mlsanityData to 14 Oct 2026

GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization

arXiv 2607.11941 ↗First posted 11 Jul 2026cs.CV cs.LGcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality. Existing deep learning-based low-dose CT (LDCT) reconstruction methods are typically optimized for fixed dose levels or specific anatomical regions, limiting their robustness and generalization in realistic clinical settings. We propose GenDiff, a generalizable diffusion-based framework for LDCT reconstruction that jointly models continuous radiation dose and anatomical information within a unified reconstruction network. The proposed framework integrates a Dose-Anatomy Encoder to learn acquisition-aware embeddings, a dose- and anatomy-conditioned cold diffusion backbone for iterative refinement, a physics-consistency update to enforce fidelity to the CT forward model, and a Structural Prior Refinement Module (SPRM) that preserves anatomical structures while suppressing dose-dependent artifacts. Extensive experiments on multi-anatomy clinical datasets, including unseen ultra-low-dose conditions as well as out-of-distribution phantom and animal datasets, demonstrate that GenDiff consistently outperforms state-of-the-art convolutional neural network and diffusion-based reconstruction methods. The proposed approach achieves superior reconstruction quality while maintaining strong robustness across different dose levels, anatomical regions, and acquisition domains, making it a promising solution for practical low-dose CT imaging.

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 25 of its 52 references that are in the map. First posted on arXiv 11 Jul 2026.

Builds on

25 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction27 Jun
  2. 2023CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization4 Apr
  3. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov
  4. 2022Low-Dose CT Using Denoising Diffusion Probabilistic Model for 20× Speedup29 Sep

Other references · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  6. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  7. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
  9. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 276
  10. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  11. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 162
  12. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 132
9 more
  1. 2018Bias and Generalization in Deep Generative Models: An Empirical Studycited by 83
  2. 2018Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?cited by 54
  3. 2021DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoisingcited by 46
  4. 2022Cold Diffusion for Speech Enhancementcited by 31
  5. 2017Sharpness-aware Low dose CT denoising using conditional generative adversarial networkcited by 29
  6. 2018Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiographycited by 23
  7. 2020MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstructioncited by 19
  8. 2023ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoisingcited by 15
  9. 2018Non-local Low-rank Cube-based Tensor Factorization for Spectral CT Reconstructioncited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising
  2. 2025Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstruction
  3. 2025AST-n: A Fast Sampling Approach for Low-Dose CT Reconstruction using Diffusion Models
  4. 2024Partitioned Hankel-based Diffusion Models for Few-shot Low-dose CT Reconstruction
  5. 2025Pseudoinverse Diffusion Models for Generative CT Image Reconstruction from Low Dose Data
  6. 2026DeVAR: Low-Dose CT Denoising via Visual Autoregressive Modeling
  7. 2026TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoising
  8. 2026Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Model