Rapid prediction of MRI-induced RF heating of active implantable medical devices using machine learning
Authors:
Open Access
- 24 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2023, 1-4
Abstract
The interaction between an active implantable medical device and magnetic resonance imaging (MRI) radiofrequency (RF) fields can cause excessive tissue heating. Existing methods for predicting RF heating in the presence of an implant rely on either extensive phantom experiments or electromagnetic (EM) simulations with varying degrees of approximation of the MR environment, the patient, or the implant. On the contrary, fast MR thermometry techniques can provide a reliable real-time map of temperature rise in the tissue in the vicinity of conductive implants. In this proof-of-concept study, we examined whether a machine learning (ML) based model could predict the temperature increase in the tissue near the tip of an implanted lead after several minutes of RF exposure based on only a few seconds of experimentally measured temperature values. We performed phantom experiments with a commercial deep brain stimulation (DBS) system to train a fully connected feedforward neural network (NN) to predict temperature rise after ~3 minutes of scanning at a 3 T scanner using only data from the first 5 seconds. The NN effectively predicted ΔT max —R 2 = 0.99 for predictions in the test dataset. Our model also showed potential in predicting RF heating for other various scenarios, including a DBS system at a different field strength (1.5 T MRI, R 2 = 0.87), different field polarization (1.2 T vertical MRI, R 2 = 0.79), and an unseen implant (cardiac leads at 1.5 T MRI, R 2 = 0.91). Our results indicate great potential for the application of ML in combination with fast MR thermometry techniques for rapid prediction of RF heating for implants in various MR environments.Clinical Relevance— Machine learning-based algorithms can potentially enable rapid prediction of MRI-induced RF heating in the presence of unknown AIMDs in various MR environments.Keywords
Funding Information
- Health
This publication has 26 references indexed in Scilit:
- Numerical Simulations of Realistic Lead Trajectories and an Experimental Verification Support the Efficacy of Parallel Radiofrequency Transmission to Reduce Heating of Deep Brain Stimulation Implants during MRIScientific Reports, 2019
- Reducing RF-Induced Heating Near Implanted Leads Through High-Dielectric Capacitive Bleeding of Current (CBLOC)IEEE Transactions on Microwave Theory and Techniques, 2019
- RF-induced heating in tissue near bilateral DBS implants during MRI at 1.5 T and 3T: The role of surgical lead managementNeuroImage, 2019
- Changes in the specific absorption rate (SAR) of radiofrequency energy in patients with retained cardiac leads during MRI at 1.5T and 3TMagnetic Resonance in Medicine, 2018
- Local SAR near deep brain stimulation (DBS) electrodes at 64 and 127 MHz: A simulation study of the effect of extracranial loopsMagnetic Resonance in Medicine, 2016
- The Rate of Magnetic Resonance Imaging in Patients with Deep Brain StimulationStereotactic and Functional Neurosurgery, 2016
- Feasibility of using linearly polarized rotating birdcage transmitters and close-fitting receive arrays in MRI to reduce SAR in the vicinity of deep brain simulation implantsMagnetic Resonance in Medicine, 2016
- Impact of capped and uncapped abandoned leads on the heating of an MR‐conditional pacemaker implantMagnetic Resonance in Medicine, 2014
- MRI thermometry: Fast mapping of RF‐induced heating along conductive wiresMagnetic Resonance in Medicine, 2008
- Calculation of MRI‐induced heating of an implanted medical lead wire with an electric field transfer functionJournal of Magnetic Resonance Imaging, 2007