EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive disease-centric learning algorithms for brain tumor classification using medical image processing

S. Mohan, N. S. Kavitha, A. Vijayalakshmi, R. S. Ramya

Journal of Biological Regulators and Homeostatic Agents · 29.07.2026 · 40 (3) · 132

DOI: 10.65746/jbrha132 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Biological Regulators and Homeostatic Agents, online erschienen am 29.07.2026. Verfasst von S. Mohan und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate analysis of brain tumors using medical image processing techniques remains a critical challenge due to high-dimensional imaging features, intra-tumor variability, and complex tissue structures present a magnetic resonance imaging (MRI) data. Conventional image-based classification methods often depend on static feature extraction and fixed learning models, which limit adaptability and predictive robustness in heterogeneous tumor datasets. To address these limitations, this paper proposes an adaptive disease-centric learning framework for brain tumor classification that are integrates between two novel algorithmic techniques. The framework incorporates an Adaptive Disease-Relevant Feature Selection (ADRFS) algorithm, which dynamically evaluates and refines extracted imaging features based on their contribution to tumor discrimination and inter-feature dependency during the learning process. By allowing that the feature spaces to evolve continuously, ADRFS reduces a redundancy while preserving diagnostically significantly to image characteristics. Building upon the optimized feature representation, a Disease-Aware Hybrid Classification (DAHC) algorithm is introduced to classify brain tumors by integrating similarity-based grouping of tumor patterns with adaptive decision modeling, ensuring that tumor-specific characteristics are explicitly embedded into a classification process. The combined application of ADRFS and DAHC enhances interpretability, reduces computational complexity, and improved classification stability for MRI-based tumor analysis. Experimental results demonstrate that the proposed approach achieves superior tumor classification accuracy and efficiency compared to existing image-based learning methods, producing a suitable for intelligent brain tumors diagnosis and clinical decision support systems.

Zitieren

APA

Mohan, S., Kavitha, N. S., Vijayalakshmi, A., & Ramya, R. S. (2026). Adaptive disease-centric learning algorithms for brain tumor classification using medical image processing. Journal of Biological Regulators and Homeostatic Agents, 40(3), 132. https://doi.org/10.65746/jbrha132

Vancouver

Mohan S, Kavitha NS, Vijayalakshmi A, Ramya RS. Adaptive disease-centric learning algorithms for brain tumor classification using medical image processing. Journal of Biological Regulators and Homeostatic Agents. 2026;40(3):132. doi:10.65746/jbrha132

BibTeX
@article{Mohan2026,
  author = {Mohan, S. and Kavitha, N. S. and Vijayalakshmi, A. and Ramya, R. S.},
  title = {Adaptive disease-centric learning algorithms for brain tumor classification using medical image processing},
  journal = {Journal of Biological Regulators and Homeostatic Agents},
  year = {2026},
  volume = {40},
  number = {3},
  pages = {132},
  doi = {10.65746/jbrha132}
}
Kostenlos starten →