MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914196713635840 |
|---|---|
| author | Liu, Yihao Gao, Chenyu Zuo, Lianrui Kim, Michael E. Boyd, Brian D. Barnes, Lisa L. Kukull, Walter A. Beason-Held, Lori L. Resnick, Susan M. Hohman, Timothy J. Taylor, Warren D. Landman, Bennett A. |
| author_facet | Liu, Yihao Gao, Chenyu Zuo, Lianrui Kim, Michael E. Boyd, Brian D. Barnes, Lisa L. Kukull, Walter A. Beason-Held, Lori L. Resnick, Susan M. Hohman, Timothy J. Taylor, Warren D. Landman, Bennett A. |
| contents | Modern deep learning methods have achieved impressive results across tasks from disease classification, estimating continuous biomarkers, to generating realistic medical images. Most of these approaches are trained to model conditional distributions defined by a specific predictive direction with a specific set of input variables. We introduce MetaVoxel, a generative joint diffusion modeling framework that models the joint distribution over imaging data and clinical metadata by learning a single diffusion process spanning all variables. By capturing the joint distribution, MetaVoxel unifies tasks that traditionally require separate conditional models and supports flexible zero-shot inference using arbitrary subsets of inputs without task-specific retraining. Using more than 10,000 T1-weighted MRI scans paired with clinical metadata from nine datasets, we show that a single MetaVoxel model can perform image generation, age estimation, and sex prediction, achieving performance comparable to established task-specific baselines. Additional experiments highlight its capabilities for flexible inference. Together, these findings demonstrate that joint multimodal diffusion offers a promising direction for unifying medical AI models and enabling broader clinical applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10041 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata Liu, Yihao Gao, Chenyu Zuo, Lianrui Kim, Michael E. Boyd, Brian D. Barnes, Lisa L. Kukull, Walter A. Beason-Held, Lori L. Resnick, Susan M. Hohman, Timothy J. Taylor, Warren D. Landman, Bennett A. Computer Vision and Pattern Recognition Artificial Intelligence Modern deep learning methods have achieved impressive results across tasks from disease classification, estimating continuous biomarkers, to generating realistic medical images. Most of these approaches are trained to model conditional distributions defined by a specific predictive direction with a specific set of input variables. We introduce MetaVoxel, a generative joint diffusion modeling framework that models the joint distribution over imaging data and clinical metadata by learning a single diffusion process spanning all variables. By capturing the joint distribution, MetaVoxel unifies tasks that traditionally require separate conditional models and supports flexible zero-shot inference using arbitrary subsets of inputs without task-specific retraining. Using more than 10,000 T1-weighted MRI scans paired with clinical metadata from nine datasets, we show that a single MetaVoxel model can perform image generation, age estimation, and sex prediction, achieving performance comparable to established task-specific baselines. Additional experiments highlight its capabilities for flexible inference. Together, these findings demonstrate that joint multimodal diffusion offers a promising direction for unifying medical AI models and enabling broader clinical applicability. |
| title | MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.10041 |