Automatic spinal disease diagnoses assisted by 3D unaligned transverse CT slices.

This paper describes a three-dimensional (3D) reconstruction method and an automatic diagnosis method for spinal diseases using unaligned transverse slices that have arbitrary angles and intervals but do not intersect to each other at regions of interest. The 3D reconstruction method extends the marching cube algorithm to generate triangulated isosurfaces for these unaligned slices. The automatic spinal disease diagnostic method analyses boundaries of discs and vertebral bodies on unaligned transverse slices to estimate the presence and extent of disc herniation and canal compression, and deformities in the spinal curve. The prototype system can be used as a qualitative and quantitative tool for the diagnosis of various spinal diseases using unaligned transverse slices.