Work

An Explainable Hybrid Deep Learning Framework with Multi-Scale Feature Fusion and Uncertainty-Aware Clinical Decision Support for Brain Tumor Classification

Year: 2026
Type: article
Abstract: Accurate diagnosis of brain tumors from magnetic resonance imaging (MRI) is crucial but is challenged by inter-observer variability and by the limited explainability of deep models. Most existing studies use standalone CNNs or Transformers without uncertainty assessment or explanation capabilities. We propose an explainable hybrid deep learning framework that combines multi-scale feature fusion with uncertainty-aware clinical decision support. On a four-class brain MRI benchmark, it was compared with EfficientNetV2, ConvNeXt, and Swin Transformer. Five explainability methods (Grad-CAM, SHAP, LIME, Integrated Gradients, and Attention Rollout) explain predictions, while Monte Carlo dropout quantifies predictive uncertainty; confidence and entropy form a Trust Score for three-tier referral. The hybrid model outperformed the baselines, achieving a test accuracy of 95.7%, a macro F1-score of 95.5%, and an AUC of 0.989. A preliminary 12-reader evaluation suggests that the clinical decision support system (CDSS) report is usable (mean System Usability Scale 78.3/100) and reduces mean reading time per case from 42.6~s to 34.8~s versus radiologist-alone reading, although underpowered for clinical endpoints. Prospective multi-institutional validation remains future work.
Language: English
Open Access status: hybrid
OpenAlex ID: W7235579673
FWCI:
Cites: 42
Cited by:
Related to: 10