Abstract: The persistently high incidence of breast cancer emphasizes the need for precise detection in its diagnosis. Computer-aided medical systems are designed to provide accurate information and reduce human errors, in which accurate and effective segmentation of medical images plays a pivotal role in improving clinical outcomes. Multilevel Threshold Image Segmentation (MTIS) is widely favored due to its stability and straightforward implementation. Especially when dealing with sophisticated anatomical structures, high-level thresholding is a crucial technique in identifying fine details. To enhance the accuracy of complex breast cancer image segmentation, this paper proposes an improved version of RIME optimizer EECRIME, denoted as the double Enhanced solution quality Crisscross RIME algorithm. The original RIME initially conducts an efficient optimization to target promising solutions. The double-enhanced solution quality (EESQ) mechanism is proposed for thorough exploitation without falling into local optimum. In contrast, the crisscross operations perform a further local exploration of the generated feasible solutions. The performance of EECRIME is verified with basic and advanced algorithms on IEEE CEC2017 benchmark functions. Furthermore, an EECRIME-based MTIS method in combination with Kapur’s entropy is applied to segment breast Infiltrating Ductal Carcinoma (IDC) histology images. The results demonstrate that the developed model significantly surpasses its competitors, establishing it as a practical approach for complex medical image processing.

Key words: Rime optimization algorithm · Double-enhanced solution quality mechanism · Crisscross optimization ,
algorithm · Image segmentation · Breast cancer