# Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction

arXiv: https://arxiv.org/abs/2506.22012 · HTML: https://mlsanity.com/paper/2506.22012/

## 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 20 of its 64 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Segment Anything in Medical Images](https://mlsanity.com/paper/2304.12306/) (2023)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?](https://mlsanity.com/paper/1811.03691/) (2018)
- [CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization](https://mlsanity.com/paper/2304.01814/) (2023)
- [3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network](https://mlsanity.com/paper/1802.05656/) (2018)
- [DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising](https://mlsanity.com/paper/2108.10772/) (2021)
- [TorchRadon: Fast Differentiable Routines for Computed Tomography](https://mlsanity.com/paper/2009.14788/) (2020)
- [Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance](https://mlsanity.com/paper/2312.16519/) (2023)
- [Diffusion Probabilistic Priors for Zero-Shot Low-Dose CT Image Denoising](https://mlsanity.com/paper/2305.15887/) (2023)
- [Low-Dose CT Denoising via Sinogram Inner-Structure Transformer](https://mlsanity.com/paper/2204.03163/) (2022)

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

- [FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising](https://mlsanity.com/paper/2508.17299/) (2025)
- [Physics-Guided Null-Space Diffusion with Sparse Masking for Corrective Sparse-View CT Reconstruction](https://mlsanity.com/paper/2509.05992/) (2025)
- [Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstruction](https://mlsanity.com/paper/2509.23885/) (2025)
- [Progressive Masked Refinement Self-supervised Learning for Low-Dose CT Denoising](https://mlsanity.com/paper/2601.14180/) (2026)
- [PLOT-CT: Pre-log Voronoi Decomposition Assisted Generation for Low-dose CT Reconstruction](https://mlsanity.com/paper/2602.11625/) (2026)
- [SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTion](https://mlsanity.com/paper/2603.00687/) (2026)
- [Projection Guided Personalized Federated Learning for Low Dose CT Denoising](https://mlsanity.com/paper/2603.13422/) (2026)
- [Distilling Photon-Counting CT into Routine Chest CT through Clinically Validated Degradation Modeling](https://mlsanity.com/paper/2604.07329/) (2026)
- [GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization](https://mlsanity.com/paper/2607.11941/) (2026)
- [Feed-Forward Hierarchical Gaussian Diffusion for Extreme CT Reconstruction](https://mlsanity.com/paper/2608.15343/) (2026)
- [Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction](https://mlsanity.com/paper/2609.18943/) (2026)

## Abstract (arXiv)

The generalization of deep learning-based low-dose computed tomography (CT) reconstruction models to doses unseen in the training data is important and remains challenging. Previous efforts heavily rely on paired data to improve the generalization performance and robustness through collecting either diverse CT data for re-training or a few test data for fine-tuning. Recently, diffusion models have shown promising and generalizable performance in low-dose CT (LDCT) reconstruction, however, they may produce unrealistic structures due to the CT image noise deviating from Gaussian distribution and imprecise prior information from the guidance of noisy LDCT images. In this paper, we propose a noise-inspired diffusion model for generalizable LDCT reconstruction, termed NEED, which tailors diffusion models for noise characteristics of each domain. First, we propose a novel shifted Poisson diffusion model to denoise projection data, which aligns the diffusion process with the noise model in pre-log LDCT projections. Second, we devise a doubly guided diffusion model to refine reconstructed images, which leverages LDCT images and initial reconstructions to more accurately locate prior information and enhance reconstruction fidelity. By cascading these two diffusion models for dual-domain reconstruction, our NEED requires only normal-dose data for training and can be effectively extended to various unseen dose levels during testing via a time step matching strategy. Extensive qualitative, quantitative, and segmentation-based evaluations on two datasets demonstrate that our NEED consistently outperforms state-of-the-art methods in reconstruction and generalization performance. Source code is made available at https://github.com/qgao21/NEED.