mlsanityData to 14 Oct 2026

MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography

arXiv 2508.09616 ↗First posted 13 Aug 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present MInDI-3D (Medical Inversion by Direct Iteration in 3D), the first 3D conditional diffusion-based model for real-world sparse-view Cone Beam Computed Tomography (CBCT) artefact removal, aiming to reduce imaging radiation exposure. A key contribution is extending the "InDI" concept from 2D to a full 3D volumetric approach for medical images, implementing an iterative denoising process that refines the CBCT volume directly from sparse-view input. A further contribution is the generation of a large pseudo-CBCT dataset (16,182) from chest CT volumes of the CT-RATE public dataset to robustly train MInDI-3D. We performed a comprehensive evaluation, including quantitative metrics, scalability analysis, generalisation tests, and a clinical assessment by 11 clinicians. Our results show MInDI-3D's effectiveness, achieving a 12.96 (6.10) dB PSNR gain over uncorrected scans with only 50 projections on the CT-RATE pseudo-CBCT (independent real-world) test set and enabling an 8x reduction in imaging radiation exposure. We demonstrate its scalability by showing that performance improves with more training data. Importantly, MInDI-3D matches the performance of a 3D U-Net on real-world scans from 16 cancer patients across distortion and task-based metrics. It also generalises to new CBCT scanner geometries. Clinicians rated our model as sufficient for patient positioning across all anatomical sites and found it preserved lung tumour boundaries well.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 68 references that are in the map. First posted on arXiv 13 Aug 2025.

Builds on

37 of 68 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  10. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
25 more
  1. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  2. 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 613
  3. 2017The Perception-Distortion Tradeoffcited by 587
  4. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  5. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 165
  6. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 132
  7. 2023Conditional Diffusion Models for Semantic 3D Brain MRI Synthesiscited by 86
  8. 2020Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directionscited by 65
  9. 2014A New 2.5D Representation for Lymph Node Detection using Random Sets of Deep Convolutional Neural Network Observationscited by 56
  10. 2024WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesiscited by 56
  11. 2023Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Modelscited by 53
  12. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  13. 2023Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Modelcited by 29
  14. 2023Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trendcited by 24
  15. 2020Modelling the Distribution of 3D Brain MRI using a 2D Slice VAEcited by 20
  16. 2024Deep Generative Models for 3D Medical Image Synthesiscited by 14
  17. 2023A 3D Conditional Diffusion Model for Image Quality Transfer -- An Application to Low-Field MRIcited by 13
  18. 2014Image processingcited by 11
  19. 2022Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Imagescited by 8
  20. 2023Multiscale Metamorphic VAE for 3D Brain MRI Synthesiscited by 8
  21. 2023CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Modelcited by 6
  22. 2023CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET imagescited by 5
  23. 2023Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse Problemscited by 5
  24. 2024Artifact Reduction in 3D and 4D Cone-beam Computed Tomography Images with Deep Learning -- A Reviewcited by 5
  25. 2024Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solvingcited by 4

Built on by

Not cited yet.