Registration-Based Segmentation of Nerve Cells in Microscopy Images

Nerve cell segmentation is important for better understanding of the connections between broken nerves. In this paper, we propose a registration-based segmentation to improve the segmentation from a series of microscopic image sequence. A global iterative closest point (ICP) registration is first employed to find the corresponding cells between neighboring frames. Then a local ICP registration is adopted to refine shape matching between corresponding cells. When registering the current frame to the previous frame, a missing cell in the current frame can obtain a dummy region with respect to the previous frame. The dummy region is then confirmed as a cell by checking the correspondence of the cell among the previous, current and next frames. Experimental results show that the proposed registration based algorithm recovers the cells that are missed in conventional segmentation.