Automated Training of Deep Convolutional Neural Networks for Cell Segmentation.

JSON

Sadanandan SK, Ranefall P, Le Guyader S, Wählby C

Sci Rep 7 (1) 7860 [2017-08-10; online 2017-08-10]

Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automatically using fluorescently labeled cells, perform similar to manual annotations.

Affiliated researcher

PubMed 28798336

DOI 10.1038/s41598-017-07599-6

Crossref 10.1038/s41598-017-07599-6

pii: 10.1038/s41598-017-07599-6
pmc: PMC5552800