# Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS

arXiv: https://arxiv.org/abs/2503.01075 · HTML: https://mlsanity.com/paper/2503.01075/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)
- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline](https://mlsanity.com/paper/1910.03866/) (2019)
- [Understanding Hallucinations in Diffusion Models through Mode Interpolation](https://mlsanity.com/paper/2406.09358/) (2024)
- [VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models](https://mlsanity.com/paper/2406.16338/) (2024)
- [On the Out-of-distribution Generalization of Probabilistic Image Modelling](https://mlsanity.com/paper/2109.02639/) (2021)
- [Enhanced generative adversarial network for 3D brain MRI super-resolution](https://mlsanity.com/paper/1907.04835/) (2019)
- [Hallucination Index: An Image Quality Metric for Generative Reconstruction Models](https://mlsanity.com/paper/2407.12780/) (2024)
- [Distribution Shift Inversion for Out-of-Distribution Prediction](https://mlsanity.com/paper/2306.08328/) (2023)
- [Tackling Structural Hallucination in Image Translation with Local Diffusion](https://mlsanity.com/paper/2404.05980/) (2024)
- [Low-field magnetic resonance image enhancement via stochastic image quality transfer](https://mlsanity.com/paper/2304.13385/) (2023)
- [SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks](https://mlsanity.com/paper/2106.02599/) (2021)
- [A 3D Conditional Diffusion Model for Image Quality Transfer -- An Application to Low-Field MRI](https://mlsanity.com/paper/2311.06631/) (2023)

## Built on by (most cited first, 11 of 11)

- [Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities](https://mlsanity.com/paper/2508.07031/) (2025)
- [RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models](https://mlsanity.com/paper/2507.12201/) (2025)
- [Converting T1-weighted MRI from 3T to 7T quality using deep learning](https://mlsanity.com/paper/2507.13782/) (2025)
- [Deep generative priors for 3D brain analysis](https://mlsanity.com/paper/2510.15119/) (2025)
- [MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction](https://mlsanity.com/paper/2603.03710/) (2026)
- [CARE: Training-Free Controllable Restoration for Medical Images via Dual-Latent Steering](https://mlsanity.com/paper/2603.25026/) (2026)
- [On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods](https://mlsanity.com/paper/2605.13146/) (2026)
- [Measurement Geometry and Design for Trustworthy Generative Inverse Problems](https://mlsanity.com/paper/2606.02309/) (2026)
- [Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates](https://mlsanity.com/paper/2606.02331/) (2026)
- [Noise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reduction](https://mlsanity.com/paper/2606.25009/) (2026)
- [VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution](https://mlsanity.com/paper/2610.20509/) (2026)

## Abstract (arXiv)

Hallucinations are spurious structures not present in the ground truth, posing a critical challenge in medical image reconstruction, especially for data-driven conditional models. We hypothesize that combining an unconditional diffusion model with data consistency, trained on a diverse dataset, can reduce these hallucinations. Based on this, we propose DynamicDPS, a diffusion-based framework that integrates conditional and unconditional diffusion models to enhance low-quality medical images while systematically reducing hallucinations. Our approach first generates an initial reconstruction using a conditional model, then refines it with an adaptive diffusion-based inverse problem solver. DynamicDPS skips early stage in the reverse process by selecting an optimal starting time point per sample and applies Wolfe's line search for adaptive step sizes, improving both efficiency and image fidelity. Using diffusion priors and data consistency, our method effectively reduces hallucinations from any conditional model output. We validate its effectiveness in Image Quality Transfer for low-field MRI enhancement. Extensive evaluations on synthetic and real MR scans, including a downstream task for tissue volume estimation, show that DynamicDPS reduces hallucinations, improving relative volume estimation by over 15% for critical tissues while using only 5% of the sampling steps required by baseline diffusion models. As a model-agnostic and fine-tuning-free approach, DynamicDPS offers a robust solution for hallucination reduction in medical imaging. The code will be made publicly available upon publication.