Accurate segmentation of breast cancer lesions is vital for early detection, precise diagnosis, and effective treatment planning. In this research work, we propose an ensemble-based segmentation approach that combines the power of the U-Net model and the SeqNet model for breast cancer segmentation. By leveraging the complementary strengths of these components, which capture both spatial and sequential information, we aim to improve the accuracy and reliability of breast cancer lesion segmentation, thereby facilitating better clinical decision-making and patient care. Experiments are conducted on BUSI dataset which is one of the standard datasets used by many researchers. A comparative analysis is also provided with the other approaches to justify the suitability of the proposed ensemble model for breast cancer segmentation task.