Topology-Guided Multi-Class Cell Context Generation for Digital Pathology
Abstract
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.
Cite
Text
Abousamra et al. "Topology-Guided Multi-Class Cell Context Generation for Digital Pathology." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.00324Markdown
[Abousamra et al. "Topology-Guided Multi-Class Cell Context Generation for Digital Pathology." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/abousamra2023cvpr-topologyguided/) doi:10.1109/CVPR52729.2023.00324BibTeX
@inproceedings{abousamra2023cvpr-topologyguided,
title = {{Topology-Guided Multi-Class Cell Context Generation for Digital Pathology}},
author = {Abousamra, Shahira and Gupta, Rajarsi and Kurc, Tahsin and Samaras, Dimitris and Saltz, Joel and Chen, Chao},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2023},
pages = {3323-3333},
doi = {10.1109/CVPR52729.2023.00324},
url = {https://mlanthology.org/cvpr/2023/abousamra2023cvpr-topologyguided/}
}