Abstract
BACKGROUND: This study aims to investigate the application of visual information processing mechanisms in the segmentation of stem cell (SC) images. The cognitive principles underlying visual information processing were analyzed, and the limitations of conventional segmentation methods were evaluated using phase-contrast microscopy images of stem cells. METHODS: An optimized segmentation method incorporating halo correction was developed to address the limitations of traditional approaches. The performance of the proposed method was experimentally validated and compared with existing techniques. RESULTS: The proposed method achieved segmentation accuracy, recall, precision, and F1-score values of 96.5%, 94.9%, 91.4%, and 93.9%, respectively, outperforming existing approaches. Additionally, the confluency error on the Human Mesenchymal Stem Cells dataset and the C2C12 dataset was 0.07 and 0.05, respectively, indicating superior performance compared to equivalent methods. CONCLUSION: The findings demonstrate that the proposed method offers enhanced efficacy for stem cell image segmentation tasks.