Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting

[thumbnail of Original Article]
Preview
PDF (Original Article) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
8MB
[thumbnail of Supplementary Data]
Preview
PDF (Supplementary Data) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
30MB

Item Type:Article
Title:CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting
Creators Name:Graham, S., Vu, Q.D., Jahanifar, M., Weigert, M., Schmidt, U., Zhang, W., Zhang, J., Yang, S., Xiang, J., Wang, X., Rumberger, J.L., Baumann, E., Hirsch, P., Liu, L., Hong, C., Aviles-Rivero, A.I., Jain, A., Ahn, H., Hong, Y., Azzuni, H., Xu, M., Yaqub, M., Blache, M.C., Piégu, B., Vernay, B., Scherr, T., Böhland, M., Löffler, K., Li, J., Ying, W., Wang, C., Snead, D., Raza, S.E.A., Minhas, F. and Rajpoot, N.M.
Abstract:Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge’s improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.
Keywords:Computational Pathology, Nuclear Recognition, Deep Learning
Source:Medical Image Analysis
ISSN:1361-8415
Publisher:Elsevier
Volume:92
Page Range:103047
Date:February 2024
Additional Information:Dagmar Kainmüller is a member of the CoNIC Challenge Consortium.
Official Publication:https://doi.org/10.1016/j.media.2023.103047

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library