OBJECTIVE: To introduce an interactive segmentation algorithm that produces very good segmentation outcomes, while requiring minimum interaction by the user. STUDY DESIGN: Images of Feulgen-thionin-stained prostate cancer tissue microarray constructed from the surgical specimens of 33 prostate cancer patients have been segmented by our previously published segmentation method. A minimally interactive segmentation correction method to improve the segmentation outcome is presented. RESULTS: Given a reasonable amount (minimal) of user input, we obtained a desirable segmentation quality that improved extraction of nuclei. CONCLUSION: We present a method to improve the extraction of nuclei from Feulgen-thionin-stained prostate cancer cell sections. These segmented nuclei are the essential starting input for developing automated quantitative digital pathology systems. Although we tested our methods on prostate cancer cells, it is possible to use this method to segment other cell types such as oral, cervix, and lung. This generalization makes our interactive method an essential core for developing a system capable of analyzing any type of tissue. © Science Printers and Publishers, Inc.