Automatic Segmentation of Spinal Canals in CT Images via Iterative Topology Refinement
The widespread use of CT imaging and the critical importance of early detection of epidural masses of the spinal canal generate a scenario ideal for the implementation of a computer-aided detection (CAD) system. Epidural masses can lead to paralysis, incontinence and loss of neurological function if not promptly detected. We present, to our knowledge, the first CAD system to detect epidural masses on CT scans. In this paper, spatially constrained Gaussian mixture model (GMM) and supervoxel-based method are proposed for epidural mass detection. The detection is performed on the Gaussian level or the supervoxel level rather than the voxel level. Cross-validation on 40 patients with epidural masses on body CT showed that the supervoxel-based method yielded a significant improvement of performance (82% at 3 false positives per patient) over the spatially constrained GMM method (55% at 3 false positives per patient).