Low-Power Hardware-Based Real-Time Cervical Spine Localization via Image Processing

Authors

• Patricia Angela R. Abu, Ateneo de Manila UniversityFollow
• Chao-Shin Liu, Feng Chia University
• Sung-Hsin Tsai, Chang Gung Memorial Hospital
• Po Lin Huang, Feng Chia University
• Hong-Kai Wang, Chang Gung Memorial Hospital
• Shih Wei Chung, Feng Chia University
• Chiung-An Chen, Ming Chi University of Technology
• Shih-Lun Chen, Chung Yuan Christian University, Taiwan
• Sze-Teng Liong, Feng Chia University
• Tsung-Yi Chen, Feng Chia University

Document Type

Conference Proceeding

Publication Date

8-2025

Abstract

With the growing prevalence of cervical spine degeneration in the aging population, there is an urgent need for accurate and real-time cervical image analysis to assist in preliminary evaluations during neurosurgical outpatient visits. This study suggests a hard-ware-based real-time cervical spine localization system that uses image preprocessing algorithms to address this need. The system can quickly finish image enhancement and greatly speed up the localization process by turning preprocessing steps like median filtering and binarization into hardware modules. With a power consumption as low as 4.859 mW, the proposed hardware-based median filter demonstrates over 60% reduction in power and 35% reduction in delay compared to existing designs, while maintaining minimal logic utilization. These improvements highlight their superior hardware efficiency and suitability for low-power applications. The overall localization accuracy increased from 92.4% to 97.4%, successfully resolving long-standing challenges in cervical vertebra identification.

Recommended Citation

Liu, C.-S., Tsai, S.-H., Huang, P. L., Wang, H.-K., Chung, S. W., Chen, C.-A., Chen, S.-L., Liong, S.-T., Chen, T.-Y., & Abu, P. A. R. (2025). Low-power hardware-based real-time cervical spine localization via image processing. Engineering Proceedings, 80(1), Article 24. https://doi.org/10.3390/xxxxx