Pix2pix training dataset for predicting nuclei form brightfield images

Dataset for training pix2pix model to predict nuclei from brightfield images of MDA-MB-231. 

This dataset contains 1600 brightfield and 1600 nuclei images. 

The nuclei were labeled using sir-DNA (Cytoskeleton). Cells were imaged live (37 °C, 5% CO2) using a Nikon Eclipse Ti2-E microscope (Nikon) equipped with an sCMOS Orca Flash4.0 camera (Hamamatsu) and controlled by the NIS-Elements software (Nikon, v 5.11.01). MDA-MB-231 cells were imaged using a 20× Nikon CFI Plan Apo Lambda objective (NA 0.75), either 1 frame per minute for 2 hours or 1 frame every 5 minutes for 17 hours. In these experiments, a camera binning of 2 × 2 was used.