Multi-Object Detection and Segmentation of Brain Structures Based on Dynamic Programming

This work aims to design a detection and segmentationmethod using a graphical model in the context of multi-object brain image segmentation. We resort to dynamic programming as the optimization strategy to find the global minimum energy for the relation graph. Compared to other graphical models like tree structures, the proposed approach offers flexibility in accommodating more interactions among objects and thus can inhibit error propagation. Also, the new method is able to detect and segment a larger number of objects by searching for the global optimum energy in an efficient way. Experimental results show that the proposed approach achieves a comparable accuracy to other state-of-theart methods.