mlsanityData to 14 Oct 2026

Structure-constrained Language-informed Diffusion Model for Unpaired Low-dose Computed Tomography Angiography Reconstruction

arXiv 2601.20304 ↗First posted 28 Jan 2026cs.CV cs.AIcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

The application of iodinated contrast media (ICM) improves the sensitivity and specificity of computed tomography (CT) for a wide range of clinical indications. However, overdose of ICM can cause problems such as kidney damage and life-threatening allergic reactions. Deep learning methods can generate CT images of normal-dose ICM from low-dose ICM, reducing the required dose while maintaining diagnostic power. However, existing methods are difficult to realize accurate enhancement with incompletely paired images, mainly because of the limited ability of the model to recognize specific structures. To overcome this limitation, we propose a Structure-constrained Language-informed Diffusion Model (SLDM), a unified medical generation model that integrates structural synergy and spatial intelligence. First, the structural prior information of the image is effectively extracted to constrain the model inference process, thus ensuring structural consistency in the enhancement process. Subsequently, semantic supervision strategy with spatial intelligence is introduced, which integrates the functions of visual perception and spatial reasoning, thus prompting the model to achieve accurate enhancement. Finally, the subtraction angiography enhancement module is applied, which serves to improve the contrast of the ICM agent region to suitable interval for observation. Qualitative analysis of visual comparison and quantitative results of several metrics demonstrate the effectiveness of our method in angiographic reconstruction for low-dose contrast medium CT angiography.

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 24 of its 45 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

24 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models5 Apr
  2. 2022Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains9 Oct
  3. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Models17 Jul

Other references · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  6. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  7. 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 641
  8. 2021ClipCap: CLIP Prefix for Image Captioningcited by 559
  9. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  10. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  11. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 183
  12. 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
9 more
  1. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problemscited by 66
  2. 2018Image-to-image translation for cross-domain disentanglementcited by 61
  3. 2023Image Restoration Through Generalized Ornstein-Uhlenbeck Bridgecited by 41
  4. 2024Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpaintingcited by 40
  5. 2018Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiographycited by 23
  6. 2023Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noisecited by 19
  7. 2024LLMRA: Multi-modal Large Language Model based Restoration Assistantcited by 8
  8. 2024Low-dose CT Denoising with Language-engaged Dual-space Alignmentcited by 7
  9. 2024Dual-Domain CLIP-Assisted Residual Optimization Perception Model for Metal Artifact Reductioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Head-Neck Dual-energy CT Contrast Media Reduction Using Diffusion Models
  2. 2025FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising
  3. 2025Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
  4. 2022One Sample Diffusion Model in Projection Domain for Low-Dose CT Imaging
  5. 2026GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization
  6. 2023Diffusion Probabilistic Priors for Zero-Shot Low-Dose CT Image Denoising
  7. 2024HC3L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesis
  8. 2024Improving Cone-Beam CT Image Quality with Knowledge Distillation-Enhanced Diffusion Model in Imbalanced Data Settings