We present a new method for segmenting phase contrast images of NIH 3T3 fibroblast cells that is accurate even when cells are in contact. The problem of segmentation, when cells are in contact, poses a challenge to the accurate automation of cell counting, tracking and lineage modeling in cell biology. The segmentation presented in this paper consists of (1) background reconstruction to obtain noise-free foreground pixels, and (2) incorporation of biological insight about dividing and non-dividing cells into the segmentation process to achieve reliable separation of foreground pixels into pixels associated with individual cells. The segmentation results were compared against manual segmentation provided by experts for a stack of 238 images, which we consider as reference data. We chose two metrics to measure the accuracy of segmentation: the adjusted rand index (ARI) to compare similarities at a pixel level between masks resulting from manual vs. automated segmentation, and the number of cells per field (NCF) to compare the number of cells identified in the field by manual vs. automated analysis. We determined that the automated segmentation compared to manual segmentation has an average ARI of 0.96 (1 being a perfect match), with a standard deviation of 0.03, and an average difference of the two numbers of cells per field equal to 5.39% with a standard deviation of 4.6%.
J. Chalfoun, Alden A. Dima; Marcin Kociolek; Michael W. Halter; Antonio Cardone; Adele P. Peskin; Peter Bajcsy; Mary C. Brady, “Segmenting time-lapse phase contrast images of adjacent NIH 3T3 cells”,
Journal of Microscopy, 2013