Litcius/Paper detail

Machine Learning-Based Prediction of MRI-Induced Power Absorption in the Tissue in Patients With Simplified Deep Brain Stimulation Lead Models

Jasmine Vu, Bach T. Nguyen, Bhumi Bhusal, Justin Baraboo, Joshua M. Rosenow, Ulaş Bağcı, Molly G. Bright, Laleh Golestanirad

2021IEEE Transactions on Electromagnetic Compatibility28 citationsDOIOpen Access PDF

Abstract

Interaction of an active electronic implant such as a deep brain stimulation (DBS) system and magnetic resonance imaging (MRI) radiofrequency (RF) fields can induce excessive tissue heating, limiting MRI accessibility. Efforts to quantify RF heating mostly rely on electromagnetic (EM) simulations to assess individualized specific absorption rate (SAR), but such simulations require extensive computational resources. Here, we investigate if a predictive model using machine learning (ML) can predict the local SAR in the tissue around tips of implanted leads from the distribution of the tangential component of the MRI incident electric field, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">tan</sub> . A dataset of 260 unique patient-derived and artificial DBS lead trajectories was constructed, and the 1 g-averaged SAR, 1 g SAR <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">max</sub> , at the lead-tip during 1.5 T MRI was determined by EM simulations. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">tan</sub> values along each lead's trajectory and the simulated SAR values were used to train and test the ML algorithm. The resulting predictions of the ML algorithm indicated that the distribution of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">tan</sub> could effectively predict 1 g SAR <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">max</sub> at the DBS lead-tip ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> = 0.82). Our results indicate that ML has the potential to provide a fast method for predicting MR-induced power absorption in the tissue around tips of implanted leads such as those in active electronic medical devices.

Topics & Concepts

Specific absorption rateDeep brain stimulationLead (geology)Absorption (acoustics)Power (physics)Computer scienceTrajectoryBiomedical engineeringSimulationPhysicsEngineeringAcousticsMedicineGeologyAstronomyGeomorphologyDiseaseTelecommunicationsParkinson's diseasePathologyAntenna (radio)Quantum mechanicsNeurological disorders and treatmentsAdvanced MRI Techniques and ApplicationsNeuroscience and Neural Engineering
Machine Learning-Based Prediction of MRI-Induced Power Absorption in the Tissue in Patients With Simplified Deep Brain Stimulation Lead Models | Litcius