EUVIMEDEUVIMED entdecken
Crossref

Repeat-consistency learning for improving repeatability of brain-age prediction from structural MRI

Lulu Wang iD

Biomedical Physics & Engineering Express · 2026

DOI: 10.1088/2057-1976/aeaeec ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, 2026. Verfasst von Lulu Wang. Beteiligte Einrichtung: Department of Engineering, Reykjavik University, Reykjavik 101, Iceland. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain, Aging, Image Processing, Computer-Assisted. Die Arbeit nennt 16 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structural magnetic resonance imaging (MRI)–based brain-age prediction is increasingly used as an imaging-derived marker of brain ageing, but good predictive accuracy does not guarantee stable estimates when the same individual is scanned repeatedly. This study proposes repeat-consistency learning (RCL), a training framework that uses same-subject, same-session repeated MRI acquisitions as paired training information. A compact three-dimensional convolutional neural network was trained using a chronological-age prediction loss together with output-level and latent feature-level consistency losses. An unweighted formulation treated all repeated-scan pairs equally, whereas a disagreement-weighted formulation reduced the influence of pairs with larger predicted-age differences. The framework was evaluated using the Open Access Series of Imaging Studies cross-sectional dataset with subject-level training, validation and held-out test partitions. Both RCL formulations showed numerically lower scan-rescan disagreement and narrower Bland–Altman limits of agreement than prediction-only training, while held-out age-prediction performance remained broadly comparable. The unweighted formulation provided the most favourable overall balance between repeatability and predictive accuracy. RCL also reduced prediction shifts under several controlled noise and affine perturbations, although substantial sensitivity to image blurring remained. These findings provide proof-of-concept evidence that repeated MRI acquisitions can be incorporated directly into model training to encourage more stable predictions and latent representations while maintaining broadly comparable chronological-age prediction performance. The observed improvements were modest and were demonstrated in a controlled, single-dataset, within-session setting. Validation in larger, multi-site, multi-scanner and longitudinal datasets is therefore required to determine the broader robustness, generalisability and practical utility of the approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBrainAgingImage Processing, Computer-AssistedHumansConvolutional Neural NetworksReproducibility of ResultsAlgorithmsCross-Sectional Studies

Stichwörter der Autor:innen

brain-age predictionrepeat-consistency learningrepeatabilityrobustnessstructural MRI

Autor:innen und Institutionen

  • Department of Engineering, Reykjavik University, Reykjavik 101, Iceland.

ORCID-Profile: Lulu Wang

Zitieren

APA

Wang, L. (2026). Repeat-consistency learning for improving repeatability of brain-age prediction from structural MRI. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/aeaeec

Vancouver

Wang L. Repeat-consistency learning for improving repeatability of brain-age prediction from structural MRI. Biomedical Physics & Engineering Express. 2026. doi:10.1088/2057-1976/aeaeec

BibTeX
@article{Wang2026,
  author = {Wang, Lulu},
  title = {Repeat-consistency learning for improving repeatability of brain-age prediction from structural MRI},
  journal = {Biomedical Physics & Engineering Express},
  year = {2026},
  doi = {10.1088/2057-1976/aeaeec}
}
Kostenlos starten →