Classification Of Scoliosis Research Articles

P37. Automated scoliosis classification from EOS full body imaging through artificial intelligence: a deep learning approach with RadImageNet

P37. Automated scoliosis classification from EOS full body imaging through artificial intelligence: a deep learning approach with RadImageNet

Validation of Artificial Intelligence in the Classification of Adolescent Idiopathic Scoliosis and the Compairment to Clinical Manual Handling.

The accurate measurement of Cobb angles is crucial for the effective clinical management of patients with adolescent idiopathic scoliosis (AIS). The Lenke classification system plays a pivotal role in determining the appropriate fusion levels for treatment planning. However, the presence of interobserver variability and time-intensive procedures presents challenges for clinicians. The purpose of this study is to compare the measurement accuracy of our developed artificial intelligence measurement system for Cobb angles and Lenke classification in AIS patients with manual measurements to validate its feasibility. An artificial intelligence (AI) system measured the Cobb angle of AIS patients using convolutional neural networks, which identified the vertebral boundaries and sequences, recognized the upper and lower end vertebras, and estimated the Cobb angles of the proximal thoracic, main thoracic, and thoracolumbar/lumbar curves sequentially. Accordingly, the Lenke classifications of scoliosis were divided by oscillogram and defined by the AI system. Furthermore, a man-machine comparison (n = 300) was conducted for senior spine surgeons (n = 2), junior spine surgeons (n = 2), and the AI system for the image measurements of proximal thoracic (PT), main thoracic (MT), thoracolumbar/lumbar (TL/L), thoracic sagittal profile T5-T12, bending views PT, bending views MT, bending views TL/L, the Lenke classification system, the lumbar modifier, and sagittal thoracic alignment. In the AI system, the calculation time for each patient's data was 0.2 s, while the measurement time for each surgeon was 23.6 min. The AI system showed high accuracy in the recognition of the Lenke classification and had high reliability compared to senior doctors(ICC 0.962). The AI system has high reliability for the Lenke classification and is a potential auxiliary tool for spinal surgeons.

Transitional and spectrum-based care for idiopathic scoliosis.

The goal of this study is to discuss the transitional nature of idiopathic scoliosis and the variation in treatment and management across the spectrum of age presentation. This is a review article that discusses the evaluation, management, and classification of idiopathic scoliosis. The authors searched PubMed/MEDLINE, Google Scholar, and the Cochrane database for articles published up to April 2024. Keywords and MeSH terms relevant to the topic were used, including adolescent idiopathic scoliosis (AIS), adult idiopathic scoliosis (AdIS), adult degenerative scoliosis, young adult idiopathic scoliosis, early-onset scoliosis (EOS), classification, management, follow-up, outcomes, natural history, Cobb angle, and transitional care. Reference lists of selected articles were also searched to identify further articles. Inclusion criteria included English language articles that summarized any type of study design, including randomized controlled trials, observational studies, case-control/series, or metaanalysis, with study populations ranging from infants to > 50-year-old patients. Inter-reviewer disagreement on inclusion of particular articles was resolved through discussion. Related information was analyzed, and relevant concepts related to the transitional period dilemma have been discussed. Each idiopathic scoliosis case needs independent assessment with regard to the age, degree of the curve, and patient-specific presentation. An accurate prediction of the curve progression by considering the patient's remaining growth potential is paramount to the treatment strategy. The classification system for EOS, AIS Lenke classification, AdIS classification, and the Scoliosis Research Society-Schwab classification are important for reliable communication between surgeons treating deformities. Untreated progressive idiopathic scoliosis warrants multidisciplinary management during the transition from EOS stage to AIS and then to AdIS. Also, surgical treatment of untreated AIS transitioning to AdIS is specific and nuanced. AdIS needs to be differentiated from adult degenerative scoliosis because the latter is associated with multiple comorbidities and anatomical differences. Idiopathic scoliosis presents across the age spectrum with specific age-related decisions that transition into adulthood. Integrated models of both surgical and nonsurgical treatment of idiopathic scoliosis are warranted.

Assessing the Accuracy of Artificial Intelligence Models in Scoliosis Classification and Suggested Therapeutic Approaches.

Background: Open-source artificial intelligence models (OSAIMs) are increasingly being applied in various fields, including IT and medicine, offering promising solutions for diagnostic and therapeutic interventions. In response to the growing interest in AI for clinical diagnostics, we evaluated several OSAIMs-such as ChatGPT 4, Microsoft Copilot, Gemini, PopAi, You Chat, Claude, and the specialized PMC-LLaMA 13B-assessing their abilities to classify scoliosis severity and recommend treatments based on radiological descriptions from AP radiographs. Methods: Our study employed a two-stage methodology, where descriptions of single-curve scoliosis were analyzed by AI models following their evaluation by two independent neurosurgeons. Statistical analysis involved the Shapiro-Wilk test for normality, with non-normal distributions described using medians and interquartile ranges. Inter-rater reliability was assessed using Fleiss' kappa, and performance metrics, like accuracy, sensitivity, specificity, and F1 scores, were used to evaluate the AI systems' classification accuracy. Results: The analysis indicated that although some AI systems, like ChatGPT 4, Copilot, and PopAi, accurately reflected the recommended Cobb angle ranges for disease severity and treatment, others, such as Gemini and Claude, required further calibration. Particularly, PMC-LLaMA 13B expanded the classification range for moderate scoliosis, potentially influencing clinical decisions and delaying interventions. Conclusions: These findings highlight the need for the continuous refinement of AI models to enhance their clinical applicability.

Automatic Lenke classification of adolescent idiopathic scoliosis with deep learning.

The Lenke classification system is widely utilized as the preoperative evaluation protocol for adolescent idiopathic scoliosis (AIS). However, manual measurement is susceptible to observer-induced variability, which consequently impacts the evaluation of progression. The goal of this investigation was to develop an automated Lenke classification system utilizing innovative deep learning algorithms. Using the database from the First Affiliated Hospital of Sun Yat-sen University, the whole spinal x-rays images were retrospectively collected. Specifically, images collection was divided into AIS and control group. The control group consisted of individuals who underwent routine health checks and did not have scoliosis. Afterwards, relative features of all images were annotated. Deep learning was implemented through the utilization of the key-point based detection method to realize the vertebral detection, and Cobb angle measurement and scoliosis classification were performed based on relevant standards. Besides, the segmentation method was employed to achieve the recognition of lumbar vertebral pedicle to determine the type of lumbar spine modifier. Finally, the model performance was further quantitatively analyzed. In the study, a total of 2082 spinal x-ray images were collected from 407 AIS patients and 227 individuals in the control group. The model for vertebral detection achieved an F1-score of 0.809 for curve type evaluation and an F1-score of 0.901 for thoracic sagittal profile. The intraclass correlation efficient (ICC) of the Cobb angle measurement was 0.925. In the analysis of performance for vertebra pedicle segmentation model, the F1-score of lumbar modification profile was 0.942, the intersection over union (IOU) of the target pixels was 0.827, and the Hausdorff distance (HD) was 6.565 ± 2.583 mm. Specifically, the F1-score for ultimate Lenke type classifier was 0.885. This study has constructed an automated Lenke classification system by employing the deep learning networks to achieve the recognition pattern and feature extraction. Our models require further validation in additional cases in the future.

A Novel Classification of Juvenile and Adolescent Idiopathic Scoliosis for Conservative Treatment

The operative classification of scoliosis is well-developed but inadequate for guiding conservative treatment. The current conservative classification for juvenile and adolescent idiopathic scoliosis (JAIS) exhibits noticeable deficiencies. This study aimed to establish the Peking Union Medical College Hospital (PUMCH) classification and assess its clinical value in the conservative treatment of JAIS. This study consisted of 2 parts. First, it involved a retrospective analysis of patients treated for JAIS in the Department of Rehabilitation Medicine, the ∗∗∗ Union Medical College Hospital, between January 2013 and June 2020. Second, it involved an ambispective cohort study that enrolled patients with JAIS in the above hospital between July and December2020. A total of 989 patients with JAIS were enrolled, with 899 patients for establishing the PUMCH classification and 90 patients with JAIS for validating the PUMCH classification. The classification demonstrated an average reliability of 88.22% with a kappa coefficient of 0.862. After 1week, the remeasured results presented a mean reproducibility of 92.78% and a kappa coefficient of 0.908. After 1-year follow-up, the Cobb angle decreased significantly from 16.61±2.88° to 12.16°±9.97° (P= 0.002) in 51 patients with PUMCH-scoliosis-specific exercise (SSE) treatment, while the Cobb angle increased significantly from 15.74±2.75° to 17.64±5.60° (P= 0.014) in 39 patients without PUMCH-SSE treatment. The PUMCH-SSE classification demonstrates good inter-observer reliability and intra-observer reproducibility. In addition, the classification may be used to guide the conservative treatment of JAIS in clinical settings.

Prediction of postoperative curve correction based on the supine radiographs for adult idiopathic scoliosis patients

BACKGROUND CONTEXTPreoperative supine radiographs are mandatory in the new adult idiopathic scoliosis (AdIS) classification. Supine radiographs are easily reproducible and highly predictive of side bending radiographs. However, few studies evaluated the use of supine radiographs in predicting postoperative curve correction after posterior spinal fusion (PSF) in AdIS. PURPOSETo investigate the use of supine and side bending (SB) radiographs in predicting postoperative curve correction in AdIS patients who underwent PSF. STUDY DESIGNRetrospective study. PATIENT SAMPLEA total of 93 AdIS patients who underwent PSF between 2022 and 2023 were included. OUTCOME MEASURESDemographic data were age, gender, height, weight, body mass index (BMI), Risser grade, Lenke curve types and Cobb angles. Main outcome measures were preoperative and immediate postoperative Cobb angle (proximal thoracic [PT], main thoracic [MT] and thoracolumbar/lumbar [TL/L] curves), Supine Cobb angle and Flexibility rate (PT, MT and TL/L), and Correction rate (PT, MT and TL/L). METHODSCorrelation study was performed between Supine Cobb angle vs postoperative Cobb angle for PT, MT and TL/L curves. A predictive formula was derived from the correlation plots. RESULTSA total of 93 subjects were included in our study with a median age of 24.7 years and comprised of 80 females (86.0%). Preoperative Supine Cobb angle (r=0.835, r=0.881, r=0.767, p<.001) and preoperative SB Cobb angle (r=0.815, r=0.872, r=0.801, p<.001) showed similar strong positive correlation with postoperative PT, MT and TL/L Cobb angle, but preoperative Supine Cobb angle had slightly stronger correlation in PT and MT, whereas preoperative SB Cobb angle had stronger correlation in TL/L curve. Using the derived predictive formulae, there was a significant, strong, positive correlation between the predicted value and actual value of postoperative standing Cobb angle, (r=0.852, p<.001), with 71.0% of the patients had predicted postoperative Cobb angle from the supine radiographs within 5° of the actual value. CONCLUSIONBoth supine radiographs and side bending radiographs had strong predictability of the postoperative Cobb angle for PT, MT and TL/L curves. In 71.0% of patients, the actual postoperative Cobb angle was within 5° of the predicted postoperative Cobb angle using the predictive formulae.

Application Of Exercise Therapy in Scoliosis Rehabilitation

Scoliosis affects people of all ages, especially young adults. Idiopathic scoliosis in adolescents is a common deformity and has a high prevalence. In the early stages, its progress is difficult to detect, but the harm is not underestimated. Therefore, early detection and early intervention or treatment awareness are particularly important for scoliosis. The aim of this paper is to provide a comprehensive review of the classification and diagnosis of scoliosis. Also, the various treatments for different types and degrees of scoliosis are heavily discussed in this paper. A wide range of factors can influence and pace the development of scoliosis, for example, nutrition, genetics, and even sex (females are more prone to have severe scoliosis than males). Currently, due to a limited understanding of the causes and development of spinal deformities, there are no comprehensive, widespread, and recognized effective treatments to prevent or alleviate scoliosis, which means that each case of scoliosis must be managed and cared for with its unique characteristics.

The Role of Muscle Biomarkers in Adolescent Idiopathic Scoliosis.

Adolescent idiopathic scoliosis (AIS) is the predominant orthopedic disorder in children, affecting 1-3% of the global population. Research in this field has tried to delineate the genetic factors behind scoliosis and its association with heredity since AIS is considered a polygenic disease and has different genetic and epigenetic factors. The current study conducted a narrative review of the literature, focusing on biomarkers in the pathophysiology of muscle in AIS patients. Articles were collected from Scopus, Pubmed, and Web of Science. The key screening parameters were scoliosis classification, sampling, and the biomarkers evaluated. This review emphasizes potential key mechanisms and molecular regulators in muscle tissue. While there has been limited focus on the proteins contributing to muscle changes in AIS, significant attention has been given to genomic studies of single-nucleotide polymorphisms, particularly in LBX1. Despite these efforts, the exact causes of AIS remain elusive, with several theories suggesting genetic and hormonal factors. This review identified critical protein biomarkers such as Gi-protein alpha subunits, fibrillin-1 and -2, and various differentially expressed proteins, which may be linked to muscle alterations in AIS. This field of research is still limited due to a lack of homogeneity in the distinction of patients by groups and curve severity. Although the pathophysiology of AIS is still unclear, molecular research is important to guide the treatment of AIS before achieving skeletal maturity, thus avoiding serious problems associated with posture changes and low quality of life. In the future, a more comprehensive synergy between orthopedic and molecular research might ameliorate the diagnosis and treatment of AIS patients.

Artificial Intelligence in Scoliosis Classification: An Investigation of Language-Based Models.

Open-source artificial intelligence models are finding free application in various industries, including computer science and medicine. Their clinical potential, especially in assisting diagnosis and therapy, is the subject of increasingly intensive research. Due to the growing interest in AI for diagnostics, we conducted a study evaluating the abilities of AI models, including ChatGPT, Microsoft Bing, and Scholar AI, in classifying single-curve scoliosis based on radiological descriptions. Fifty-six posturographic images depicting single-curve scoliosis were selected and assessed by two independent neurosurgery specialists, who classified them as mild, moderate, or severe based on Cobb angles. Subsequently, descriptions were developed that accurately characterized the degree of spinal deformation, based on the measured values of Cobb angles. These descriptions were then provided to AI language models to assess their proficiency in diagnosing spinal pathologies. The artificial intelligence models conducted classification using the provided data. Our study also focused on identifying specific sources of information and criteria applied in their decision-making algorithms, aiming for a deeper understanding of the determinants influencing AI decision processes in scoliosis classification. The classification quality of the predictions was evaluated using performance evaluation metrics such as sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and balanced accuracy. Our study strongly supported our hypothesis, showing that among four AI models, ChatGPT 4 and Scholar AI Premium excelled in classifying single-curve scoliosis with perfect sensitivity and specificity. These models demonstrated unmatched rater concordance and excellent performance metrics. In comparing real and AI-generated scoliosis classifications, they showed impeccable precision in all posturographic images, indicating total accuracy (1.0, MAE = 0.0) and remarkable inter-rater agreement, with a perfect Fleiss' Kappa score. This was consistent across scoliosis cases with a Cobb's angle range of 11-92 degrees. Despite high accuracy in classification, each model used an incorrect angular range for the mild stage of scoliosis. Our findings highlight the immense potential of AI in analyzing medical data sets. However, the diversity in competencies of AI models indicates the need for their further development to more effectively meet specific needs in clinical practice.

Y-shaped osteotomy in the apical vertebra for treating congenital complex rigid scoliosis:at least 2-year follow-up

Objective: To investigate the clinical outcome of the coronal Y-shaped osteotomy in the apical vertebra for treating congenital complex rigid scoliosis. Methods: A retrospective analysis was conducted on 66 cases who underwent Y-shaped osteotomy treatment for congenital complex rigid scoliosis in the uppermost vertebra at the Department of Orthopedics,the Second Hospital of Shanxi Medical University from June 2007 to August 2020. There were 19 males and 47 females,with an age of (13.1±5.3) years(range:2 to 30 years).Classification of congenital scoliosis:25 cases (37.9%) were incomplete,13 cases (19.7%) were dysarthritic,and 28 cases (42.4%) were mixed. There were 25 cases (37.9%) with thoracic or rib malformations. 45 cases (68.2%) were complicated with spinal cord malformation.The main radiological indicators included Cobb angle of the curvature,Cobb angle of the local bend,apical vertebral translation (AVT),trunk shift (TS),thoracic trunk shift (TTS),radiographic shoulder height (RSH),coronal balance and sagittal vertebral axis. The preoperative,postoperative immediate,and last follow-up radiological indicators were collected and the operation time,blood loss,hospitalization time,and operation-related complications were recorded. Data were compared by repeated measure ANOVA and paired-t test. Results: All patients underwent surgery successfully. The duration of the first surgery was (221.4±52.8) minutes,and the blood loss during the first surgery was (273.2±41.8) ml. The length of the first hospital stay was (8.8±1.7) days.Unilateral fixation was performed in 19 cases (28.8%),while bilateral fixation was performed in 47 cases (71.2%). The fused segments were 7.5±2.9,and the vertebral pedicle screw density was (68.5±20.6)%. The follow-up time for the 66 patients was (36.7±17.0) months(range:24 to 102 months).The main curve Cobb Angle was improved from (58.5±18.9)°before surgery to (21.1±11.8)°after surgery,and was (23.6±15.3) ° at the last follow-up(F=273.957,P<0.01),with a correction rate of 66.2%. Segmental curve Cobb Angle was improved from (47.9±18.0)° to (16.0±11.3)° after surgery,and was (16.8±12.8) °at the last follow-up (F=270.483,P<0.01)with a correction rate of 69.2%. The AVT,TS,TTS and RSH values improved significantly at the final follow-up (all P<0.05),while coronal balance and sagittal vertical axis were maintained without significant differences between pre-operation and post-operation(both P>0.05). A total of 5 patients underwent staged operation,all of which were residual scoliosis aggravated after the first stage of orthosis operation and had good prognosis after the second stage of operation. Conclusions: Y-shaped osteotomy for the treatment of congenital rigid scoliosis results in good clinical and radiological outcomes without serious complications. This procedure can be considered as an option for the treatment of congenital complex rigid scoliosis.

Analysis of the mechanism and clinical classification of thoracolumbar scoliosis using three-dimensional EOS and surface electromyography

To analyze a thoracolumbar scoliosis group, we analyzed data from the acquired database by groups: the sEMG group (n = 16) and 3D-EOS group (n = 55). The asymmetric hyper/hypoactivation ratio of muscle and LLD (>3 mm) were measured in the sEMG group. In the 3D-EOS group, we recorded the values of parameters including LLD, pelvis rotation, and kyphosis/lordosis. In the sEMG study, sEMG examinations were conducted individually in patients with idiopathic scoliosis to analyze hyper/hypoactivation of the paraspinal muscle. In the three-dimensional EOS study, the Cobb angle, femoral height difference, and thoracic kyphosis and lumbar lordosis angles were measured using 2D images and 3D reconstructed images.Sixteen patients with thoracolumbar scoliosis were classified into asymmetric hyperactivation (A-Hyper) and asymmetric hypoactivation (A-Hypo) groups. The Cobb angle of the A-Hyper subtype was significantly higher than that of the A-Hypo subtype (22.41 versus 15.2, p = 0.023). Coronal deviation (p = 0.028) and the pelvis rotation angle (p = 0.001) were significantly higher in the LLD (+) subtype than in the LLD (−) subtype. When we classified patients cross-sectionally along with A-Hyper/Hypo and LLD (±), A-Hyper elevated the Cobb angle, and LLD (+) was significantly correlated with coronal deviation and pelvis rotation. In the 3D-EOS evaluation, the pelvic height difference (p = 0.043) and coronal deviation (p = 0.001) were significantly higher in the LLD (+) subtype than in the LLD (−) subtype.In conclusions, paraspinal muscular asymmetry and LLD can be strong factors in inducing or progressing thoracolumbar scoliosis.

Lenke Classification of Scoliosis Based on Segmentation Network and Adaptive Shape Descriptor

Scoliosis is a common spinal deformity that seriously affects patients’ physical and mental health. An accurate Lenke classification is greatly significant for evaluating and treating scoliosis. Currently, the clinical diagnosis mainly relies on manual measurement; however, using computer vision assists with an intelligent diagnosis. Due to the complex rules of Lenke classification and the characteristics of medical imaging, the fully automated Lenke classification of scoliosis remains a considerable challenge. Herein, a novel Lenke classification method for scoliosis using X-rays based on segmentation networks and adaptive shape descriptors is proposed. Three aspects of our method should be noted in comparison with the previous approaches. We used Unet++ to segment the vertebrae and designed a post-processing operation to improve the segmentation effect. Then, we proposed a new shape descriptor to extract the shape features for segmented vertebrae in greater detail. Finally, we proposed a new Lenke classification framework for scoliosis that contains two schemes based on Cobb angle measurement and shape classification, respectively. After rigorous experimental evaluations on a public dataset, our method achieved the best performance and outperformed other sophisticated approaches.

RETRATO EPIDEMIOLÓGICO DE ESCOLIOSE PEDIÁTRICA EM UM HOSPITAL TERCIÁRIO NO BRASIL

ABSTRACT Objective: To trace the epidemiological profile of patients with pediatric scoliosis in a tertiary hospital in the region of Campinas - SP, seeking to understand and evaluate the demand of these patients, the results of delay in treatment, and its impact on the progression of the deformity. Methods: An epidemiological, observational, and cross-sectional study was carried out in a digital database, including patients from 0 to 18 years of age, where sociodemographic variables, scoliosis classification, and institutional follow-up and treatment data were collected. Results: The sample had 30 patients who met the inclusion criteria. The age of the patients ranged from 5 years to 18 years, with a mean of 12.8 years. Neuromuscular scoliosis was the most prevalent etiology (40%), followed by congenital scoliosis (36.6%) and, to a lesser extent, idiopathic scoliosis (23.3%). The patient follow-up time between the first and last appointment has an average of 74.7 months. When the specialty monitors the patient, the initial and final Cobb angles are evaluated in degrees, with a percentage increase of 40.3%. Delay in care (outpatient care, conservative treatment, or surgery) was identified in 25 patients (83.3% of the sample). Conclusion: Most of the patients evaluated showed evolution of the scoliosis condition, especially due to the delay in care, failure to obtain surgical treatment, or even conservative treatment in an adequate time, with an increase in the magnitude of the curve and greater severity of the case. Level of Evidence III; Observational, Cross-Sectional Study.

Semi-automatic method for pre-surgery scoliosis classification on X-ray images using Bending Asymmetry Index.

Bending Asymmetry Index (BAI) has been proposed to characterize the types of scoliotic curve in three-dimensional ultrasound imaging. Scolioscan has demonstrated its validity and reliability in scoliosis assessment with manual assessment-based X-ray imaging. The objective of this study is to investigate the ultrasound-derived BAI method to X-ray imaging of scoliosis, with supplementary information provided for the pre-surgery planning. About 30 pre-surgery scoliosis subjects (9 males and 21 females; Cobb: 50.9 ± 19.7°, range 18°-115°) were investigated retrospectively. Each subject underwent three-posture X-ray scanning supine on a plain mattress on the same day. BAI is an indicator to distinguish structural or non-structural curves through the spine flexibility information obtained from lateral bending spinal profiles. BAI was calculated semi-automatically with manual annotation of vertebral centroids and pelvis level inclination adjustment. BAI classification was validated with the scoliotic curve type and traditional Lenke classification using side-bending Cobb angle measurement (S-Cobb). 82 curves from 30 pre-surgery scoliosis patients were included. The correlation coefficient was R2 = 0.730 (p < 0.05) between BAI and S-Cobb. In terms of scoliotic curve type classification, all curves were correctly classified; out of 30 subjects, 1 case was confirmed as misclassified when applying to Lenke classification earlier, thus has been adjusted. BAI method has demonstrated its inter-modality versatility in X-ray imaging application. The curve type classification and the pre-surgery Lenke classification both indicated promising performances upon the exploratory dataset. A fully-automated of BAI measurement is surely an interesting direction to continue our endeavor. Deep learning on the vertebral-level segmentation should be involved in further study.

Identification and Classification of Scoliosis Using CNN And SVM Algorithms

Identification and Classification of Scoliosis Using CNN And SVM Algorithms

Classification of mild and severe adolescent idiopathic scoliosis (AIS) from healthy subjects via a supervised learning model based on electromyogram and ground reaction force data during gait

At early stages, adolescent idiopathic scoliosis (AIS) is quite hard to be distinguished from healthy (HC) subjects by the naked eye. AIS demands multiple corrective surgeries when detected later, thereby causing significant physical and psychological trauma as no mathematical models exist for the classification of mild AIS (MS) (20° < Cobb’s angle < 40°) from HC, we propose a k-nearest neighbour (kNN) method based model. In this work, we collected both the EMG and GRF data from nine severe AIS (SS), three MS and four female HC during gait. Delayed muscle activation in Erector spinatus Iliocostalis, Gluteus Medius and Gastrocnemius lateralis was observed in SS compared to HC. However, no such distinction was noticed between MS and HC motivating for a mathematical model. Eighteen time-domain and nine frequency-domain features were computed from the EMG data of 14 lower extremity muscles, while five time-domain features were calculated from GRF data during gait. Out of all the features computed for each subject, the principal component analysis (PCA) yielded 15 principal components that coupled both time and frequency domains (TFD). Further, the kNN model classified SS, MS and HC from each other by these 15 TFD features. The model was trained and validated using 32 and 21 EMG and GRF data datasets during gait, respectively. The classification and validation accuracy of 90.6% and 85.7% were obtained among SS, MS and HC. The proposed model is capable of early detection of AIS and can be used by medical professionals to plan treatments and corrective measures.

Computerized-Assisted Scoliosis Diagnosis Based on Faster R-CNN and ResNet for the Classification of Spine X-Ray Images.

In order to reduce the subjectivity of preoperative diagnosis and achieve accurate and rapid classification of idiopathic scoliosis and thereby improving the standardization and automation of spinal surgery diagnosis, we implement the Faster R-CNN and ResNet to classify patient spine images. In this paper, the images are based on spine X-ray imaging obtained by our radiology department. We compared the results with the orthopedic surgeon's measurement results for verification and analysis and finally presented the grading results for performance evaluation. The final experimental results can meet the clinical needs, and a fast and robust deep learning-based scoliosis diagnosis algorithm for scoliosis can be achieved without manual intervention using the X-ray scans. This can give rise to a computerized-assisted scoliosis diagnosis based on X-ray imaging, which has strong potential in clinical utility applied to the field of orthopedics.

Scoliosis in dysplastic spondylolisthesis: a clinical survey of 50 young patients

BackgroundDysplastic spondylolisthesis is a rare spinal deformity that occurs mainly in young patients. Although its sagittal parameters had been well stated, coronal abnormalities in these patients were poorly studied. The purposes of this study were: (1) to investigate the prevalence of scoliosis in dysplastic spondylolisthesis;(2) to assess scoliosis resolution or persistence after surgery; and (3) to propose a modified classification of scoliosis associated with dysplastic spondylolisthesis.MethodsFifty patients (average age 14.9 ± 5.6 years) diagnosed with dysplastic spondylolisthesis who underwent surgical treatment were followed up and their data were analyzed. Standing posteroanterior and lateral full spine radiographs were used to measure the coronal and sagittal parameters. Patients with scoliosis, which was defined as a coronal Cobb angle greater than 10°, were divided into three groups according to their curve characteristics: “independent” scoliosis (IS) group, spasm scoliosis (SS) group, and olisthetic scoliosis (OS) group. SS and OS were spondylolisthesis-induced scoliosis. The radiographic parameters and patient-reported outcomes were collected before and after surgery and compared between groups.ResultsThe average slip percentage was 62.8% ± 23.1% and the average follow-up time was 51.5 ± 36.4 months (range 3–168 months). Twenty-eight of the 50 (56%) dysplastic spondylolisthesis patients showed scoliosis, of which 8 were IS (24.7° ± 15.2°), 11 were SS (13.9° ± 3.0°), and 9 were OS (12.9° ± 1.9°). By the last follow-up, no scoliosis resolution was observed in the IS group whereas all SS patients were relieved. Of the nine patients with OS, four (44.4%) had scoliosis resolution after surgery.ConclusionDistinguishing different types of scoliosis in dysplastic spondylolisthesis patients may help surgeons to plan treatment and understand prognosis. For patients with significant scoliosis, whether “independent” or spondylolisthesis-induced, treatment of spondylolisthesis should be performed first and scoliosis should be observed for a period of time and treated according to the corresponding principles.

Integrated Evolving Spiking Neural Network and Feature Extraction Methods for Scoliosis Classification

Adolescent Idiopathic Scoliosis (AIS) is a deformity of the spine that affects teenagers. The current method for detecting AIS is based on radiographic images which may increase the risk of cancer growth due to radiation. Photogrammetry is another alternative used to identify AIS by distinguishing the curves of the spine from the surface of a human’s back. Currently, detecting the curve of the spine is manually performed, making it a time-consuming task. To overcome this issue, it is crucial to develop a better model that automatically detects the curve of the spine and classify the types of AIS. This research proposes a new integration of ESNN and Feature Extraction (FE) methods and explores the architecture of ESNN for the AIS classification model. This research identifies the optimal Feature Extraction (FE) methods to reduce computational complexity. The ability of ESNN to provide a fast result with a simplicity and performance capability makes this model suitable to be implemented in a clinical setting where a quick result is crucial. A comparison between the conventional classifier (Support Vector Machine (SVM), Multi-layer Perceptron (MLP) and Random Forest (RF)) with the proposed AIS model also be performed on a dataset collected by an orthopedic expert from Hospital Universiti Kebangsaan Malaysia (HUKM). This dataset consists of various photogrammetry images of the human back with different types of Malaysian AIS patients to solve the scoliosis problem. The process begins by pre-processing the images which includes resizing and converting the captured pictures to gray-scale images. This is then followed by feature extraction, normalization, and classification. The experimental results indicate that the integration of LBP and ESNN achieves higher accuracy compared to the performance of multiple baseline state-of-the-art Machine Learning for AIS classification. This demonstrates the capability of ESNN in classifying the types of AIS based on photogrammetry images.