Highlights:
Generative deep network encoded latent representation of live-imaged melanoma cells
Supervised machine-learning classified metastatic efficiency using latent cell representations
Validated classifier prediction on melanoma cell lines in mouse xenografts
Interpreted metastasis-driving features in amplified generative cell image models
Paper: https://www.sciencedirect.com/science/article/pii/S2405471221001587.
Twitter summary: https://twitter.com/AssafZaritsky/status/1400044956262322177.
Press release and popular news: here (UTSW), here, here, here, here, and here.
And the paper was featured on the cover!
