A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography

Validating the Accuracy of a Patient-Facing Clinical Decision Support System in Predicting Lumbar Disc Herniation: Diagnostic Accuracy Study

BACKGROUND

Low back pain (LBP) is a major cause of disability globally, and the diagnosis of LBP is challenging for clinicians.

OBJECTIVE

Using new software called Therapha, this study aimed to assess the accuracy level of artificial intelligence as a Clinical Decision Support System (CDSS) compared to MRI in predicting lumbar disc herniated patients.

METHODS

One hundred low back pain patients aged ≥18 years old were included in the study. The study was conducted in three stages. Firstly, a case series was conducted by matching MRI and Therapha diagnosis for 10 patients. Subsequently, Delphi methodology was employed to establish a clinical consensus. Finally, to determine the accuracy of the newly developed software, a cross-sectional study was undertaken involving 100 patients.

RESULTS

The software showed a significant diagnostic accuracy with the area under the curve in the ROC analysis determined as 0.84 with a sensitivity of 88% and a specificity of 80%.

CONCLUSIONS

The study's findings revealed that CDSS using Therapha has a reasonable level of efficacy, and this can be utilized clinically to acquire a faster and more accurate screening of patients with lumbar disc herniation.

Sagittal balance parameters measurement on cervical spine MR images based on superpixel segmentation

Introduction: Magnetic Resonance Imaging (MRI) is essential in diagnosing cervical spondylosis, providing detailed visualization of osseous and soft tissue structures in the cervical spine. However, manual measurements hinder the assessment of cervical spine sagittal balance, leading to time-consuming and error-prone processes. This study presents the Pyramid DBSCAN Simple Linear Iterative Cluster (PDB-SLIC), an automated segmentation algorithm for vertebral bodies in T2-weighted MR images, aiming to streamline sagittal balance assessment for spinal surgeons. Method: PDB-SLIC combines the SLIC superpixel segmentation algorithm with DBSCAN clustering and underwent rigorous testing using an extensive dataset of T2-weighted mid-sagittal MR images from 4,258 patients across ten hospitals in China. The efficacy of PDB-SLIC was compared against other algorithms and networks in terms of superpixel segmentation quality and vertebral body segmentation accuracy. Validation included a comparative analysis of manual and automated measurements of cervical sagittal parameters and scrutiny of PDB-SLIC's measurement stability across diverse hospital settings and MR scanning machines. Result: PDB-SLIC outperforms other algorithms in vertebral body segmentation quality, with high accuracy, recall, and Jaccard index. Minimal error deviation was observed compared to manual measurements, with correlation coefficients exceeding 95%. PDB-SLIC demonstrated commendable performance in processing cervical spine T2-weighted MR images from various hospital settings, MRI machines, and patient demographics. Discussion: The PDB-SLIC algorithm emerges as an accurate, objective, and efficient tool for evaluating cervical spine sagittal balance, providing valuable assistance to spinal surgeons in preoperative assessment, surgical strategy formulation, and prognostic inference. Additionally, it facilitates comprehensive measurement of sagittal balance parameters across diverse patient cohorts, contributing to the establishment of normative standards for cervical spine MR imaging.

Recommended Requirements and Essential Elements for Proper Reporting of the Use of Artificial Intelligence Machine Learning Tools in Biomedical Research and Scientific Publications

Essential elements required for proper use of artificial intelligence machine learning tools in biomedical research and scientific publications include (1) explanation justifying why a machine learning approach contributes to the purpose of the study; (2) description of the adequacy of the data (input) to produce the desired results (output); (3) details of the algorithmic (i.e., computational) approach including methods for organizing the data (preprocessing); the machine learning computational algorithm(s) assessed; on what data the models were trained; the presence of bias and efforts to mitigate these effects; and the methods for quantifying the variables (features) most influential in determining the results (e.g., Shapley values); (4) description of methods, and reporting of results, quantitating performance in terms of both model accuracy and model calibration (level of confidence in the model's predictions); (5) availability of the programming code (including a link to the code when available-ideally, the code should be available); (6) discussion of model internal validation (results applicable and sensitive to the population investigated and data on which the model was trained) and external validation (were the results investigated as to whether they are generalizable to different populations? If not, consideration of this limitation and discussion of plans for external validation, i.e., next steps). As biomedical research submissions using artificial intelligence technology increase, these requirements could facilitate purposeful use and comprehensive methodological reporting.

Application of machine learning standardized integral area algorithm in measuring the scoliosis

This study was to develop a computer vision evaluation method to automatically measure the degree of scoliosis based on the machine learning algorithm. For the X-ray images of 204 patients with idiopathic scoliosis who underwent full-spine radiography, histogram equalization of original image was performed before a flipping method was used to magnify asymmetric elements, search for the global maximum pixel value in each line, and scan local maximal pixel value, with the intersection set of two point sets being regarded as candidate anchor points. All fine anchors were fitted with cubic spline algorithm to obtain the approximate curve of the spine, and the degree of scoliosis was measured by the standardized integral area. All measured data were analyzed. In manual measurement, the Cobb angle was 11.70-25.00 (20.15 ± 3.60), 25.20-44.70 (33.89 ± 5.41), and 45.10-49.40 (46.98 ± 1.25) in the mild, moderate and severe scoliosis group, respectively, whereas the value for the standardized integral area algorithm was 0.072-0.298 (0.185 ± 0.040), 0.100-0.399 (0.245 ± 0.050), and 0.246-0.901 (0.349 ± 0.181) in the mild, moderate and severe scoliosis group, respectively. Correlation analysis between the manual measurement of the Cobb angle and the evaluation of the standardized integral area algorithm demonstrated the Spearman correlation coefficient r = 0.643 (P < 0.001). There was a positive correlation between the manual measurement of the Cobb angle and the measurement of the standardized integral area value. Two methods had good consistency in evaluating the degree of scoliosis. ROC curve analysis of the standardized integral area algorithm to measure the degree of scoliosis showed he cutoff value of the standardized integral area algorithm was 0.20 for the moderate scoliosis with an AUC of 0.865, sensitivity 0.907, specificity 0.635, accuracy 0.779, positive prediction value 0.737 and negative prediction value 0.859, and the cutoff value of the standardized integral area algorithm was 0.40 for the severe scoliosis with an AUC of 0.873, sensitivity 0.188, specificity 1.00, accuracy 0.936, positive prediction value 1 and a negative prediction value 0.935. Using the standardized integral area as an independent variable and the Cobb angle as a dependent variable, a linear regression equation was established as Cobb angle = 13.36 + 70.54 × Standardized area, the model has statistical significance. In conclusion, the integrated area algorithm method of machine learning can quickly and efficiently assess the degree of scoliosis and is suitable for screening the degree of scoliosis in a large dataset as a useful supplement to the fine measurement of scoliosis Cobb angle.

A preliminary study in classification of the severity of spine deformation in adolescents with lumbar/thoracolumbar idiopathic scoliosis using machine learning algorithms based on lumbosacral joint efforts during gait

To assess the severity and progression of adolescents with idiopathic scoliosis (AIS), radiography with X-rays is usually used. The methods based on statistical observations have been developed from 3D reconstruction of the trunk or topography. Machine learning has shown great potential to classify the severity of scoliosis on imaging data, generally on X-ray measurements. It is also known that AIS leads to the development of gait disorder. To our knowledge, machine learning has never been tested on spine intervertebral efforts during gait as a radiation-free method to classify the severity of spinal deformity in AIS. Develop automated machine learning algorithms in lumbar/thoracolumbar scoliosis to classify the severity of spinal deformity of AIS based on the lumbosacral joint (L5-S1) efforts during gait. The lumbosacral joint efforts of 30 individuals with lumbar/thoracolumbar AIS were used as distinctive features fed to the machine learning algorithms. Several tests were run using various classification algorithms. The labeling consisted of three classes reflecting the severity of scoliosis i.e. mild, moderate and severe. The ensemble classifier algorithm including k-nearest neighbors, support vector machine, random forest and multilayer perceptron achieved the most promising results, with accuracy scores of 91.4%. This preliminary study shows lumbosacral joint efforts can be used to classify the severity of spinal deformity in lumbar/thoracolumbar AIS. This method showed the potential of being used as an assessment tool to follow-up the progression of AIS as a radiation-free method, alternative to radiography. Future studies should be performed to test the method on other categories of AIS.

Artificial Intelligence in Spinal Imaging: Current Status and Future Directions

Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Joint Spine Segmentation and Noise Removal From Ultrasound Volume Projection Images With Selective Feature Sharing

Volume Projection Imaging from ultrasound data is a promising technique to visualize spine features and diagnose Adolescent Idiopathic Scoliosis. In this paper, we present a novel multi-task framework to reduce the scan noise in volume projection images and to segment different spine features simultaneously, which provides an appealing alternative for intelligent scoliosis assessment in clinical applications. Our proposed framework consists of two streams: i) A noise removal stream based on generative adversarial networks, which aims to achieve effective scan noise removal in a weakly-supervised manner, i.e., without paired noisy-clean samples for learning; ii) A spine segmentation stream, which aims to predict accurate bone masks. To establish the interaction between these two tasks, we propose a selective feature-sharing strategy to transfer only the beneficial features, while filtering out the useless or harmful information. We evaluate our proposed framework on both scan noise removal and spine segmentation tasks. The experimental results demonstrate that our proposed method achieves promising performance on both tasks, which provides an appealing approach to facilitating clinical diagnosis.

Machine Learning Applications of Surgical Imaging for the Diagnosis and Treatment of Spine Disorders: Current State of the Art

Recent developments in machine learning (ML) methods demonstrate unparalleled potential for application in the spine. The ability for ML to provide diagnostic faculty, produce novel insights from existing capabilities, and augment or accelerate elements of surgical planning and decision making at levels equivalent or superior to humans will tremendously benefit spine surgeons and patients alike. In this review, we aim to provide a clinically relevant outline of ML-based technology in the contexts of spinal deformity, degeneration, and trauma, as well as an overview of commercial-level and precommercial-level surgical assist systems and decisional support tools. Furthermore, we briefly discuss potential applications of generative networks before highlighting some of the limitations of ML applications. We conclude that ML in spine imaging represents a significant addition to the neurosurgeon's armamentarium-it has the capacity to directly address and manifest clinical needs and improve diagnostic and procedural quality and safety-but is yet subject to challenges that must be addressed before widespread implementation.

Electromyographic Analysis of Paraspinal Muscles of Scoliosis Patients Using Machine Learning Approaches

A large number of studies have used electromyography (EMG) to measure the paraspinal muscle activity of adolescents with idiopathic scoliosis. However, investigations on the features of these muscles are very limited even though the information is useful for evaluating the effectiveness of various types of interventions, such as scoliosis-specific exercises. The aim of this cross-sectional study is to investigate the characteristics of participants with imbalanced muscle activity and the relationships among 13 features (physical features and EMG signal value). A total of 106 participants (69% with scoliosis; 78% female; 9–30 years old) are involved in this study. Their basic profile information is obtained, and the surface EMG signals of the upper trapezius, latissimus dorsi, and erector spinae (thoracic and erector spinae) lumbar muscles are tested in the static (sitting) and dynamic (prone extension position) conditions. Then, two machine learning approaches and an importance analysis are used. About 30% of the participants in this study find that balancing their paraspinal muscle activity during sitting is challenging. The most interesting finding is that the dynamic asymmetry of the erector spinae (lumbar) group of muscles is an important (third in importance) predictor of scoliosis aside from the angle of trunk rotation and height of the subject.

Supervised and unsupervised learning to classify scoliosis and healthy subjects based on non-invasive rasterstereography analysis

The aim of our study was to classify scoliosis compared to to healthy patients using non-invasive surface acquisition via Video-raster-stereography, without prior knowledge of radiographic data. Data acquisitions were made using Rasterstereography; unsupervised learning was adopted for clustering and supervised learning was used for prediction model Support Vector Machine and Deep Network architectures were compared. A M-fold cross validation procedure was performed to evaluate the results. The accuracy and balanced accuracy of the best supervised model were close to 85%. Classification rates by class were measured using the confusion matrix, giving a low percentage of unclassified patients. Rasterstereography has turned out to be a good tool to distinguish subject with scoliosis from healthy patients limiting the exposure to unnecessary radiations.

A Survey of Methods and Technologies Used for Diagnosis of Scoliosis

The purpose of this article is to present diagnostic methods used in the diagnosis of scoliosis in the form of a brief review. This article aims to point out the advantages of select methods. This article focuses on general issues without elaborating on problems strictly related to physiotherapy and treatment methods, which may be the subject of further discussions. By outlining and categorizing each method, we summarize relevant publications that may not only help introduce other researchers to the field but also be a valuable source for studying existing methods, developing new ones or choosing evaluation strategies.

Artificial intelligence in orthopaedics: A scoping review

There is a growing interest in the application of artificial intelligence (AI) to orthopaedic surgery. This review aims to identify and characterise research in this field, in order to understand the extent, range and nature of this work, and act as springboard to stimulate future studies. A scoping review, a form of structured evidence synthesis, was conducted to summarise the use of AI in orthopaedics. A literature search (1946-2019) identified 222 studies eligible for inclusion. These studies were predominantly small and retrospective. There has been significant growth in the number of papers published in the last three years, mainly from the USA (37%). The majority of research used AI for image interpretation (45%) or as a clinical decision tool (25%). Spine (43%), knee (23%) and hip (14%) were the regions of the body most commonly studied. The application of artificial intelligence to orthopaedics is growing. However, the scope of its use so far remains limited, both in terms of its possible clinical applications, and the sub-specialty areas of the body which have been studied. A standardized method of reporting AI studies would allow direct assessment and comparison. Prospective studies are required to validate AI tools for clinical use.

Applications of Machine Learning to Imaging of Spinal Disorders: Current Status and Future Directions

STUDY DESIGN

Narrative review.

OBJECTIVES

We aim to describe current progress in the application of artificial intelligence and machine learning technology to provide automated analysis of imaging in patients with spinal disorders.

METHODS

A literature search utilizing the PubMed database was performed. Relevant studies from all the evidence levels have been included.

RESULTS

Within spine surgery, artificial intelligence and machine learning technologies have achieved near-human performance in narrow image classification tasks on specific datasets in spinal degenerative disease, spinal deformity, spine trauma, and spine oncology.

CONCLUSION

Although substantial challenges remain to be overcome it is clear that artificial intelligence and machine learning technology will influence the practice of spine surgery in the future.

A narrative review of machine learning as promising revolution in clinical practice of scoliosis

Machine learning (ML), as an advanced domain of artificial intelligence (AI), is progressively changing our view of the world. By implementing its algorithms, our ability to detect previously undiscoverable patterns in data has the potential to revolutionize predictive analytics. Scoliosis, as a relatively specialized branch in the spine field, mainly covers the pediatric, adult and the elderly populations, and its diagnosis and treatment remain difficult. With recent efforts and interdisciplinary cooperation, ML has been widely applied to investigate issues related to scoliosis, and surprisingly augment a surgeon's ability in clinical practice related to scoliosis. Meanwhile, ML models penetrate in every stage of the clinical practice procedure of scoliosis. In this review, we first present a brief description of the application of ML in the clinical practice procedures regarding scoliosis, including screening, diagnosis and classification, surgical decision making, intraoperative manipulation, complication prediction, prognosis prediction and rehabilitation. Meanwhile, the ML models and specific applications adopted are presented. Additionally, current limitations and future directions are briefly discussed regarding its use in the field of scoliosis. We believe that the implementation of ML is a promising revolution to assist surgeons in all aspects of clinical practice related to scoliosis in the near future.

An Application of Artificial Intelligence to Diagnostic Imaging of Spine Disease: Estimating Spinal Alignment From Moiré Images

The use of artificial intelligence (AI) as a tool supporting the diagnosis and treatment of spinal diseases is eagerly anticipated. In the field of diagnostic imaging, the possible application of AI includes diagnostic support for diseases requiring highly specialized expertise, such as trauma in children, scoliosis, symptomatic diseases, and spinal cord tumors. Moiré topography, which describes the 3-dimensional surface of the trunk with band patterns, has been used to screen students for scoliosis, but the interpretation of the band patterns can be ambiguous. Thus, we created a scoliosis screening system that estimates spinal alignment, the Cobb angle, and vertebral rotation from moiré images. In our system, a convolutional neural network (CNN) estimates the positions of 12 thoracic and 5 lumbar vertebrae, 17 spinous processes, and the vertebral rotation angle of each vertebra. We used this information to estimate the Cobb angle. The mean absolute error (MAE) of the estimated vertebral positions was 3.6 pixels (~5.4 mm) per person. T1 and L5 had smaller MAEs than the other levels. The MAE per person between the Cobb angle measured by doctors and the estimated Cobb angle was 3.42°. The MAE was 4.38° in normal spines, 3.13° in spines with a slight deformity, and 2.74° in spines with a mild to severe deformity. The MAE of the angle of vertebral rotation was 2.9°±1.4°, and was smaller when the deformity was milder. The proposed method of estimating the Cobb angle and AVR from moiré images using a CNN is expected to enhance the accuracy of scoliosis screening.

Development and validation of deep learning algorithms for scoliosis screening using back images

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

Artificial intelligence and machine learning in spine research

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer-aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content-based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.

Machine Learning in Orthopedics: A Literature Review

In this paper we present the findings of a systematic literature review covering the articles published in the last two decades in which the authors described the application of a machine learning technique and method to an orthopedic problem or purpose. By searching both in the Scopus and Medline databases, we retrieved, screened and analyzed the content of 70 journal articles, and coded these resources following an iterative method within a Grounded Theory approach. We report the survey findings by outlining the articles' content in terms of the main machine learning techniques mentioned therein, the orthopedic application domains, the source data and the quality of their predictive performance.

Effect of natural sagittal trunk lean on standing balance in untreated scoliotic girls

BACKGROUND

Generally, scoliotic girls have a tendency to lean further back than a comparable group of non-scoliotic girls. To date, no study has addressed how standing balance in untreated scoliotic girls is affected by a natural backwardly or forwardly inclined trunk.

METHODS

27 able-bodied young girls and 27 young girls with a right thoracic curve were classified as leaning forward or backward according to the median of their trunk sagittal inclination. Participants stood upright barefoot. Trunk and pelvis orientations were calculated from 8 bony landmarks. Upright standing balance was assessed by 9 parameters calculated from the excursion of the center of pressure and the free moment.

FINDINGS

In the anterior-posterior direction, backward scoliotic girls had a greater center of pressure range (P=0.036) and speed (P=0.015) by 10.4mm and 2.8mm/s respectively than the forward scoliotic group. Compared to their matching non-scoliotic group, the backward scoliotic girls stood more on their heels by 14.6mm (P=0.017) and display greater center of pressure speed by 2.5mm/s (P=0.028). Medio-lateral center of pressure range (P=0.018) and speed (P=0.008) were statistically higher by 8.7mm and 3.6mm/s for the backward group. Only the free moment RMS was significantly larger (P=0.045) for the backward scoliotic group when compared to the forwardly inclined scoliotic group.

INTERPRETATION

Only those with a backward lean displayed statistically significant differences from both forward scoliotic girls and non-scoliotic girls. Untreated scoliotic girls with an exaggerated back extension could profit more from postural rehabilitation to improve their standing balance.

Gait Analysis Using a Support Vector Machine for Lumbar Spinal Stenosis

Lumbar spinal canal stenosis (LSS) is diagnosed based on physical examination and radiological documentation of lumbar spinal canal narrowing. Differential diagnosis of the level of lumbar radiculopathy is difficult in multilevel spinal stenosis. Therefore, the authors focused on gait analysis as a classification method to improve diagnostic accuracy. The goal of this study was to identify gait characteristics of L4 and L5 radiculopathy in patients with LSS and to classify L4 and L5 radiculopathy using a support vector machine (SVM). The study group comprised 13 healthy volunteers (control group), 11 patients with L4 radiculopathy (L4 group), and 22 patients with L5 radiculopathy (L5 group). Light-emitting diode markers were attached at 5 sites on the affected side, and walking motion was analyzed using video recordings and the authors' development program. Potential gait characteristics of each group were identified to use as SVM parameters. In the knee joint of the L4 group, the waveform was similar to that of normal gait, but knee extension at initial contact was slightly greater than that of the other groups. In the ankle joint of the L5 group, the one-peak waveform pattern with disappearance of the second peak was present in 10 (45.5%) of 22 cases. The total classification accuracy was 80.4% using the SVM. The highest and lowest classification accuracies were obtained in the control group (84.6%) and the L4 group (72.7%), respectively. The authors' walking motion analysis system identified several useful factors for differentiating between healthy individuals and patients with L4 and L5 radiculopathy, with a high accuracy rate.

Examination of the compatibility of the photogrammetric method with the phenomenon of mora projection in the evaluation of scoliosis

Introduction. The aim of this study was to evaluate the compatibility of external measurements of parameters characterizing scoliosis using the photogrammetric method. Material. The study involved 120 children between the ages of 7 and 11 years in Podkarpackie (Poland). Method. Measurements of body posture characteristics were performed using the photogrammetric method with mora projection. Each person was examined twice, once by two different therapists, with a time lapse of 20 minutes in between examinations. Results. High accuracy and no statistical significance were found among different measurements of asymmetry parameters characterizing the shoulder blades and hips. Regularities were also found in the characteristic measurements of curves of scoliosis. The POSTI parameter showed a significant variation and lack of compatibility of results. Conclusions. (1) The photogrammetric method used to assess the pathological changes caused by scoliosis gives significant results in terms of parameters characterizing the position of the shoulder blades and shoulders, as well as pelvis rotation. (2) High compliance measurements are also characterized by the length of the right and left arcs of scoliosis.

Pelvic morphology, body posture and standing balance characteristics of adolescent able-bodied and idiopathic scoliosis girls

The purpose of this study was to determine how pelvic morphology, body posture, and standing balance variables of scoliotic girls differ from those of able-bodied girls, and to classify neuro-biomechanical variables in terms of a lower number of unobserved variables. Twenty-eight scoliotic and twenty-five non-scoliotic able-bodied girls participated in this study. 3D coordinates of ten anatomic body landmarks were used to describe pelvic morphology and trunk posture using a Flock of Birds system. Standing balance was measured using a force plate to identify the center of pressure (COP), and its anteroposterior (AP) and mediolateral (ML) displacements. A multivariate analysis of variance (MANOVA) was performed to determine differences between the two groups. A factor analysis was used to identify factors that best describe both groups. Statistical differences were identified between the groups for each of the parameter types. While spatial orientation of the pelvis was similar in both groups, five of the eight trunk postural variables of the scoliotic group were significantly different that the able-bodied group. Also, five out of the seven standing balance variables were higher in the scoliotic girls. Approximately 60% of the variation is supported by 4 factors that can be associated with a set of variables; standing balance variables (factor 1), body posture variables (factor 2), and pelvic morphology variables (factors 3 and 4). Pelvic distortion, body posture asymmetry, and standing imbalance are more pronounced in scoliotic girls, when compared to able-bodied girls. These findings may be beneficial when addressing balance and ankle proprioception exercises for the scoliotic population.

Is radiation-free diagnostic monitoring of adolescent idiopathic scoliosis feasible using upright positional magnetic resonance imaging?

STUDY DESIGN

Prospective clinical trial.

OBJECTIVE

The purpose of this study was to determine if an upright positional magnetic resonance imaging (MRI) protocol could produce reliable spinal curvature images and measurements compared with traditional radiograph.

SUMMARY OF BACKGROUND DATA

Concerns about the oncological potential from cumulative doses of ionizing radiation in children and adolescents being monitored for adolescent idiopathic scoliosis (AIS) initiated a search for radiation-free diagnostic imaging modalities, including MRI. We submit that upright, positional MRI (uMRI) produces reliable spinal curvature images compared with traditional radiograph.

METHODS

Twenty-five consecutive patients (16 female; 9 male; average age, 14.6 yr; range, 12-18 yr) with a diagnosis of AIS were enrolled. Average major curve magnitude was 30° (range, 6°-70°). Subjects received anterior-posterior and lateral plain radiographical scoliosis imaging followed within 1 week by uMRI. MRI data acquisition was performed in less than 7 minutes. Two independent observers performed all Cobb angle, T5-T12 kyphosis, and vertebral rotation measurements for comparison. The Pearson correlation method was performed to compare radiograph to uMRI measurements, while inter-rater and intrarater correlations were performed to assess reliability.

RESULTS

We found outstanding correlation between all plain film radiography and uMRI measurements (P = 0.01); major Cobb angles (R = 0.901), minor Cobb angles (R = 0.838), and kyphosis (R = 0.943). Inter-rater reliability for both radiographical and MRI measurements of major Cobb angles (R = 0.959, 0.896, respectively), minor Cobb angles (R = 0.951, 0.857, respectively), and vertebral rotation (R = 0.945) were outstanding. Intrarater reliability for both radiographical and MRI measurements of major Cobb angles (R = 0.966, 0.966, respectively) and minor Cobb angles (R = 0.945, 0.943, respectively) were also outstanding.

CONCLUSION

Our results show that uMRI is capable of producing coronal and sagittal plane measurements that highly correlate with traditional plain film radiographical measurements. This, in addition to reliable vertebral rotation measurements, makes uMRI a valuable, radiation-free alternative/substitute for diagnostic evaluation in AIS.

Non invasive clinical assessment of trunk deformities associated with scoliosis

Besides the spinal deformity, scoliosis modifies notably the general appearance of the trunk resulting in trunk rotation, imbalance and asymmetries which constitutes patients' major concern. Existing classifications of scoliosis, based on the type of spinal curve as depicted on radiographs, are currently used to guide treatment strategies. Unfortunately, even though a perfect correction of the spinal curve is achieved, some trunk deformities remain, making patients dissatisfied with the treatment received. The purpose of this study is to identify possible shape patterns of trunk surface deformity associated with scoliosis. First, trunk surface is represented by a multivariate functional trunk shape descriptor based on 3D clinical measurements computed on cross sections of the trunk. Then, the classical formulation of hierarchical clustering is adapted to the case of multivariate functional data and applied to a set of 236 trunk surface 3D reconstructions. The highest internal validity is obtained when considering 11 clusters that explain up to 65% of the variance in our dataset. Our clustering result shows a concordance with the radiographic classification of spinal curves in 68% of the cases. As opposed to radiographic evaluation, the trunk descriptor is three-dimensional and its functional nature offers a compact and elegant description of not only the type, but also the severity and extent of the trunk surface deformity along the trunk length. In future work, new management strategies based on the resulting trunk shape patterns could be thought of in order to improve the esthetic outcome after treatment, and thus patients satisfaction.

Non invasive classification system of scoliosis curve types using least-squares support vector machines

OBJECTIVE

To determine scoliosis curve types using non invasive surface acquisition, without prior knowledge from X-ray data.

METHODS

Classification of scoliosis deformities according to curve type is used in the clinical management of scoliotic patients. In this work, we propose a robust system that can determine the scoliosis curve type from non invasive acquisition of the 3D back surface of the patients. The 3D image of the surface of the trunk is divided into patches and local geometric descriptors characterizing the back surface are computed from each patch and constitute the features. We reduce the dimensionality by using principal component analysis and retain 53 components using an overlap criterion combined with the total variance in the observed variables. In this work, a multi-class classifier is built with least-squares support vector machines (LS-SVM). The original LS-SVM formulation was modified by weighting the positive and negative samples differently and a new kernel was designed in order to achieve a robust classifier. The proposed system is validated using data from 165 patients with different scoliosis curve types. The results of our non invasive classification were compared with those obtained by an expert using X-ray images.

RESULTS

The average rate of successful classification was computed using a leave-one-out cross-validation procedure. The overall accuracy of the system was 95%. As for the correct classification rates per class, we obtained 96%, 84% and 97% for the thoracic, double major and lumbar/thoracolumbar curve types, respectively.

CONCLUSION

This study shows that it is possible to find a relationship between the internal deformity and the back surface deformity in scoliosis with machine learning methods. The proposed system uses non invasive surface acquisition, which is safe for the patient as it involves no radiation. Also, the design of a specific kernel improved classification performance.

Pelvis morphology, trunk posture and standing imbalance and their relations to the Cobb angle in moderate and severe untreated AIS

Adolescent idiopathic scoliosis (AIS) is the most common form of scoliosis and usually affects young girls. Studies mostly describe the differences between scoliotic and non-scoliotic girls and focus primarily on a single set of parameters derived from spinal and pelvis morphology, posture or standing imbalance. No study addressed all these three biomechanical aspects simultaneously in pre-braced AIS girls of different scoliosis severity but with similar curve type and their interaction with scoliosis progression. The first objective of this study was to test if there are differences in these parameters between pre-braced AIS girls with a right thoracic scoliosis of moderate (less than 27°) and severe (more than 27°) deformity. The second objective was to identify which of these parameters are related to the Cobb angle progression either individually or in combination of thereof. Forty-five scoliotic girls, randomly selected by an orthopedic surgeon from the hospital scoliosis clinic, participated in this study. Parameters related to pelvis morphology, pelvis orientation, trunk posture and quiet standing balance were measured. Generally moderate pre-brace idiopathic scoliosis patients displayed lower values than the severe group characterized by a Cobb angle greater than 27°. Only pelvis morphology and trunk posture were statistically different between the groups while pelvis orientation and standing imbalance were similar in both groups. Statistically significant Pearson coefficients of correlation between individual parameters and Cobb angle ranged between 0.32 and 0.53. Collectively trunk posture, pelvis morphology and standing balance parameters are correlated with Cobb angle at 0.82. The results suggest that spinal deformity progression is not only a question of trunk morphology distortion by itself but is also related to pelvis asymmetrical bone growth and standing neuromuscular imbalance.

Automatic recognition of surface landmarks of anatomical structures of back and posture

Faulty postures, scoliosis and sagittal plane deformities should be detected as early as possible to apply preventive and treatment measures against major clinical consequences. To support documentation of the severity of deformity and diminish x-ray exposures, several solutions utilizing analysis of back surface topography data were introduced. A novel approach to automatic recognition and localization of anatomical landmarks of the human back is presented that may provide more repeatable results and speed up the whole procedure. The algorithm was designed as a two-step process involving a statistical model built upon expert knowledge and analysis of three-dimensional back surface shape data. Voronoi diagram is used to connect mean geometric relations, which provide a first approximation of the positions, with surface curvature distribution, which further guides the recognition process and gives final locations of landmarks. Positions obtained using the developed algorithms are validated with respect to accuracy of manual landmark indication by experts. Preliminary validation proved that the landmarks were localized correctly, with accuracy depending mostly on the characteristics of a given structure. It was concluded that recognition should mainly take into account the shape of the back surface, putting as little emphasis on the statistical approximation as possible.

Reliability of photogrammetry in the evaluation of the postural aspects of individuals with structural scoliosis

PURPOSE

The purpose of this study was to investigate the reliability of photogrammetry in the measurement of the postural deviations in individuals with idiopathic scoliosis.

METHODS

Twenty participants with scoliosis (17 women and three men), with a mean age of 23.1 ± 9 yrs, were photographed from the posterior and lateral views. The postural aspects were measured with CorelDRAW software.

RESULTS

High inter-rater and test-retest reliability indices were found. It was observed that with more severity of scoliosis, greater were the variations between the thoracic kyphosis and lumbar lordosis measures obtained by the same examiner from the left lateral view photographs. A greater body mass index (BMI) was associated with greater variability of the trunk rotation measures obtained by two independent examiners from the right, lateral view (r = 0.656; p = 0.002). The severity of scoliosis was also associated with greater inter-rater variability measures of trunk rotation obtained from the left, lateral view (r = 0.483; p = 0.036).

CONCLUSIONS

Photogrammetry demonstrated to be a reliable method for the measurement of postural deviations from the posterior and lateral views of individuals with idiopathic scoliosis and could be complementarily employed for the assessment procedures, which could reduce the number of X-rays used for the follow-up assessments of these individuals.

Computer algorithms and applications used to assist the evaluation and treatment of adolescent idiopathic scoliosis: a review of published articles 2000-2009

Adolescent idiopathic scoliosis (AIS) is a complex spinal deformity whose assessment and treatment present many challenges. Computer applications have been developed to assist clinicians. A literature review on computer applications used in AIS evaluation and treatment has been undertaken. The algorithms used, their accuracy and clinical usability were analyzed. Computer applications have been used to create new classifications for AIS based on 2D and 3D features, assess scoliosis severity or risk of progression and assist bracing and surgical treatment. It was found that classification accuracy could be improved using computer algorithms that AIS patient follow-up and screening could be done using surface topography thereby limiting radiation and that bracing and surgical treatment could be optimized using simulations. Yet few computer applications are routinely used in clinics. With the development of 3D imaging and databases, huge amounts of clinical and geometrical data need to be taken into consideration when researching and managing AIS. Computer applications based on advanced algorithms will be able to handle tasks that could otherwise not be done which can possibly improve AIS patients' management. Clinically oriented applications and evidence that they can improve current care will be required for their integration in the clinical setting.

Reliability and validity of the photogrammetry for scoliosis evaluation: a cross-sectional prospective study

OBJECTIVE

The purpose of this study was to investigate the reliability and validity of photogrammetry in measuring the lateral spinal inclination angles.

METHODS

Forty subjects (32 female and 8 males) with a mean age of 23.4 +/- 11.2 years had their scoliosis evaluated by radiographs of their trunk, determined by the Cobb angle method, and by photogrammetry. The statistical methods used included Cronbach alpha, Pearson/Spearman correlation coefficients, and regression analyses.

RESULTS

The Cronbach alpha values showed that the photogrammetric measures showed high internal consistency, which indicated that the sample was bias free. The radiograph method showed to be more precise with intrarater reliabilities of 0.936, 0.975, and 0.945 for the thoracic, lumbar, and thoracolumbar curves, respectively, and interrater reliabilities of 0.942 and 0.879 for the angular measures of the thoracic and thoracolumbar segments, respectively. The regression analyses revealed a high determination coefficient although limited to the adjusted linear model between the radiographic and photographic measures. It was found that with more severe scoliosis, the lateral curve measures obtained with the photogrammetry were for the thoracic and lumbar regions (R = 0.619 and 0.551).

CONCLUSIONS

The photogrammetric measures were found to be reproducible in this study and could be used as supplementary information to decrease the number of radiographs necessary for the monitoring of scoliosis.

Using support vector machines to detect therapeutically incorrect measurements by the MiniMed CGMS

BACKGROUND

Current continuous glucose monitors have limited accuracy mainly in the low range of glucose measurements. This lack of accuracy is a limiting factor in their clinical use and in the development of the so-called artificial pancreas. The ability to detect incorrect readings provided by continuous glucose monitors from raw data and other information supplied by the monitor itself is of utmost clinical importance. In this study, support vector machines (SVMs), a powerful statistical learning technique, were used to detect therapeutically incorrect measurements made by the Medtronic MiniMed CGMS.

METHODS

Twenty patients were monitored for three days (first day at the hospital and two days at home) using the MiniMed CGMS. After the third day, the monitor data were downloaded to the physician's computer. During the first 12 hours, the patients stayed in the hospital, and blood samples were taken every 15 minutes for two hours after meals and every 30 minutes otherwise. Plasma glucose measurements were interpolated using a cubic method for time synchronization with simultaneous MiniMed CGMS measurements every five minutes, obtaining a total of 2281 samples. A Gaussian SVM classifier trained on the monitor's electrical signal and glucose estimation was tuned and validated using multiple runs of k-fold cross-validation. The classes considered were Clarke error grid zones A+B and C+D+E.

RESULTS

After ten runs of ten-fold cross-validation, an average specificity and sensitivity of 92.74% and 75.49%, respectively, were obtained (see Figure 4). The average correct rate was 91.67%.

CONCLUSIONS

Overall, the SVM performed well, in spite of the somewhat low sensitivity. The classifier was able to detect the time intervals when the monitor's glucose profile could not be trusted due to incorrect measurements. As a result, hypoglycemic episodes missed by the monitor were detected.

Nonlinear support vector machine visualization for risk factor analysis using nomograms and localized radial basis function kernels

Nonlinear classifiers, e.g., support vector machines (SVMs) with radial basis function (RBF) kernels, have been used widely for automatic diagnosis of diseases because of their high accuracies. However, it is difficult to visualize the classifiers, and thus difficult to provide intuitive interpretation of results to physicians. We developed a new nonlinear kernel, the localized radial basis function (LRBF) kernel, and new visualization system visualization for risk factor analysis (VRIFA) that applies a nomogram and LRBF kernel to visualize the results of nonlinear SVMs and improve the interpretability of results while maintaining high prediction accuracy. Three representative medical datasets from the University of California, Irvine repository and Statlog dataset-breast cancer, diabetes, and heart disease datasets-were used to evaluate the system. The results showed that the classification performance of the LRBF is comparable with that of the RBF, and the LRBF is easy to visualize via a nomogram. Our study also showed that the LRBF kernel is less sensitive to noise features than the RBF kernel, whereas the LRBF kernel degrades the prediction accuracy more when important features are eliminated. We demonstrated the VRIFA system, which visualizes the results of linear and nonlinear SVMs with LRBF kernels, on the three datasets.