A novel fast solving method for targeted drug-delivery capsules in the gastrointestinal tract

• Published in: Technology and health care Vol. 27; no. 3; pp. 335 - 341
• Main Authors: Guo, Xudong, Zhang, Na, Cui, Haipo, Wang, Jing, Jiang, Qinfen
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.01.2019; Sage Publications Ltd
• Subjects: Back propagation networks; Capsules - pharmacology; Diagnostic systems; Diagnostic Techniques and Procedures; Drug Delivery Systems; Field strength; Gastrointestinal Diseases - diagnosis; Gastrointestinal system; Gastrointestinal tract; Gastrointestinal Tract - drug effects; Humans; Iterative methods; Machine learning; Magnetic fields; Neural networks; Neural Networks, Computer; Nonlinear equations; Particle swarm optimization; Search algorithms; Tracking problem; Tracking systems; Drug-delivery capsules; gastrointestinal tract; particle swarm optimization; fast tracking; neural network
• ISSN: 0928-7329; 1878-7401; 1878-7401
• DOI: 10.3233/THC-181484

BACKGROUND: As an innovative technique without cable connection, targeted drug-delivery capsules improve diagnostic and therapeutic capabilities in the gastrointestinal (GI) tract. OBJECTIVE: To fast track targeted drug-delivery capsules in the GI tract, a tracking method based on the multiple alternating magnetic sources with adaptive adjustment of the excitation intensity has been investigated. METHODS: The functional prototype of the tracking system has been developed. The tracking model between the magnetic field strength and the capsule’s location has been established, which shows a nonlinear equation group with multiple local extremum. Particularly, an improved back-propagation (BP) neural network by particle swarm optimization (PSO) is investigated to solve the tracking problem in real time. The PSO is introduced at an early stage to optimize the weights and thresholds of the BP neural network to improve the generalizability and global search ability. Consequently, the Levenberg-Marquardt (LM) algorithm is used as the learning rule to obtain a higher accuracy and convergence rate. RESULTS: The performance on the PSO-BP neural network is experimentally analyzed by comparing it with the standard BP network and the LM-BP network. CONCLUSIONS: The tracking experiments show that the PSO-BP neural network can solve the tracking problem successfully. The PSO-BP network can get the solution faster than iterative search algorithms.