An improved honey badger algorithm for global optimization and multilevel thresholding segmentation: real case with brain tumor images

Abstract

Global optimization and biomedical image segmentation are crucial in diverse scientific and medical fields. The Honey Badger Algorithm (HBA) is a newly developed metaheuristic that draws inspiration from the foraging behavior of honey badgers. Similar to other metaheuristic algorithms, HBA encounters difficulties associated with exploitation, being trapped in local optima, and the pace at which it converges. This study aims to improve the performance of the original HBA by implementing the Enhanced Solution Quality (ESQ) method. This strategy helps to prevent becoming stuck in local optima and speeds up the convergence process. We conducted an assessment of the enhanced algorithm, mHBA, by utilizing a comprehensive collection of benchmark functions from IEEE CEC’2020. In this evaluation, we compared mHBA with well-established metaheuristic algorithms. mHBA demonstrates exceptional performance, as shown by both qualitative and quantitative assessments. Our study not only focuses on global optimization but also investigates the field of biomedical image segmentation, which is a crucial process in numerous applications involving digital image analysis and comprehension. We specifically focus on the problem of multi-level thresholding (MT) for medical image segmentation, which is a difficult process that becomes more challenging as the number of thresholds needed increases. In order to tackle this issue, we suggest a revised edition of the standard HBA, known as mHBA, which utilizes the ESQ approach. We utilized this methodology for the segmentation of Magnetic Resonance Images (MRI). The evaluation of mHBA utilizes existing metrics to gauge the quality and performance of its segmentation. This evaluation showcases the resilience of mHBA in comparison to many established optimization algorithms, emphasizing the effectiveness of the suggested technique.