Hybrid Quantum-Classical Neural Network for Brain Tumor Detection: A Literature Survey Towards Sustainable Healthcare

Brain tumor detection from Magnetic Resonance Imaging (MRI) is essential for early diagnosis, treatment planning, and improved patient outcomes. Recent advances in Deep Learning (DL), particularly Convolutional Neural Networks (CNNs) and transfer learning models, have enhanced automated brain tumor classification. However, conventional DL approaches often require significant computational resources and may struggle to capture complex nonlinear patterns in high-dimensional medical imaging data. Quantum Machine Learning (QML) has emerged as a promising alternative by integrating quantum computing principles with machine learning to improve feature representation and classification performance.

This paper presents a comprehensive survey of hybrid quantum-classical approaches for MRI-based brain tumor detection. The review examines recent developments in Quantum Neural Networks (QNNs), Quantum Convolutional Neural Networks (QCNNs), Variational Quantum Circuits (VQCs), and hybrid learning frameworks applied to medical image analysis. Existing studies demonstrate encouraging results, but challenges related to scalability, limited quantum hardware, class imbalance, false-negative reduction, and clinical deployment remain unresolved. The survey identifies key research gaps and discusses a future research direction that combines EfficientNet-B2 with Variational Quantum Circuits for enhanced brain tumor classification. The proposed direction supports Sustainable Development Goal (SDG) 3 and SDG 9 by promoting intelligent and innovative healthcare technologies.