Elliptical Magnetic Nanoparticle Swarm Formation by an Artificial Neural Network-Based Rotating Magnetic Field

Biomedical applications of magnetic nanoparticle (MNP) swarm control rely on precise manipulation of the swarm using magnetic fields. This approach improves the accessibility and maneuverability of the swarm and enhances targeted therapies and drug delivery. In this study, we applied artificial intelligence to control the shape of elliptical MNP swarms by adjusting the parameters of a rotating magnetic field (RMF). The resulting RMF controlled the major axis and slant angle of the ellipse-shaped swarm. We constructed a dataset of diverse swarm shapes and corresponding RMF parameters, and applied it to train an artificial neural network (ANN). The trained ANN was used to predict the experimental RMF parameters required to achieve the desired shapes of elliptical MNP swarms. After ANN training, differences between the predicted and actual root mean square error (RMSE) values were evaluated to verify the model. The RMSEs of the major and minor axis lengths and slant angle were 0.21 mm, 0.06 mm, and 6.01°, respectively. This simple, inference-based approach to swarm formation yielded higher swarm formation accuracy and allowed fine control of the swarm. Note to Practitioners—Magnetic nanoparticle swarms have shown good potential for precise and non-invasive targeted drug delivery and therapies. The motivation for this work originates from the need for a faster and more efficient process of generating magnetic nanoparticle swarms and their shape control. Currently used approaches for swarm formation rely on generating a table of rotating field parameters corresponding to different swarm shapes and size or automatic closed loop controllers. These processes are slow and can result in collapse of swarm shape due to instantaneous change in the rotating magnetic field parameters. To tackle these drawbacks, we propose a machine learning based model for swarm formation and shape control. The trained artificial neural network not only enabled faster swarm formation due to its fast inference time but also allowed for easier shape control, as the user could select any elliptical swarm shape parameter to obtain the required rotating magnetic field parameters.