An optimal nuclei segmentation method based on enhanced multi-objective GWO

Abstract In breast cancer image analysis, reliable segmentation of the nuclei is still an open-ended research problem. this paper, a new clustering-based method presented. First, proposed pre-processes histopathology through SLIC method. Then, novel variant multi-objective grey wolf optimizer employed to group obtained super-pixels into optimal clusters. Lastly, cluster with minimum value segmented as region. The experimental results demonstrates that algorithm surpasses existing algorithms over ten standard benchmark functions belonging different categories. Particularly, has achieved best fitness more than 0.90 on 90% considered functions. Further, accuracy validated H&E-stained estrogen receptor positive (ER+) images. Experimental illustrates attained dice-coefficient 0.52 80% This efficient in producing efficacious segmenting histology images Breast cancer.