Patients with deep brain stimulation (DBS) implants can significantly benefit from MRI; however, their access is limited due to safety concerns associated with RF heating of implants. RF heating depends significantly on the trajectory of an implanted lead, but there is a lack of surgical guidelines about positioning the extracranial portion of the leads, resulting in substantial patient-to-patient variation in DBS lead trajectories. Thus, quick and reliable patient-specific assessment of RF heating is highly desirable. Here we present an artificial neural network (ANN) model that demonstrates great potential in predicting local SAR at the tips of the DBS leads.
This abstract and the presentation materials are available to members only; a login is required.