Comparison of Bio-Inspired Algorithms From The Point of View of Medical Image Segmentation

As new technological challenges depending on the computational performance of bio-inspired algorithms emerge, the demand for more efficient heuristic solutions grows up at same rate. Specifically, the medical field is one of the most challenging, due to the fact of the pre-processing steps, such as multilevel segmentation of color spaces, require greater precision. Thus, many algorithms inspired by natural behavior have emerged successfully aiming to find approximate solutions compatible with optimal ones, but with much higher performance in terms of computational time. Although they perform well, some of these newer algorithms have not yet been analyzed from their practical applicability in one or more medical databases. This paper presents a comparative study from a practical point of view of three of these new algorithms: Cuckoo Search (CS), KH (Krill Herd) and EHO (Elephant Herd Optimization). Our results suggest that these three algorithms are compatible in terms of performance in medical databases, but with EHO showing the best performance among all three.