Objective: To develop a novel automated image analysis system to differentiate immunohistochemically stained cells from background.
Study design: Cell segmentation was performed by applying global thresholding algorithms to find an approximate threshold at which cells could be separated from background followed by a novel refinement algorithm to erode edge pixels of the region. To separate overlapping cells, a new decomposition method was developed that uses both semantic knowledge and high-level relational information. Both the cell segmentation and separation methods were evaluated on images of stained tissue sections and the manually outlined cell areas and numbers compared to the computed.
Results: Macrophage areas computed at the first stage by Otsu's algorithm did not differ significantly (P = .07) from those traced manually, while the areas computed by Kittler's and Kurita's algorithms did not agree (P < .01). Both Otsu's and Kurita's algorithms performed well when combined with edge pixel erosion. Kittler's algorithm proved unsuccessful even with edge erosion. Comparison of the computed and manually determined cell numbers showed a significant correlation, and regression analysis resulted in the unity curve.
Conclusion: A combination of global thresholding and a novel edge erosion technique allowed identification of immunohistochemically stained macrophages; the computed cell areas agreed with the manual results.