Submitted by elm4010 on April 29, 2021 - 3:31pm
Title | MRSaiFE: towards the real-time prediction of tissue heating in MRI - a feasibility study |
Publication Type | Conference Proceedings |
Year of Conference | 2021 |
Authors | Winkler SA, Motovilova E, Gökyar S, Saniour I, Robb F, Chaudhari A |
Conference Name | ISMRM Virtual Conference |
Abstract | A crucial safety concern for UHF MRI is the significant RF power deposition in the body in the form of local specific absorption rate (SAR) hotspots,leading to dangerous tissue heating/damage. This work is a proof-of-concept demonstration of an artificial intelligence (AI) based real-time MRI safetyprediction software (MRSaiFE) facilitating safe generation of 3T and 7T images by means of accurate local SAR-monitoring at sub-W/kg levels. Thisfeasibility study demonstrates that SAR patterns can be predicted with a root-mean-square error (RMSE) of <11% along with a structural similarity (SSIM)level of >84% for both field strengths. |