Development and validation of AI-based automatic measurement of coronal Cobb angles in degenerative scoliosis using sagittal lumbar MRI

Jasper W van der Graaf, Miranda L van Hooff, Bram van Ginneken, Merel Huisman, Matthieu Rutten, Dominique Lamers, Nikolas Lessmann, Marinus de Kleuver 
Eur Radiol 2024 Feb 21.doi: 10.1007/s00330-024-10616-8


Objectives: Severity of degenerative scoliosis (DS) is assessed by measuring the Cobb angle on anteroposterior radiographs. However, MRI images are often available to study the degenerative spine. This retrospective study aims to develop and evaluate the reliability of a novel automatic method that measures coronal Cobb angles on lumbar MRI in DS patients.

Materials and methods: Vertebrae and intervertebral discs were automatically segmented using a 3D AI algorithm, trained on 447 lumbar MRI series. The segmentations were used to calculate all possible angles between the vertebral endplates, with the largest being the Cobb angle. The results were validated with 50 high-resolution sagittal lumbar MRI scans of DS patients, in which three experienced readers measured the Cobb angle. Reliability was determined using the intraclass correlation coefficient (ICC).

Results: The ICCs between the readers ranged from 0.90 (95% CI 0.83-0.94) to 0.93 (95% CI 0.88-0.96). The ICC between the maximum angle found by the algorithm and the average manually measured Cobb angles was 0.83 (95% CI 0.71-0.90). In 9 out of the 50 cases (18%), all readers agreed on both vertebral levels for Cobb angle measurement. When using the algorithm to extract the angles at the vertebral levels chosen by the readers, the ICCs ranged from 0.92 (95% CI 0.87-0.96) to 0.97 (95% CI 0.94-0.98).

Conclusion: The Cobb angle can be accurately measured on MRI using the newly developed algorithm in patients with DS. The readers failed to consistently choose the same vertebral level for Cobb angle measurement, whereas the automatic approach ensures the maximum angle is consistently measured.

Clinical relevance statement: Our AI-based algorithm offers reliable Cobb angle measurement on routine MRI for degenerative scoliosis patients, potentially reducing the reliance on conventional radiographs, ensuring consistent assessments, and therefore improving patient care.

Key points: • While often available, MRI images are rarely utilized to determine the severity of degenerative scoliosis. • The presented MRI Cobb angle algorithm is more reliable than humans in patients with degenerative scoliosis. • Radiographic imaging for Cobb angle measurements is mitigated when lumbar MRI images are available.

Keywords: Cobb angle; Deep learning; Magnetic resonance imaging; Scoliosis; Spine.

Introduction to target trial emulation in rehabilitation: a systematic approach to emulate a randomized controlled trial using observational data

Pierre Côté, Stefano Negrini, Sabrina Donzelli, Carlotte Kiekens, Chiara Arienti, Maria G Ceravolo, Douglas P Gross, Irene Battel, Giorgio Ferriero,, Stefano G Lazzarini, Bernard Dan, Heather M Shearer, Jessica J Wong,; Participants in the 5th Cochrane Rehabilitation Methodological Meeting
Eur J Phys Rehabil Med. 2024 Feb;60(1):145-153.doi: 10.23736/S1973-9087.24.08435-1.


Rehabilitation providers and policymakers need valid evidence to make informed decisions about the healthcare needs of the population. Whenever possible, these decisions should be informed by randomized controlled trials (RCTs). However, there are circumstances when evidence needs to be generated rapidly, or when RCTs are not ethical or feasible. These situations apply to studying the effects of complex interventions, including rehabilitation as defined by Cochrane Rehabilitation.
Therefore, we explore using the target trial emulation framework by Hernán and colleagues to obtain valid estimates of the causal effects of rehabilitation when RCTs cannot be conducted. Target trial emulation is a framework guiding the design and analysis of non-randomized comparative effectiveness studies using observational data, by emulating a hypothetical RCT.
In the context of rehabilitation, we outline steps for applying the target trial emulation framework using real world data, highlighting methodological considerations, limitations, potential mitigating strategies, and causal inference and counterfactual theory as foundational principles to estimating causal effects. Overall, we aim to strengthen methodological approaches used to estimate causal effects of rehabilitation when RCTs cannot be conducted.

Adolescent idiopathic scoliosis: is there a relationship between Risser staging and the proximal humerus ossification system?

Calcagni Julián, Davies Néstor Ricardo, Remondino Rodrigo, Tello Carlos A, Piantoni Lucas, Galaretto Eduardo, Arispe Juan Pablo, Noel Mariano 
Spine Deform. 2024 Feb 5. doi: 10.1007/s43390-023-00812-9. 


Purpose: To evaluate whether there is a mismatch between Risser staging and the proximal humerus ossification system (PHOS); and to analyze the correlation in the skeletal maturity stages between the two humeral epiphyses.

Methods: Data from patients aged 10 to 18 years with adolescent idiopathic scoliosis (AIS) seen between 2018 to 2021 were analyzed. In an anteroposterior (AP) spine radiograph the ossification process was evaluated using the Risser classification method and bilateral PHOS (if both humeral epiphyses were visualized). A mismatch between methods was defined as a Risser 0-1 (relatively skeletally immature) with a PHOS 4-5 (skeletally mature), or a Risser 2-5 (relatively skeletally mature) with a PHOS 1-3 (skeletally immature). The McNemar test was used to calculate the significance of the mismatch.

Results: A mismatch between Risser and PHOS stages was observed in 28.5% of 105 patients, which was statistically significant (p < 0.001). Of the 49 patients with a Risser 0-1, 55.1% (n = 27) had a PHOS 4-5. None of the patients with a Risser 2-5 had a PHOS 1-3. In the 47 patients in whom both humeri were visualized, the absolute correlation between the left and right PHOS values was 95.7%.

Conclusion: Of AIS patients who are relatively skeletally immature according to Risser staging, more than half may be skeletally mature when measured with PHOS. In patients with a Risser 0-1, it is recommended to measure skeletal maturity in an AP spine radiograph using the PHOS method, which may more accurately guide treatment decision-making, without the need to visualize both humeral epiphyses in this radiographic projection.

Level of evidence: IV.

Keywords: Adolescent idiopathic scoliosis; Peak height velocity; Proximal humerus ossification system; Risser.

Heath-related quality of life and functional outcomes in patients with congenital or juvenile idiopathic scoliosis after an average follow-up of 25 years: a cohort study

Heemskerk, Nienke W Willigenburg , Ben E E M J Veraart, Eric W Bakker, René M Castelein, Mark C Altena, Diederik H R Kempen
Spine J. 2023 Nov 28:S1529-9430(23)03503-9.doi:10.1016/j. spinee.2023.11.012.


Background context: Congenital and juvenile scoliosis are both early-onset deformities that develop before the age of 10. Children are treated to prevent curve progression and problems in adulthood such as back pain and a decreased quality of life but literature on long-term outcomes remains scarce.

Purpose: To evaluate the health-related quality of life (HRQoL) and potential disability of children with congenital scoliosis (CS) or juvenile idiopathic scoliosis (JIS) after a minimum of 20 years follow-up.

Study design: Comparative cohort study.

Patient sample: A consecutive cohort of CS and JIS patients were retrospectively identified from a single-center scoliosis database. Patients born between 1968 and 1981 and treated during skeletal growth were eligible for participation.

Outcome measures: HRQoL (SF-36, SRS-22r, ODI).

Methods: The primary aim was to evaluate the HRQoL of CS and JIS patients using the general SF-36 questionnaire. Both patient cohorts were compared with age-matched national norms. The secondary aim was to analyze the differences between conservatively and surgically treated patients using the scoliosis-specific Scoliosis Research Society-22r questionnaire (SRS-22r) and the Oswestry Disability Index (ODI). T-tests were used for statistical comparison.

Results: In total, 114 patients (67% of the eligible patients) completed the questionnaire, with a mean follow-up of 25.5±5.5 years after their final clinical follow-up. Twenty-nine patients with CS were included with a mean age of 44.4±3.8 years (79.3% female), and 85 patients with JIS with a mean age of 43.7±4.2 years (89.4% female). Of the SF-36 domains, only the vitality score (60.6±18.0 for CS and 58.1±17.6 for JIS cohort) and mental health score (70.0±18.4 for CS and 72.1±18.1 for JIS cohort) were significantly lower compared with the general population (68.6±19.3 for vitality, and 76.8±17.4 for mental health). These decreased scores were larger than the determined minimum clinically important difference threshold of 4.37. Surgically treated JIS patients had a significantly lower score on the SRS-22r pain domain than their non-surgically treated peers (3.6±0.9 vs. 4.1±0.7l p=.019). Surgically treated CS patients had a significantly higher score on the SRS-22r mental health domain than their non-surgically treated peers (4.3±0.5 vs. 3.5±1.0; p=.023). No significant differences were found in the other domains.

Conclusions: Except for vitality and mental health domains, congenital and juvenile idiopathic scoliosis patients treated during skeletal growth had similar HRQoL on most SF-36 domains in adulthood compared with national norms. Surgical treated JIS patients experienced more pain compared with brace treated patients, while braced CS patients had a significantly lower mental scores compared with surgical treated patients. These long-term outcomes are essential to inform patients and can guide shared decision-making between clinicians and patients.

Keywords: Back pain; Brace; Bracing; Congenital scoliosis; EOS, early-onset scoliosis; HRQoL, health-related quality of life; JIS, juvenile idiopathic scoliosis; Long-term outcome; ODI, Oswestry Disability Index; QoL, quality of life; Refined SRS-22r; SF-36; Scoliosis Research Society 22-item Questionnaire; Surgery; Treatment.

BrAIST-Calc: Prediction of Individualized Benefit from Bracing for Adolescent Idiopathic Scoliosis

Lori A Dolan, Stuart L Weinstein, Matthew B Dobbs, John M Jack Flynn, Daniel W Green, Matthew F Halsey, M Timothy Hresko, Walter F Krengel 3rd, Charles T Mehlman, Todd A Milbrandt, Peter O Newton, Nigel Price , James O Sanders, Michael L Schmitz, Richard M Schwend, Suken A Shah, Kit Song, Vishwas Talwalkar
Spine (Phila Pa 1976). 2023 Nov 23.doi: 10.1097/BRS.0000000000004879.


Study design: Prospective multicenter study data used for model derivation; externally-validated using retrospective cohort data.

Objective: Derive and validate a prognostic model of benefit from bracing for adolescent idiopathic scoliosis (AIS).

Summary of background data: The Bracing in Adolescent Idiopathic Scoliosis Trial (BrAIST) demonstrated superiority of bracing over observation to prevent curve progression to surgical threshold; 42% of untreated subjects had a good outcome and 28% progressed to surgical threshold despite bracing, likely due to poor adherence. To avoid over-treatment and to promote patient goal setting and adherence, bracing decisions (who and how much) should be based on physician and patient discussions informed by individual-level data from high-quality predictive models.

Methods: Logistic regression was used to predict curve progression to <45 degrees at skeletal maturity (good prognosis) in 269 BrAIST subjects who were observed or braced. Predictors included age, sex, body mass index (BMI), Risser stage, Cobb angle, curve pattern and treatment characteristics (hours of brace wear and in-brace correction). Internal and external validity were evaluated using jackknifed samples of the BrAIST dataset and an independent cohort (n=299) via estimates of discrimination and calibration.

Results: The final model included age, sex, BMI, Risser stage, Cobb angle and hours of brace wear/day. The model demonstrated strong discrimination (c-statistics 0.83 – 0.87) and calibration in all datasets. Classifying patients as low risk (high probability of a good prognosis) at the probability cut point of 70% resulted in a specificity of 92% and positive predictive value of 89%.

Conclusion: This externally-validated model can be used by clinicians and families to make informed, individualized decisions about when, and how much, to brace to avoid progression to surgery. If widely adopted, this model could decrease over-bracing of AIS, improve adherence and most importantly, decrease the likelihood of spinal fusion in this population.

Living in a brace

We know how important it is to share experiences and get comfort from those who are going through the same difficulties in a tiring and demanding therapy like that with exercises and braces. For this reason, a few months ago, we collected short testimonies from some of our patients participating in a summer camp organised by Isico.

Below, you can find one of these

I’m Alice- and I’ve been wearing a brace for more than two years. When I first got it, I was in my first year of High-School, and at the time, I was allowed 8 brace-off hours a day. Since I didn’t want to have to give up my dance and music, I started wearing my brace to school right from the start. I’ve never had any problems at school.

Between 2021 (when I first started my treatment) and today, I have managed to change, so drastically, the way I see my brace. The thing that helped me the most was being open about it, first with the people closest to me, of course. The fact that I stopped “hiding” my situation actually worked to my advantage.

My closest friends have always been very understanding and have never said anything even vaguely offensive. This has given me the confidence not to care or worry if someone notices my brace or if I have to mention it.

A very important person on this path was my physio Marta, whose sweet and smiley nature has made me enjoy my physiotherapy sessions, which, in theory, you would expect to be extremely boring.

Finally, I have to mention the summer camp in Riva del Garda Isico organised by Isico. It is a week-long camp where anyone can take part, as long as they wear or have worn a brace. This year I participated for the second time, together with the people who are probably my best friends, the other “braced guys” I met there last year. With them, going around with just your brace on, bathing in the lake, and swimming (as best you can, given your blocked back) were never a problem. In fact, we have loads of photos that show how much fun we all had. I know from experience how useful it can be to get to know someone who is in the same situation as you!

The effects of physiotherapeutic scoliosis-specific exercise on idiopathic scoliosis in children and adolescents: a systematic review and meta-analysis

Every year, the Italian Scoliosis Study Group selects the best published papers on conservative spine treatment from the global scientific literature.
Here is the abstract from one of these papers. 

The effects of physiotherapeutic scoliosis-specific exercise on idiopathic scoliosis in children and adolescents: a systematic review and meta-analysis

Kaiyue Ma, Chao Wang, Yajun Huang, Yu Wang, Dongsheng Li, Gang He 
Physiotherapy. 2023 Jul 24:121:46-57.doi: 10.1016/


Background: Physiotherapeutic scoliosis-specific exercise (PSSE) is recommended by SOSORT as the first step in the treatment of adolescent idiopathic scoliosis (AIS). However, a thorough summary and meta-analysis of the evidence for the effectiveness of PSSE is lacking.

Objective: To summarise the up-to-date evidence on the efficacy of PSSE in AIS compared with the other non-surgical therapies.

Data sources: The PubMed, Web of Science, Cochrane, Scopus, Embase and CNKI databases were systematically searched from 1 January 2012 to 1 November 2022.

Study selection: Controlled trials comparing the effects of PSSE and other non-surgical therapies on improving Cobb angle and quality of life in young people aged 6-18 years were included.

Data synthesis: Three researchers independently extracted data and evaluated methodological quality. Meta-analysis was performed where possible; otherwise, descriptive syntheses were reported.

Results: Seventeen studies with a total of 930 participants (76% female) were included. Among them, ten studies were RCTs. Six studies were of excellent quality. Thirteen studies were included in the meta-analysis. PSSE corrected the Cobb angle in patients better than other non-surgical therapies (I2 = 82%, MD = -2.82, 95%CI = -4.17 to -1.48, P < 0.01). PSSE was more effective than brace in improving patients’ pain, self-image and mental health. Patients with a Risser grade of 0-3 or who had never received brace therapy had better outcomes.

Conclusion: Evidence from higher quality studies suggests that PSSE was superior to general exercise and conventional therapy for correcting the Cobb angle in AIS.

Systematic review registration number: PROSPERO ID CRD42022345157 CONTRIBUTION OF THE PAPER.

Keywords: Adolescents; Meta-analysis; Physiotherapeutic scoliosis-specific exercise; Scoliosis.

Validation of an artificial intelligence-based method to automate Cobb angle measurement on spinal radiographs of children with adolescent idiopathic scoliosis

Every year, the Italian Scoliosis Study Group selects the best published papers on conservative spine treatment from the global scientific literature.
Here is the abstract from one of these papers. 

Validation of an artificial intelligence-based method to automate Cobb angle measurement on spinal radiographs of children with adolescent idiopathic scoliosis

Jason C Wong, Marek Z Reformat, Eric C Parent, Kyle P Stampe, Sarah C Southon Hryniuk, Edmond H Lou 

Eur. J Phys Rehabil Med. 2023 Aug;59(4):535-542. doi: 10.23736/S1973-9087.23.08091-7.


Background: Accurately measuring the Cobb angle on radiographs is crucial for diagnosis and treatment decisions for adolescent idiopathic scoliosis (AIS). However, manual Cobb angle measurement is time-consuming and subject to measurement variation, especially for inexperienced clinicians.

Aim: This study aimed to validate a novel artificial-intelligence-based (AI) algorithm that automatically measures the Cobb angle on radiographs.

Design: This is a retrospective cross-sectional study.

Setting: The population of patients attended the Stollery Children’s Hospital in Alberta, Canada.

Population: Children who: 1) were diagnosed with AIS, 2) were aged between 10 and 18 years old, 3) had no prior surgery, and 4) had a radiograph out of brace, were enrolled.

Methods: A total of 330 spinal radiographs were used. Among those, 130 were used for AI model development and 200 were used for measurement validation. Automatic Cobb angle measurements were validated by comparing them with manual ones measured by a rater with 20+ years of experience. Analysis was performed using the standard error of measurement (SEM), inter-method intraclass correlation coefficient (ICC<inf>2,1</inf>), and percentage of measurements within clinical acceptance (≤5°). Subgroup analysis was conducted by severity, region, and X-ray system to identify any systematic biases.

Results: The AI method detected 346 of 352 manually measured curves (mean±standard deviation: 24.7±9.5°), achieving 91% (316/346) of measurements within clinical acceptance. Excellent reliability was obtained with 0.92 ICC and 0.79° SEM. Comparable performance was found throughout all subgroups, and no systematic biases in performance affecting any subgroup were discovered. The algorithm measured each radiograph approximately 18s on average which is slightly faster than the estimated measurement time of an experienced rater. Radiographs taken by the EOS X-ray system were measured more quickly on average than those taken by a conventional digital X-ray system (10s vs. 26s).

Conclusions: An AI-based algorithm was developed to measure the Cobb angle automatically on radiographs and yielded reliable measurements quickly. The algorithm provides detailed images on how the angles were measured, providing interpretability that can give clinicians confidence in the measurements.

Clinical rehabilitation impact: Employing the algorithm in practice could streamline clinical workflow and optimize measurement accuracy and speed in order to inform AIS treatment decisions.

Impact of Scoliosis Severity on Gastrostomy-Related Complications in Children

Every year, the Italian Scoliosis Study Group selects the best published papers on conservative spine treatment from the global scientific literature.
Here is the abstract from one of these papers. 

Impact of Scoliosis Severity on Gastrostomy-Related Complications in Children

Sade Toker Kurtmen, Aslihan Nalli, Mustafa Onur Oztan, Gokhan Koyluoglu 
Pediatr Gastroenterol Nutr. 2023 Jun 29.doi: 10.1097/MPG.0000000000003879


Objectives: This study aimed to determine the relationship between scoliosis and risk of developing complications in patients who underwent gastrostomy.

Methods: Patients who underwent percutaneous gastrostomy (PEG) or surgical gastrostomy (SG) between 2012 and 2022 were included. Leakage, discharge, granuloma, and hyperemia were considered minor complications, while visceral injury, ileus, and re-do surgery were considered major complications. The degree of scoliosis was calculated using the Cobb angle. The SG and PEG groups were compared by evaluating the complications and their correlation with scoliosis.

Results: A total of 104 patients with a mean age of 5.0 ± 5.3 were included. 58% of patients were treated with SG. Patients in the SG group were younger (p<0.001). Minor complications were significantly more common in the PEG group (p=0.018). There was no difference between the groups in terms of major complications (p=1,000). Scoliosis was observed in 32.7% of the patients (n=34). In the SG group, no correlation was found between the Cobb angle and the frequency of minor (p=0.173) or major complications (p=0.305). There was no significant difference between the Cobb angles of patients with and without minor complications in the PEG group (p=0.478); the Cobb angles of patients with major complications (75-degrees) were significantly higher than those without (36-degrees) (p=0.030).

Conclusion: Gastrostomy is important for weight gain and nutritional needs of children. This study showed that the risk of complications in SGs did not correlate with the degree of scoliosis and that the risk of major complications in PEGs increased in patients with a high degree of scoliosis.

Directed Versus non-directed Standing Postures in Adolescent Idiopathic Scoliosis: Its Impact on Curve Magnitude, Alignment and Clinical Decision Making

Every year, the Italian Scoliosis Study Group selects the best published papers on conservative spine treatment from the global scientific literature.
Here is the abstract from one of these papers. 

Prudence Wing Hang Cheung, Hei Lung Wong, Damian S L Lau, Jason Pui Yin Cheung 
Spine (Phila Pa 1976). 2023 Jul 3. doi: 10.1097/BRS.0000000000004731. Online ahead of print


Study design: Prospective study.

Objective: To investigate the difference in major curve Cobb angle and alignment between directed and non-directed positioning for adolescent idiopathic scoliosis (AIS) and to evaluate implications on treatment decision-making.

Summary of background data: Proper positioning of patients with spinal deformities is important for assessing usual functional posture in standing, so management strategies can be customized accordingly. Whether postural variability affects coronal and sagittal radiological parameters and the impact of posture on management decisions remain unknown.

Methods: Patients with AIS presenting for initial consultation at the tertiary scoliosis clinic were recruited. They were asked to stand in two positions: passive, non-directed position; and directed position by the radiographer. Radiological assessment included major and minor Cobb angle, coronal balance, spinopelvic parameters, sagittal balance and alignment. Cobb angle difference >5⁰ between directed and non-directed positioning was considered clinically impactful. Patients with or without such difference were compared. Over- or under-estimation of the major curve (at 25⁰ or 40⁰) by non-directed positioning were examined due to relevance to bracing and surgical indications.

Results: This study included 198 patients, with 22.2% experiencing Cobb angle difference (>5⁰) between positioning. The major curve Cobb angle was smaller in non-directed than directed positioning (median difference: -6.0⁰, upper and lower quartile: -7.8, 5.8), especially for curves ≥30⁰. Patients with a Cobb angle difference had changes in shoulder balance (P=0.007) when assuming a directed position. Non-directed positioning had 14.3% of major Cobb 25⁰ underestimated and 8.8% overestimated, whereas 11.1% of curves >40⁰ were underestimated.

Conclusion: Strict adherence to a standardized radiographic protocol is mandatory for reproducing spine radiographs reliable for curve assessment, as a non-directed position demonstrates smaller Cobb angles. Postural variation may lead to over-, or under-estimation, of the curve size relevant for both bracing and surgical decision-making.