Tumor cell morphology is closely related to its invasiveness characteristics and migratory behaviors. An invasive tumor cell has a highly irregular shape, whereas a spherical cell is non-metastatic. Thus, quantitative analysis of cell features is crucial to determine tumor malignancy or to test the efficacy of anticancer treatment. We use phase-contrast microscopy to analyze single cell morphology and to monitor its change because it enables observation of long-term activity of living cells without photobleaching and phototoxicity, which is common in other fluorescence-labeled microscopy. Despite this advantage, there are image-level drawbacks to phase-contrast microscopy, such as local light effect and contrast interference ring, among others. Thus, we first applied a local filter to compensate for non-uniform illumination. Then, we used intensity distribution information to detect the cell boundary. In phase-contrast microscopy images, the cell normally appears as a dark region surrounded by a bright halo. As the halo artifact around the cell body is minimal and has an asymmetric diffusion pattern, we calculated the cross-sectional plane that intersected the center of each cell and was orthogonal to the first principal axis. Then, we extracted the dark cell region by level set. However, a dense population of cultured cells still rendered single-cell analysis difficult. Finally, we measured roundness and size to classify tumor cells into malignant and benign groups. We validated segmentation accuracy by comparing our findings with manually obtained results.