Lucas Fidon@Owkin "How to apply deep learning to small pathology datasets"

Computational pathology offers unprecedented opportunities for improved efficiency in treatment decisions by enabling pathologists to achieve higher precision and objectivity in disease classification, tumor microenvironment description and identification of new biomarkers.

But computational pathology comes with significant challenges, one of them being that annotated data is scarce. Self-Supervised Learning (SSL), a machine learning technique, has emerged as a promising solution to this challenge.

Join this talk to learn more about the application of SSL, why it matters for computational pathology, and how it could pave the way for the development of a foundation model for histopathology.”

Room added: Cavendish C2.07
Ask for the Bioinformatics meetup at the reception, they will have the list of registered participants. Remember to RSVP!

Approximate schedule:

6:30: doors open
6:45: chitchat, announcements
7:00: talk starts
7:45: talk ends, adjourn to pub