Swarm Intelligence Integrated Graph-Cut for Liver Segmentation from 3D-CT Volumes

Algorithm 1

Variant ACO algorithm.

Input: ROI-based enhanced image of input abdominal CT slice

Output: Boundary detected using ACO

Begin

  Phase 1: ACO Initialization

   (I) Initialize the edge attractiveness (pheromone) and path visibility (heuristic) for each edge.

   (II) Initialize evaporation rate (, pheromone decay coefficient , count index

     (positive integer), and influencer parameters

  Phase 2: Solving process

    For < maxIteration do

       For each artificial ant do

        From node , choose probabilistically (as in the following equation) the next state (if ) to move into

                  ,

        where is neighborhood of in 2D space

         Add the edge ( to the tabu list for each ant

         Repeat until each ant completes a solution

       end for

           Update,

       For each ant completed a tour       // find the local best tour

          Update the local best tour,

       end for

       if (  %   ==  0)

          Global best-tour,

          Global updation of

       end if

    end for