mlsanityData to 7 Oct 2026

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

arXiv 2304.02255 ↗First posted 5 Apr 2023eess.IV cs.CVcited by 7

Not on the map. Why?

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.

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

Builds on

19 of 60 references.

References · 19

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 387
  4. 2019Topology-Preserving Deep Image Segmentationcited by 198
  5. 2018Micro-Net: A unified model for segmentation of various objects in microscopy imagescited by 56
  6. 2019Deep learning-based survival prediction for multiple cancer types using histopathology imagescited by 47
  7. 2020Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Datacited by 38
  8. 2020Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Imagescited by 33
  9. 2019PseudoEdgeNet: Nuclei Segmentation only with Point Annotationscited by 27
  10. 2021Multi-Class Cell Detection Using Spatial Context Representationcited by 24
  11. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  12. 2020Divide-and-Rule: Self-Supervised Learning for Survival Analysis in Colorectal Cancercited by 17
7 more
  1. 2019Weakly Supervised Multi-Task Learning for Cell Detection and Segmentationcited by 16
  2. 2021Sharp-GAN: Sharpness Loss Regularized GAN for Histopathology Image Synthesiscited by 10
  3. 2022DeepLIIF: An Online Platform for Quantification of Clinical Pathology Slidescited by 9
  4. 2022Region-guided CycleGANs for Stain Transfer in Whole Slide Imagescited by 8
  5. 2022SIAN: Style-Guided Instance-Adaptive Normalization for Multi-Organ Histopathology Image Synthesiscited by 5
  6. 2020SAFRON: Stitching Across the Frontier for Generating Colorectal Cancer Histology Imagescited by 2
  7. 2021Primary Tumor and Inter-Organ Augmentations for Supervised Lymph Node Colon Adenocarcinoma Metastasis Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 3.

7 papers.

  1. 2024TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Modelcited by 16
  2. 2024Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Modelcited by 8
  3. 2024Spatial Diffusion for Cell Layout Generationcited by 5
  4. 2025Topology Optimization in Medical Image Segmentation with Fast Euler Characteristiccited by 5
  5. 2024Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Reviewcited by 1
  6. 2025Instance Migration Diffusion for Nuclear Instance Segmentation in Pathologycited by 0
  7. 2025Classification of Histopathology Slides with Persistent Homology Convolutionscited by 0