EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis

Bailiang Jian, Jiazhen Pan, Yitong Li, Fabian Bongratz, Ruochen Li, Daniel Rueckert, Benedikt Wiestler, Christian Wachinger

IEEE Transactions on Medical Imaging · 2026

DOI: 10.1109/tmi.2026.3674458 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026. Verfasst von Bailiang Jian und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Brain, Magnetic Resonance Imaging, Aging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Federal Ministry for Economic Affairs and Energy (BMWi) (Project “NeuroTEMP”) Research Funding and Munich Center for Machine Learning, European Research Council (ERC) Project Deep4MI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Longitudinal brain analysis is essential for understanding healthy aging and identifying pathological deviations. Longitudinal registration of sequential brain MRI underpins such analyses. However, existing methods are limited by reliance on densely sampled time series, a trade-off between accuracy and temporal smoothness, and an inability to prospectively forecast future brain states. To overcome these challenges, we introduce TimeFlow, a learning-based framework for longitudinal brain MRI registration. TimeFlow uses a U-Net backbone with temporal conditioning to model neuroanatomy as a continuous function of age. Given only two scans from an individual, TimeFlow estimates accurate and temporally coherent deformation fields, enabling non-linear extrapolation to predict future brain states. This is achieved by our proposed inter-/extrapolation consistency constraints applied to both the deformation fields and deformed images. Remarkably, these constraints preserve temporal consistency and continuity without requiring explicit smoothness regularizers or densely sampled sequential data. Extensive experiments demonstrate that TimeFlow outperforms state-of-the-art methods in terms of both future timepoint forecasting and registration accuracy. Moreover, TimeFlow supports novel biological brain aging analyses by differentiating neurodegenerative trajectories from normal aging without requiring segmentation, thereby eliminating the need for labor-intensive annotations and mitigating segmentation inconsistency. TimeFlow offers an accurate, data-efficient, and annotation-free framework for longitudinal analysis of brain aging and chronic diseases, capable of forecasting brain changes beyond the observed study period.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BrainMagnetic Resonance ImagingAgingImage Processing, Computer-AssistedNeuroimagingHumansAlgorithmsLongitudinal Studies

Förderung

  • the Federal Ministry for Economic Affairs and Energy (BMWi) (Project “NeuroTEMP”) Research Funding and Munich Center for Machine Learning
  • European Research Council (ERC) Project Deep4MI

Zitieren

APA

Jian, B., Pan, J., Li, Y., Bongratz, F., Li, R., Rueckert, D., Wiestler, B., & Wachinger, C. (2026). Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2026.3674458

Vancouver

Jian B, Pan J, Li Y, Bongratz F, Li R, Rueckert D, et al. Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis. IEEE Transactions on Medical Imaging. 2026. doi:10.1109/tmi.2026.3674458

BibTeX
@article{Jian2026,
  author = {Jian, Bailiang and Pan, Jiazhen and Li, Yitong and Bongratz, Fabian and Li, Ruochen and Rueckert, Daniel and Wiestler, Benedikt and Wachinger, Christian},
  title = {Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2026},
  doi = {10.1109/tmi.2026.3674458}
}
Kostenlos starten →