Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.16577 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917154237972480 |
|---|---|
| author | Disch, Nico Albert Roy, Saikat Ulrich, Constantin Kirchhoff, Yannick Rokuss, Maximilian Peretzke, Robin Zimmerer, David Maier-Hein, Klaus |
| author_facet | Disch, Nico Albert Roy, Saikat Ulrich, Constantin Kirchhoff, Yannick Rokuss, Maximilian Peretzke, Robin Zimmerer, David Maier-Hein, Klaus |
| contents | Forecasting how 3D medical scans evolve over time is important for disease progression, treatment planning, and developmental assessment. Yet existing models either rely on a single prior scan, fixed grid times, or target global labels, which limits voxel-level forecasting under irregular sampling. We present CRONOS, a unified framework for many-to-one prediction from multiple past scans that supports both discrete (grid-based) and continuous (real-valued) timestamps in one model, to the best of our knowledge the first to achieve continuous sequence-to-image forecasting for 3D medical data. CRONOS learns a spatio-temporal velocity field that transports context volumes toward a target volume at an arbitrary time, while operating directly in 3D voxel space. Across three public datasets spanning Cine-MRI, perfusion CT, and longitudinal MRI, CRONOS outperforms other baselines, while remaining computationally competitive. We will release code and evaluation protocols to enable reproducible, multi-dataset benchmarking of multi-context, continuous-time forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16577 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series Disch, Nico Albert Roy, Saikat Ulrich, Constantin Kirchhoff, Yannick Rokuss, Maximilian Peretzke, Robin Zimmerer, David Maier-Hein, Klaus Computer Vision and Pattern Recognition I.4; I.2; I.5; J.3 Forecasting how 3D medical scans evolve over time is important for disease progression, treatment planning, and developmental assessment. Yet existing models either rely on a single prior scan, fixed grid times, or target global labels, which limits voxel-level forecasting under irregular sampling. We present CRONOS, a unified framework for many-to-one prediction from multiple past scans that supports both discrete (grid-based) and continuous (real-valued) timestamps in one model, to the best of our knowledge the first to achieve continuous sequence-to-image forecasting for 3D medical data. CRONOS learns a spatio-temporal velocity field that transports context volumes toward a target volume at an arbitrary time, while operating directly in 3D voxel space. Across three public datasets spanning Cine-MRI, perfusion CT, and longitudinal MRI, CRONOS outperforms other baselines, while remaining computationally competitive. We will release code and evaluation protocols to enable reproducible, multi-dataset benchmarking of multi-context, continuous-time forecasting. |
| title | CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series |
| topic | Computer Vision and Pattern Recognition I.4; I.2; I.5; J.3 |
| url | https://arxiv.org/abs/2512.16577 |