S113 - Pre-training Segmentation Models for Histopathology

Payden McBee, Nazanin Moradinasab, Donald E Brown, Sana Syed

Show abstract - PDF - Reviews

In limited data settings, transfer learning has proven useful in initializing model parameters. In this work, we compare random initialization, pre-training on ImageNet, and pre-training on histopathology datasets for 2 model architectures across 4 segmentation histopathology datasets. We show that pre-training on histopathology datasets does not always significantly improve performance relative to ImageNet pre-trained weights for both model architectures. We conclude that unless larger labeled datasets or semi-supervised techniques are leveraged, ImageNet pre-trained weights should be used in initializing segmentation models for histopathology.
Hide abstract

Short paper

Schedule: Tuesday, July 11: Posters — 10:30–12:00 & 15:00–16:00
Poster location: T55