Time series spinal radiographs as prognostic factors for scoliosis and progression of spinal deformities.

The effectiveness of clinical measures to predict scoliotic progression is unclear. The objective of this study was to identify potential prognostic factors affecting scoliosis progression. Consecutive measurements (181) from 35 non-instrumented adolescent idiopathic scoliosis patients with at least two follow-up assessments were studied. Potential prognostic factors of gender, curve pattern, age, curve magnitude, apex location and lateral deviation and spinal growth were analyzed. Stable and progressed groups were compared (threshold: Cobb angle ≥5° or 10°) with sequential clinical data collected in 6-month intervals. Double curves progressed simultaneously or alternatively on curve regions. Age was not significantly different prior to and at maximal Cobb angle. Maximal Cobb angles were significantly correlated to initial Cobb angles (r = 0.81-0.98). Progressed males had larger initial Cobb angles than progressed females. Apex locations were higher in progressed than stable groups, and at least a half vertebra level higher in females than males. Maximal apex lateral deviations correlated significantly with the initial ones (r = 0.73-0.97) and moderately with maximal Cobb angles (r = 0.33-0.85). In the progressed groups, males had larger apex lateral deviations than females. Spinal growth did not relate to curve progression (r = -0.64 to +0.59) and was not significantly different between groups and genders. Scoliosis may dynamically progress between major and minor curves. Gender, curve magnitude, apex location and lateral deviation have stronger effects on scoliosis progression than age or spinal growth. Females with high apex locations may be expected to progress.

Prediction of scoliosis progression with serial three-dimensional spinal curves and the artificial progression surface technique.

Adolescent idiopathic scoliosis (AIS) progression is clinically monitored by a series of full spinal X-rays. To decrease radiation exposure, an artificial progression surface (APS) is proposed to predict progression. Fifty-six acquisitions (posteroanterior radiographs, 0° and 20°) were obtained from 11 AIS patients (29.8 ± 9.6° Cobb angle). Three-dimensional curves were constructed through vertebral pedicle centers. Three previous serial spinal curves (6-month intervals) were used to construct an APS with a Non-uniform Rational B-Spline surfacing technique. Future progression was achieved by aligning the curves on the APS using the generalized cross-validation extrapolation technique. With three and four previous serial spinal curves, the prediction accuracies of future progression at the next 6-month interval were 4.1 ± 3.3° for Cobb angles and 3.6 ± 3.5 mm for apex lateral deviations. Apex locations and Cobb regions varied within one vertebral level. The proposed technique shows potential as an accurate three-dimensional prediction method for AIS progression and could help pediatricians make decisions about treatment. However, it could only be applied once before more radiographic data would be needed.

Scoliotic progression patterns in prognostic factors and future prediction of spinal deformity progression.

This study investigated how an adolescent idiopathic scoliosis progresses with time. 154 consecutive measurements from 26 consecutive AIS patients were analyzed. Each subject had at least four successive scans at six-month intervals. Progression patterns of Cobb angle and apex lateral deviation were extracted from 34 serial data sets of the most common AIS type RT-LL, in the format of four serial data sets, by using the fuzzy c-means clustering technique. Progression of spinal deformity was predicted with previous serial data of Cobb angle and apex lateral deviation by using a GCV extrapolating technique alone and in conjunction with progression patterns. Our results showed that scoliotic progression appears to follow progression patterns. Progression of spinal deformity has potential to be accurately predicted with previous serial spinal deformities by using GCV extrapolating technique with assistance of progression patterns.

Prediction of scoliosis progression in time series using a hybrid learning technique.

Scoliosis is a common and poorly understood spinal disorder that is clinically monitored with a series of full spinal X-rays. The purpose of this study was to predict scoliosis future progression at 6- and 12-month intervals with successive spinal indices and a hybrid learning technique (i.e., the combination of fuzzy c-means clustering and artificial neural network (ANN)). Ultimately this could decrease scoliotic patients' radiation exposure and the associated cancer risk in growing adolescents. Seventy-two data sets were derived from a database of 56 acquisitions from 11 subjects (29.8 +/- 9.6 degrees Cobb angle, 11.4 +/- 2.4 yr), each consisting of 4 sequential values of Cobb angle and lateral deviations at apices in 6- and 12-month intervals in the coronal plane. Progression patterns in Cobb angles (n = 10) and lateral deviations (n = 8) were successfully identified using a fuzzy c-means clustering algorithm. The accuracies of the trained ANN, having a structure of three input variables, four nonlinear hidden nodes, and one linear output variable, for training and test data sets were within 3.64 degrees (+/- 2.58 degrees) and 4.40 degrees (+/- 1.86 degrees) of Cobb angles, and within 3.59 (+/-3.96) mm and 3.98 (+/- 3.41) mm of lateral deviations, respectively. Those results were twice the accuracy of typical clinical measurement (~10 degrees) and in close agreement with those using cubic spline extrapolation and adaptive neuro-fuzzy inference system (ANFIS) techniques. The adapted technique for predicting the scoliosis deformity progression holds significant promise for clinical applications.