An Evolving Transformer Model with Reinforcement Learning-Enhanced Particle Swarm Optimization for Medical Image Segmentation
Sensors · 20.11.2026 · 26 (22) · 7351
DOI: 10.3390/s26227351 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.11.2026. Verfasst von Jingtong Chen und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovate UK.
Abstract (Originalsprache)
Medical image segmentation presents inherent challenges due to its complexity and heterogeneity. In this research, we propose an evolving segmentation model with dynamic transformer blocks and Gaussian, Levy, and 3D geometric surface-enhanced self-attention methods to extract fine-grained nuances and global contexts simultaneously. These new self-attention methods generate attention biases using Gaussian and Levy distributions and 3D formulae with patch distances as inputs to emphasize local regions. A new PSO variant is proposed to optimize the number of transformer blocks, self-attention variant types, encoder fusion weights, and key learning settings to fine-tune local and global dependency extraction to better adapt to different application contexts. The proposed PSO model employs sine-cosine search coefficients, reinforcement learning-based search action selection, and multiple optimal signals to avoid being trapped in local optima. Our model with the proposed PSO-optimized transformer architecture and learning settings achieves impressive mean Dice scores of 89.24%, 87.38%, 98.13%, 83.27%, and 82.73% for ACDC, CHAOS (MRI), CHAOS (CT), CHASE_DB1, and STARE, respectively. It also outperforms various recent state-of-the-art transformer and CNN baselines in tackling diverse binary and multi-class segmentation tasks.
Förderung
- Innovate UK
Zitieren
APA
Chen, J., Zhang, L., Lim, C. P., Asadi, H., Adamyk, B., Yu, Y., Gao, R., & Huang, H. (2026). An Evolving Transformer Model with Reinforcement Learning-Enhanced Particle Swarm Optimization for Medical Image Segmentation. Sensors, 26(22), 7351. https://doi.org/10.3390/s26227351
Vancouver
Chen J, Zhang L, Lim CP, Asadi H, Adamyk B, Yu Y, et al. An Evolving Transformer Model with Reinforcement Learning-Enhanced Particle Swarm Optimization for Medical Image Segmentation. Sensors. 2026;26(22):7351. doi:10.3390/s26227351
BibTeX
@article{Chen2026,
author = {Chen, Jingtong and Zhang, Li and Lim, Chee Peng and Asadi, Houshyar and Adamyk, Bogdan and Yu, Yonghong and Gao, Rong and Huang, Haoqian},
title = {An Evolving Transformer Model with Reinforcement Learning-Enhanced Particle Swarm Optimization for Medical Image Segmentation},
journal = {Sensors},
year = {2026},
volume = {26},
number = {22},
pages = {7351},
doi = {10.3390/s26227351}
}
EUVIMED