REBSA: Enhanced backtracking search for multi-threshold segmentation of breast cancer images

Breast cancer has become one of the most common cancers among women globally. Early diagnosis and intervention play a crucial role in breast cancer management. Automatic segmentation of histological images of breast cancer utilizing Multi-Threshold Image Segmentation (MTIS) technology can assist doctors in making more accurate diagnostic decisions for patients. However, traditional methods face challenges in terms of segmentation efficiency and accuracy. This paper proposes a Renyi entropy-based MTIS to address this issue using an improved backtracking search algorithm (REBSA). The proposed method enhances the original BSA by introducing a random reselection strategy to enhance diversity of the population and enhance the algorithm's exploration capability. Additionally, an enhanced quality mechanism is incorporated, which improves the quality of candidate solutions while maintaining a degree of randomness. The integration of these two approaches significantly enhances the performance of the BSA. In order to confirm the performance of the proposed REBSA, several tests were carried out using the CEC 2017 benchmark functions, including diversity balance analysis, parameter sensitivity analysis, and stability analysis. Additionally, REBSA was compared with various basic and advanced algorithms. The results demonstrate that REBSA achieved the top rank on most functions across different dimensions, proving its exceptional optimization performance and robustness. Finally, the proposed REBSA was applied to MTIS tasks on breast cancer histopathological images. The results verified that REBSA achieved higher segmentation accuracy and efficiency. Compared to other approaches, it can retain more pathological tissue details and rank higher than other methods in several image evaluation metrics, demonstrating its ability to handle the difficult problem of breast cancer tissue image segmentation. Moreover, this study utilized a real clinical dataset of breast cancer histopathological images, further demonstrating the suggested method's efficacy in practical diagnostic scenarios. It provides reliable technical support for medical image analysis, assisting doctors in improving diagnostic accuracy and early screening efficiency.