EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Retrospection dropout bare-bones particle swarm optimization for feature-based brain tumor classification in MRI images

Wenting Chen, Tiezhu Shi, Jia Guo, Ling Fu

Frontiers in Oncology · 13.04.2026 · 16

DOI: 10.3389/fonc.2026.1738658 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 13.04.2026. Verfasst von Wenting Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, State Key Laboratory of Digital Medical Engineering, Key Laboratory of Biomedical Engineering of Hainan Province, H…. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain cancer remains a critical global health challenge, where early and accurate diagnosis remains a critical challenge in clinical practice. Current supervised learning methods for tumor classification face substantial limitations due to their dependence on large labeled datasets requiring costly pixel-level annotations, susceptibility to annotation biases, and poor generalization across diverse populations. To address these challenges, this paper proposes Retrospection Dropout Bare-Bones Particle Swarm Optimization (RDBPSO), a novel feature-based classification framework that requires only image-level class labels without the need for pixel-level annotation or manual segmentation masks. The proposed RDBPSO introduces two key innovations: (1) a retrospection mechanism that maintains dual-layer memory structures (optimal and sub-optimal solutions) to enhance particle diversity and prevent premature convergence, and (2) a dropout strategy that reduces computational complexity through intelligent particle interaction sampling. Extensive experiments on an 800-image brain MRI dataset demonstrate RDBPSO’s superior performance. The proposed method achieves 90.12% classification accuracy, outperforming standard PSO (89.25%), GMM (77.50%), and K-means (72.75%), while delivering robust clustering quality with an ARI of 0.6436, NMI of 0.5511, and FMI of 0.8229. These results demonstrate the algorithmic promise of RDBPSO as an annotation-efficient framework for brain tumor MRI classification, warranting further investigation on more diverse and clinically representative datasets.

Schlagwörter

Stichwörter der Autor:innen

MRI imagesbare-bonesbrain tumorparticle swarm optimizationretrospection dropout

Autor:innen und Institutionen

  • School of Biomedical Engineering, State Key Laboratory of Digital Medical Engineering, Key Laboratory of Biomedical Engineering of Hainan Province, Hainan University, Haikou, China.
  • Hematology Department of Hainan General Hospital, Hainan, Haikou, China.
  • State Key Laboratory of Subtropical Building and Urban Science & Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Shenzhen University, Shenzhen, China.
  • Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, Wuhan, China.
  • School of Information Engineering, Hubei University of Economics, Wuhan, China.
  • Graduate School of Computer and Information Sciences, Hosei University, Tokyo, Japan.

Zitieren

APA

Chen, W., Shi, T., Guo, J., & Fu, L. (2026). Retrospection dropout bare-bones particle swarm optimization for feature-based brain tumor classification in MRI images. Frontiers in Oncology, 16. https://doi.org/10.3389/fonc.2026.1738658

Vancouver

Chen W, Shi T, Guo J, Fu L. Retrospection dropout bare-bones particle swarm optimization for feature-based brain tumor classification in MRI images. Frontiers in Oncology. 2026;16. doi:10.3389/fonc.2026.1738658

BibTeX
@article{Chen2026,
  author = {Chen, Wenting and Shi, Tiezhu and Guo, Jia and Fu, Ling},
  title = {Retrospection dropout bare-bones particle swarm optimization for feature-based brain tumor classification in MRI images},
  journal = {Frontiers in Oncology},
  year = {2026},
  volume = {16},
  doi = {10.3389/fonc.2026.1738658}
}
Kostenlos starten →