MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916997682429952 |
|---|---|
| author | Barco, Daniel Stadelmann, Marc Oswald, Martin Herzig, Ivo Lichtensteiger, Lukas Paysan, Pascal Peterlik, Igor Walczak, Michal Menze, Bjoern Schilling, Frank-Peter |
| author_facet | Barco, Daniel Stadelmann, Marc Oswald, Martin Herzig, Ivo Lichtensteiger, Lukas Paysan, Pascal Peterlik, Igor Walczak, Michal Menze, Bjoern Schilling, Frank-Peter |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09616 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography Barco, Daniel Stadelmann, Marc Oswald, Martin Herzig, Ivo Lichtensteiger, Lukas Paysan, Pascal Peterlik, Igor Walczak, Michal Menze, Bjoern Schilling, Frank-Peter Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09616 |