Sailfish optimizer with Levy flight, chaotic and opposition-based multi-level thresholding for medical image segmentation

Image segmentation is a procedure of dividing the digital image into multiple set of pixels. The intention of the segmentation is to transform the representation of medical images into a meaningful subject. Multi-level thresholding is an application of efficacious segmentation method. Several segmentation techniques were used previously to segment the affected portion from the medical images, but those techniques do not provide sufficient results. Therefore, in this paper, sailfish optimizer with Levy flight, chaotic and opposition-based multi-level thresholding is proposed for accurate medical image segmentation. Here, abdomen images, lung image and brain image are segmented using the optimal multi-level threshold with Otsu's strategy and Kapur's entropy strategy. To get the optimal segmentation results, the weight parameters of the Otsu's strategy and Kapur's entropy is optimized with the help of Levy flight sail fish optimizer (LFSFO)-chaotic sail fish optimizer (CSFO)-opposite sail fish optimizer (OSFO) for the segmentation of medical image. Finally, the performance of the proposed MLT-LFSFO-CSO-OSFO-MIS method attains lower mean square error and higher accuracy than three existing methods.

Automated summary

Image segmentation is the process of dividing a digital image into multiple sets of pixels to create a meaningful representation of medical images. The proposed method in this paper combines the sailfish optimizer with Levy flight, chaotic and opposition-based multi-level thresholding to achieve accurate segmentation. By optimizing the weight parameters and using Otsu's strategy and Kapur's entropy with the help of the proposed optimizer, the proposed method achieves lower mean square error and higher accuracy compared to existing methods.