Panoptic segmentation with highly imbalanced semantic labels

Item Type:	Conference or Workshop Item
Title:	Panoptic segmentation with highly imbalanced semantic labels
Creators Name:	Rumberger, J.L. and Baumann, E. and Hirsch, P. and Janowczyk, A. and Zlobec, I. and Kainmueller, D.
Abstract:	We describe here the panoptic segmentation method we devised for our participation in the CoNIC: Colon Nuclei Identification and Counting Challenge at ISBI 2022. Key features of our method are a weighted loss specifically engineered for semantic segmentation of highly imbalanced cell types, and a state-of-the art nuclei instance segmentation model, which we combine in a Hovernet-like architecture.
Keywords:	Nuclei Segmentation, Cell Classification, Digital Pathology, Challenge Submission
Source:	2022 IEEE International Symposium on Biomedical Imaging Challenges (ISBIC)
Title of Book:	2022 IEEE International Symposium on Biomedical Imaging Challenges (ISBIC)
ISBN:	9781665429238
Publisher:	IEEE
Page Range:	1-4
Date:	17 August 2022
Official Publication:	https://doi.org/10.1109/isbic56247.2022.9854551

Repository Staff Only: item control page