# Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image Segmentation

arXiv: https://arxiv.org/abs/2210.17408 · HTML: https://mlsanity.com/paper/2210.17408/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Diffusion Models for Implicit Image Segmentation Ensembles](https://mlsanity.com/paper/2112.03145/) (2021)
- [Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge](https://mlsanity.com/paper/1904.00682/) (2019)
- [Accelerating Diffusion Models via Early Stop of the Diffusion Process](https://mlsanity.com/paper/2205.12524/) (2022)
- [Noise Estimation for Generative Diffusion Models](https://mlsanity.com/paper/2104.02600/) (2021)
- [Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images](https://mlsanity.com/paper/1802.05203/) (2018)

## Built on by (most cited first, 18 of 18)

- [MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer](https://mlsanity.com/paper/2301.11798/) (2023)
- [Ambiguous Medical Image Segmentation using Diffusion Models](https://mlsanity.com/paper/2304.04745/) (2023)
- [Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images](https://mlsanity.com/paper/2301.04802/) (2023)
- [Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing](https://mlsanity.com/paper/2303.15288/) (2023)
- [HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation](https://mlsanity.com/paper/2407.03548/) (2024)
- [A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI](https://mlsanity.com/paper/2311.11383/) (2023)
- [A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation](https://mlsanity.com/paper/2411.16370/) (2024)
- [A Recycling Training Strategy for Medical Image Segmentation with Diffusion Denoising Models](https://mlsanity.com/paper/2308.16355/) (2023)
- [BrainMRDiff: A Diffusion Model for Anatomically Consistent Brain MRI Synthesis](https://mlsanity.com/paper/2504.04532/) (2025)
- [DMCIE: Diffusion Model with Concatenation of Inputs and Errors to Improve the Accuracy of the Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2507.00983/) (2025)
- [ReCoSeg++:Extended Residual-Guided Cross-Modal Diffusion for Brain Tumor Segmentation](https://mlsanity.com/paper/2508.01058/) (2025)
- [Label-efficient multi-organ segmentation with a diffusion model](https://mlsanity.com/paper/2402.15216/) (2024)
- [Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer](https://mlsanity.com/paper/2408.00347/) (2024)
- [Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models](https://mlsanity.com/paper/2505.02753/) (2025)
- [ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning](https://mlsanity.com/paper/2312.01682/) (2023)
- [Diffusion-Based Semantic Segmentation of Lumbar Spine MRI Scans of Lower Back Pain Patients](https://mlsanity.com/paper/2411.10755/) (2024)
- [Enhancing AI Face Realism: Cost-Efficient Quality Improvement in Distilled Diffusion Models with a Fully Synthetic Dataset](https://mlsanity.com/paper/2505.02255/) (2025)
- [Enhancing Low Back Pain Assessment with Diffusion Models for Lumbar Spine MRI Segmentation](https://mlsanity.com/paper/2608.04906/) (2026)

## Abstract (arXiv)

Based on the Denoising Diffusion Probabilistic Model (DDPM), medical image segmentation can be described as a conditional image generation task, which allows to compute pixel-wise uncertainty maps of the segmentation and allows an implicit ensemble of segmentations to boost the segmentation performance. However, DDPM requires many iterative denoising steps to generate segmentations from Gaussian noise, resulting in extremely inefficient inference. To mitigate the issue, we propose a principled acceleration strategy, called pre-segmentation diffusion sampling DDPM (PD-DDPM), which is specially used for medical image segmentation. The key idea is to obtain pre-segmentation results based on a separately trained segmentation network, and construct noise predictions (non-Gaussian distribution) according to the forward diffusion rule. We can then start with noisy predictions and use fewer reverse steps to generate segmentation results. Experiments show that PD-DDPM yields better segmentation results over representative baseline methods even if the number of reverse steps is significantly reduced. Moreover, PD-DDPM is orthogonal to existing advanced segmentation models, which can be combined to further improve the segmentation performance.