Skip to main content
. 2020 Oct 29;25(5):1735–1746. doi: 10.1109/JBHI.2020.3034863

Fig. 1.

Fig. 1.

Visualization of our RBCNet pipeline with two stages: training and testing. In the training stage, U-Net and Faster R-CNN are used to train on raw image tiles, while in the inference stage, we apply a Faster R-CNN trained network to cell cluster raw image regions corresponding to the connected components produced by U-Net.