Efficient subtyping of ovarian cancer histopathology whole slide images using active sampling in multiple instance learning – Jack Breen 2023

In this study we developed a novel method for classifying histopathology slides and found that it achieved similar classification performance to a standard method while requiring substantially less memory and computing time. The aim of this research is to make AI more practical for histopathology labs, which do not have access to the advanced computing hardware which is typically required to run state-of-the-art models.

This is available as a full publication or a pre-print.

Published on April 6, 2023
[ Conference_Publication  ]