EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

F1‐Weighted Ensemble of CNN and Local Features for Explainable Brain Tumor MRI Classification

Oscar Vianney Eone Etoua, Hippolyte Michel Tapamo Kenfack, Jules-Raymond Tapamo

Applied Computational Intelligence and Soft Computing · 2026-01 · 2026 (1)

DOI: 10.1155/acis/7961939 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Computational Intelligence and Soft Computing, online erschienen am 10.08.2026. Verfasst von Oscar Vianney Eone Etoua und 2 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and interpretable brain tumor classification from MRI scans remains a critical challenge in medical image analysis, owing to limited annotated data, high intraclass variability, and the need for trustworthy models. We present an F1‐weighted ensemble that integrates handcrafted texture descriptors (LBP) with deep features extracted from lightweight convolutional neural networks ([CNN] MobileNetV2, SqueezeNet 1.0, and EfficientNet‐B0). The CNN backbones are used as frozen ImageNet feature extractors without any fine‐tuning, ensuring a modular and leakage‐free pipeline. Grad‐CAM visualizations are generated using a separate, task‐specifically fine‐tuned CNN instance (5 epochs, intrafold), ensuring that saliency maps reflect brain tumor‐relevant activation patterns rather than generic ImageNet features. Each component model is weighted according to its macro‐F1 score estimated on an internal 20% validation subset of the training fold, preventing weight collapse due to classifier overfitting on training data. The optimal number of neighbors for the KNN classifier was determined by a cross‐validated grid search over k ∈ {1, 3, 5, 7, 9}, yielding k = 1 as the best configuration (macro‐F1 score = 97.38 ± 0.39%). The framework is evaluated on two heterogeneous datasets, including a rebalanced 15‐class variant, under a strict stratified 5‐fold cross‐validation protocol in which normalization and augmentation are applied exclusively within the training partition of each fold, preventing any statistical leakage between training and validation sets. It achieves 97.93%±0.18% accuracy (97.91%±0.19% macro‐F1 score) and 99.86%±0.06% AUC on the 4‐class dataset, and 97.75%±0.65% accuracy on the challenging 15‐class setting. Beyond predictive performance, we provide technical post hoc model explanation through Grad‐CAM, SHAP (stability , three independent runs, extended to both 4‐class and 15‐class settings), and error‐correlation analysis, which highlight the complementary nature of CNN and LBP features. A representative state‐of‐the‐art (SOTA) method was reproduced under identical 5‐fold cross‐validation conditions (Acc = 99.38%±0.23%), confirming that the residual performance gap reflects deliberate design trade‐offs—computational efficiency, interpretability, and robustness under class imbalance—rather than evaluation protocol heterogeneity. This work introduces a rigorous and computationally efficient framework that combines performance and transparency, paving the way for reliable computer‐aided systems to support neuroradiologists in brain tumor diagnosis.

Zitieren

APA

Etoua, O. V. E., Kenfack, H. M. T., & Tapamo, J. (2026). F1‐Weighted Ensemble of CNN and Local Features for Explainable Brain Tumor MRI Classification. Applied Computational Intelligence and Soft Computing, 2026(1). https://doi.org/10.1155/acis/7961939

Vancouver

Etoua OVE, Kenfack HMT, Tapamo J. F1‐Weighted Ensemble of CNN and Local Features for Explainable Brain Tumor MRI Classification. Applied Computational Intelligence and Soft Computing. 2026;2026(1). doi:10.1155/acis/7961939

BibTeX
@article{Etoua2026,
  author = {Etoua, Oscar Vianney Eone and Kenfack, Hippolyte Michel Tapamo and Tapamo, Jules-Raymond},
  title = {F1‐Weighted Ensemble of CNN and Local Features for Explainable Brain Tumor MRI Classification},
  journal = {Applied Computational Intelligence and Soft Computing},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/acis/7961939}
}
Kostenlos starten →