Unsupervised quantum machine learning and computer vision transformer methods for brain tumor classification

Abstract

The early detection and diagnosis of brain tumors is linked with improved patient quality of life, treatment, and health outcomes. Identifying the presence of brain tumors is typically done using magnetic resonance imaging (MRI) scans. Creating a computerized system to determine whether a patient has a brain tumor, and what kind, remains challenging due to the complexity and visual similarity of brain MRI data. This challenge motivates the creation of methods and systems that can classify patient MRI data automatically without requiring supervised training. We propose a quantum machine learning and computer vision transformer (ViT) framework for unsupervised brain MRI classification. The Quantum Transformer for Clustering MRI (QTCM) framework combines classical computing methods with a quantum ViT to better identify and classify brain tumors in MRI scan data. We demonstrate that a quantum transformer-based system can improve classification rates when compared to similar classical systems. This dissertation also evaluates the role of clustering strategy selection in brain MRI tumor classification. In this study, we introduce DQC1-projected, a method inspired by deterministic quantum computation with one qubit, and compare its performance against several classical clustering algorithms across two public brain MRI benchmarks. The results show that DQC1-projected achieves the strongest performance among the evaluated methods. Finally, we investigate the feasibility of QTCM on quantum hardware by extending the study from simulation to deployment on a present-day quantum device. These experiments evaluate the effects of hardware noise and resource limitations on the proposed method. Together, these results demonstrate the potential of quantum machine learning and computer ViT methods for advancing brain MRI analysis.