Low-Power CMOS Architecture for Quantum Fuzzy Clustered Image Segmentation in Intracranial Tumor Detection

Early and precise detection of intracranial tumors is critical for improving diagnostic accuracy and patient survival in neuroimaging applications. Conventional image segmentation techniques often suffer from high computational complexity, poor noise tolerance, and increased power consumption, making them unsuitable for portable and embedded medical diagnostic systems. To address these limitations, this paper proposes a Low-Power CMOS Architecture for Quantum Fuzzy Clustered Image Segmentation (QFCIS) for efficient intracranial tumor detection from brain MRI images. The proposed framework integrates quantum-inspired fuzzy clustering with CMOS-based hardware optimization to enhance segmentation precision while minimizing energy consumption and computational latency. Initially, MRI images are preprocessed using adaptive normalization and contrast enhancement techniques to improve image quality. Then, quantum fuzzy clustering is employed for accurate tumor boundary extraction by utilizing probabilistic membership mapping and quantum state transition mechanisms. The segmentation algorithm is implemented through a low-power CMOS architecture designed with optimized transistor-level switching logic and reduced leakage current pathways for hardware efficiency. Experimental analysis conducted on benchmark MRI datasets demonstrates that the proposed method achieves a segmentation accuracy of 98.74%, sensitivity of 97.92%, specificity of 98.31%, and Dice similarity coefficient of 97.85%, outperforming conventional fuzzy C-means and deep segmentation approaches. Additionally, the CMOS implementation reduces power consumption by 34.6%, area utilization by 29.4%, and processing latency by 26.8% compared to existing FPGA-based architectures. These results validate the effectiveness of the proposed model for real-time, portable, and energy-efficient intracranial tumor diagnosis systems.