A Hybrid Optimization Approach for Improving Sensor Configuration to Enhance Nasogastric Tube (NGT) Localization During Insertion and Withdrawal

The increasing usage of passive magnetic field-based localization systems offers real-time, non-invasive tracking solutions for medical devices such as nasogastric tubes (NGTs) within the human body. These systems rely on external magnetic sensors to detect the magnetic field produced by a small permanent magnet attached to the NGT, allowing for accurate, real-time tracking. However, achieving great precision usually necessitates many sensors, increasing computational burden and system complexity. To overcome this issue, we propose a novel approach that reduces the number of sensors needed while retaining accurate localization. By incorporating mathematical models of magnetic dipoles into a Genetic Algorithm (GA), our technology dynamically optimizes the sensor setup, lowering the system’s processing demands while maintaining accuracy. Experiments show that this hybrid approach can help identify optimal sensor combinations using around 33% fewer sensors, while keeping localization accuracy within a 5% range. These results indicate the potential for clinical applications, as fewer sensors reduce system complexity and costs while maintaining good localization performance.