Cell Count
(Label-Free)

Culture of cell lines is one of the most useful and commonly practiced disciplines in life the sciences. The ability to count cells in culture is a requirement at numerous stages of most experimental procedures that utilize cultured cells. This may be determining whether cells have reached a high enough density to initiate an experiment, or the assertation of the effects of an agonist on cell growth and division.

Counting individual cells has traditionally been a difficult task and has often required that application of fluorescent stains against whole cells or nuclei to gain accurate counts (Ligasová & Koberna 2019) while counting of unlabeled cells requires complex image processing algorithms (Lin et al. 2022).

The use of deep learning models capable of segmenting individual unlabeled cells or nuclei has greatly improved both the accuracy and ease of this process. The Image-Pro Cell Count Protocol when combined with the unlabelled Cells or unlabelled nuclei model allows analysis of large volumes of data in complex formats such as multi-well plates with little to no image analysis experience. These models are effective with unlabeled cells imaged with phase contrast, pseudo-phase contrast or differential interference contrast (DIC).