An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917431638753280 |
|---|---|
| author | Zuo, Lianrui Liu, Yihao Rudravaram, Gaurav Ramadass, Karthik Krishnan, Aravind R. Phillips, Michael D. Bodien, Yelena G. Patel, Mayur B. Trujillo, Paula Martinez, Yency Forero Deppen, Stephen A. Grogan, Eric L. Maldonado, Fabien McGann, Kevin Holmes, Hudson M. Cutting, Laurie E. Huo, Yuankai Landman, Bennett A. |
| author_facet | Zuo, Lianrui Liu, Yihao Rudravaram, Gaurav Ramadass, Karthik Krishnan, Aravind R. Phillips, Michael D. Bodien, Yelena G. Patel, Mayur B. Trujillo, Paula Martinez, Yency Forero Deppen, Stephen A. Grogan, Eric L. Maldonado, Fabien McGann, Kevin Holmes, Hudson M. Cutting, Laurie E. Huo, Yuankai Landman, Bennett A. |
| contents | Medical imaging research is increasingly shifting from controlled benchmark evaluation toward real-world clinical deployment. In such settings, applying analytical methods extends beyond model design to require dataset-aware workflow configuration and provenance tracking. Two requirements therefore become central: \textbf{adaptability}, the ability to configure workflows according to dataset-specific conditions and evolving analytical goals; and \textbf{reproducibility}, the guarantee that all transformations and decisions are explicitly recorded and re-executable. Here, we present an artifact-based agent framework that introduces a semantic layer to augment medical image processing. The framework formalizes intermediate and final outputs through an artifact contract, enabling structured interrogation of workflow state and goal-conditioned assembly of configurations from a modular rule library. Execution is delegated to a workflow executor to preserve deterministic computational graph construction and provenance tracking, while the agent operates locally to comply with most privacy constraints. We evaluate the framework on real-world clinical CT and MRI cohorts, demonstrating adaptive configuration synthesis, deterministic reproducibility across repeated executions, and artifact-grounded semantic querying. These results show that adaptive workflow configuration can be achieved without compromising reproducibility in heterogeneous clinical environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21936 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing Zuo, Lianrui Liu, Yihao Rudravaram, Gaurav Ramadass, Karthik Krishnan, Aravind R. Phillips, Michael D. Bodien, Yelena G. Patel, Mayur B. Trujillo, Paula Martinez, Yency Forero Deppen, Stephen A. Grogan, Eric L. Maldonado, Fabien McGann, Kevin Holmes, Hudson M. Cutting, Laurie E. Huo, Yuankai Landman, Bennett A. Artificial Intelligence Computer Vision and Pattern Recognition Multiagent Systems Medical imaging research is increasingly shifting from controlled benchmark evaluation toward real-world clinical deployment. In such settings, applying analytical methods extends beyond model design to require dataset-aware workflow configuration and provenance tracking. Two requirements therefore become central: \textbf{adaptability}, the ability to configure workflows according to dataset-specific conditions and evolving analytical goals; and \textbf{reproducibility}, the guarantee that all transformations and decisions are explicitly recorded and re-executable. Here, we present an artifact-based agent framework that introduces a semantic layer to augment medical image processing. The framework formalizes intermediate and final outputs through an artifact contract, enabling structured interrogation of workflow state and goal-conditioned assembly of configurations from a modular rule library. Execution is delegated to a workflow executor to preserve deterministic computational graph construction and provenance tracking, while the agent operates locally to comply with most privacy constraints. We evaluate the framework on real-world clinical CT and MRI cohorts, demonstrating adaptive configuration synthesis, deterministic reproducibility across repeated executions, and artifact-grounded semantic querying. These results show that adaptive workflow configuration can be achieved without compromising reproducibility in heterogeneous clinical environments. |
| title | An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Multiagent Systems |
| url | https://arxiv.org/abs/2604.21936 |