A Novel Hybrid Algorithm for Enhanced Low-Conductivity Material Imaging in Magnetic Induction Tomography

Abstract

Background: Magnetic Induction Tomography (MIT) faces significant challenges in imaging low-conductivity materials, particularly in optimizing multi-frequency excitation parameters for enhanced detection sensitivity. Conventional approaches face challenges in processing weak electromagnetic responses from low-conductivity materials (10^-18 to 10^-12 S/m). This limitation results in poor image quality and reduced detection capabilities.

Purpose: This study introduces an innovative adaptive multi-frequency optimization framework integrated with deep learning for MIT, specifically designed to enhance the detection and characterization of low-conductivity materials. The framework introduces a novel HBDL-TVR-MF-ACC-MIT algorithm that dynamically optimizes excitation frequencies while leveraging deep learning for improved signal processing and image reconstruction.

Method: We developed an integrated approach combining adaptive frequency optimization (1 kHz - 10 MHz) with deep learning architectures. The system employs frequency-hopping techniques and custom-designed CNN for optimization and reconstruction. The framework was validated through comprehensive COMSOL Multiphysics simulations and experimental testing using standardized phantoms.

Results: The framework demonstrated substantial improvements in MIT imaging performance, including enhanced detection sensitivity for ultra-low conductivity materials, significant reduction in reconstruction time, and improved spatial resolution. The system achieved consistent performance across diverse material types, with notable improvements in image quality metrics and system stability. Key achievements include a 45% reduction in reconstruction time and 40% improvement in spatial resolution compared to conventional methods.

Conclusion: This adaptive multi-frequency optimization approach represents a significant advancement in low-conductivity MIT imaging, enabling accurate and efficient detection of previously challenging materials. The integration of deep learning with optimized frequency selection establishes a robust framework for non-invasive imaging applications in medical diagnostics and industrial monitoring, with potential for substantial cost reduction and efficiency improvements in both sectors.