mlsanityData to 7 Oct 2026

3D Vessel Graph Generation Using Denoising Diffusion

arXiv 2407.05842 ↗First posted 8 Jul 2024cs.CVcited by 9

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Blood vessel networks, represented as 3D graphs, help predict disease biomarkers, simulate blood flow, and aid in synthetic image generation, relevant in both clinical and pre-clinical settings. However, generating realistic vessel graphs that correspond to an anatomy of interest is challenging. Previous methods aimed at generating vessel trees mostly in an autoregressive style and could not be applied to vessel graphs with cycles such as capillaries or specific anatomical structures such as the Circle of Willis. Addressing this gap, we introduce the first application of textitdenoising diffusion models in 3D vessel graph generation. Our contributions include a novel, two-stage generation method that sequentially denoises node coordinates and edges. We experiment with two real-world vessel datasets, consisting of microscopic capillaries and major cerebral vessels, and demonstrate the generalizability of our method for producing diverse, novel, and anatomically plausible vessel graphs.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 22 of its 31 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

22 of 31 references.

References · 22

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  4. 2020A Generalization of Transformer Networks to Graphscited by 653
  5. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  6. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  7. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  8. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 96
  9. 2022Diffusion Models for Graphs Benefit From Discrete State Spacescited by 69
  10. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  11. 2023The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiographycited by 48
  12. 2023Graph Denoising Diffusion for Inverse Protein Foldingcited by 44
10 more
  1. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
  2. 2023MUDiff: Unified Diffusion for Complete Molecule Generationcited by 41
  3. 20233D molecule generation by denoising voxel gridscited by 38
  4. 2021Scalable Robust Graph and Feature Extraction for Arbitrary Vessel Networks in Large Volumetric Datasetscited by 17
  5. 2023Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotationscited by 16
  6. 2018Blood Vessel Geometry Synthesis using Generative Adversarial Networkscited by 13
  7. 2023VesselVAE: Recursive Variational Autoencoders for 3D Blood Vessel Synthesiscited by 13
  8. 2021The RETA Benchmark for Retinal Vascular Tree Analysiscited by 12
  9. 2022Physiology-based simulation of the retinal vasculature enables annotation-free segmentation of OCT angiographscited by 12
  10. 2023Link Prediction for Flow-Driven Spatial Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025VesselGPT: Autoregressive Modeling of Vascular Geometrycited by 5
  2. 2025Hierarchical Part-based Generative Model for Realistic 3D Blood Vesselcited by 4
  3. 2025Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generationcited by 3
  4. 2025Semantically Consistent Discrete Diffusion for 3D Biological Graph Modelingcited by 2
  5. 2026High-Fidelity Medical Shape Generation via Skeletal Latent Diffusioncited by 1
  6. 2026VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generationcited by 1
  7. 2026Sparse Representation Learning for Vesselscited by 1
  8. 2025Recursive Variational Autoencoders for 3D Blood Vessel Generative Modelingcited by 0
  9. 2026SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Shape-guided Conditional Latent Diffusion Models for Synthesising Brain Vasculature
  2. 2025VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis
  3. 2022Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation
  4. 2025Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
  5. 2024vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation
  6. 2023Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models
  7. 2026Semantically Conditioned Diffusion Models for Cerebral DSA Synthesis
  8. 2026VesselFusion: Diffusion Models for Vessel Centerline Extraction from 3D CT Images