Topology-Guided Multi-Class Cell Context Generation for Digital Pathology

In digital pathology, the spatial context of cells is important for cell classification, cancer diagnosis and prognosis. To model such complex cell context, however, is challenging. Cells form different mixtures, lineages, clusters and holes. To model such structural patterns in a learnable fashion,...

Full description

Saved in:
Bibliographic Details
Published inProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Vol. 2023; pp. 3323 - 3333
Main Authors Abousamra, Shahira, Gupta, Rajarsi, Kurc, Tahsin, Samaras, Dimitris, Saltz, Joel, Chen, Chao
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.06.2023
Subjects
cell microscopy
Layout
Mathematical models
Medical and biological vision
Microscopy
Pathology
Pattern recognition
Prognostics and health management
Task analysis
Online AccessGet full text

Cover

More Information
Summary:In digital pathology, the spatial context of cells is important for cell classification, cancer diagnosis and prognosis. To model such complex cell context, however, is challenging. Cells form different mixtures, lineages, clusters and holes. To model such structural patterns in a learnable fashion, we introduce several mathematical tools from spatial statistics and topological data analysis. We incorporate such structural descriptors into a deep generative model as both conditional inputs and a differentiable loss. This way, we are able to generate high quality multi-class cell layouts for the first time. We show that the topology-rich cell layouts can be used for data augmentation and improve the performance of downstream tasks such as cell classification.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR52729.2023.00324