A Lightweight ScaleDense–Transformer Framework with Auxiliary Quantum-Inspired Bottleneck Module for Whole-Lifespan Brain Age Prediction
Brain Sciences · 29.05.2026 · 16 (6) · 581
DOI: 10.3390/brainsci16060581 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 29.05.2026. Verfasst von Lan Lin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Beijing Municipality Natural Science Foundation.
Abstract (Originalsprache)
Background/Objectives: This study introduces Lightweight ScaleDense–Transformer (LST-Net), a design-driven framework for whole-lifespan brain age prediction, aiming to improve prediction accuracy while maintaining structural and biological plausibility.
Methods
LST-Net utilizes a ScaleDense–Transformer architecture specifically engineered to mirror the dual-nature of brain aging: ScaleDense modules capture fine-grained local anatomical changes, while Transformers model global, network-level reorganizations. The framework was developed and evaluated using a modeling cohort of 22,271 subjects from 17 heterogeneous data sources, covering a 96-year lifespan. Additionally, an auxiliary quantum module (VQC) was incorporated within the latent bottleneck to facilitate nonlinear latent representation transformation and improve representation expressiveness. Performance was primarily assessed using Mean Absolute Error (MAE).
Results
LST-Net achieved a competitive MAE of 2.71 years in brain age prediction, demonstrating stability across a wide lifespan (0–96 years) and varying data sources. Longitudinal assessments and test–retest analysis further confirmed the model’s high reproducibility, yielding an Intraclass Correlation Coefficient (ICC) of 0.994.
Conclusions
The current findings establish LST-Net as a scalable tool for brain health monitoring and large-scale screenings.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China.
- Intelligent Physiological Measurement and Clinical Translation, Beijing International Base for Scientific and Technological Cooperation, Beijing University of Technology, Beijing 100124, China.
ORCID-Profile: Lan Lin, Hongjian Gao, Shen Sun
Förderung
- National Natural Science Foundation of China
- Beijing Municipality Natural Science Foundation
Zitieren
APA
Lin, L., Zhu, X., Gao, H., & Sun, S. (2026). A Lightweight ScaleDense–Transformer Framework with Auxiliary Quantum-Inspired Bottleneck Module for Whole-Lifespan Brain Age Prediction. Brain Sciences, 16(6), 581. https://doi.org/10.3390/brainsci16060581
Vancouver
Lin L, Zhu X, Gao H, Sun S. A Lightweight ScaleDense–Transformer Framework with Auxiliary Quantum-Inspired Bottleneck Module for Whole-Lifespan Brain Age Prediction. Brain Sciences. 2026;16(6):581. doi:10.3390/brainsci16060581
BibTeX
@article{Lin2026,
author = {Lin, Lan and Zhu, Xinyu and Gao, Hongjian and Sun, Shen},
title = {A Lightweight ScaleDense–Transformer Framework with Auxiliary Quantum-Inspired Bottleneck Module for Whole-Lifespan Brain Age Prediction},
journal = {Brain Sciences},
year = {2026},
volume = {16},
number = {6},
pages = {581},
doi = {10.3390/brainsci16060581}
}
EUVIMED