Pre-processing range data for the analysis of torso shape and symmetry of scoliosis patients.

This paper presents a procedure for pre-processing and reconstructing surface scans comprising an interactive technique for cropping stray points and extremities. The procedure involves three stages: cross-sectioning and clipping, hole-filling and sub-sampling, and surface re-generation. The accuracy of the reconstruction obtained was assessed by creating different patterns of holes and stray points on 30 models of the torso and pre-processing the models using the proposed procedure and existing procedures based on Bezier interpolation and Moving Least Squares (MLS) interpolation. Results obtained indicate that the proposed procedure was at least as good as the better of Bezier and MLS interpolation for all the models tested, particularly outperforming both procedures when holes account for up to 5% of the surface. Its accuracy of reconstruction ranged from 90-100% compared to 80-100% for Bezier and 50-100% for MLS. This work is a crucial step in developing techniques for understanding and assessing changes in torso shape and symmetry from torso surface scans of scoliosis patients.