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

arXiv: https://arxiv.org/abs/2304.02255 · HTML: https://mlsanity.com/paper/2304.02255/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 60 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Topology-Preserving Deep Image Segmentation](https://mlsanity.com/paper/1906.05404/) (2019)
- [Micro-Net: A unified model for segmentation of various objects in microscopy images](https://mlsanity.com/paper/1804.08145/) (2018)
- [Deep learning-based survival prediction for multiple cancer types using histopathology images](https://mlsanity.com/paper/1912.07354/) (2019)
- [Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data](https://mlsanity.com/paper/2006.00080/) (2020)
- [Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images](https://mlsanity.com/paper/2004.03037/) (2020)
- [PseudoEdgeNet: Nuclei Segmentation only with Point Annotations](https://mlsanity.com/paper/1906.02924/) (2019)
- [Multi-Class Cell Detection Using Spatial Context Representation](https://mlsanity.com/paper/2110.04886/) (2021)
- [SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2108.04476/) (2021)
- [Divide-and-Rule: Self-Supervised Learning for Survival Analysis in Colorectal Cancer](https://mlsanity.com/paper/2007.03292/) (2020)
- [Weakly Supervised Multi-Task Learning for Cell Detection and Segmentation](https://mlsanity.com/paper/1910.12326/) (2019)
- [Sharp-GAN: Sharpness Loss Regularized GAN for Histopathology Image Synthesis](https://mlsanity.com/paper/2110.14709/) (2021)
- [DeepLIIF: An Online Platform for Quantification of Clinical Pathology Slides](https://mlsanity.com/paper/2204.04494/) (2022)
- [Region-guided CycleGANs for Stain Transfer in Whole Slide Images](https://mlsanity.com/paper/2208.12847/) (2022)
- [SIAN: Style-Guided Instance-Adaptive Normalization for Multi-Organ Histopathology Image Synthesis](https://mlsanity.com/paper/2209.02412/) (2022)
- [SAFRON: Stitching Across the Frontier for Generating Colorectal Cancer Histology Images](https://mlsanity.com/paper/2008.04526/) (2020)
- [Primary Tumor and Inter-Organ Augmentations for Supervised Lymph Node Colon Adenocarcinoma Metastasis Detection](https://mlsanity.com/paper/2109.09518/) (2021)

## Built on by (most cited first, 7 of 7)

- [TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model](https://mlsanity.com/paper/2412.06011/) (2024)
- [Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model](https://mlsanity.com/paper/2407.14434/) (2024)
- [Spatial Diffusion for Cell Layout Generation](https://mlsanity.com/paper/2409.03106/) (2024)
- [Topology Optimization in Medical Image Segmentation with Fast Euler Characteristic](https://mlsanity.com/paper/2507.23763/) (2025)
- [Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review](https://mlsanity.com/paper/2410.19820/) (2024)
- [Instance Migration Diffusion for Nuclear Instance Segmentation in Pathology](https://mlsanity.com/paper/2504.01577/) (2025)
- [Classification of Histopathology Slides with Persistent Homology Convolutions](https://mlsanity.com/paper/2507.14378/) (2025)

## Abstract (arXiv)

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.