Anomaly detection through registration

摘要

We introduce a system that automatically segments and classifies features in brain MRI volumes. It segments 144 structures of a 256×256×124 voxel image in 18 minutes on an SGI computer with four 194 MHz R10K processors. The algorithm uses an atlas, a hand-segmented and classified MRI of a normal brain, which is warped in 3-D using a hierarchical deformable matching algorithm until it closely matches the subject. This customized atlas contains the segmentation and classification of the subject’s anatomical structures. We have conducted tests on 139 MRIs of normal brains, and 3 MRIs and 1 CT of brains with pathologies. We present qualitative and quantitative evaluations of the system’s performance. Combined with domain knowledge, the registration algorithm is capable of detecting asymmetries and abnormal variations in the subject’s data that indicate the existence and location of pathologies.