The pathogenesis of scoliosis progression remains poorly understood. Seventy-two subject data sets, consisting of four successive values of Cobb-angle and lateral deviations at apices for six and twelve-months intervals in the coronal plane, were used to train and test an artificial neural network (ANN) to predict spinal deformity progression. The accuracies of the trained ANN (3-4-1) for training and testing data were within 3.64° (±2.58°) and 4.40° (±1.86°) of Cobb angles, and within 3.59 (±3.96) mm and 3.98 (±3.41) mm of lateral deviations, respectively. The adapted technique for predicting the scoliosis deformity progression has promising clinical applications.

Scoliosis is a common and poorly understood three-dimensional spinal deformity. The study purpose is to predict scoliosis progression at six and twelve months intervals in the future using successive spinal indices with an artificial neural network (ANN).

The adapted ANN technique enables earlier detection of scoliosis progression with high accuracy. Improved prediction of scoliosis progression will impact bracing or surgical treatment decisions, and may decrease hazardous X-ray exposure.

Seventy-two data sets from adolescent idiopathic scoliosis subjects recruited at the Alberta Children’s Hospital were used in this study. Data sets composed of four successive values of Cobb angles and lateral deviations at apices for six and twelvemonth intervals (coronal plane) were extracted to train and test a specific ANN for predicting scoliosis progression.

Progression patterns in Cobb angles (n = 10) and lateral deviations (n = 8) were successfully identified. The accuracies of the trained ANN (3-4-1) with the training and testing data sets were 3.64° (±2.58°) and 4.40° (±1.86°) of Cobb angles, 3.59 (±3.96) mm and 3.98 (±3.41) mm of lateral deviations, respectively. These results are in close agreement with those using cubic spline extrapolation techniques (3.49° ± 1.85° and 3.31 ± 4.22 mm) and adaptive neuro-fuzzy inference system (3.92° ±3.53° and 3.37 ±3.95 mm) for the same testing data.

ANN can be a promising technique for prediction of scoliosis progression with substantial improvements in accuracy over current techniques, leading to potentially important implications for scoliosis monitoring and treatment decisions.

Funding: AHFMR, CIHR, Fraternal Order of Eagles, NSERC, GEOIDE.

Spine and torso models were generated concurrently with x-rays for twenty-three patients undergoing scoliosis brace treatment. Clinical indices of spinal deformity and torso surface asymmetry indices were computed from models obtained when patient was first recruited and at approximately one year’s follow-up. Significant correction changes of the torso shape were detected in indices including orientation of cross-sectional principal axes of inertia (p=0.048) and Back Surface Rotation (p=0.08) though spinal corrections were from not significant to subtle (0.20_p_0.88). Trunk asymmetry should be assessed for an objective evaluation and understanding of the effect produced by a specific treatment.

To assess changes in torso geometry and spinal deformity during treatment of idiopathic scoliosis with rigid brace.

Relationship between torso surface geometry and spinal deformity when a rigid brace is applied is essential for better understanding of brace treatment mechanism and optimal application of external forces.

Three-dimensional torso surface models were generated concurrently with postero-anterior x-rays for twenty-three patients undergoing scoliosis brace treatment, when first recruited and at approximately one year’s follow-up. Torso asymmetry indices describing principal axis orientation, back surface rotation, and asymmetry of the centroid line, left and right half-areas and the spinous process line were computed. The statistical paired t-Test (95% CI) was performed to test the probability that no difference exist after one year of treatment in both spinal and torso asymmetry indices.

After one year follow-up patients showed a mean increase of only 2° for the major Cobb angle. This was consistent with not significant to subtle corrections found in clinical (p=0.88) and computed (p=0.75) Cobb angle, lateral deviation (p=0.20), orientation of plane of maximum deformity (p= 0.58) and maximum vertebral axial rotation (p=0.83). Furthermore, significant correction changes of the torso shape were detected in the orientation of cross-sectional principal axes (PAX) of inertia (p=0.048) and Back Surface Rotation (p=0.08).

Here we have shown that we can acquire 3D torso surface and reliably measured a set of indices of transverse torso asymmetry. Future work will look at indication of predictive potential of torso surface indices.

Funding: AHFMR, CIHR, Fraternal Order of Eagles, NSERC, GEOIDE.