Saved in:
Bibliographic Details
Main Authors: Disch, Nico Albert, Roy, Saikat, Ulrich, Constantin, Kirchhoff, Yannick, Rokuss, Maximilian, Peretzke, Robin, Zimmerer, David, Maier-Hein, Klaus
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