Using deep neural networks to predict RF heating of implanted conductive leads exclusively from implant trajectory and RF coil features
ISMRM & SMRT Annual Meeting, Digital Poster 2279
Abstract
An abstract is not available in the lab archive. View the paper at its source.
This 2021 ISMRM digital poster presents a deep-learning approach to predict trajectory-specific maximum local specific absorption rate in tissue around implanted lead models. The conference program identifies the work as abstract 2279.
Summary
The study addresses radiofrequency (RF) heating around implanted conductive leads, a safety concern that can limit MRI access for people with active electronic implants. The authors describe a deep-learning approach to predict trajectory-specific maximum local specific absorption rate (SAR)—a measure of RF power absorbed in tissue—near implanted lead tips. The conference abstract states that full-wave electromagnetic simulations were the standard method for quantifying RF heating and required substantial computational resources and simulation time. The abstract does not report quantitative evaluation results or establish clinical readiness.
The work was presented as digital poster 2279 in the MRI & Implants: The Good, The Bad & The Ugly session at the ISMRM & SMRT Annual Meeting. The program lists the poster session on May 18, 2021.
- Authors: Jasmine Vu, Bach T Nguyen, Bhumi Bhusal, Justin Baraboo, Joshua Rosenow, Ulas Bagci, Molly G Bright, and Laleh Golestanirad.
Cite this work
Jasmine Vu, Bach T Nguyen, Bhumi Bhusal, Justin Baraboo, Joshua Rosenow, Ulas Bagci, Molly G Bright, Laleh Golestanirad (2021). Using deep neural networks to predict RF heating of implanted conductive leads exclusively from implant trajectory and RF coil features. ISMRM & SMRT Annual Meeting, Digital Poster 2279 https://www.ismrm.org/21/program-files/D-156.htm
BibTeX