Hierarchical Deep Feature Fusion and Ensemble Learning for Enhanced Brain Tumor MRI Classification

2025-06-14

AI Summary

To address insufficient classification accuracy and poor clinical robustness in brain tumor MRI diagnosis, this paper proposes a two-level ensemble framework: deep features are extracted via multi-source pretrained Vision Transformers (ViTs) and fused at the feature level; diverse machine learning classifiers, optimized via Bayesian hyperparameter tuning, are ensembled at the decision level. The method integrates standardized preprocessing, domain-adaptive MRI data augmentation, and transfer learning to substantially enhance generalization. Its key innovation lies in the first implementation of synergistic ensemble integration—both at the feature and classifier levels—along with systematic validation of the critical performance gains conferred by hyperparameter optimization and fine-grained preprocessing for clinical-grade diagnosis. Evaluated on two Kaggle public benchmarks, the approach achieves state-of-the-art accuracy of 98.7% and 97.3%, respectively, reducing generalization error by 26.5% compared to existing methods.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate brain tumor classification is crucial in medical imaging to ensure reliable diagnosis and effective treatment planning. This study introduces a novel double ensembling framework that synergistically combines pre-trained deep learning (DL) models for feature extraction with optimized machine learning (ML) classifiers for robust classification. The framework incorporates comprehensive preprocessing and data augmentation of brain magnetic resonance images (MRI), followed by deep feature extraction using transfer learning with pre-trained Vision Transformer (ViT) networks. The novelty lies in the dual-level ensembling strategy: feature-level ensembling, which integrates deep features from the top-performing ViT models, and classifier-level ensembling, which aggregates predictions from hyperparameter-optimized ML classifiers. Experiments on two public Kaggle MRI brain tumor datasets demonstrate that this approach significantly surpasses state-of-the-art methods, underscoring the importance of feature and classifier fusion. The proposed methodology also highlights the critical roles of hyperparameter optimization (HPO) and advanced preprocessing techniques in improving diagnostic accuracy and reliability, advancing the integration of DL and ML for clinically relevant medical image analysis.

Problem

• Accurate brain tumor classification from MRI scans
• Combining deep learning and machine learning for robust diagnosis
• Improving diagnostic accuracy with feature and classifier fusion

Innovation

• Double ensembling framework for robust classification
• Feature extraction with pre-trained ViT networks
• Hyperparameter-optimized ML classifiers fusion