Multi-label versus multi-class classification of blood cells and their aggregates in microfluidic channels
It is shown that, unlike MC classification, ML classification can identify cell aggregates not represented in the training data, and it also avoids the need for exhaustive, strictly defined aggregate labels, thereby simplifying and speeding up annotation.
I. Zingman, S. Abuhattum, Sara Kaliman et al.
· 0 citations