Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

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., Baumann, E., Hirsch, P., Janowczyk, A., 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

Open Access
MDC Library