# Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation

arXiv: https://arxiv.org/abs/2509.01330 · HTML: https://mlsanity.com/paper/2509.01330/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses](https://mlsanity.com/paper/1612.00197/) (2016)
- [No New-Net](https://mlsanity.com/paper/1809.10483/) (2018)
- [Anomaly Detection With Conditional Variational Autoencoders](https://mlsanity.com/paper/2010.05531/) (2020)
- [Contrastive Conditional Latent Diffusion for Audio-visual Segmentation](https://mlsanity.com/paper/2307.16579/) (2023)
- [Edward: A library for probabilistic modeling, inference, and criticism](https://mlsanity.com/paper/1610.09787/) (2016)
- [DeepMIM: Deep Supervision for Masked Image Modeling](https://mlsanity.com/paper/2303.08817/) (2023)
- [SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space](https://mlsanity.com/paper/2312.08200/) (2023)
- [Explore In-Context Segmentation via Latent Diffusion Models](https://mlsanity.com/paper/2403.09616/) (2024)
- [Deep ensembles in bioimage segmentation](https://mlsanity.com/paper/2112.12955/) (2021)
- [Cross-modal Medical Image Generation Based on Pyramid Convolutional Attention Network](https://mlsanity.com/paper/2411.17420/) (2024)

## Built on by (most cited first, 1 of 1)

- [Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution](https://mlsanity.com/paper/2510.19166/) (2025)

## Abstract (arXiv)

Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework that learns voxel-wise distributions while maintaining strong calibration and practical sampling efficiency. PGRD embeds discrete labels as one-hot targets in a continuous space to align segmentation with diffusion modeling. A coarse prior predictor provides step-wise guidance; the diffusion network then learns the residual to the prior, accelerating convergence and improving calibration. A deep diffusion supervision scheme further stabilizes training by supervising intermediate time steps. Evaluated on representative MRI and CT datasets, PGRD achieves higher Dice scores and lower NLL/ECE values than Bayesian, ensemble, Probabilistic U-Net, and vanilla diffusion baselines, while requiring fewer sampling steps to reach strong performance.