3D Segmentation of the Mouse Spleen in microCT via Active Contours
Deniz Aykac, Jeffery R. Price, Jonathan S. Wall · 2006
We present in this paper a novel method for 3D segmentation of the mouse spleen in X-ray CT (microCT) data. Our approach is based upon the 2D "active contours for smooth without edges" algorithm. We introduce a simple statistical weighting scheme that improves region contrast and segmentation performance. We extend the 2D approach to 3D by slice-to-slice processing, including the 3D flow of image statistics. The technique requires no training and operates semi-automatically, requiring only the entry of a single seed point within the spleen. Results are shown that demonstrate the effectiveness of our approach