Adolescent idiopathic scoliosis is the most common spinal disorder in adolescents with a prevalence of 0.5–5.2% worldwide. The traditional methods for scoliosis screening are easily accessible but require unnecessary referrals and radiography exposure due to their low positive predictive values. The application of deep learning algorithms has the potential to reduce unnecessary referrals and costs in scoliosis screening. Here, we developed and validated deep learning algorithms for automated scoliosis screening using unclothed back images. The accuracies of the algorithms were superior to those of human specialists in detecting scoliosis, detecting cases with a curve ≥20°, and severity grading for both binary classifications and the four-class classification. Our approach can be potentially applied in routine scoliosis screening and periodic follow-ups of pretreatment cases without radiation exposure.

To explore the interventional effect of exercise therapy on idiopathic scoliosis and identify an optimal intervention window, we did a prospective controlled cohort study. The results shows the efficacy of our exercise protocol, and younger patients with a lower Risser grade are most likely to respond.

3.

No abstract

No abstract

Background The severe rigid deformity patients with pulmonary dysfunction could not tolerate complicated corrective surgery. Preoperative traction are used to reduce the curve magnitude and improve the pulmonary function before surgery, including halo-gravity traction (HGT) and halo-pelvic traction (HPT). The present study aimed to retrospectively compare the radiographic, pulmonary and clinical outcomes of preoperative HGT and HPT in severe rigid spinal deformity with respiratory dysfunction. Methods 81 cases of severe rigid kyphoscoliosis treated with preoperative traction prior to corrective surgery for spinal deformity between 2016 and 2019 were retrospectively reviewed. Two patient groups were compared, HPT group (N = 30) and HGT group (N = 51). Patient demographics, coronal and sagittal Cobb angles and correction rates, pulmonary function, traction time, osteotomy grade, and postoperative neurological complications were recorded for all cases. Results The coronal Cobb angle was corrected from 140.67 ± 2.63 to a mean of 120.17 ± 2.93° in the HGT group, and from 132.32 ± 4.96 to 87.59 ± 3.01° in the HPT group (mean corrections 15.33 ± 1.53 vs. 34.86 ± 3.11 %) (P = 0.001). The mean major sagittal curve decreased from 134.28 ± 3.77 to 113.03 ± 4.57° in the HGT group and from 129.60 ± 8.45 to 65.61 ± 7.86° in the HPT group (P < 0.001); the mean percentage corrections were 16.50 ± 2.13 and 44.09 ± 9.78 % (P < 0.001). A significant difference in the pulmonary function test results was apparent between the two groups; the mean improvements in the FVC% of the HGT and HPT groups were 6.76 ± 1.85 and 15.6 ± 3.47 % (P = 0.024). The HPT group tended to exhibit more FEV% improvement than the HGT group, but the difference was not significant (5.15 ± 2.27 vs. 11.76 ± 2.22 %, P = 0.91). Conclusions Patients with severe rigid kyphoscoliosis who underwent preoperative HPT exhibited better radiographic correction of the deformity, and pulmonary function, and required fewer osteotomies compared to the HGT group. Thus, HPT may be useful for severe rigid spinal deformity patients with pulmonary dysfunction.

4.

No abstract