Bladder inverted papilloma is a histologically benign tumor located in the bladder, however it has also been reported that some bladder inverted papilloma could recur and develop into cancer. Diagnosis of bladder inverted papilloma primarily depends on biopsy, where p53 immunohistochemistry is the most frequently used marker. In clinical practice, diagnosis of bladder inverted papilloma is determined human-visually in terms of the percentage of positively stained cells in tissue samples, which is subjective or/and inconsistent. To enable quantitative, objective, and reproducible measurements, image analysis techniques are introduced to computerize cell analysis. The success of an automatic cell analysis system largely depends on the quality of segmentation. However, segmentation of cell images is far from easy due to the complex natures of histology images. Development of sophisticated cell image segmentation algorithms is necessary to ensure success of automatic cell analysis. This is the objective of the present study.