mlsanityData to 14 Oct 2026

Generative diffusion model surrogates for mechanistic agent-based biological models

arXiv 2505.09630 ↗First posted 1 May 2025q-bio.QM cs.CV cs.ETcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Mechanistic, multicellular, agent-based models are commonly used to investigate tissue, organ, and organism-scale biology at single-cell resolution. The Cellular-Potts Model (CPM) is a powerful and popular framework for developing and interrogating these models. CPMs become computationally expensive at large space- and time- scales making application and investigation of developed models difficult. Surrogate models may allow for the accelerated evaluation of CPMs of complex biological systems. However, the stochastic nature of these models means each set of parameters may give rise to different model configurations, complicating surrogate model development. In this work, we leverage denoising diffusion probabilistic models to train a generative AI surrogate of a CPM used to investigate in vitro vasculogenesis. We describe the use of an image classifier to learn the characteristics that define unique areas of a 2-dimensional parameter space. We then apply this classifier to aid in surrogate model selection and verification. Our CPM model surrogate generates model configurations 20,000 timesteps ahead of a reference configuration and demonstrates approximately a 22x reduction in computational time as compared to native code execution. Our work represents a step towards the implementation of DDPMs to develop digital twins of stochastic biological systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 23 of its 49 references that are in the map. First posted on arXiv 1 May 2025.

Builds on

23 of 49 references.

References · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  8. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 402
  9. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 299
  10. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 110
  11. 2024DiffDA: a Diffusion Model for Weather-scale Data Assimilationcited by 61
  12. 2020TorchMD: A deep learning framework for molecular simulationscited by 55
11 more
  1. 2023Interpolating between Images with Diffusion Modelscited by 38
  2. 2024CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulationcited by 35
  3. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  4. 2020Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvaluescited by 27
  5. 2017Deep Learning the Physics of Transport Phenomenacited by 26
  6. 2024Avoiding mode collapse in diffusion models fine-tuned with reinforcement learningcited by 12
  7. 2019Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulationscited by 7
  8. 2021Deep learning approaches to surrogates for solving the diffusion equation for mechanistic real-world simulationscited by 5
  9. 2024A Comprehensive Evaluation of Generative Models in Calorimeter Shower Simulationcited by 5
  10. 2023Analyzing the Performance of Deep Encoder-Decoder Networks as Surrogates for a Diffusion Equationcited by 4
  11. 2024Zephyr quantum-assisted hierarchical Calo4pQVAE for particle-calorimeter interactionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Action
  2. 2025Learning Diffusion Models with Flexible Representation Guidance
  3. 2025Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery
  4. 2024Diffusion Models to Enhance the Resolution of Microscopy Images: A Tutorial
  5. 2023Denoising Diffusion Probabilistic Models for Generation of Realistic Fully-Annotated Microscopy Image Data Sets
  6. 2024An Organism Starts with a Single Pix-Cell: A Neural Cellular Diffusion for High-Resolution Image Synthesis
  7. 2025Revealing Subtle Phenotypes in Small Microscopy Datasets Using Latent Diffusion Models
  8. 2024Annotated Biomedical Video Generation using Denoising Diffusion Probabilistic Models and Flow Fields