EQDA-Net: an enhanced quantum-inspired dragonfly algorithm integrated with efficientnet for brain tumor detection

Abstract Synthesizing quantum-inspired computation with advanced swarm intelligence, this study presents an evolutionary framework for brain tumor detection in Magnetic Resonance Imaging (MRI). Beginning with our baseline Quantum-inspired Dragonfly Algorithm (QDA), which achieved 92.3% accuracy, we describe the enhancements that led to the Enhanced Quantum-inspired Dragonfly Algorithm (EQDA) and its integration with EfficientNet-B4 for classification within the BraTS 2020 evaluation setting. By combining quantum-inspired search mechanisms, multiswarm optimization, adaptive control, attention modules, and multiscale feature fusion, the proposed framework improves optimization efficiency for deep medical image analysis. The experimental results on BraTS 2020 indicate that the revised EQDA-Net configuration achieves strong performance, reaching approximately 97.5% accuracy under the reported split and cross-validation protocol while also reducing convergence iterations relative to the baseline variants considered in this study. These findings support the potential of quantum-inspired optimization for heterogeneous brain MRI analysis; however, independent external validation is still required before broader claims regarding generalizability or clinical applicability can be made.