EUVIMEDObjevte EUVIMED
Crossref

Multi‐class brain tumor diagnosis using MRI: A dynamic reinforcement ensemble learning approach

Jia Sheng Yang, Xiao Yang, Xu Xiao

Medical Physics · 2025-08 · 52 (8)

DOI: 10.1002/mp.18003 ↗

At a glance

Journal article in Medical Physics, published online on 2025-08-15. Written by Jia Sheng Yang and 2 co-authors. Institution: Academician Workstation, Changsha Medical University, Changsha, China. Major MEDLINE topics: Brain Neoplasms, Magnetic Resonance Imaging, Machine Learning, Image Processing, Computer-Assisted. Cited 2 times so far (Crossref); 51 references. Funded by: Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Early and accurate diagnosis is essential for effective clinical decision‐making, particularly when working with complex and imbalanced medical datasets. Traditional static ensemble models often struggle to adapt to such challenges, limiting their generalization and performance.

Purpose

This study aims to develop a novel dynamic ensemble learning framework that enhances diagnostic accuracy by addressing the limitations of static ensemble strategies through adaptive model selection and dynamic weight adjustment.

Methods

We propose a Dynamic Reinforcement Ensemble Learning Model that leverages reinforcement learning (RL) to dynamically select the most suitable base classifiers and adjust their contribution weights based on input data characteristics. The model was evaluated on three benchmark medical datasets: LSBTDK‐DAT, FIGSHARE‐DAT, and THYROID‐DAT. Comparative analyses and ablation studies were conducted to assess performance gains and the impact of each dynamic component.

Results

On LSBTDK‐DAT, the proposed model achieved an accuracy of 99.55% and an F1‐score of 99.54%. On THYROID‐DAT, it reached 99.35% accuracy and an F1‐score of 98.89%. Across all datasets, the model outperformed existing state‐of‐the‐art methods by up to 7% in accuracy and 5% in F1‐score. Ablation experiments confirmed that the combination of dynamic selection and dynamic weighting consistently produced the best outcomes.

Conclusions

The integration of dynamic reinforcement ensemble selection with adaptive weighting enables the model to robustly handle diverse and complex medical data. These results demonstrate the model's potential for intelligent clinical decision support systems and lay the foundation for scalable, high‐precision medical AI solutions.

Subjects

MeSH terms (MEDLINE)

Brain NeoplasmsMagnetic Resonance ImagingMachine LearningImage Processing, Computer-AssistedHumansEnsemble Learning

Author keywords

brain tumor classificationdynamic reinforcement ensemble learningmedical diagnosistransfer learning

Authors and institutions

  • Academician Workstation, Changsha Medical University, Changsha, China.

Funding

  • Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations

Cite

APA

Yang, J. S., Yang, X., & Xiao, X. (2025). Multi‐class brain tumor diagnosis using MRI: A dynamic reinforcement ensemble learning approach. Medical Physics, 52(8). https://doi.org/10.1002/mp.18003

Vancouver

Yang JS, Yang X, Xiao X. Multi‐class brain tumor diagnosis using MRI: A dynamic reinforcement ensemble learning approach. Medical Physics. 2025;52(8). doi:10.1002/mp.18003

BibTeX
@article{Yang2025,
  author = {Yang, Jia Sheng and Yang, Xiao and Xiao, Xu},
  title = {Multi‐class brain tumor diagnosis using MRI: A dynamic reinforcement ensemble learning approach},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {8},
  doi = {10.1002/mp.18003}
}
Start for free →