Use of Artificial Intelligence in Cobb Angle Measurement for Scoliosis: Retrospective Reliability and Accuracy Study of a Mobile App.

BACKGROUND: Scoliosis is a spinal deformity in which one or more spinal segments bend to the side or show vertebral rotation. Some artificial intelligence (AI) apps have already been developed for measuring the Cobb angle in patients with scoliosis. These apps still require doctors to perform certain measurements, which can lead to interobserver variability. The AI app (cobbAngle pro) in this study will eliminate the need for doctor measurements, achieving complete automation. OBJECTIVE: We aimed to evaluate the reliability and accuracy of our new AI app that is based on deep learning to automatically measure the Cobb angle in patients with scoliosis. METHODS: A retrospective analysis was conducted on the clinical data of children with scoliosis who were treated at the Pediatric Orthopedics Department of the Children's Hospital affiliated with Fudan University from July 2019 to July 2022. Three measurers used the Picture Archiving and Communication System (PACS) to measure the coronal main curve Cobb angle in 802 full-length anteroposterior and lateral spine X-rays of 601 children with scoliosis, and recorded the results of each measurement. After an interval of 2 weeks, the mobile AI app was used to remeasure the Cobb angle once. The Cobb angle measurements from the PACS were used as the reference standard, and the accuracy of the Cobb angle measurements by the app was analyzed through the Bland-Altman test. The intraclass correlation coefficient (ICC) was used to compare the repeatability within measurers and the consistency between measurers. RESULTS: Among 601 children with scoliosis, 89 were male and 512 were female (age range: 10-17 years), and 802 full-length spinal X-rays were analyzed. Two functionalities of the app (photography and photo upload) were compared with the PACS for measuring the Cobb angle. The consistency was found to be excellent. The average absolute errors of the Cobb angle measured by the photography and upload methods were 2.00 and 2.08, respectively. Using a clinical allowance maximum error of 5°, the 95% limits of agreement (LoAs) for Cobb angle measurements by the photography and upload methods were -4.7° to 4.9° and -4.9° to 4.9°, respectively. For the photography and upload methods, the 95% LoAs for measuring Cobb angles were -4.3° to 4.6° and -4.4° to 4.7°, respectively, in mild scoliosis patients; -4.9° to 5.2° and -5.1° to 5.1°, respectively, in moderate scoliosis patients; and -5.2° to 5.0° and -6.0° to 4.8°, respectively, in severe scoliosis patients. The Cobb angle measured by the 3 observers twice before and after using the photography method had good repeatability (P<.001). The consistency between the observers was excellent (P<.001). CONCLUSIONS: The new AI platform is accurate and repeatable in the automatic measurement of the Cobb angle of the main curvature in patients with scoliosis.

Analysis on the related factors of misplacement of freehand pedicle screws via posterior approach in degenerative scoliosis.

BACKGROUND: To study the risk factors associated with misplacement of freehand pedicle screws through a posterior approach for degenerative scoliosis. METHODS: A total of 204 patients who underwent posterior pedicle screw-rod system surgery for degenerative scoliosis in our hospital from December 2020 to December 2023 were retrospectively analyzed. Patient demographics, radiographic accuracy, and surgery-related information were recorded. RESULTS: A total of 204 patients were included. A total of 2496 screws were placed. 2373 (95.07%) were in good position. Misplacement screws were 123 (4.93%). None of the patients had postoperative spinal nerve symptoms due to screw malposition. The misplacement rate of thoracic (T10-T12) pedicle screws was 11.11% (60/540). Misplacement of pedicle screws in the lumbar spine (L1-L5) was 3.22% (63/1956). Age, gender, surgeon, and operation time had no significant effect on misplacement of pedicle screws (P>0.05). Body mass index, Hu value, number of screw segments, Cobb angle, vertebral rotation, and spinal canal morphology had some correlation with pedicle screw misplacement. Among them, BMI, Hu value, number of screw segments, Cobb angle, and vertebral rotation grade were independent risk factors for PS misplacement (P<0.05). The height of the posterior superior iliac spine had a significant effect on pedicle screw misplacement in the lower lumbar spine (L4/5) (P<0.05). CONCLUSION: BMI, Hu value, number of screw levels, Cobb angle, and vertebral rotation grade were independent risk factors for pedicle screw misplacement in patients with degenerative scoliosis. Posterior superior iliac spine height has a large impact on PS placement in the lower lumbar spine. Patients with degenerative scoliosis should be preoperatively planned for the size and direction of the placed screws by X-ray and CT three-dimensional, to reduce the misplacement rate of pedicle screws.

Long-term results of single-stage posterior hemivertebra resection and short segment fusion using pedicle screws fixation in thoracolumbar congenital early-onset scoliosis: an 8.97-year average follow-up study.

BACKGROUND: This study aims to evaluate the long-term outcomes of one-stage posterior hemivertebra resection and short segment fusion with pedicle screw fixation in children with thoracolumbar congenital early-onset scoliosis (TLCEOS). It specifically investigates the durability of spinal correction and the incidence of complications over an average follow-up of 8.97 years. METHODS: A retrospective review was conducted on 32 patients treated at a tertiary scoliosis referral center from April 2003 to December 2019. Inclusion criteria were thoracolumbar hemivertebra (T11-L1), treatment via posterior hemivertebra resection and short segment fusion (≤ 5 segments), age under 10 years at surgery, and a follow-up of at least 5 years. Exclusions included idiopathic, syndromic, or neuromuscular scoliosis. Data on demographics, surgical procedures, and radiographic outcomes were collected, and clinical outcomes were evaluated using the Scoliosis Research Society-22 (SRS-22) questionnaire. Statistical analysis was performed using SPSS and R software. RESULTS: The study included 32 patients (22 males, 10 females) with a mean age of 5.00 ± 2.42 years at surgery and an average follow-up of 8.97 ± 2.81 years. On average, 3.47 ± 1.11 segments were fused. The main curve corrected from 38.64° ± 14.12° preoperatively to 9.06° ± 7.29° postoperatively, with a final correction rate of 61%. Significant improvements were observed in the SRS-22 domains of Appearance and Satisfaction with Treatment. There were 17 complications, including neurological, pulmonary, and mechanical issues, with some cases requiring revision surgery. CONCLUSIONS: One-stage posterior hemivertebra resection and short segment fusion with pedicle screw fixation effectively correct TLCEOS long-term, offering significant improvements in patient appearance and satisfaction, with a manageable complication profile.

Mid- to long-term radiological and respiratory outcomes following surgery for older early-onset scoliosis patients with Marfan syndrome.

This study aimed to elucidate mid- to long-term radiological and respiratory outcomes in patients aged 7-11 years at index surgery with Marfan syndrome and early-onset scoliosis (EOS) in a retrospective multicenter study. Primary outcomes were final thoracic height and final percentage of predicted vital capacity (%VC) at or after 16 years of age. We identified 21 (6 male and 15 female) patients with a mean age of 9.9 years and mean follow-up period of 149.3 months. Fifteen patients underwent primary fusion, whereas six underwent growth-friendly surgery (GFS). The mean preoperative and final T1-T12 heights were 204.0 mm and 248.0 mm, respectively. Final pulmonary function tests were available for 16 patients, and the mean final %VC was 54.0% with 10 patients exhibiting a final %VC < 60%. A significant moderate association was observed between the final T1-T12 height and final %VC. The predicted final T1-T12 height required for a final %VC of 60% was approximately 260 mm. Although most older patients with Marfan syndrome and EOS acquired a considerably large final T1-T12 height, a larger thoracic height was required for satisfactory respiratory function in many cases; hence, GFS may be indicated even in this population.

Ultrasound-guided spinal anaesthesia for a patient with severe scoliosis.

Ultrasound (US) guided spinal anaesthesia is gaining recognition for its ability to minimise technical difficulties encountered in patients with atypical spinal anatomy. Spinal anaesthesia is administered during a surgical procedure lithotripsy in patients with respiratory complications that can result from severe scoliosis or cerebral palsy. Here, we report a case in which US-guided spinal anaesthesia proved feasible and advantageous in a patient with cerebral paralysis and severe scoliosis. A man in his 60s with cerebral paralysis and severe scoliosis was scheduled for spinal anaesthesia because of his nocturnal SpO2 drops and need for nasal high flow. Using US guidance, we confirmed that the needle entry angle was consistent with the rotating spinous process. The spinal needle was then advanced successfully, and spinal anaesthesia was administered without issue. The US technique for detecting the rotation of the vertebrae and puncturing them is useful in patients with severe scoliosis.

The impact of halo-pelvic traction on sagittal kyphosis in the treatment of severe scoliosis and kyphoscoliosis.

BACKGROUND: Halo-pelvic traction (HPT) is acknowledged for enhancing pulmonary function and reducing neurological complications in severe and rigid scoliosis and kyphoscoliosis. While its role in improving coronal balance is established, its impact on sagittal kyphosis remains under-researched. This study aims to assess HPT's effects on sagittal alignment in these conditions. METHODS: A retrospective review of 37 patients with severe and rigid scoliosis or kyphoscoliosis was conducted to evaluate HPT's efficacy. The analysis focused on the impact of HPT on coronal and sagittal parameters, pulmonary function tests (PFTs) and complications. Radiographic assessments included main cobb angle in coronal, sagittal major kyphosis. RESULTS: HPT was applied for an average of 2.9 months, significantly reducing the primary coronal curve from 127.7°±30.3° to 74.9°±28.3° (P < 0.05), achieving a 41.3% correction rate. Sagittal kyphosis correction was more pronounced, with angles decreasing from 80.4°±26.4° to 41.3°±24.4° (P < 0.05), resulting in a 48.6% correction rate. Pulmonary function tests showed improvements in forced vital capacity (FVC) (from 1.32 ± 0.91 to 1.55 ± 0.83) and forced expiratory volume in 1 s (FEV1) (from 1.03 ± 0.76 to 1.28 ± 0.72), with percentage predicted values also increasing (FVC%: 40.4%±24.3-51.4%±23.1%; FEV1%: 37.8%±25.2-48.1%±22.7%; all P < 0.05). CONCLUSION: HPT effectively reduces spinal deformity severity and improves pulmonary function in patients with severe and rigid scoliosis and kyphoscoliosis. Sagittal kyphosis correction was notably greater than coronal scoliosis correction. The correlation between PFT improvements and coronal curve adjustments suggests that correcting the coronal Cobb angle is pivotal for pulmonary function enhancement.

Leadless pacemaker implantation using halo-shape technique in a severe dextroscoliosis octogenarian.

The halo-shape technique (HST) is an emerging approach for implanting a leadless pacemaker in scoliosis patients in recent years. Severe scoliosis and humpback made it challenging to push the tip of the delivery catheter towards the ventricular septum using the conventional gooseneck-shape technique. The feasibility and safety of the use of HST in an octogenarian with severe dextroscoliosis and humpback have not been well-assessed. Here, we report a case of high-degree atrioventricular block octogenarian with severe dextroscoliosis and humpback who successfully received a leadless pacemaker implantation using HST. Procedure-related complications were not observed, and the electrical parameters were stable at 6-month follow-up.

Puberty changes the natural history of idiopathic scoliosis: three prediction models for future radiographic curve severity from 1563 consecutive patients.

PURPOSE: Understanding idiopathic scoliosis (IS) natural history during growth is essential for shared decision-making between patients and physicians. We developed a retrospective model with the largest available sample in the literature and we aimed to investigate if using three peri-pubertal growth periods provides better prediction than a unique model. METHODS: Secondary analysis of a previous study on IS natural history data from radiographs before and at the first consult. Three groups: BEFORE (age 6-10), AT (age 11-Risser 2) and AFTER (from Risser 3) the pubertal growth spurt. Available predictors: Cobb angle, curve type, sex, observation time, and Risser score. We used linear mixed-effects models to predict future Cobb angles in each group. We internally validated prediction accuracy with over 100 patients per group (3 to 5-fold cross-validation). RESULTS: We included 1563 participants (275 BEFORE, 316 AFTER, 782 females and 190 males AT). Curves increased over time mostly in AT, importantly in BEFORE, but also in AFTER. All models performed better than the general one. In BEFORE, 74.2% of the predictions were within ± 5o, 71.8% in AFTER, 68.2% in AT females, and 60.4% in males. The predictors (baseline curve, observation time also squared and cubic, and Risser score) were similar in all the models, with sex influencing only AFTER. CONCLUSION: IS curve severities increase differently during growth with puberty stages. Model accuracy increases when tailored by growth spurt periods. Our models may help patients and clinicians share decisions, identify the risk of progression and inform treatment planning.

A retrospective analysis of 513 patients undergoing pedicle subtraction osteotomy for adult spinal deformity by a single surgical team: are elderly patients at an elevated risk for complications?

OBJECTIVE: This study aimed to assess whether elderly patients (aged ≥ 70 years) face an elevated risk of complications following pedicle subtraction osteotomy (PSO) for adult spinal deformity (ASD) compared with younger patients (< 70 years) and to evaluate if clinical and radiological outcomes differ between these age groups. METHODS: A retrospective analysis of 513 patients undergoing PSO for ASD by a single surgical team between January 2006 and January 2023 was conducted. Patients were categorized by age (≥ 70 years and < 70 years). Data on clinical, demographic, comorbidity, and radiographic details were collected and compared between the groups. For health-related quality of life assessment, the authors recorded the Oswestry Disability Index (ODI), numeric rating scale (NRS), and Scoliosis Research Society-22 revised (SRS-22r) scores preoperatively and at 6 weeks and 1 year postoperatively. Perioperative complications included major (neurological deficit, death, acute myocardial infarction, stroke), minor (ileus, arrhythmia, delirium), and intraoperative (durotomy, vascular injury). RESULTS: Of 513 patients, 412 were included in the study. Clinical outcomes, as measured by NRS, ODI, and SRS-22r scores, were comparable between groups, with both groups showing significant improvements postoperatively. Radiographic outcomes also showed significant and comparable improvements in sagittal balance and spinopelvic harmony in both groups. Deformity corrections were also well maintained at 1 year postoperatively. The elderly group (mean age 75.48 years) had a higher rate of perioperative complications (44.64%) than the younger group (mean age 59.60 years; 30.33%) (p = 0.0030), primarily minor complications such as delirium and arrhythmia (16.07% vs 8.61%, p = 0.0279). There was no significant difference between groups regarding the major complication rate (elderly group: 20.83% vs younger group: 14.34%, p = 0.1087), intraoperative complication rate (2.98% vs 3.69%, p = 0.6949), short-term complication rate (10.12% vs 8.20%, p = 0.5024), mechanical complication rate (30.95% vs 32.79%, p = 0.6949), and reoperation rate due to mechanical complications (38.46% vs 43.75% p = 0.5470). CONCLUSIONS: Elderly patients undergoing PSO for ASD experience a higher rate of minor complications but can achieve clinical and radiological outcomes that are comparable to those of younger patients. The authors found no significant increase in major, intraoperative, short-term, or mechanical complication rates and their subsequent reoperation rates among the elderly. These findings underscore the effectiveness of PSO in improving the quality of life for patients with ASD across age groups, emphasizing the critical role of personalized perioperative management in enhancing outcomes and minimizing risks for all patients.

Prognostic model development for risk of curve progression in adolescent idiopathic scoliosis: a prospective cohort study of 127 patients.

BACKGROUND AND PURPOSE:  The study's purpose was to develop and internally validate a prognostic survival model exploring baseline variables for adolescent idiopathic scoliosis curve progression. METHODS:  A longitudinal prognostic cohort analysis was performed on trial data (n = 135) including girls and boys, Cobb angle 25-40°, aged 9-17 years, remaining growth > 1 year, and previously untreated. Prognostic outcome was defined as curve progression of Cobb angle of > 6° prior to skeletal maturity. 34 candidate prognostic variables were tested. Time-to-event was measured with 6-month intervals. Cox proportional hazards regression survival model (CoxPH) was used for model development and validation in comparison with machine learning models (66.6/33.3 train/test data set). The models were adjusted for treatment exposure. RESULTS:  The final primary prognostic model included 127 patients, predicting progress with acceptable discriminative ability (concordance = 0.79, 95% confidence interval [CI] 0.72-0.86). Significant prognostic risk factors were Risser stage of 0 (HR 4.6, CI 2.1-10.1, P < 0.001), larger major curve Cobb angle (HRstandardized 1.5, CI 1.1-2.0, P = 0.005), and higher score on patient-reported pictorial Spinal Appearance Questionnaire (pSAQ) (HRstandardized 1.4, CI 1.0-1.9, P = 0.04). Treatment exposure, entered as a covariate adjustment, contributed significantly to the final model (HR 3.1, CI 1.5-6.0, P = 0.001). Sensitivity analysis displayed that CoxPH maintained acceptable discriminative ability (AUC 0.79, CI 0.65-0.93) in comparison with machine learning algorithms. CONCLUSION:  The prognostic model (Risser stage, Cobb angle, pSAQ, and menarche) predicted curve progression of > 6° Cobb angle with acceptable discriminative ability. Adding patient report of the pSAQ may be of clinical importance for the prognosis of curve progression.

The Effect of Radiological Assessment of Volunteers for French Paratrooper Training: A Five-Year Retrospective Study.

INTRODUCTION: A systematic radiological examination is needed for military airborne troops in order to detect subclinical medical contraindications for airborne training. Many potential recruits are excluded because of scoliosis, kyphosis, or spondylolisthesis. This study aimed to determine whether complementary radiological assessment excludes too many recruits and whether medical standards might be lowered without increasing medical risk to appointees. METHODS: This retrospective, epidemiological, cross-sectional single-center study spanned 5 years at the French paratroopers' initial training center. We analyzed all medical files and full-spine X-ray results of all enlisted troops during this period. Secondary evaluation by an orthopedic surgeon enabled 23 enlisted personnel, deemed medically unacceptable because of X-ray findings, to be given waivers for airborne training. A follow-up review of their 23 files was conducted to determine whether static-line parachute jumps were hazardous to those who were initially declared medically unacceptable. RESULTS: Of the 3,993 full-spine X-rays, 67.5% (2,695) were described as having normal alignment and structure; 21.8% (871) had lateral spinal deviation; and 10.7% (427) had scoliosis. Sixty-six recruits (1.6%) were deemed unfit because of findings that did not meet the standard on the fullspine X-ray: 53 enlisted personnel had scoliosis greater than 15°, and 13 had spondylolisthesis (grade II or III). Of the 23 patients granted waivers, 82.3% with scoliosis (14) and all patients with kyphosis had not declared any back pain after 5 years. CONCLUSION: The findings, supported by a literature review of foreign military data, suggest that spondylolisthesis above grade I and low back pain are more significant than scoliosis and kyphosis for establishing airborne standards.

Simultaneous Single-Position Oblique Lumbar Interbody Fusion and Percutaneous Pedicle Screw Fixation under O-Arm Navigation for Modified MISDEF Type II Adult Degenerative Scoliosis: Case Series and Surgical Technique.

PURPOSE: Oblique lumbar interbody fusion (OLIF) has become a popular technique for treating adult degenerative scoliosis (ADS), but traditional OLIF technology often requires repositioning for one-stage or staged posterior fixation. The objective of this pilot study was to describe the surgical technique of simultaneous single-position OLIF and percutaneous pedicle screw fixation (OLIF 360) under O-Arm navigation for modified MISDEF type II ADS. METHODS: Between June 2022 and December 2023, six patients classified as having modified MISDEF type II ADS underwent OLIF 360 assisted by O-Arm navigation at our institution. Intraoperative blood loss, duration of operation, and complications related to the OLIF 360 procedure were recorded. The preoperative and postoperative spinal pelvic parameters were measured using X-rays. The accuracy of pedicel screws was recorded in accordance with the modified Gertzbein-Robbins classification on CT. Postoperative MRI was performed to evaluate the indirect decompressive effect. The Japanese Orthopedic Association score for low back pain was used to evaluate surgical outcomes. RESULTS: Navigated OLIF 360 were performed in six ADS patients with 44 percutaneous pedicel screws and 16 cages placement, including four women and two men. The mean operation time was 160.83 ± 33.23 min, and the mean blood loss was 111.67 ± 39.71 mL. Postoperative spinal pelvic parameters and spinal stenosis degree improved significantly on X-ray and MRI. All screws were clinically acceptable according to the Gertzbein-Robbins classification, with 92.7% grade A and 7.3% grade B. No serious intraoperative and postoperative adverse events were recorded in all patients. The JOA scores for low back pain of all patients were significantly improved at postoperative 1 month and the final follow-up. CONCLUSION: We report on a case series and describe navigated OLIF 360 in treating modified MISDEF type II ADS patients. Navigation-assisted OLIF 360 has shown encouraging surgical outcomes with good spinal imbalance correction and indirect decompression.

Improving prediction of progression of idiopathic scoliosis based on curve size and skeletal maturity.

PURPOSE: To define the risk of curve progression of idiopathic scoliosis (IS) to 35°, 40°, 45°, and 50° based on current curve magnitude and Sanders stage for boys and girls, using a large cohort of patients and encounters, to improve granularity and allow more accurate estimations to guide treatment. METHODS: Retrospective analysis of a prospectively collected scoliosis database. Generalized estimation equation logistic regression models estimated probabilities of curve progression to 35°, 40°, 45°, and 50° based on starting curve size and Sanders stage. Probabilities and their 95% confidence intervals were calculated for each combination of variables to each endpoint separately for boys and girls. RESULTS: A total of 309 patients (80% girls) were included. Starting curve size and Sanders stage were significant predictors for progression in both sexes (all P ≤ 0.04). Higher starting curve sizes and lower Sanders stages were associated with greater odds of progression. Risk of progression was still present even at higher Sanders stages. CONCLUSION: IS curves follow a predictable pattern, having more risk for progression when curves are larger and Sanders stages are smaller. Risk of curve progression is a spectrum based on these factors, indicating some risk of progression exists even for many smaller curves with higher Sanders stages. The improved granularity of this analysis compared to prior efforts may be useful for counseling patients about the risks of curve progression to various curve size endpoints and may aid shared decision-making regarding treatments. LEVEL OF EVIDENCE OR CLINICAL RELEVANCE: Level III: retrospective cohort study.

Prognosticating accelerated deterioration in skeletally mature adolescent idiopathic scoliosis curves of 40-50° using uniplanar radiographic measures of axial rotation.

PURPOSE: The management of adolescent idiopathic scoliosis (AIS) curves between 40 and 50° is controversial. Here, we investigated the prognostic significance of simple radiographic rotational parameters to identify curves of this magnitude with accelerated deterioration following skeletal maturity. METHODS: Seventy-three patients were identified with AIS and Cobb angles of the major curve between 40 and 50° at skeletal maturity. We defined fast progressive curves as those increasing by ≥ 2° per year after skeletal maturity. From the apical vertebra of the major curve upon presentation and skeletal maturity, we determined the modified Nash-Moe index (×100), and from thoracic major curves, the Rib Index. T tests were performed to compare fast-progressive curves with those that deteriorated by < 2° per year. Receiver operator characteristic (ROC) curves were plotted to establish optimal cutoffs, sensitivity, and specificity measures for rotational parameters. RESULTS: The average duration of follow-up post was 11.8 ± 7.3 years. Thirteen out of seventy-three patients were fast progressors. The modified Nash-Moe index was similar between groups at presentation (p = 0.477) but significantly higher in fast progressors than non-fast progressors at maturity for major thoracic curves (25.40 ± 6.60 vs. 19.20 ± 4.40, p < 0.001). Rib Index values were also higher among fast progressors at skeletal maturity (2.50 ± 0.90 vs. 1.80 ± 0.60, p = 0.026). An ROC curve for a modified Nash-Moe index of 0.235 for thoracic curves achieved an area under the curve (AUC) of 0.76 for discriminating fast progressors. A threshold of 1.915 for Rib Index at maturity achieved an AUC of 0.72 for discriminating fast progressors. In combining both rotational parameters, an AUC of 0.81 was achieved. CONCLUSION: These simple rotational parameters may be useful to predict fast progression in 40-50° AIS curves following skeletal maturity indicated for early fusion, but further validation upon larger cohorts and non-thoracic major curves is required.

Applications of artificial intelligence for adolescent idiopathic scoliosis: mapping the evidence.

PURPOSE: Adolescent idiopathic scoliosis (AIS) is a common spinal deformity with varying progression, complicating treatment decisions. Artificial intelligence (AI) and machine learning (ML) are increasingly prominent in orthopedic care, aiding in diagnosis, risk-stratification, and treatment guidance. This scoping review outlines AI applications in AIS. METHODS: This study followed PRISMA-ScR guidelines and included articles that reported the development, use, or validation of AI models for treating, diagnosing, or predicting clinical outcomes in AIS. RESULTS: 40 full-text articles were included, with most studies published in the last 5 years (77.5%). Common ML techniques were convolutional neural networks (55%), decision trees and random forests (15%), and artificial neural networks (15%). Most AI applications in AIS were for imaging analysis (25/40; 62.5%), focusing on automatic measurement of Cobb angle, and axial vertebral rotation (13/25; 52%) and curve classification/severity (13/25; 52%). Prediction was the second most common application (15/40; 37.5%), with studies predicting curve progression (9/15; 60%), and Cobb angles (9/15; 60%). Only 15 studies (37.5%) reported clinical implementation guidelines for AI in AIS management. 52.5% of studies reported model accuracy, with an average of 85.4%. CONCLUSION: This review highlights the applications of AI in AIS care, notably including automatic radiographic analysis, curve type classification, prediction of curve progression, and AIS diagnosis. However, the current lack of clear clinical implementation guidelines, model transparency, and external validation of studied models limits clinician trust and the generalizability and applicability of AI in AIS management.

The Effect of Global Spinal Alignment on Cervical Degeneration in Patients with Degenerative Lumbar Scoliosis.

OBJECTIVE: To elucidate the effect of global spinal alignment on cervical degeneration in patients with degenerative lumbar scoliosis (DLS). METHODS: This study included 117 patients with DLS and 42 patients with lumbar spinal stenosis as a control group. Patients with DLS (study group) were categorized according to the Scoliosis Research Society-Schwab classification. Spinopelvic parameters were measured in cervical and full-length spine radiographs. Cervical degeneration was assessed using the cervical degeneration index (CDI) scoring system. RESULTS: There were significant differences in C2-C7 sagittal vertical axis, T1 slope, thoracic kyphosis, lumbar lordosis (LL), and pelvic tilt between DLS and control groups. Although the DLS and control groups did not differ significantly with regard to CDI scores, a striking difference was noted when sagittal spinopelvic modifiers were considered individually. Patients with a pelvic incidence (PI)-LL mismatch modifier grade of ++ had significantly higher CDI scores than patients with grade 0, and patients with a PI-LL or sagittal vertical axis modifier grade of ++ had significantly higher CDI scores than the control group. Disk narrowing scores were highest in patients with a PI-LL modifier grade of ++ followed by patients with a grade of +. Additionally, CDI scores were more associated with LL rather than cervical lordosis. CONCLUSIONS: Patients with DLS may be at greater risk of cervical spine degeneration, especially patients with a PI-LL or sagittal vertical axis modifier grade of ++. A surgical strategy for patients with DLS should be carefully selected considering the restoration of LL.

A classification algorithm for prioritizing surgery in Pediatric patients with idiopathic scoliosis when Long Surgical delays are expected.

PURPOSE: To identify the clinical phenotypes associated with the rate of progression while waiting for surgery and propose a classification scheme for identifying subgroups of patients to prioritize for surgery when long surgical delays are expected. METHODS: We reviewed the clinical and radiographic data of a prospective cohort of patients scheduled for IS surgery from 2004 to 2020 with a minimum 1-year wait prior to surgery. Candidate predictors consisted of age, sex, Risser sign, menarchal status, angle of trunk rotation, scoliotic curve type, and main Cobb angle at baseline when scheduled for surgery. Univariate and Regression Tree analysis were performed to identify predictors associated with the annual curve progression rate in the main Cobb angle between baseline and surgery. RESULTS: There were 214 patients (178 females) aged 15 ± 2 years, with a Risser sign 3.4 ± 1.6 and a main Cobb angle 55°±10° at baseline. The average wait prior to surgery was 1.3 ± 0.4 years. Only the Risser sign, menarchal status and sex were significantly associated with the annual progression rate. We have identified 3 clinically and significantly different groups of patients presenting slow (3 ± 4°/yr if Risser sign 3 to 5), moderate (8 ± 4°/yr if female with Risser sign 0 to 2 and post-menarchal), and fast (15 ± 10°/yr if Risser sign 0 to 2 and premenarchal or male) progression rates. CONCLUSION: We present an evidence-based surgical prioritization algorithm for pediatric idiopathic scoliosis that can easily be implemented in clinical practice when long surgical delays are expected.

Reliability and accuracy of scoliotic parameters on using a wireless handheld 3D ultrasound for children with adolescent idiopathic scoliosis: a pilot study.

PURPOSE: To report the accuracy and reliability of Cobb angle (CA), axial vertebral rotation (AVR), kyphotic and lordotic angles (KA and LA) measurements on using a new 3D ultrasound (US) system. METHODS: Forty participants (34 F, 6 M, aged 14.0 ± 2.3 years) were recruited. The first 20 participants were scanned by the validated US system and the new US system. The other 20 participants were scanned with the new US system only. Two raters (R1 and R2) performed the measurements: R1 has 10 years of experience in radiology but is new in ultrasound scoliosis, while R2 has 30 years of scoliosis experience. All US images were measured twice by R1, and once by R2. Forty posteroanterior and 30 lateral standing radiographs were obtained and measured once by R1. Statistical analysis consisted of mean absolute difference (MAD), intraclass correlation coefficient (ICC (2,1)), and Bland-Altman plots. RESULTS: R1 showed excellent intra-rater and inter-rater reliability for US measurements with ICCs(2,1) ≥ 0.91. The inter-method reliability was good between the two US systems for all parameters with ICCs(2,1) ≥ 0.85 and maximum MAD of 3.4°. The new US showed good reliability and accuracy compared to radiographs for CA, AVR and KA with ICCs(2,1) ≥ 0.81 and maximum MAD of 5.8°, but poor results for LA with ICCs(2,1) of 0.27-0.35 and MADs of 14.0°-15.4°. CONCLUSION: The new 3D US system showed good reliability and accuracy for CA, AVR and KA measurements, but a large measurement discrepancy on LA. A new measurement method for US LA may need to investigate.

Using machine learning to automatically measure kyphotic and lordotic angle measurements on radiographs for children with adolescent idiopathic scoliosis.

Measuring the kyphotic angle (KA) and lordotic angle (LA) on lateral radiographs is important to truly diagnose children with adolescent idiopathic scoliosis. However, it is a time-consuming process to measure the KA because the endplate of the upper thoracic vertebra is normally difficult to identify. To save time and improve measurement accuracy, a machine learning algorithm was developed to automatically extract the KA and LA. The accuracy and reliability of the T1-T12 KA, T5-T12 KA, and L1-L5 LA were reported. A convolutional neural network was trained using 100 radiographs with data augmentation to segment the T1-L5 vertebrae. Sixty radiographs were used to test the method. Accuracy and reliability were reported using the percentage of measurements within clinical acceptance (≤9°), standard error of measurement (SEM), and inter-method intraclass correlation coefficient (ICC2,1). The automatic method detected 95 % (57/60), 100 %, and 100 % for T1-T12 KA, T5-T12 KA, and L1-L5 LA, respectively. The clinical acceptance rate, SEM, and ICC2,1 for T1-T12 KA, T5-T12 KA, and L1-L5 LA were (98 %, 0.80°, 0.91), (75 %, 4.08°, 0.60), and (97 %, 1.38°, 0.88), respectively. The automatic method measured quickly with an average of 4 ± 2 s per radiograph and illustrated how measurements were made on the image, allowing verifications by clinicians.