Two-Stage Deep Learning Model for Diagnosis of Lumbar Spondylolisthesis Based on Lateral X-Ray Images.

BACKGROUND: Diagnosing early lumbar spondylolisthesis is challenging for many doctors because of the lack of obvious symptoms. Using deep learning (DL) models to improve the accuracy of X-ray diagnoses can effectively reduce missed and misdiagnoses in clinical practice. This study aimed to use a two-stage deep learning model, the Res-SE-Net model with the YOLOv8 algorithm, to facilitate efficient and reliable diagnosis of early lumbar spondylolisthesis based on lateral X-ray image identification. METHODS: A total of 2424 lumbar lateral radiographs of patients treated in the Beijing Tongren Hospital between January 2021 and September 2023 were obtained. The data were labeled and mutually identified by 3 orthopedic surgeons after reshuffling in a random order and divided into a training set, validation set, and test set in a ratio of 7:2:1. We trained 2 models for automatic detection of spondylolisthesis. YOLOv8 model was used to detect the position of lumbar spondylolisthesis, and the Res-SE-Net classification method was designed to classify the clipped area and determine whether it was lumbar spondylolisthesis. The model performance was evaluated using a test set and an external dataset from Beijing Haidian Hospital. Finally, we compared model validation results with professional clinicians' evaluation. RESULTS: The model achieved promising results, with a high diagnostic accuracy of 92.3%, precision of 93.5%, and recall of 93.1% for spondylolisthesis detection on the test set, the area under the curve (AUC) value was 0.934. CONCLUSIONS: Our two-stage deep learning model provides doctors with a reference basis for the better diagnosis and treatment of early lumbar spondylolisthesis.

Distribution of bone tunnel positions and treatment efficacy of bone landmark positioning method for anatomical reconstruction of the anterior cruciate ligament: a case control study.

BACKGROUND: This study aimed to investigate the distribution of femoral tunnel and explore the influences of bone tunnel positions on knee functions. The bone landmark positioning method was used to position the femoral tunnel during the anatomical reconstruction surgery in patients with anterior cruciate ligament (ACL) rupture. METHODS: Data of patients who underwent anatomical reconstruction of the ACL between January 2015 and July 2018, were retrospectively analyzed. The distribution of the femoral tunnel was recorded on 3-D CT after surgery. The tunnel positions were classified into good and poor position groups based on whether the position was in the normal range (24-37% on the x-axis and 28-43% on the y-axis). The Lysholm and IKDC scores, KT-1000 side-to-side difference, pivot shift test and Lachman test results of the knee joints were recorded, and then the differences in knee joint functions between the two groups were analyzed. RESULTS: 84 eligible patients (84 knees) were finally included in this study. Twenty-two and 62 of the patients were categorized in the good and poor position groups, respectively, and the rate of good position was 26.2%. The distribution of bone tunnel was as follows: (x-axis) deep position in 10 patients (12%), normal position in 58 patients (69%), and shallow position in 16 patients (19%); (y-axis) high position in 54 patients (64%), normal position in 26 patients (31%), and low position in 4 patients (5%). 1 year later, the Lysholm and IKDC scores were significantly better in the good position group (P < 0.05), the KT-1000 side to side difference, the pivot shift test and Lachman test results were better in the good position group (P < 0.05). CONCLUSIONS: The bone tunnels were found to be distributed in and beyond the normal range using the bone landmark method to position the femoral tunnel in the single-bundle anatomical reconstruction of ACL, while the rate of good bone tunnel position was low. The knee joint function scores and stability were lower in patients with poor position of the femoral tunnel.

An Analysis of the Risk Factors for Adding-on Phenomena After Posterior Hemivertebral Resection and Pedicle Screw Fixation for the Treatment of Congenital Scoliosis Caused by Hemivertebral Malformation.

Objective: To retrospectively analyze the risk factors for adding-on phenomena (AOP) after posterior hemivertebral resection (PHR) and pedicle screw fixation for the treatment of congenital scoliosis (CS) caused by hemivertebral (HV) malformation. Methods: Patients with CS who underwent surgery and were followed up for more than five years were included in this study. The d general data, such as gender, age, HV segment, Risser sign, and triangular cartilage, postoperative complications, and imaging data at different periods, including the standard anteroposterior and lateral x-rays of the total spine were collected. Results: In total, 58 patients were included in this study, of which 10 experienced AOP and 48 did not. The results of the single-factor analysis showed that there were statistically significant differences between the patients with AOP and those without in terms of the HV direction, lowest instrumented vertebra (LIV)-upper instrumented vertebra (UIV) (P < 0.05), and postoperative trunk shift (P < 0.05). The results of the logistic regression analysis showed that the HV direction and the postoperative trunk displacement distance were the main risk factors for postoperative AOP. The area under the receiver operating characteristic curve was 0.842 (P < 0.001). The best cut-off value of the adding-on index as an indicator of the occurrence of AOP after surgery was 0.67. When the adding-on index was >0.67, the incidence of postoperative AOP was 90.0%, and the non-occurrence rate was 22.9%. Conclusion: PHR and pedicle screw fixation is an effective way to treat HV malformation in CS. The HV direction, LIV-UIV, and postoperative TS are risk factors for AOP in patients with CS treated with PHR and pedicle screw fixation. The adding-on index has a high degree of accuracy for the prediction of the occurrence of AOP after PHR and pedicle screw fixation.

A review of the hemivertebrae and hemivertebra resection.

Hemivertebra (HV) is a congenital spinal abnormality. Most hemivertebrae have normal growth plates so create a progressive deformity with growth leading to asymmetric loads on adjacent vertebrae which also show an asymmetric growth. We review the condition and its treatment.

Clinical comparison of percutaneous transforaminal endoscopic discectomy and unilateral biportal endoscopic discectomy for single-level lumbar disc herniation.

Purpose: To compare the clinical outcomes of percutaneous transforaminal endoscopic discectomy (PTED) and unilateral biportal endoscopic discectomy (UBE) for the treatment of single-level lumbar disc herniation (LDH). Materials and methods: From January 2020 to November 2021, 62 patients with single-level LDH were retrospectively reviewed. All patients underwent spinal surgeries at the Affiliated Hospital of Chengde Medical University and Beijing Tongren Hospital, Capital Medical University. Among them, 30 patients were treated with UBE, and 32 were treated with PTED. The patients were followed up for at least one year. Patient demographics and perioperative outcomes were reviewed before and after surgery. The Oswestry Disability Index (ODI), visual analog scale (VAS) for back pain and leg pain, and modified MacNab criteria were used to evaluate the clinical outcomes. x-ray examinations were performed one year after surgery to assess the stability of the lumbar spine. Results: The mean ages in the UBE and PTED groups were 46.7 years and 48.0 years, respectively. Compared to the UBE group, the PTED group had better VAS scores for back pain at 1 and 7 days after surgery (3.06 ± 0.80 vs. 4.03 ± 0.81, P < 0.05; 2.81 ± 0.60 vs. 3.70 ± 0.79, P < 0.05). The UBE and PTED groups demonstrated significant improvements in the VAS score for leg pain and ODI score, and no significant differences were found between the groups at any time after the first month (P > 0.05). Although the good-to-excellent rate of the modified MacNab criteria in the UBE group was similar to that in the PTED group (86.7% vs. 87.5%, P > 0.05), PTED was advantageous in terms of the operation time, estimated blood loss, incision length, and length of postoperative hospital stay. Conclusions: Both UBE and PTED have favorable outcomes in patients with single-level LDH. However, PTED is superior to UBE in terms of short-term postoperative back pain relief and perioperative quality of life.

Os odontoideum associated with a retro-odontoid cyst treated with posterior C1-C3 fixation: A case report and literature review.

Background: Os odontoideum is a rare abnormality of the upper cervical spine, and os odontoideum associated with a retro-odontoid cyst has been described as a marker of local instability. Case description: This paper reports a case of a 52-year-old female patient who was diagnosed with os odontoideum associated with a retro-odontoid cyst. The patient underwent posterior C1-C3 fixation without surgical removal of the cyst. Magnetic resonance imaging (MRI) two days later revealed that the retro-odontoid cyst was still present and that there were no significant changes to it when compared with the preoperative MRI. Conclusion: Retro-odontoid cysts associated with unstable os odontoideum can lead to symptomatic spinal cord compression. Posterior C1-C3 fixation can restore atlantoaxial stability by allowing the gradual resorption of the cyst and ensuring spinal cord decompression. Fixation can also avoid the surgical risk associated with a high-riding vertebral artery.

Posterior thoracolumbar hemivertebra resection and short-segment fusion in congenital scoliosis: surgical outcomes and complications with more than 5-year follow-up.

BACKGROUND: Treatment of congenital hemivertebra is challenging and data on long-term follow-up (≥ 5 years) are lacking. This study evaluated the surgical outcomes of posterior thoracolumbar hemivertebra resection and short-segment fusion with pedicle screw fixation for treatment of congenital scoliosis with over 5-year follow-up. METHODS: This study evaluated 27 consecutive patients with congenital scoliosis who underwent posterior thoracolumbar hemivertebra resection and short-segment fusion from January 2007 to January 2015. Segmental scoliosis, total main scoliosis, compensatory cranial curve, compensatory caudal curve, trunk shift, shoulder balance, segmental kyphosis, and sagittal balance were measured on radiographs. Radiographic outcomes and all intraoperative and postoperative complications were recorded. RESULTS: The segmental main curve was 40.35° preoperatively, 11.94° postoperatively, and 13.24° at final follow-up, with an average correction of 65.9%. The total main curve was 43.39° preoperatively, 14.13° postoperatively, and 16.06° at final follow-up, with an average correction of 60.2%. The caudal and cranial compensatory curves were corrected from 15.78° and 13.21° to 3.57° and 6.83° postoperatively and 4.38° and 7.65° at final follow-up, with an average correction of 69.2% and 30.3%, respectively. The segmental kyphosis was corrected from 34.30° to 15.88° postoperatively and 15.12° at final follow-up, with an average correction of 61.9%. A significant correction (p < 0.001) in segmental scoliosis, total main curve, caudal compensatory curves and segmental kyphosis was observed from preoperative to the final follow-up. The correction in the compensatory cranial curve was significant between preoperative and postoperative and 2-year follow-up (p < 0.001), but a statistically significant difference was not observed between the preoperative and final follow-up (p > 0.001). There were two implant migrations, two postoperative curve progressions, five cases of proximal junctional kyphosis, and four cases of adding-on phenomena. CONCLUSION: Posterior thoracolumbar hemivertebra resection after short-segment fusion with pedicle screw fixation in congenital scoliosis is a safe and effective method for treatment and can achieve rigid fixation and deformity correction.

Effects of Single-Foot Centered and Double-Foot Centered X-ray Projection on Hallux Valgus Measurement.

OBJECTIVE: To investigate whether use of single-foot centered and double-foot centered weight-bearing X-rays has an impact on the relevant indicators of hallux valgus. METHODS: A total of 55 female patients from the Department of Ankle Surgery of Beijing Tongren Hospital with hallux valgus (110 feet) were collected from September to December 2015. The age of these patients ranged from 18 to 43 years, with an average age of 47.9 ± 8.5 years. All selected patients fit the diagnostic criteria of hallux valgus and had weight-bearing single foot centered and double foot centered radiographs taken. During the projection, all patients were instructed to stand on the X-ray box, with the knee joint straightened and legs perpendicular to the floor. The projection center of the single foot was directed at the lateral part of the scaphoid bone of the foot, while the projection center was directed at the position between the scaphoid bones of both feet for the double-foot shooting. The hallux valgus angle (HAV), the intermetatarsal angle between the first and second metatarsals (IMA), the intermetatarsal angle between the first and fifth metatarsals (IM1-5), and the metatarsal adduction angle (MAA) were measured and examined. The difference between these two shooting conditions was compared and analyzed. RESULTS: The differences in X-ray measurement results (IMA, HAV, IM1-5, and MMA) between different measures for the same patient were not statistically significant. The values of HAV, IMA, IM1-5, and MAA are common indexes for evaluating hallux valgus. The average IMA was 15.9° for single-foot centered and 14.1° for double-foot centered X-rays. The average HAV was 30.2° for single-foot centered and 29.7° for double-foot centered X-rays. The average IM1-5 was 31.1° for single-foot centered and 29.7° for double-foot centered X-rays. The average of metatarsal adduction angle was 13.8° for single-foot centered and 14.1° for double-foot centered X-rays. The differences between single-foot centered and double-foot centered X-rays were statistically significant in terms of the measurement index (P < 0.05). In addition, compared with double-foot centered weight-bearing X-rays, the focus of single-foot centered X-rays was located on the lateral part of the scaphoid bone of the foot, and the ray was closer to the vertical foot in the single-foot centered weight-bearing X-ray. CONCLUSION: When the weight-bearing position and projection distance are the same, the single-foot centered weight-bearing X-ray is more effective in evaluating the severity of hallux valgus compared with the double-foot centered weight-bearing X-ray.

Transforaminal Endoscopic Discectomy and Foraminoplasty for Treating Central Lumbar Stenosis.

OBJECTIVE: Lumbar spinal stenosis is a medical condition characterized by the narrowing of the spinal canal as a consequence of bone and soft tissue degeneration, including disc herniation, facet and ligamentum flavum hypertrophy, and osteophyte formation. The percutaneous transforaminal endoscopic discectomy (PTED) technique is one of the emerging surgical alternatives for treating central lumbar stenosis. The present study aims to describe the present techniques of PTED and foraminoplasty for central lumbar stenosis, and discuss the feasibility and advantages of this technique. METHODS: A total of 55 patients with an average age of 50 years were recruited in this study. They were operated on between August 2017 and June 2018 by a single surgeon for symptomatic lumbar stenosis using the PTED and foraminoplasty technique, along with a detailed description of the present technique. The retrospective analysis of 55 patients operated between August 2017 and June 2018 by a single surgeon for symptomatic lumbar stenosis using the PTED and foraminoplasty techniques, and the detailed description of the present technique were the focus of the present study. For all patients, the PTED and foraminoplasty procedure was performed under local anesthesia in the lateral position on a radiolucent table using C-arm fluoroscopy. The retrospective analysis evaluated the outcomes of symptoms through follow-up interviews at six weeks, six months, and one year after surgery. The analyzed parameters included surgery time, intraoperative blood loss, postoperative complications, visual analog scale (VAS) score, Japan Orthopedic Association (JOA) score, and the Oswestry Disability Index (ODI). The modified MacNab criteria were adopted. RESULTS: The average duration of symptoms was 15.6 weeks. The mean operative time was 161 minutes. The mean volume of intraoperative blood loss was 21 mL. The mean follow-up period was 14.6 months. The average preoperative VAS score for leg pain and low back pain was 6.8 and 5.5, respectively. The preoperative ODI and JOA score was 49.2 and 14.6, respectively. At the final follow-up, all 55 patients had an average VAS score of 1.1 for leg pain and 0.5 for low back pain. At the same time, the average ODI and JOA score was seven and 24.5, respectively. The statistical analysis showed that the VAS score, ODI value, and JOA score were significantly lower in all time-points at post-operation, when compared to those at pre-operation. For the modified MacNab criteria, the final outcome results were excellent in 39 patients (70.9%), good in nine patients (16.4%), fair in four patients (7.3%), and poor in two patients (3.6%), and the overall success rate was 89.1%. Two patients underwent a second operation during the follow-up period, and their symptoms were released after the reoperation. CONCLUSION: PTED and foraminoplasty technique showed promising outcomes in the treatment of central lumbar stenosis in a 1-year follow-up period. It suggested that PTED and foraminoplasty might be applied as a safe and effective therapeutic option for patients with lumbar stenosis.