occur frequently in association with high-degree ruptures and lacertus fibrosus tears. The presence of a turtle neck retraction did not affect reparability. Surgeons should be aware of this curled-up retraction to avoid mistaking it for an absent tendon or a muscle-tendon disruption.

Abnormally Prolonged Bleeding After an Arthroscopic Knee Reconstruction Because of an Inherited Factor XIII Deficiency: A Case Report.

CASE: An 18-year-old man developed ecchymosis after arthroscopic anterior cruciate ligament reconstruction with semitendinosus graft and meniscal repair. The results of routine coagulation studies were normal, but factor assays showed a reduction in factor XIII levels. The bleeding symptoms were dramatically improved after administration of cryoprecipitate. CONCLUSION: Factor XIII deficiency is one of the rare clotting factor deficiencies that can be present at birth or be manifested later in life. Clinical awareness of factor XIII deficiency is essential so that appropriate testing and treatment can be achieved.

Preoperative Ultrasound Evaluation of the Semitendinosus Tendon for Anterior Cruciate Ligament Reconstruction.

BACKGROUND: Adequate graft size and length are crucial factors that correlate with improved outcomes after anterior cruciate ligament reconstruction with a semitendinosus (ST) tendon autograft alone. Anthropometric parameters could be used as predictors of graft measurements but they have shown imprecise correlation in some patients. PURPOSE: To evaluate the accuracy of ultrasound (US) for the preoperative evaluation of ST graft size and length. STUDY DESIGN: Cohort study (diagnosis); Level of evidence, 3. METHODS: A total of 40 patients were included in this study. Patient sex, age, anthropometric parameters, and preoperative US measurements were recorded. After the ST tendons were harvested, their lengths as well as the diameters of the 4-strand ST grafts were recorded. Correlations between patient US measurements were analyzed. Inadequate ST graft length was defined at <28 cm, and inadequate 4-strand ST graft diameter was defined at <8 mm. RESULTS: The prevalence of patients with an ST graft length <28 cm was 47.5%, and the prevalence of patients with a 4-strand ST graft diameter <8 mm was 42.5%. US measurements had a strong, significant correlation with the ST graft length (P < .001) and a moderate correlation with the 4-strand ST graft diameter (P < .001). Absolute agreement between the preoperative US measurement of ST graft length and the intraoperative ST graft length showed good reliability (ICC2,1 = 0.825). The cross-sectional area (CSA) of the ST tendon at the knee joint level by US showed a weak correlation (r = 0.207) with the 4-strand ST graft diameter (P = .200). A CSA of 16 mm2 measured by US could be used to predict a 4-strand ST graft diameter ≥8 mm, with a sensitivity of 73.9% and specificity of 76.5%. CONCLUSION: Preoperative US measurements of ST tendons had a strong correlation with intraoperative ST graft length and provided good sensitivity to detect a 4-strand ST graft diameter ≥8 mm. All other anthropometric parameters showed a weak to moderate correlation with ST graft length and size.

Anterior open-wedge hepta-lateral osteotomy for severe post-traumatic genu recurvatum: a case report and review of the literature.

Severe post-traumatic genu recurvatum is an uncommon condition in orthopedics. The typical symptoms are pain, weakness, and instability. For severe and symptomatic genu recurvatum patient, the surgical correction should be performed to relieve symptoms and prevent progression of deformity. Many procedures were proposed to treat this condition, but there are some complications such as patella baja, secondary deformity, skin complication, and inadequate correction. Most of the procedures need an additional procedure such as tibial tuberosity transfer to correct the patellar height. In this case, the authors report a new technique in which the osteotomy was performed near the center of rotation angulation. And, the correction did not influence the patellar height.

Tuberculous Distal Biceps Tendon Rupture: Case Report and Review of the Literature.

Tuberculous distal biceps tendon rupture is a rare condition in orthopedics. Musculoskeletal tuberculosis usually presents with bursitis, synovitis, myositis, and osteomyelitis, conditions which demonstrate an excellent response to antituberculosis chemotherapy. Tendon rupture is often associated with delayed diagnosis and treatment. We report a rare manifestation of musculoskeletal tuberculosis in the distal biceps tendon with delayed diagnosis.

Cadaveric study of the anatomical reference points for proximal humeral plate positioning.

BACKGROUND: Complications following locking plate fixation in proximal humeral fractures often related to malposition plates and inadequate screw fixation. However, literature did not define the best anatomical reference point for plate positioning. We conducted a study to assess the occurrence of subacromial impingement and screw perforation with two anatomical reference points for proximal humeral plate positioning. METHOD: Sixty shoulders of 30 cadavers were dissected, and proximal humeral locking plate was placed in two different levels in the coronal plane of the upper tip of plate: (1) the proximal portion of bicipital groove group and (2) the most prominent of lesser tuberosity group. Subacromial impingement during passive forward elevation and screw perforation were assessed in relation to the plate positioning. RESULTS: No subacromial impingement during passive motion contacted to the plate in both groups. The calcar screw perforation rate was significantly lower in the proximal portion of the bicipital groove group (2 of 60 specimens, 3.33%) than the most prominent of lesser tuberosity group (52 of 60 specimens, 86.67%). The most proximal screws of the plate were no humeral head perforation in all specimens. CONCLUSION: Our study would suggest that two anatomical reference points could be used to be the landmark to avoid the subacromial impingement and the most proximal screw perforation. However, the placement of the locking plate using the proximal portion of bicipital groove reference is better for calcar screw insertion.

Acromioclavicular joint dislocation: a Dog Bone button fixation alone versus Dog Bone button fixation augmented with acromioclavicular repair-a finite element analysis study.

BACKGROUND: Suspension suture button fixation was frequently used to treat acromioclavicular joint (ACJ) dislocation. However, there were many studies reporting about complications and residual horizontal instability after fixation. Our study compared the stability of ACJ after fixation between coracoclavicular (CC) fixation alone and CC fixation combined with ACJ repair by using finite element analysis (FEA). MATERIALS AND METHODS: A finite element model was created by using CT images from the normal shoulder. The model 1 was CC fixation with suture button alone, and the model 2 was CC fixation with suture button combined with ACJ repair. Three different forces (50, 100, 200 N) applied to the model in three planes; inferior, anterior and posterior direction load to the acromion. The von Mises stress of the implants and deformation at ACJs was recorded. RESULTS: The ACJ repair in the model 2 could reduce the peak stress on the implant after applying the loading forces to the acromion which the ACJ repair could reduce the peak stress of the FiberWire at suture button about 90% when compared to model 1. And, the ACJ repair could reduce the deformation of the ACJ after applying the loading forces to the acromion in both vertical and horizontal planes. CONCLUSION: This FEA supports that the high-grade injuries of the ACJ should be treated with CC fixation combined with ACJ repair because this technique provides excellent stability in both vertical and horizontal planes and reduces stress to the suture button.

Short-term outcomes of subacromial injection of combined corticosteroid with low-volume compared to high-volume local anesthetic for rotator cuff impingement syndrome: a randomized controlled non-inferiority trial.

BACKGROUND: In symptomatic tendinosis, a corticosteroid injection into the subacromial space is a palliative treatment option. This study compares high volumes (10 cc) of local anesthetic (LA) combined with triamcinolone acetate (TA) with low volumes (4 cc) of LA combined with TA to see whether the latter would provide similar pain, function and complication outcomes for subacromial injections in patients with impingement syndrome. MATERIALS AND METHODS: This single-center, randomized, single-blind, non-inferiority trial included patients with shoulder pain and positive multiple clinical tests supporting the diagnosis of impingement syndrome. All 52 patients received subacromial injections, with either high-volume corticosteroid injections (HCI) (10 mL total volume of 1% lidocaine plus 40 mg TA) in 26 patients or low-volume corticosteroid injections (LCI) (4 mL total volume of 1% lidocaine plus 40 mg TA) in 26 patients. The demographic data were reported with the primary outcomes being VAS and WORC scores measured at 30 min, then 2 and 8 weeks after receiving the injections. A non-inferiority margin of 13% was assumed. RESULTS: Fifty-two patients (26 patients per group) were enrolled in the HCI and LCI. Mean VAS and WORC scores of HCI and LCI at baseline were 6.96, 33.85, 6.81 and 36.54, respectively. The mean VAS measured at 30 min, 2 and 8 weeks was 4.04, 2.08 and 1.20, respectively, in HCI group and 2.65, 1.95 and 1.26, respectively, in LCI group. The mean WORC at 2 and 8 weeks was 67.46 and 81.74, respectively, in HCI group and 65.42 and 80.12 in LCI group. These were not statistically significantly different (P > 0.05 in all). CONCLUSION: Corticosteroid injections can be used in the treatment of subacromial impingement syndrome. Low-volume (4 cc) corticosteroid injections have non-inferior pain results for VAS score when compared with high-volume (10 cc) corticosteroid injections. CLINICALTRIALS.GOV: NCT03120923. LEVEL OF EVIDENCE: Level I.

Distal anastomosis patterns of the descending branch of the lateral circumflex femoral artery.

BACKGROUND: The reverse anterolateral thigh (ALT) flap has shown good results in the treatment of patients who have skin and soft tissue defects around the knee and shin. The objective of this study was to show the anastomotic patterns of the descending branch of lateral femoral circumflex artery (db-LCFA) and locate the appropriate pivot point for reverse ALT flap. MATERIALS AND METHODS: Fifty thighs from 25 embalmed cadavers from the Anatomy Department, Khon Kaen University in 2012, were dissected. The patterns of distal anastomoses of db-LCFA were recorded and appropriate pivot points for the reverse ALT flap were measured. RESULTS: Three patterns of distal anastomosis of the db-LCFA were identified, including the anastomoses to the superolateral genicular arteries (46%), anastomoses to the profunda femoral arteries (28%), and unidentified distal anastomoses (26%). The mean distance of the pivot point was 9.4 ± 3.7 cm from the lateral epicondyle. The mean pedicular length was 13.2 ± 5.4 cm (mean ± SD). Most cadavers, 76%, showed a single db-LCFA. In cases where there was more than one db-LCFA, the distal anastomoses were found to be originating from the most medial db-LCFA. CONCLUSION: The reverse ALT flap technique showed good results in the treatment of patients with skin and soft tissue defects around the knee and shin. Variations of the anastomoses and branching patterns of the db-LCFA may influence flap survival. Additional preoperative vascular evaluations would be helpful in defining the most compatible area from which to harvest the flap.

Superior Patellar Dislocation Misdiagnosed as Patellar Tendon Rupture: The Value of Ultrasonography.

Superior dislocation of the patella with intact patellar tendon is a rare condition. Most cases in literatures were diagnosed by clinical examination and plain radiography; however there are many cases that were misdiagnosed as patellar tendon rupture. In this case, we demonstrate the use of ultrasound for diagnosis of superior dislocation of the patella in the emergency department. We also include a literature review of similar cases and discuss the advantages of different types of imaging for diagnosis in this condition.