Topology-Guided Multi-Class Cell Context Generation for Digital Pathology
This work addresses the problem of generating realistic cell layouts for data augmentation in digital pathology, which is incremental as it builds on existing generative models with new structural descriptors.
The paper tackled the challenge of modeling complex spatial cell contexts in digital pathology by introducing mathematical tools from spatial statistics and topological data analysis into a deep generative model, resulting in the first high-quality multi-class cell layouts that improved downstream cell classification performance.
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.