When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909477264949248 |
|---|---|
| author | Cheung, Matt Y. Zorek, Sophia Netherton, Tucker J. Court, Laurence E. Al-Kindi, Sadeer Veeraraghavan, Ashok Balakrishnan, Guha |
| author_facet | Cheung, Matt Y. Zorek, Sophia Netherton, Tucker J. Court, Laurence E. Al-Kindi, Sadeer Veeraraghavan, Ashok Balakrishnan, Guha |
| contents | Diffusion models demonstrate state-of-the-art performance on image generation, and are gaining traction for sparse medical image reconstruction tasks. However, compared to classical reconstruction algorithms relying on simple analytical priors, diffusion models have the dangerous property of producing realistic looking results \emph{even when incorrect}, particularly with few observations. We investigate the utility of diffusion models as priors for image reconstruction by varying the number of observations and comparing their performance to classical priors (sparse and Tikhonov regularization) using pixel-based, structural, and downstream metrics. We make comparisons on low-dose chest wall computed tomography (CT) for fat mass quantification. First, we find that classical priors are superior to diffusion priors when the number of projections is ``sufficient''. Second, we find that diffusion priors can capture a large amount of detail with very few observations, significantly outperforming classical priors. However, they fall short of capturing all details, even with many observations. Finally, we find that the performance of diffusion priors plateau after extremely few ($\approx$10-15) projections. Ultimately, our work highlights potential issues with diffusion-based sparse reconstruction and underscores the importance of further investigation, particularly in high-stakes clinical settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02771 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT Cheung, Matt Y. Zorek, Sophia Netherton, Tucker J. Court, Laurence E. Al-Kindi, Sadeer Veeraraghavan, Ashok Balakrishnan, Guha Medical Physics Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Applications Diffusion models demonstrate state-of-the-art performance on image generation, and are gaining traction for sparse medical image reconstruction tasks. However, compared to classical reconstruction algorithms relying on simple analytical priors, diffusion models have the dangerous property of producing realistic looking results \emph{even when incorrect}, particularly with few observations. We investigate the utility of diffusion models as priors for image reconstruction by varying the number of observations and comparing their performance to classical priors (sparse and Tikhonov regularization) using pixel-based, structural, and downstream metrics. We make comparisons on low-dose chest wall computed tomography (CT) for fat mass quantification. First, we find that classical priors are superior to diffusion priors when the number of projections is ``sufficient''. Second, we find that diffusion priors can capture a large amount of detail with very few observations, significantly outperforming classical priors. However, they fall short of capturing all details, even with many observations. Finally, we find that the performance of diffusion priors plateau after extremely few ($\approx$10-15) projections. Ultimately, our work highlights potential issues with diffusion-based sparse reconstruction and underscores the importance of further investigation, particularly in high-stakes clinical settings. |
| title | When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT |
| topic | Medical Physics Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Applications |
| url | https://arxiv.org/abs/2502.02771 |