Abstract

We present high-throughput quantitative phase imaging cytometry (>10,000 cells/sec) assisted by neural-networked-based transfer learning that critically overcomes the batch effects and enables accurate label-free multi-class lung cancer types classification at single-cell precision (>91%).

© 2020 The Author(s)

PDF Article

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription